A low-pass filter is essential for stabilizing strictly proper repetitive-control systems, but it inevitably degrades steady-state tracking accuracy due to gain attenuation and phase lag. This article presents a new filter design and optimization method that improves both transient response and steady-state accuracy in continuous-time repetitive-control systems. First, the gain and phase characteristics of conventional filter-based repetitive controllers are rigorously analyzed to reveal the relationship between filter parameters and tracking performance. Based on this analysis, a new filter structure is designed to precisely compensate for gain attenuation and phase delay, specifically at the fundamental frequency, by minimizing the error term without increasing the filter bandwidth. A guideline for selecting the filter parameters for varying periodic trajectories is also provided. In addition, according to the one-to-one mapping between control and learning behaviors and their respective gains, dual performance indices are constructed to account for tracking error and control effort across multiple learning cycles. A multiobjective optimization framework is then developed to directly tune these gains subject to stability constraints, achieving an optimal balance between rapid transient convergence and control energy efficiency. Experimental results validate the effectiveness and superiority of the design.

Continuum robots (CRs) show great potential in complex environments due to their excellent deformability. For practical applications, the position control of the CRs is an important research field. The common drives of the CRs are rigid motors with mature control schemes. However, the driving force of the rigid motors is often impactive, which may cause safety concerns during interaction. Soft drives based on pneumatic soft actuators (PSAs) can provide compliant driving force for the CRs robot bodies to solve this problem, but it is necessary to comprehensively consider the control of the soft drives and the robot bodies. This article takes a CR with soft drives as the research objective, and proposes a double closed-loop adaptive position control method to achieve the endpoint position control of the CR. This CR includes a length-variable robot body with millimeter-scale diameter and pneumatic soft drives. The kinematic model of the robot body is built based on the piecewise constant curvature (PCC) method, and the static models of the soft drives are derived from the three-element model. Based on these models, we propose a double closed-loop adaptive position control method. The inner loop is used to control the displacements of the soft drives, and the outer loop combines the endpoint position control with the nonsingular fast terminal sliding mode function to adaptively control the endpoint position based on the inner loop. By Lyapunov method, we prove the convergence of the endpoint position error. The effectiveness of the proposed control method is verified through experiments.

During drilling process, variations in formation hardness and frictional resistance often cause a mismatch between drilling operating parameters and actual conditions, reducing efficiency. A fuzzy decision-making strategy for drilling operating parameters is developed that enables feed speed and rotational speed to adapt to actual conditions. The formation hardness is accurately characterized using only drilling data through the integration of fuzzy C-means clustering method and defuzzification method. Meanwhile, the computational model for frictional resistance is established. They serve as inputs for subsequent decision-making models. The decision-making models for feed speed and rotational speed are developed based on the Mamdani fuzzy inference method, respectively. The effectiveness of the approach is demonstrated through an industrial case study based on actual drilling data.

Utilizing the waste heat recovered from the coke dry quenching process for power generation is an important energy-saving measure for steel enterprises. However, the discontinuous nature of the coke discharging operation leads to instability in waste heat supply and constant load fluctuations in the process of recovering the sensible heat from red hot coke, thereby affecting the power generation. Consequently, short-term prediction of power generation in coke dry quenching process is essential to provide guidance for the power scheduling of steel companies. In this paper, a prediction model is developed based on the Crossformer network. Experimental results based on real production data show that the proposed prediction model can relatively accurately predict power generation in the coke dry quenching process, which provides guidance for the short-term power scheduling of the steel company.

In coal seam drilling, wall friction along the borehole introduces complex, spatially distributed disturbances that degrade the dynamic performance of the drill string. Due to its slender and flexible structure, the drill string is highly sensitive to such multi-point excitations, leading to frequent velocity fluctuations and reduced tracking accuracy. To address this, a robust H-infinity control strategy is proposed. A disturbance weighting function is designed to give the controller notch-filter characteristics, enabling targeted suppression of resonance-induced vibrations. Relying only on inlet measurements, the controller ensures accurate tracking of the reference feeding speed while effectively mitigating wall friction effects. Simulation results show significant improvements in steady-state accuracy, disturbance rejection, and robustness compared to conventional methods, confirming the effectiveness of the proposed approach.

Measurement of ocean current velocity profiles is critical for marine operations, yet traditional methods such as Acoustic Doppler Current Profilers face limitations in cost, resolution, and penetration depth. Existing inversion techniques often rely on idealized assumptions limiting their practical applicability. To address these challenges, this paper proposes stratified hybrid convolutional network, a novel deep learning-based soft sensing method for reconstructing ocean current velocity profiles. The proposed method leverages a physically guided stratification of ocean currents into distinct layers based on temperature-salinity-density correlations and their driving mechanisms. An adaptive feature selection algorithm mitigates overfitting by filtering redundant inputs and aligning features with layer-specific dynamics. A hybrid neural network architecture combines two-dimensional convolutions along depth and feature dimensions to capture nonlinear relationships, followed by multi-layer perceptrons for high-dimensional nonlinear mapping. Experimental results demonstrate superior performance. This method provides a practical solution for the inversion of ocean current velocity profiles.

This paper proposes efficient modeling and control methods for a continuum robot (CR) composed of a three-segment robot body (two proximal segments and a distal segment with an endpoint) and soft drives. Each segment incorporates multiple mutually exclusive magnetic spacer disks for a flexible structure, and the soft drives are designed based on pneumatic soft actuators (PSAs) to ensure operational safety. For both computational efficiency and tracking performance, an open-loop control method based on the kinematic model of the robot body is adopted to operate the two proximal segments, and a feedforward-feedback control method based on the dynamic model of the distal segment derived from the Euler-Lagrange method is proposed to control the endpoint trajectory. During the dynamic modeling process of the distal segment, the magnetic potential energy is considered additionally by simplifying the magnetic spacer disks to multiple magnetic dipoles. Moreover, the relationship between the input pressures of the soft drives and the generalized force of the dynamic model is derived from the three-element model and the principle of virtual power. Experiments demonstrate the effectiveness of the proposed modeling and control method.

A multibranch adaptive graph convolutional network is proposed for human action recognition by combining graph convolutional networks (GCNs), adaptive learning, and multibranch feature extraction. Through the adaptive graph convolution module, this method can adaptively change parameters during the training process, thereby enhancing the flexibility of the model. Furthermore, the integration of shallow-level features (skeleton joints), with deep-level features including skeleton information, motion information, and motion difference information allows our model to capture both spatial and temporal dynamics of human actions, leading to a more comprehensive representation of human action features. The introduction of the spatio-temporal attention mechanism enables our model to focus on key frames and skeleton joints. The attitude correction module makes the input data to the network more reasonable and reduces the interference of noise. The inclusion of the adaptive mechanism makes the network no longer limited to the inherent physical connections, and the flexibility of the network is enhanced. The addition of second-order features makes the features of the skeletal data fully exploited. This attention mechanism enhances the discriminative ability of the model and improves its ability to recognize subtle variations and important cues in human actions. Through experiments on benchmark datasets, NTU-RGB-D and Kinetics-400, our method achieves significant improvements in action recognition performance compared with existing approaches. On the Kinetics-400 dataset, we achieved 36.5% and 59.6% recognition rates under the Top-1 and Top-5 evaluation metrics, respectively, which is an improvement of about 1% compared with the state-of-the-art method. On the NTU-RGB-D dataset, we achieved 95.8% and 89.4% recognition rates under the X-view and X-subject modes, respectively, with excellent results. These results validate the effectiveness of the multi-branch adaptive graph convolutional network for human action recognition tasks.

Microwave filters (MFs) are indispensable in communication systems for selecting specific frequency signals. The tuning of MFs is a demanding and time-consuming task, which can be addressed by the inverse decision-making model (IDMM). However, two main challenges arise in the sampling process for IDMM, namely, low efficiency due to the large number of samples and poor adaptability in the presence of uncertain initial positions. To overcome these challenges, a fuzzy nonuniform sampling (FNUS) method is proposed, leveraging the flexibility of the fuzzy logic system. Specifically, an adaptive sampling framework based on a fuzzy logic system is presented to handle the uncertainty of initial positions. Under this framework, a nonuniform sampling approach is devised to collect fewer samples far from the target and more samples close to the target. Given the similarity and single-sided distribution of samples in the raw dataset oriented to modeling, the tailored enhancement strategies are designed to improve dataset quality. Finally, the efficiency and adaptability of FNUS are demonstrated to be superior to the existing methods through simulations. Furthermore, the practicality of FNUS is validated by experiments on physical MFs.

Semi-autogenous grinding (SAG) processes are widely used in mineral processing. In industrial production, operators often lack a comprehensive and objective assessment of the operating conditions of an SAG process and usually make different control decisions based on experience to meet production demands. This paper explains a two-level fuzzy comprehensive evaluation method for the load and efficiency of an SAG process. First, the operation mechanism of an SAG process is analyzed, and the evaluation indicators of load and efficiency are determined. Then the levels and weights of each indicator are determined by combining expert experience and actual production data. Finally, the operating load level is first evaluated by combining the information entropy weight and fuzzy computation. When the load level is within an acceptable range, a fuzzy comprehensive evaluation of the efficiency level is then performed. The modeling method of efficiency indicator, circulating load ratio (CLR), is integrated with random forest (RF) and Bayesian optimization (BO) to carry out the efficiency evaluation. Experiments using actual production data demonstrate CLR modeling performance with a mean absolute error (MAE) of 1.084% and a mean absolute percentage error (MAPE) of 9.415%. The accuracy of the operating efficiency evaluation is 81.69%. This method provides an objective and uniform criterion for operators to evaluate the operating load and efficiency of an SAG process, thus guiding the regulation of actual production.

This article presents a two-degree-of-freedom structure of a fuzzy repetitive-control system that accurately tracks periodic signals and effectively suppresses aperiodic disturbances based on an enhanced equivalent-input-disturbance (EEID) method. To make full use of the learning characteristic, a 2-D model of the fuzzy repetitive-control system is established to independently regulate the control and learning behaviors. The EEID approach decouples the design of the observer and the estimator by adding a flexible controller to the estimator. This makes it possible to simultaneously reduce the estimated and filtered errors, which is a contradictory problem in the conventional EID method. The two errors cannot be eliminated due to the lack of an internal model of the external disturbance. To actively cancel the negative influence of the two errors, a new observation-error compensator is added to the observer input to improve the disturbance-suppression performance. Two low-conservative linear-matrix-inequality stability conditions are derived using the Lyapunov–Krasovskii functionals and zero equations with free-weighting matrices. The nondominated sorting genetic algorithm II and the particle swarm optimization algorithm are used to optimize the parameters of the controllers for the tracking and disturbance-suppression systems based on the stability conditions and performance indexes. The effectiveness and superiority of the design are verified by numerical simulation and comparison results.

In a continuous annealing process (CAP), an accurate and timely temperature prediction is crucial, particularly during transitions between different types of strips. Predicting transition states is challenging due to process nonlinearities and time-varying characteristics induced by these transitions. In addition, extensive historical datasets hold valuable insights that can be harnessed to detect consistent and similar changes within transition groups. In this study, we introduce a data-driven framework known as the “progressive search and parallel model” to forecast transition states rapidly. The “progressive search” is executed by categorizing subclasses based on parameter properties and spatial locations, each with varying priority levels. Specifically, parameters are subdivided into segments along a piecewise linear scale, and a just-in-time learning framework is employed to establish local models at these levels concurrently. We apply this framework in both stable and transitional CAP conditions, demonstrating its robust performance in effectively tracking shifting trends during state transitions.

In practice, repetitive control (RC) is a type of learning control that exhibits good tracking performance. However, existing nonlinear RC methods lack analysis and design of the learning property, which results in limited performance. This study addresses the learning-enhanced issue. First, a new fuzzy Lyapunov candidate is constructed for stability analysis, which contains an integral term associated with the membership function and a double integral term. The design of the learning-dependent term integrates the nonlinear membership function information, which enhances the learning ability. Second, an additional first-order low-pass filter is incorporated into the conventional equivalent input disturbance estimator. The new filter acts as an integrator that adjusts the bandwidth of the disturbance compensation and gradually eliminates the disturbances in the output error. Third, a recursive optimization algorithm is used to design the controllers. Experimental comparisons on motor drive systems demonstrate the effectiveness and superiority of the method.

Severe drill-string vibration is a significant source of drilling problems. Most existing methods for vibration recognition rely on downhole data, facing great limitations in practice. In addition, complex and changeable formations result in limited ability of single-scale features to characterize the vibration. To resolve these issues, an end-to-end vibration recognition model using only surface drilling data is proposed based on multiscale features extraction. A multiscale temporal convolutional network is developed to extract multiscale temporal features of multisensor data, enhancing the vibration representation capability to adapt to complex formations. To further improve recognition capability, the bidirectional long short-term memory network is utilized to obtain contextual linkage of multiscale features. Experiments conducted with field data have verified the efficiency of proposed method. It has achieved 97% accuracy, and outperforms existing methods. Furthermore, compared with the recognition result based on single-scale features, it has improved by 6% in accuracy. The proposed method provides automated diagnostics of drill-string vibration.

This article is concerned with the balance between improving rate-of-penetration and suppressing drill-string vibrations by optimizing weight-on-bit and rotational speed. The main contribution of this article lies in three points. First, due to the lack of downhole data, the problem of suppressing drill-string vibrations is transformed into reducing state fluctuation of drill-string system. Meanwhile, a multiobjective optimization scheme is established. Second, the temporal relations are revealed, including modeling time, optimization time, resampling time, controller response time, buffer time, and optimization interval. They act as constraints for subsequent modeling and optimization. Third, the improved extreme learning machine methods are developed to build the calculation models of rate-of-penetration and state fluctuation of drill-string system, separately. The nondominated sorting genetic algorithm II, technique for order preference by similarity to an ideal solution method, and moving window are used to obtain the optimal weight-on-bit and rotational speed. The effectiveness of the approach is demonstrated through an industrial case study based on the actual drilling data.

Due to the complex nonlinear behavior and external sensitivity of pneumatic soft actuators (PSAs), it is difficult to design control methods to achieve their control objectives by establishing their precise specific models. This article takes a PSA with bellow-type folds, called pneumatic bellow actuator (PBA), as the object, and proposes an adaptive nonsingular fast terminal sliding mode (NFTSM) control method with time-delay estimation (TDE) to achieve the trajectory tracking control of the PBA without relying on its specific model. The model framework of the PBA is first discussed, but the specific model is unknown, and all the unknown model information is defined as the lumped unknown dynamics. The TDE is applied to obtain the estimation of the lumped unknown dynamics using only the measured system states. Based on the estimation information, an adaptive NFTSM control method is proposed. This control method is nonsingular, continuous, adaptive, and accurate. Since the step of establishing the specific model of the PBA is omitted, and the model framework used in this article is universal for many PSAs, this control method exhibits universal applicability for controlling other PSAs that have difficulty obtaining specific models. The effectiveness is validated through stability analysis and PBA tracking experiments under different loads.

Carbon consumption dynamic modeling is essential for energy saving, emission reduction, and green manufacturing of iron ore sintering process. This article proposes a novel adaptive weighted broad echo state learning system (AWBESLS) for carbon consumption dynamic prediction in the sintering process by integrating adaptive weights and a reservoir with echo state characteristics. Different from previous studies, the AWBESLS adaptively matches a weight to each production data to overcome the effects of anomalous data in production data and utilizes an echo state network (ESN) for catching the dynamic state in sintering process. Carbon consumption experiments using actual production data reveal the effectiveness of the AWBESLS and compare it with some state-of-the-art methods. The results show that the AWBESLS is superior to other methods in improving the prediction performance with lowest prediction error. In summary, the AWBESLS is an effective and applicable technique for dynamic modeling of the sintering process that is easily applicable for the modeling of other manufacturing processes.

In a two-crane cooperative lift process, unreasonable load distribution on the two cranes may cause one of the cranes to overload, which may cause a dangerous overturn accident. Therefore, the load distribution should be taken as a constraint to yield a safe path for a cooperative lift. Besides, the load distribution on the two cranes varies with the changing postures of the cranes. However, the explicit relationship between the load distribution and the postures has not been reported. Therefore, this article first presents a relationship model between the postures of the two cranes and the load distribution on them. Next, a new path-planning method based on reinforcement learning is explained, which utilizes the load constraint as the optimization object in the cooperative two-crane lift. Simulation results show that the new method yields a short lift path with reasonable load distribution.

It becomes apparent that time-series dynamic prediction for carbon consumption in sintering production process holds immense significance in the steel industry, as it plays a pivotal role in determining the efficiency and environmental impact of the operation. Given the complexities of the sintering process, encompassing multiple operating conditions, numerous parameters, nonlinearities, etc., this article proposes a time-series dynamic modeling method for carbon consumption based on an improved just-in-time learning (JITL) and a gated recurrent unit-based temporal cascade broad learning system (GRU-TCBLS). First, the data correlation analysis method is employed to determine the process parameters affecting carbon consumption. Further, an improved JITL method incorporating moving window and JITL is developed to obtain relevant training data in real-time for model training. Finally, based on these relevant training data, the GRU-TCBLS is formulated to construct a carbon consumption prediction model. Experiments based on actual production data demonstrate the superiority of the proposed method with respect to some state-of-the-art modeling methods.

This article studies nonconservative stability conditions of continuous-time switched linear systems under mode-dependent dwell time (MDT). To establish a unified analysis approach for switched systems with stable and/or unstable subsystems, a concept called “dictionary” is introduced to characterize admissible MDT switching sequences. Subsequently, two equivalent nonconservative conditions of the global uniform asymptotic stability (GUAS) are obtained based on quadratic Lyapunov functions (LFs). Moreover, the stability results are transformed into convex conditions for facilitating the controller design. In addition, the developed stability results are applied toL2-gain analysis andH∞controller design for the continuous-time switched linear system subject to external disturbances. Simulations are provided to validate the effectiveness and the superiority over existing results.

Ignition temperature in a sintering process is an important factor for the quality and yield of sinter ore. Due to the diversity of the calorific value and the flow rate in the sintering process, there are many different steady states in the combustion process. Under different steady states, the change interval and fluctuation range of calorific value and flow rate are completely different which shows the sintering data is one kind of typical imperfect data. In this case, if these data are used to model and control in conventional machine learning methods, it will lead to inaccurate results. This paper presents an intelligent control strategy for ignition temperature based on working-condition recognition to stabilize the ignition temperature. First, this paper describes the structure of the intelligent control system for ignition temperature, including the working-condition recognition module and the different fuzzy prediction controllers. Then, this paper explains a fuzzy C-means clustering algorithm to recognize the working-condition of an ignition process. Next, this paper presents the detailed design of the fuzzy prediction controller for each specific working-condition, including an Elman prediction model optimized by the particle swarm optimization and a fuzzy controller. Finally, some experimental results based on actual production data show that the method controls the ignition temperature accurately in the complex production environmentNote to Practitioners—The motivation of this paper is to control the ignition temperature in the sintering process to improve ignition efficiency. The existing methods for ignition temperature control mainly focus on the design of the model and controller, and rarely consider the influence of ignition conditions on the system. This paper presents an intelligent control method of ignition temperature by recognizing different working conditions to accurately control the ignition parameters. The working condition recognization effectively solves the problem of the large difference between different data and states. By applying the proposed control strategy, the control error of the sintering plant is kept in a small range to meet the actual control requirements of the sintering plant. Future work is to extend the proposed method to more industrial application scenarios that have imperfect datasets characterized.

Real industrial processes often present coupled static and dynamic characteristics, leading to significant challenges for fault detection and isolation. However, traditional dynamic modeling methods may lead to the coupling problem of statics and dynamics, which provide ambiguous process status descriptions and incorrect fault isolation results. In this work, a novel full decoupling high-order dynamic mode decomposition (FDHODMD) method is developed for fault detection and isolation of dynamic processes. Different from the existing dynamic methods, the proposed FDHODMD can separate the high-order dynamic information from static information. First, the static characteristics are separated by discarding the decomposed features corresponding to smaller singular values. Then, a high-order dynamic model is established to present the temporal relationships between variables. In this way, the effect of static characteristics on dynamics analysis can be eliminated. Accordingly, from both static and dynamic perspectives, multiple statistics are designed to comprehensively detect the anomalies and provide an explicit status identification. In addition to the static fault isolation strategy, a dynamic fault isolation strategy is designed to recognize the fault variables after detecting the deviation, which divides the complex dynamic system into several individual dynamic modes to avoid the interaction of dynamic characteristics. Thereupon, the contributions of different variables to each dynamic mode can be clearly presented to recognize the fault variables. Finally, the validity of the proposed method is illustrated through both a numerical case and a real industrial process. Note to Practitioners—In industrial processes, the static and dynamic characteristics of data are often coupled. This work presents a FDHODMD method, which can be considered the high-order version of DMD, to achieve the decoupling of dynamics and statics while extracting high-order dynamic characteristics. Then the proposed fault detection strategy designs multiple statistics for monitoring the process from both dynamic and static perspectives, which ensures the safe operation of industrial processes. After detecting the anomaly, the proposed fault isolation strategy can recognize the fault variables separately dominating the dynamic and static deviation, which may help engineers locate the fault source.

Microwave cavity filters are essential electromechanical coupling devices in communication systems. Structural-parameter tuning by experienced operators improves the filter performance but is demanding and time-consuming. The automatic tuning method has received extensive research attentions using data-driven modeling approaches. However, two main issues affect the accuracy and efficiency of the model construction: 1) features of tuning processes, as model inputs, have limited adaptability and extraction accuracy to different resonant states and 2) models require plentiful training data and the training process is time-consuming. Thus, dynamic hybrid models are developed in this study with self-selected inputs, self-organized samples, and a self-learning structure. First, spatial features are extracted to flexibly depict the tuning characteristic, and double-domain (spatial or circuital) features are selected adaptively to accommodate distinct resonance states. Second, a trustworthiness-curiosity-driven active sampling method is exploited to attain fewer and better-training data. Third, an improved glsms broad learning system acrlong BLS is developed using new modules of incremental node calculation and weight pruning, characterized by more lightweight and flexible structures. The proposed method is effective and flexible demonstrated by simulations and experiments, and the tuning task of microwave cavity filters is fulfilled in a more accurate and efficient manner.

The event-triggered model predictive control (MPC) problem is addressed for polytopic uncertain systems. A new dynamic event-triggered mechanism (DETM) with a bounded dynamic variable and a time-varying threshold is proposed to manage measurement data packet releases. The dynamic output-feedback MPC issue is detailed as a "min-max" optimization problem (OP) with an objective function over an infinite horizon, where the hard constraint on the predictive control is required. By applying a Lyapunov-like function containing the bounded dynamic variable, an auxiliary OP constrained by several matrix inequalities is proposed, and the design methods of the output-feedback gains are provided if this auxiliary OP is feasible. The designed MPC controller ensures that the closed-loop system is input-to-state practically stable. Two examples including an event-triggered DC motor are given to illustrate the validity of the developed MPC algorithm. Simulation results verify that the proposed DETM has advantages over some existing triggering mechanisms in decreasing the consumption of resources while meeting the required performance.

This research investigates the stability of discrete-time neural networks (DNNs) with a time-varying delay by using the Lyapunov-Krasovskii functional (LKF) method. Recent researches acquired some less conservatism stability criteria for time-varying delayed systems via some augmented LKFs. However, the forward difference of such LKFs resulted in high-degree time-varying delay-dependent polynomials. This research aims to develop some augmented state-related vectors and the corresponding extended free-weighting matrices zero equations to avoid the appearance of such high-degree polynomials and help to provide more freedom for the estimation results. Besides, an augmented delay-product-type LKF is also established for ameliorating the stability conditions of the time-varying delayed DNNs. Then, based on the above methods and Jensen's summation inequality, the auxiliary-function-based summation inequality, and the reciprocally convex matrix inequality, some less conservatism stability criteria for time-varying delayed DNNs are formulated. The validity of the proposed time-varying delay-dependent stability criteria is illustrated by two numerical examples.

It is inevitable to encounter through different formations in the drilling process for deep exploration, and the penetration resistance coefficient (PRC) is an uncertain parameter related to lithology. In this article, a parameter-estimation-based gain-scheduling controller is developed to eliminate undesired system performance deterioration due to the uncertain parameter. First, a drill-string axial finite element model with the uncertain PRC is established, and a control-oriented low-order model is derived via mode selection. A gain-scheduling controller is computed based on the quadratic stability condition of the closed-loop system, which can cope with the system's parameter uncertainty using variable low-frequency gain. An adaptive observer is designed to estimate the unmeasurable scheduling variable. Field data from a geothermal drilling well is obtained to validate our model. According to this drilling well scenario, both numerical and experimental results illustrate the effectiveness of our method. The explicit relationship between the controller gain and the uncertain parameter is presented. It is found that the performance of the closed-loop system is more sensitive to the controller gain when drilling in soft formations, requiring more attention in such scenarios.

Time series anomaly in the sintering process is a direct manifestation of equipment failure and abnormal operating mode, and effective detection of time series anomaly is important to improve the stability of the sintering process. This paper presents a time series anomaly detection via rectangular information granulation, whose originality is to apply the similarity of information granules as a reference for anomaly detection. It converts time series into rectangular granules, and the similarity of time series is measured with rectangular granules. The one-way analysis of variance method is used to detect the difference for the similarity between the time series to be detected and the historical time series and the similarity between any two historical time series, thus achieving the anomaly detection of the time series. The experiment is conducted on real-world data from an enterprise. The result shows that the proposed method outperforms the probability density analysis method and can effectively detect abnormal time series.

This study presents a two-dimensional (2-D) repetitive control method to address the issues of periodic tracking and disturbance suppression in uncertain Takagi–Sugeno systems. The disturbance and uncertainty are treated as an equivalent-input-disturbance (EID). However, the conventional EID estimators typically suppress the EID through high gain. Meanwhile, the low-pass filter associated with EID causes a certain degree of phase lag. A proportional–integral (PI) filter is integrated with an EID estimator to develop a PI-EID structure to improve the estimation accuracy. Based on the self-learning mechanism of repetitive control, the 2-D repetitive controller is used to achieve a high level of tracking. Unlike the conventional nonlinear repetitive control methods, the state observer and the PI-EID estimator are membership function dependent. The gains of both controllers switch in line with the signs of the time derivative of the normalized premise variables, and this framework takes full account of the information of the nonlinear membership functions. The controller design procedures and the stability conditions are detailedly presented. Finally, a rotation speed control experiment is conducted to validate the developed PI-EID method.

An original attention-based indoor scene recognition model combining local and global features is proposed. Multi-strategy data augmentation using several different functions and intensities can improve the classification performance. Then, local features are extracted using a convolutional layer and a single self-attention, thus solving the problem of large intra-class variance. The multi-attention mechanism is used to fuse the local feature information extracted from different foci to obtain a more complete global feature representation. The multi-head attention mechanism allows the network to extract features in parallel in different directions of attention, which helps the network to better capture global information, improves the network's ability to understand and represent the input data, and solves the problem of high inter-class similarity. Finally, the extracted features are fed into the classifier to complete the classification of indoor scene images. Experiments are conducted on four data sets (IndoorCVPR09, SUN397, 15-Scenes and self-built small sample scientific indoor scene dataset), yield excellent results. The results show that the developed algorithm effectively solves the two problems of high intra-class diversity and high inter-class similarity. As a result, the model has achieved competitive results. Preliminary application experiments are developed in our HRI system, indicating that the proposed indoor scene recognition model can be applied to the complete environmental perception in HRI.

Optimization control of the rate of penetration (ROP) is crucial due to its vital role in maximizing the drilling efficiency. In this article, a dynamic optimization-based intelligent control system for drilling ROP is proposed considering the drilling characteristics. First of all, the framework of the proposed system is described, which has two layers (intelligent optimization layer and basic automation layer). In the former layer, two stages (ROP modeling stage and ROP optimization/implementation stage) are executed alternatively by using the moving window strategy. Moving window-Extreme learning machine and tenfold cross validation are used to establish the dynamic model between the rotation speed (RPM), weight on bit (WOB), depth, and ROP. In addition, hybrid bat algorithm is introduced to search the controllable parameters while the inputs for ROP optimization are RPM, WOB, depth, constraints, and ROP model, and the outputs are the optimized RPM and optimized WOB. After that, the outputs are recommended to the driller to be used as the setpoints of the basic automation layer. Comparison results of simulation with seven well-known methods demonstrate the effectiveness of the proposed system. In addition, in an industrial application to a real-world drilling process in the Xiangyang area, Central China, the ROP was improved by 15.9%.

In this article, a state decomposition technique (SDT) is used to address the output-feedback control challenge for nonlinear singular systems with exogenous disturbance. The objective is to design an output-feedback controller to enhance system performance. First, a disturbance estimator is built to estimate and compensate for the adverse impacts of exogenous disturbance on the system. Second, the closed-loop nonlinear singular system is decomposed into an algebraic subsystem and a differential subsystem based on the SDT. Then, a state decomposition Lyapunov function is designed to obtain a new admissible criterion with fewer decision variables. Third, an output-feedback controller is designed using the admissible criterion and depends on the controller gain's decomposition component. Finally, a comparison between a sliding-mode control and the presented approach through a practical application model demonstrates the practicability and efficacy of the presented approach.

Burn-through point (BTP) is an essential thermal state parameter in a sintering process, which is a direct reflection of the stability of this process. However, it cannot be measured online. Soft-sensing technology offers a reliable method for estimating unmeasurable variables in industrial processes. Here, a soft-sensing model for BTP based on weighted kernel just-in-time learning (WKJITL) and fuzzy broad-learning system (FBLS) is built. First, an abnormal production data detection and correction strategy is employed to process the production data, and the mechanism analysis and mutual information analysis are utilized to specify the detectable process variables that are directly related to BTP. Then, the WKJITL method is proposed to obtain historical production data similar to the query data of BTP for local learning modeling, and the FBLS is utilized as an efficient modeling method for the soft-sensing prediction of BTP. Finally, the results of simulation experiments based on actual sintering production data reveal that the developed soft-sensing model of BTP exhibits better prediction accuracy and efficiency compared with some advanced modeling methods. Furthermore, the proposed method is of general nature and can also be easily applied to other industrial processes.

Alarm systems are commonly deployed in modern industrial facilities to monitor process operations. However, due to the presence of nuisance alarms and alarm floods, their efficiencies are much degraded. Especially, alarm floods are among the most difficult issues in industrial alarm management and recognized as the main causes of many industrial accidents. To address alarm floods, this article proposes a root cause identification (RCI) method for industrial alarm floods based on word embedding and few-shot learning. The contributions are threefold: 1) A textual encoding method based on word embedding is proposed to convert alarm messages into numerical word vectors that can be used in the modeling of RCI; 2) an alarm-priority-based adaptive weighting strategy is designed to make the RCI more sensitive to alarms of higher priorities and appearing earlier; 3) a few-shot learning method based on long short-term memory is adapted to identify the root causes of alarm floods based on limited instances of labeled data. The effectiveness and superiority of the proposed method are demonstrated by a case study based on data from the vinyl acetate monomer public model.

The temperature of the cooling stave (TCS) is an important state parameter to indicate the states of the slag crust during the blast furnace ironmaking process. The state of the slag crust affects the quality and production of pig iron, and the gas flow distribution in the blast furnace. Thus, it is necessary to recognize the states of the slag crust. This article proposes a condition recognition strategy based on fuzzy clustering endowed with a novel distance with information granulation for recognizing the states of the slag crust. First, the raw TCS time-series data are split into segments according to the appropriate segmentation length, and the segments are represented in a granular form by the information granulation method. Then, information granules are clustered using fuzzy clustering endowed with a novel distance. After completing the data representation, each information granule is compounded of a lower bound and an upper bound that indicate the dynamic characteristics of the corresponding segments. In the fuzzy clustering, information granulation distance, a new distance, is established to measure the similarity between two information granules. Finally, the data experiments using the datasets from the UCR time-series database and actual industrial data from the blast furnace demonstrate the effectiveness and superiority of the proposed condition recognition strategy.

This article investigates the efficient model predictive load frequency control problem for multiarea power systems, where the measured state is transmitted under a new dynamic event-triggered mechanism (DETM) with hybrid variables. By applying$H_{2}$/$H_{\infty }$performance index, a DETM-based efficient model predictive control (EMPC) method is presented. This EMPC issue is described as a “min-max” optimization problem (OP) with hard constraints on system state. By utilizing a Lyapunov function with internal dynamic variable, an offline auxiliary OP with constraints of matrix inequalities is put forward to optimize the feedback gain and the weighting matrix of the DETM. Another offline OP is also proposed to maximize the size of initial feasible region (IFR). To steer the augmented state in IFR into the terminal constraint set and improve the control performance, a sequence of admissible control is implemented whose perturbation parameters are designed by solving an online OP. A case study on a three-area power system demonstrates the validity and superiority of the designed DETM and dynamic event-based EMPC algorithm.

Soft manipulators have been widely developed due to their manipulation safety, design versatility, and motion dexterity. However, accurate kinematic modeling and control of soft manipulators are still challenging due to the complex nonlinear hysteresis in their motion characteristics. This article presents the fabrication of an elephant-trunk-inspired soft manipulator (ESM) using pneumatic bellows actuators (PBAs) and proposes a kinematic modeling and control method considering hysteresis. The ESM contains three soft arms and a pneumatic claw, while each soft arm consists of four PBAs connected in parallel. The forward kinematics of the ESM are modeled using the piecewise constant curvature (PCC) method. The kinematic model of the ESM consists of three parts: actuator space, configuration space, and task space. To address the inability of the PCC method to characterize the nonlinearity of soft materials, the hysteresis of the PBA in the actuator space is modeled using the Prandtl–Ishlinskii model. The inverse kinematic model of the ESM is derived from its forward kinematic model, and on this basis, a feedforward controller is developed to achieve position control of the ESM. The positional workspace of the ESM is analyzed using the Monte Carlo method. The validity of the kinematic model is verified experimentally. Position control and application experiments are conducted to demonstrate the practical application of the ESM.

Data-driven fault diagnosis methods have been widely applied at present. In actual processes, there usually exist multiple failure modes; the data frequency spectrum varies in different failure modes, which would bring challenges for feature extraction and subsequent fault diagnosis. In this article, a decision fusion scheme based on the mode decomposition and evidence theory is proposed for fault diagnosis during drilling. The raw data are decomposed into multiple series with different center frequencies, the decomposed series are reconstructed to several groups. For each group, the local diagnosis model is established, thus, several local diagnostic results are obtained. Then, all local diagnostic results are fed into the evidence theory-based decision fusion model. Meanwhile, a confidence matrices-based weight adjustment method is designed to enhance the reliability of fused results. An industrial case study based on the actual drilling data verifies that the proposed method is beneficial to improve the diagnostic effect during drilling.

A coupled multimodal emotional feature analysis (CMEFA) method based on broad-deep fusion networks, which divide multimodal emotion recognition into two layers, is proposed. First, facial emotional features and gesture emotional features are extracted using the broad and deep learning fusion network (BDFN). Considering that the bi-modal emotion is not completely independent of each other, canonical correlation analysis (CCA) is used to analyze and extract the correlation between the emotion features, and a coupling network is established for emotion recognition of the extracted bi-modal features. Both simulation and application experiments are completed. According to the simulation experiments completed on the bimodal face and body gesture database (FABO), the recognition rate of the proposed method has increased by 1.15% compared to that of the support vector machine recursive feature elimination (SVMRFE) (without considering the unbalanced contribution of features). Moreover, by using the proposed method, the multimodal recognition rate is 21.22%, 2.65%, 1.61%, 1.54%, and 0.20% higher than those of the fuzzy deep neural network with sparse autoencoder (FDNNSA), ResNet-101 + GFK, C3D + MCB + DBN, the hierarchical classification fusion strategy (HCFS), and cross-channel convolutional neural network (CCCNN), respectively. In addition, preliminary application experiments are carried out on our developed emotional social robot system, where emotional robot recognizes the emotions of eight volunteers based on their facial expressions and body gestures.

This article investigates the problem of dynamic event-triggered finite-time$H_{\infty }$state estimation for a class of discrete-time nonlinear two-time-scale Markov jump complex networks. A hybrid adjusting variables-dependent dynamic event-triggered mechanism (DETM) is proposed to regulate the releases of measurement outputs of a node to a remote state estimator. Such a DETM contains both an additive dynamically adjusting variable (DAV) and a multiplicative adaptively adjusting variable. The aim is to design a DETM-based mode-dependent state estimator, which guarantees that the resultant error dynamics is stochastically finite-time bounded with$H_{\infty }$performance. By constructing a mode-dependent Lyapunov function with multiple DAVs and a singular perturbation parameter associated with time scales, a matrix-inequalities-based sufficient condition is derived, the feasible solutions of which facilitate the design of the parameters of the state estimator. The validity of the designed state estimator and the superiority of the devised DETM are verified by two examples. It is verified that the devised DETM is capable of saving network resources and simultaneously improving the estimation performance.

Convolutional feature-based broad learning with long short-term memory (CBLSTM) is proposed to recognize multidimensional facial emotions in human–robot interaction. The CBLSTM model consists of convolution and pooling layers, broad learning (BL), and long- and short-term memory network. It aims to obtain the depth, width, and time scale information of facial emotion through three parts of the model, so as to realize multidimensional facial emotion recognition. CBLSTM adopts the structure of BL after processing was done at the convolution and pooling layer to replace the original random mapping method and extract features with more representation ability, which significantly reduces the computational time of the facial emotion recognition network. Moreover, we adopted incremental learning, which can quickly reconstruct the model without a complete retraining process. Experiments on three databases are developed, including CK+, MMI, and SFEW2.0 databases. The experimental results show that the proposed CBLSTM model using multidimensional information produces higher recognition accuracy than that without time scale information. It is 1.30% higher on the CK+ database and 1.06% higher on the MMI database. The computation time is 9.065 s, which is significantly shorter than the time reported for the convolutional neural network (CNN). In addition, the proposed method obtains improvement compared to the state-of-the-art methods. It improves the recognition rate by 3.97%, 1.77%, and 0.17% compared to that of CNN-SIPS, HOG-TOP, and CMACNN in the CK+ database, 5.17%, 5.14%, and 3.56% compared to TLMOS, ALAW, and DAUGN in the MMI database, and 7.08% and 2.98% compared to CNNVA and QCNN in the SFEW2.0 database.

Prompt detection of bit bounce can prevent serious incidents and is of great importance for safe and efficient deep geological drilling. In the early stage of bit bounce, signal changes are relatively weak. In addition, there are differences in the topological relationships of samples at different time instances in normal state and bit bounce. These factors present a challenge to timely and accurate bit bounce detection. Therefore, this paper proposes a bit bounce detection method based on multi-feature graph and graph convolution networks. A multi-feature graph construction method using process variables, mean value, Mahalanobis distance, and Euclidean distance is proposed, and a two-layer graph convolutional network is designed to realize deep feature extraction and incident detection. The effectiveness and superiority of the proposed method are demonstrated by a real drilling industrial case.

Social Internet of Things (SIoT) is an emerging application area that supports the spread of multimedia information. Detecting critical nodes based on the results of influence prediction is the main solution to maximizing the information propagation in SIoT. However, while the tasks of predicting an influence probability and a cascade size are both critical in influence prediction, there has not yet a study that thoroughly investigates these two influence parameters. This article presents an end-to-end method that learns dual-task network embeddings to jointly predict influence probabilities and cascade sizes, which is called a multidimensional influence-to-vector method (Multi-Influor). First, multidimensional influence contexts are generated based on random walks, incorporating multiple estimating factors for pairwise node interaction, network structure, and global preference similarity. A new method of learning dual-task network embeddings is then devised to simultaneously capture influence probabilities and cascade sizes. The two tasks are both formulated into a unified framework via enforcing an information-sharing embedding matrix. Finally, stochastic gradient descent (SGD) is used to optimize two loss functions for influence prediction in an alternating manner, and the tasks are jointly accomplished that produces an accurate prediction. Extensive simulation results on real-world data sets show that Multi-Influor outperforms six state-of-the-art methods in accuracy and efficiency, and that a joint training method for the two tasks improves the overall prediction performance. Moreover, Multi-Influor is a practical method for SIoT sustainable computing.

This article is concerned with the problem of dissipativity for discrete-time singular systems with time-varying delays. First, the discrete-state decomposition technique is proposed after performing the restricted equivalent transformation for singular systems. To reduce the use of decision variables, the state-decomposed Lyapunov function is established based on the decomposed state vectors. Second, to obtain the condition with less conservatism, the two zero-value equations, especially concerning difference subsystems and algebraic ones, the discrete Wirtinger-based inequality and the extended reciprocally convex inequality are employed to bound the forward difference of the Lyapunov function. Then, the less conservative dissipativity criteria with lower computational complexity are obtained. Finally, simulation results are provided to demonstrate the superiority of the proposed technique.

This article presents a method of suppressing packet losses and exogenous disturbances for a networked control system (NCS) subject to network-introduced delays. The NCS has two feedback loops: 1) a local one and 2) a main one. The local feedback loop contains a state observer, an equivalent-input-disturbance (EID) estimator, and state feedback. It is used to ensure prompt disturbance suppression. The controller in the main feedback loop contains an internal model to track a reference input. The system is divided into two subsystems for the design of controllers. The state-observer gain is designed for one subsystem using the concept of perfect regulation to ensure disturbance estimation performance. The state-feedback gains of the other subsystem are designed based on a stability condition in the form of a linear matrix inequality (LMI). A tracking specification is embedded in the LMI-based stability condition to ensure satisfactory tracking performance. A case study on a two-finger robot hand control system and a comparison with a Smith-EID and$H_{\infty }$controller approach validate the effectiveness and superiority of the presented method.

For a three-link vertical underactuated manipulator (TVUM) with only one active joint, the control target is to swing up its endpoint from the straight-down equilibrium point (SDEP) and to stabilize the endpoint at the straight-up equilibrium point (SUEP) eventually. Up to now, there are few effective control strategies to achieve the above control target. In this article, we propose an effective control method based on the trajectory optimization to realize the system control target, and the main steps of this article are: 1) a continuous trajectory that consists of two segments with design parameters is planned for the actuated link, along which the actuated link can be swung up from the initial states to the final states; 2) the design parameters are optimized by using the intelligent optimization algorithm to guarantee that the states of the underactuated links are continuous at the junction. In this way, the underactuated links are also moved to their final states with the actuated link simultaneously; 3) a tracking controller is designed by using the sliding-mode method to track the trajectory with optimized design parameters, so the endpoint is swung up from the SDEP to the SUEP directly; and 4) a stabilizing controller is further devised through the LQR method to keep the endpoint being stable at the SUEP. Finally, simulation results show that the proposed control method achieves the swing-up and stable control target of the system, and the control performance of the proposed method is superior than that of the existing control methods through the comparisons.

In this article, a coupled axial-torsional drill-string vibration model is established, which considers the influence of bit balling on rock-breaking and drill-string vibration. First, a bit-rock interaction model considering normal drilling and bit balling conditions is established, where the different rock-breaking conditions are classified based on the Gaussian mixture model. The fuzzy method is used to solve clustering inaccuracies problems in the bit balling formation and disappearance phases, and a fuzzy bit-rock interaction model is established in these two phases. The bit-rock interaction modeling method has higher accuracy in describing bit balling than the Real, Ritto, and Karnopp models. Finally, the coupled axial-torsional drill-string vibration model considering bit balling is established based on the established bit-rock interaction model, using the drilling tool parameters of a geothermal well and the bit-rock interaction model parameter identification result. The effectiveness of the modeling method is illustrated by micro-rig experiments and field data verification.

The emotion perception capability could endow machines with deeper feedback evaluation of human–machine interaction (HMI), which makes the experience of HMI more harmonious and natural. Currently, how to obtain the robust surface and semantic facial representation features has not been fully explored, moreover, the parameters and computation of conventional convolutional neural network models, which are adopted in facial expression recognition (FER) are too heavy, it is not conducive to the deployment of the HMI system. Therefore, this article proposes a representation reinforcement network (RRN) and transfer self-training (TST) based efficient FER method. Our designed RRN is mainly composed of two modules, i.e., surface representation reinforcement (SurRR) module and semantic representation reinforcement (SemaRR) module. SurRR module fuses the facial features in different dimensions and highlights key feature messaging nodes in feature maps. SemaRR module establishes the deep semantic representation of global facial regions on spatial and channel dimensions. Therefore, RRN has stronger feature extraction capability when the parameters and computational complexity are significantly reduced, and TST is proposed for contributing to the training effect of RRN at the condition of insufficient training data. We tested our method on the extended Cohn-Kanade dataset (CK+), Radboud faces database (RaFD), FERPLUS, and the real-world affective faces database (RAF-DB) datasets, and the recognition accuracy are 100%, 98.62%, 89.64%, and 88.72%, respectively. Furthermore, the preliminary application experiment, which demonstrates the feasibility of our method in practice during HMI.

Complicated geological environments lead to a high risk of drilling incidents. Early warning of loss and kick for the drilling process is essential to ensure process safety. On account of the nonlinear and temporal correlation of drilling parameters, an early warning method for loss and kick based on sparse autoencoder with multivariate time series is proposed. The sparse autoencoder is utilized for multivariate time series abnormality detection of the drilling process. Abnormal drilling parameter isolation is performed through contribution analysis. Reconstruction analysis and time series segmentation approaches are integrated for abnormal time series trend evaluation. The characteristic of drilling parameters under normal operation learned by the sparse autoencoder and the property of the original time series are taken into account. The final early warning result can be obtained through expert rules based on the trend evaluation result. Case studies are presented based on the data from an actual drilling project. The experiment result shows the effectiveness of the proposed method.

In the geological drilling process, predicting the rate of penetration (ROP) is significantly important for improving drilling efficiency and reducing nondrilling time. However, due to the drilling data pollution and the complex nonlinearity in the geological drilling process, a reliable and highly accurate ROP prediction model is not easy to construct, and the model accuracy is affected by the value of model hyperparameters. In order to overcome the difficulties in modeling, a novel ROP model is developed to handle abnormal data and achieve nonlinear fitting. First, a local outlier factor is introduced to automatically detect the abnormal data, and then, replace it with the nearest normal data. Then, the support vector regression (SVR) method is applied to construct nonlinear prediction model for ROP, and a modified bat algorithm (MBA) is developed to solve the non-convex problem in determining optimal value of hyperparameters for SVR-based ROP model. The MBA has six modifications to improve the global search ability, which achieves better performance in global search ability compared with other nine algorithms based on the experiments of IEEE 2005 benchmark functions. The developed ROP prediction model that combines SVR and MBA methods is tested based on actual drilling data and a semiphysical system, and the simulation and application results show that the developed modeling method has higher ROP prediction accuracy compared with the other modeling methods.

This article is concerned with passivity analysis of neural networks with a time-varying delay. Several techniques in the domain are improved to establish the new passivity criterion with less conservatism. First, a Lyapunov-Krasovskii functional (LKF) is constructed with two general delay-product-type terms which contain any chosen degree of polynomials in time-varying delay. Second, a general convexity lemma without conservatism is developed to address the positive-definiteness of the LKF and the negative-definiteness of its time-derivative. Then, with these improved results, a hierarchical passivity criterion of less conservatism is obtained for neural networks with a time-varying delay, whose size and conservatism vary with the maximal degree of the time-varying delay polynomial in the LKF. It is shown that the conservatism of the passivity criterion does not always reduce as the degree of the time-varying delay polynomial increases. Finally, a numerical example is given to illustrate the proposed criterion and benchmark against the existing results.

The two-stage fuzzy fusion based-convolution neural network is proposed for dynamic emotion recognition by using both facial expression and speech modalities, which not only can extract discriminative emotion features which contain spatio-temporal information, but also can effectively fuse facial expression and speech modalities. Moreover, the proposal is able to handle situations where the contributions of each modality data to emotion recognition are very imbalanced. The local binary patterns coming from three orthogonal planes and spectrogram are considered first to extract low-level dynamic emotion, so that the spatio-temporal information of these modalities can be obtained. To reveal more discriminative features, two deep convolution neural networks are constructed to extract high-level emotion semantic features. Moreover, the two stage fuzzy fusion strategy is developed by integrating canonical correlation analysis and fuzzy broad learning system, so as to take into account the correlation and difference between different modal features, as well as handle the ambiguity of emotional state information. The experimental results obtained on benchmark databases show that the accuracies of the proposed method are higher than those of existing methods (such as the hybrid deep model, and the rule-based and machine learning method) on SAVEE, eNTERFACE’05, and AFEW databases.

This article presents an improved equivalent-input-disturbance (EID) approach to handle unknown disturbances and plant uncertainties. The disturbances and uncertainties are treated as a lumped disturbance in an EID-based control system. The effect of the lumped disturbance is compensated by an EID estimator. A constraint between design parameters and uncertainties is imposed on the design of the estimator. In addition, there are insufficient analyses of the influence of uncertainties on the control performance and the stability of the system. A new filter is devised for an improved EID estimator in this article to remove the constraint. This ensures that the sensitivity of the system to disturbances at low frequencies can be freely decreased. An analysis of the system reveals that uncertainties not only influence disturbance-rejection and reference-tracking performance but also affect system stability. A sufficient stability criterion is derived with consideration of uncertainties. The validity of the presented method is demonstrated by simulation and experimental results.

Sintering is the preproduction process of ironmaking, whose products are the basis of ironmaking. How to improve the operating performance of the iron ore sintering process has always been a problem that operators are committed to solve. An operating performance improvement method based on prediction and grade assessment is presented in this article. First, considering the data distribution characteristics of the process, a performance index prediction model based on the Gaussian process regression is built, in which the mutual information analysis method is used to select the inputs of the performance index prediction model. Then, the operating performance grade is assessed by a threshold division method. Next, the operating performance grade guides the control of the burn-through point to improve the operating performance. Finally, experimental verification is performed based on the actual running data. The results show that the proposed method has high prediction accuracy, and it is also significant in improving the operating performance. Therefore, this approach provides an effective solution to predict and improve operating performance.

This article investigates the optimal synchronization problem for unknown discrete-time nonlinear heterogeneous multiagent systems (MASs). It is very intractable to derive the analytical solutions of coupled Bellman's equations, which are necessary to overcome this problem. We propose a data-based optimal synchronization control strategy based on a hierarchical and distributed optimal control framework composed of a model reference adaptive control (MRAC) layer and a distributed control layer. In the MRAC layer, the similar-offline MRAC algorithm is developed to make subsystems of MASs track their reference models, respectively. Then, the distributed optimal control problem of nonlinear heterogeneous MASs is transformed into that of homogeneous MASs composed of the reference models and the leader. In the distributed control layer, the distributed reference policy iteration algorithm is proposed to derive the solutions of coupled composite nonlinear Bellman's equations, which ensure that the homogeneous MASs reach synchronization with optimum. The suboptimal synchronization control is achieved via optimization further. Convergence analysis of both algorithms is rigorously provided. The simulation results verify the effectiveness of the proposed strategy.

A key energy consumption in steel metallurgy comes from an iron ore sintering process. Enhancing carbon utilization in this process is important for green manufacturing and energy saving and its prerequisite is a time-series prediction of carbon efficiency. The existing carbon efficiency models usually have a complex structure, leading to a time-consuming training process. In addition, a complete retraining process will be encountered if the models are inaccurate or data change. Analyzing the complex characteristics of the sintering process, we develop an original prediction framework, that is, a weighted kernel-based fuzzy C-means (WKFCM)-based broad learning model (BLM), to achieve fast and effective carbon efficiency modeling. First, sintering parameters affecting carbon efficiency are determined, following the sintering process mechanism. Next, WKFCM clustering is first presented for the identification of multiple operating conditions to better reflect the system dynamics of this process. Then, the BLM is built under each operating condition. Finally, a nearest neighbor criterion is used to determine which BLM is invoked for the time-series prediction of carbon efficiency. Experimental results using actual run data exhibit that, compared with other prediction models, the developed model can more accurately and efficiently achieve the time-series prediction of carbon efficiency. Furthermore, the developed model can also be used for the efficient and effective modeling of other industrial processes due to its flexible structure.

This article presents a novel reconstructed model for the delayed load frequency control (LFC) schemes considering wind power, which aims to improve the computational efficiency for PID controllers while retaining their dynamic performance. Via fully exploiting system states influenced by time delays directly, this novel reconstructed method is proposed with a controller isolated. Hence, when the PID controllers are unknown, the stability criterion based on this model can resolve controller gains with less time consumed. For given PID gains, this model can be employed to establish criteria for stability analysis, which can realize the tradeoff between the calculation accuracy and efficiency. The case study is first based on a two-area traditional LFC system to validate the merits of a novel reconstructed model, including accurately estimating the influence of time delay on system frequency stability with increased computational capability. Then, under traditional and deregulated environments, case studies are carried out on the two-area and three-area schemes, respectively. Through the novel reconstructed model, the efficiency of obtaining controller parameters is highly improved while their robustness against the random wind power, tie-line power changes, inertial reductions, and time delays remains almost unchanged.

In this article, the fault detection (FD) filter design problem is addressed for discrete-time memristive neural networks with time delays. When constructing the system model, an event-triggered communication mechanism is investigated to reduce the communication burden and a fault weighting matrix function is adopted to improve the accuracy of the FD filter. Then, based on the Lyapunov functional theory, an augmented Lyapunov functional is constructed. By utilizing the summation inequality approach and the improved reciprocally convex combination method, an FD filter that guarantees the asymptotic stability and the prescribed$H_{\infty }$performance level of the residual system is designed. Finally, numerical simulations are provided to illustrate the effectiveness of the presented results.

The stability of neural networks with a time-varying delay is studied in this article. First, a relaxed Lyapunov-Krasovskii functional (LKF) is presented, in which the positive-definiteness requirement of the augmented quadratic term and the delay-product-type terms are set free, and two double integral states are augmented into the single integral terms at the same time. Second, a new negative-definiteness determination method is put forward for quadratic functions by utilizing Taylor's formula and the interval-decomposition approach. This method encompasses the previous negative-definiteness determination approaches and has less conservatism. Finally, the proposed LKF and the negative-definiteness determination method are applied to the stability analysis of neural networks with a time-varying delay, whose advantages are shown by two numerical examples.

When a flexible link manipulator lacks a joint motor, how to use the remaining motors to achieve the control objective is a challenge, and the research in this direction is limited. This article presents a tip position control and vibration suppression approach for a planar two-link rigid-flexible (TLRF) underactuated manipulator with a passive first joint. First, we establish a dynamic model of the system by using the assumed mode method (AMM) and the Lagrangian modeling method. Then, we obtain the dynamic coupling relationship of the two links based on the dynamic model. According to this dynamic coupling relationship, we find that the passive rigid link can be controlled indirectly by controlling the active flexible link. Thus, we calculate the target angles of the two links by using the inverse kinematic method and design a controller for the active flexible link to stabilize it at its target angle and to suppress its vibration. Next, we optimize the parameters of this controller by using the genetic algorithm (GA). GA helps us simultaneously stabilize the passive rigid link at its target angle while realizing the control objective of the active flexible link. The simulation results demonstrate the effectiveness of the proposed control approach.

The issue of fault detection and isolation (FDI) under an event-triggered mechanism (ETM) is investigated for switched linear systems. An improved dynamic ETM (DETM), which includes some existing ETMs as special cases, is devised. Such a DETM contains two internal dynamic variables (IDVs), the mode information and seven adjustable parameters, and thus is flexible in adjusting the data packet transmissions to save network resources. The aim is to design a fault detection (FD) filter (FDF) and fault isolation filters (FIFs) such that the resultant filtering error systems are exponentially stable with prescribed exponential$H_{\infty }$performance. A new Lyapunov function, which depends on the switching mode and two IDVs, is constructed. By utilizing the Lyapunov method and the average dwell time approach, sufficient conditions are derived to guarantee the existence of the desired FDF and FIFs, whose design methods are given accordingly. A numerical example is provided to demonstrate the effectiveness of the FDI method and the superiority of the devised DETM in reducing the waste of network resources while maintaining the FD filtering performance.

The tuning of microwave cavity filters (MCFs) is mostly conducted by experienced operators, and thus, is time and resource intensive. The automatic tuning method has received lots of research attention. However, the experience of tuning experts is not described systematically, and the existing methods are not adequate for MCFs with individual differences. Considering that fuzzy expert systems are superior in flexibility and interpretability, a dynamic-attention-based heuristic fuzzy expert system is proposed in this article to achieve automatic tuning with high applicability, accuracy, and efficiency. First, the dynamic tuning process is divided into several stages, and the evaluation function of filtering performance is designed for each stage. Second, an improved expert system with dynamic attention is constructed to facilitate the comprehensive evaluation of filtering performance and to balance tuning efficiency and accuracy. Third, a heuristic fuzzy logic system is presented to obtain appropriate tuning values, with low design complexity of fuzzy rules and high utilization of tuning process information. Finally, the effectiveness, applicability, and practicality of the proposed method are demonstrated by both simulations and experiments.

Information granules can discover interpretable and meaningful relationships offering a full description for time series. This article presents an information granulation method with rectangular information granules and applies it to time-series similarity measurement. First, the fuzzy$c$-means clustering algorithm transforms the time series and its first-order difference time series to data clusters. With the maximum volume of rectangular information granules viewed as the criterion, the optimal rectangular information granules are formed using the data cluster by the principle of justifiable granularity and the gravitational search algorithm. The time-series similarity is measured by calculating the similarity between the upper and lower bounds of the optimal rectangular information granules built from the time series. Finally, an experiment is performed on a public dataset to verify the feasibility of the proposed method. The result shows that the rectangular information granulation method can capture the change characteristics of time series. The similarity measurement method can effectively evaluate the similarity of the time series belonging to different classes.

This article proposesa control performance standard (CPS)-based fuzzy event-triggered scheme for load frequency control (LFC) of power systems with a limited communication bandwidth. First, a CPS-based fuzzy LFC system is established to reduce the wear and tear of the generating unit equipment. Then, based on the Lyapunov stability theory, a stability criterion of the LFC system is proposed to ensure the stable operation of the LFC system, which considers the threshold parameter of the event-triggered condition and the fuzzy gain in the fuzzy LFC system. Next, based on the stability criterion and the Gaussian-type curve-fitting method, a functional expression between the fuzzy gain and the threshold parameter is obtained. According to the expression, the threshold parameter is updated in real time with the change of fuzzy gain, so as to further save usage of the communication network bandwidth. Case studies based on a one-area power system and an IEEE 39-bus benchmark test system are undertaken. Simulation results show that the proposed scheme achieves three objectives: 1) to comply with CPS1 and CPS2 in the North American Electric Reliability Council; 2) to reduce wear and tear of the generating unit equipment; and 3) tosave more communication network resources.

This article is concerned with the optimal synchronization problem for discrete-time nonlinear heterogeneous multiagent systems (MASs) with an active leader. To overcome the difficulty in the derivation of the optimal control protocols for these systems, we develop an observer-based adaptive synchronization control approach, including the designs of a distributed observer and a distributed model reference adaptive controller with no prior knowledge of all agents' dynamics. To begin with, for the purpose of estimating the state of a nonlinear active leader for each follower, an adaptive neural network distributed observer is designed. Such an observer serves as a reference model in the distributed model reference adaptive control (MRAC). Then, a reinforcement learning-based distributed MRAC algorithm is presented to make every follower track its corresponding reference model on behavior in real time. In this algorithm, a distributed actor-critic network is employed to approximate the optimal distributed control protocols and the cost function. Through convergence analysis, the overall observer estimation error, the model reference tracking error, and the weight estimation errors are proved to be uniformly ultimately bounded. The developed approach further achieves the synchronization by means of synthesizing these results. The effectiveness of the developed approach is verified through a numerical example.

This article deals with an uncertain two-link rigid-flexible manipulator with vibration amplitude constraint, intending to achieve its position control via motion planning and adaptive tracking approach. In motion planning, the motion trajectories for the two links of the manipulator are planned based on virtual damping and online trajectories correction techniques. The planned trajectories can not only guarantee that the two links can reach their desired angles, but also have the ability to suppress vibration, which can be adjusted to meet the vibration amplitude constraint by limiting the parameters of the planned trajectories. Then, the adaptive tracking controller is designed using the radial basis function neural network and the sliding mode control technique. The developed controller makes the two links of the manipulator track the planned trajectories under the uncertainties including unmodeled dynamics, parameter perturbations, and persistent external disturbances acting on the joint motors. The simulation results verify the effectiveness of the proposed control strategy and also demonstrate the superior performance of the motion planning and the tracking controller.

This article studies the group coordinated control problem for distributed nonlinear multiagent systems (MASs) with unknown dynamics. Cloud computing systems are employed to divide agents into groups and establish networked distributed multigroup-agent systems (ND-MGASs). To achieve the coordination of all agents and actively compensate for communication network delays, a novel networked model-free adaptive predictive control (NMFAPC) strategy combining networked predictive control theory with model-free adaptive control method is proposed. In the NMFAPC strategy, each nonlinear agent is described as a time-varying data model, which only relies on the system measurement data for adaptive learning. To analyze the system performance, a simultaneous analysis method for stability and consensus of ND-MGASs is presented. Finally, the effectiveness and practicability of the proposed NMFAPC strategy are verified by numerical simulations and experimental examples. The achievement also provides a solution for the coordination of large-scale nonlinear MASs.

The issue of finite-time$H_{\infty }$state estimation is studied for a class of discrete-time nonlinear two-time-scale complex networks (TTSCNs) whose measurement outputs are transmitted to a remote estimator via a bandwidth-limited communication network under the stochastic communication protocol (SCP). To reflect different time scales of state evolutions, a new discrete-time TTSCN model is devised by introducing a singular perturbation parameter (SPP). For the sake of avoiding/alleviating the undesirable data collisions, the SCP is adopted to schedule the data transmissions, where the transition probabilities involved are assumed to be partially unknown. By constructing a new Lyapunov function dependent on the information of the SCP and SPP, a sufficient condition is derived which ensures that the resulting error dynamics is stochastically finite-time bounded and satisfies a prescribed$H_{\infty }$performance index. By resorting to the solutions of several matrix inequalities, the gain matrices of the state estimator are given and the admissible upper bound of the SPP can be evaluated simultaneously. The performance of the designed state estimator is demonstrated by two examples.

Disturbance rejection and time-delay compensation are important for control systems in practice. This article presents an observer-and-predictor-based method to reject an unknown exogenous disturbance for an input-delay system in which only delayed output is available. First, the equivalent-input-disturbance method is employed to reconstruct the system state and to estimate the disturbance. A prediction of the disturbance is calculated to reduce the effect of a phase lag caused by the delays. A new predictive scheme is designed for feedback control. Next, the system is divided into two subsystems for analysis and design: one for reference tracking and the other for disturbance rejection. Sufficient conditions are derived to guarantee the system’s stability. An analysis of the method reveals that the disturbance rejection can be viewed as a patch to the predictor-based feedback control. Finally, two case studies are used to show the validity and superiority of the method.

This article is concerned with the trajectory optimization problem of a drilling process, which is of significance to drilling efficiency and safety. Due to the difference between an actual trajectory and a planned trajectory, this problem is a multiobjective optimization problem (MOP) with parameter uncertainties. To solve the problem, this study devises a new approach named nondominated sorting genetic Algorithm II using outlier removal (OR-NSGA-II). First, the optimization problem with parameter uncertainties is formulated, including two objective functions: 1) a trajectory length and 2) an expected value of drill-string torque. Then, an outlier-removal mechanism is devised in the sorting process of NSGA-II to reduce the negative effects of parameter uncertainties. Next, the crowding distance calculation in NSGA-II is improved to ensure population diversity. Comparison of simulation results show that our method is effective on the MOP with parameter uncertainties.

The control objective of the vertical plane underactuated manipulator (VPUM) is generally to swing up the end point (EP) from the vertical down equilibrium point (VDEP) to the vertical up equilibrium point (VUEP), and finally, to stabilize it at the VUEP. The zone control methods are usually used to achieve this control objective, but the problem of these methods is that they cannot find a unified zone range, and it is easy to appear singularity in the motion process. In this article, for two-link VPUMs, we propose a control strategy based on trajectory planning and optimization, which does not need to divide the zone range, avoids the singularity problem, and can achieve the control objective quickly and smoothly. We design the trajectory by using the time scale method for the active link according to the initial and target states. Then, we obtain the trajectory parameters by employing differential evolution algorithm to ensure that the passive link can also move from the initial states to the target states simultaneously. We design a sliding mode tracking controller to make the active link move along the designed trajectory, so the EP is moved to VUEP. Meantime, we design a sliding mode stabilization controller to ensure that the system is stable at VUEP. Finally, the universality and robustness of the proposed method are proved by simulations.

The safe and efficient operation of geological drilling systems is critically dependent on proper process monitoring. A monitoring model based on probabilistic principal component analysis is presented to deeply exploit performance feature information hidden among the process data in this paper. First, the offline monitoring model is established with historical process data collected from different sources to reveal different characteristics, and the monitoring statistics as a benchmark are obtained. Then, actual operating data are introduced to the established model to realize online monitoring. Finally, the monitoring effect is discussed, and the causes of inefficient drilling are tracked. The experimental results indicate that the proposed method can effectively monitor the operating performance of the drilling process.

The aim of this paper is to implement a robust weight on bit control design in an unified experimental system. A laboratory drilling rig is used to simulate the real world bit-rock interaction. Via communication between programmable logic controller (PLC) and OLE for Process Control (OPC) server, the laboratory drilling rig can exchange data with a finite element drill-string model and a hoisting system model which are realized in MATLAB/Simulink. Thus, an unified experimental system is established to reproduce the actual drilling process. The penetration resistance coefficient of the experiment rock sample is tested to obtain the bit-rock interaction model for controller design. Considering the high-order mode of the slender drill-string, a reduced order model with multiplicative weighting function is derived. Based on the developed model, a robust integrated controller is obtained by connecting a PI controller and a dynamic output feedback controller. Experiment results are presented to show the effectiveness of our method and the established system.

Drilling trajectory optimization (DTO) is an important step in intelligent control of directional drilling process. DTO in complex multiple strata geological environment is a new nonlinear, strongly constrained, black-box multi-objective optimization problem with discrete objectives. In this paper, a multi-objective evolutionary algorithm (MOEA) optimization framework is present for an obstacle avoidance drilling trajectory design model. First, a new three-segment trajectory model is established by natural curve method to measure the whole trajectory positions. Meanwhile, a drilling point wellbore stability model is derived by Mohr-Coulomb failure criteria. Based on this calculation model, the trajectory data is mapping to get a multi-strata parameter field. Several representative MOEAs are adopted to design the highest wellbore stability trajectory in this multi-strata geological environment. A case study from actual drilling site shows that the result of adaptive non-dominated sorting genetic algorithm (ANSGAIII) is better than that of traditional trail and error drilling trajectory design, which has a good application prospect in drilling engineering.

Complicated geological environments lead to a high risk of drilling incidents. Incident early warning for drilling process is in demand for industry field. An incident early warning method for loss and kick based on sparse autoencoder and decision fusion is proposed in this paper. Sparse autoencoder is employed to detect the abnormality of the drilling parameter time series. Mann-Kendall trend test approach is performed to extract the trend of the time series that is detected as abnormal. The abnormality detection and trend extraction results of each drilling parameter are fused to get the final incident early warning result. Experiments are executed with the actual data collected from a practical drilling process. The experiment results indicate the effectiveness of the proposed method.

This paper is concerned with the problem of reachable set estimation for discrete-time Markovian jump neural networks with generally incomplete transition probabilities (TPs). This kind of TP may be exactly known, merely known with lower and upper bounds, or unknown. The aim of this paper is to derive a precise reachable set description for the considered system via the Lyapunov-Krasovskii functional (LKF) approach. By constructing an augmented LKF, using an equivalent transformation method to deal with the unknown TPs and utilizing the extended reciprocally convex matrix inequality, and the free matrix weighting approach to estimate the forward difference of the constructed LKF, several sufficient conditions that guarantee the existence of an ellipsoidal reachable set are established. Finally, a numerical example with simulation results is given to demonstrate the effectiveness and superiority of the proposed results.

Wind is the dominant factor for wind power generation. However, wind, which is intermittent and fluctuating all the time, is hard to be accurately forecasted, especially only by single-source numerical weather prediction. This article presents a short-term wind power prediction method based on multisource wind speed fusion. First, the relationships among the weather factors and wind power, and the characteristics of three independent forecasted wind speed (FWS) provided by three organizations are analyzed. Next, a weighted naive Bayes method is described to fuse the three FWSs in order to estimate an accurate wind speed according to their characteristics. Then, a backpropagation neural network is designed to predict the wind power based on the fused wind speed. Finally, application results show that the method accurately predicts wind power generation, and the accuracy is much higher than that predicted by conventional methods.

Accurately and promptly detecting downhole abnormalities is of great importance to ensure safe and efficient operation of geological drilling systems. In view of the lack of abnormal data and the presence of multiple operating states, this article proposes a new abnormality detection method for geological drilling processes based on the Jensen-Shannon divergence and adaptive alarm limits. The major contributions are twofold: 1) a novel framework is proposed to detect downhole abnormalities by identifying normal operating conditions first and then establishing the normal operating zones; 2) an adaptive alarm limit design method is proposed to determine the normal operating zones by modeling the relation between the distribution feature and the variational trend feature based on the boundary points. The effectiveness and practicability of the proposed method are demonstrated by an industrial case study. The results demonstrate that the proposed method has superior performance to other methods in downhole abnormality detection.

Uncertain transmission delays, sampling periods, parameters uncertainties regarding the power system, load fluctuations, and the intermittent generation of renewable energy sources (RESs) will significantly influence a power system's frequency. This article designs a robust delay-dependent PI-based load frequency control (LFC) scheme for a power system based on sampled-data control. First, a sampled-data-based delay-dependent LFC model of power system is constructed. Then, by applying the Lyapunov theory, and the linear matrix inequality technique, a novel stability criterion is developed for the LFC of the power system by considering the sampling period, and transmission delay of the communication network, which ensures that the proposed scheme operates in large sampling periods, and under transmission delays. Next, an exponential decay rate (EDR) is introduced to guide the design of a robust PI-based LFC scheme. The LFC scheme with robustness is designed by setting a small EDR. The values of EDR are adjusted by the given robust performance evaluation conditions of parameter uncertainties, and$H_\infty$performance. Finally, case studies are carried out based on a one-area power system, and a three-area power system with RESs. Simulation results show that the proposed LFC scheme performs strong robustness against parameter uncertainties regarding the power system, and communication network, load fluctuations, and the intermittent generation of RESs.

To reduce energy consumption and harmful emission, it is of great significance to improve carbon efficiency in sintering process, which is able to be achieved if the carbon efficiency can be accurately predicted. In this article, the ratio of CO and CO2(CO/CO2) is taken as a measurement of the carbon efficiency. As CO/CO2is hard to measure, and there exist multiple working conditions, multiple variables, and nonlinearity, a hybrid CO/CO2prediction model is devised based on the aforementioned characteristics. First, the sintering process is analyzed, and the key characteristics to predict the CO/CO2are extracted. Next, the configuration of the prediction model is given based on the analysis. The model consists by two submodels, one is to predict the state variables by an improved just-in-time learning model, combining three neural network (NN) models. The other is to predict CO/CO2with semisupervised algorithm, based on deep belief network with a combination of the three NN regression methods. Then, the configurations of the two submodels are introduced in detail. The test results based on actual running data exhibit the good performance of the model.

Speech personality recognition relies on training models that require an excessive number of features and are, in most cases, designed specifically for certain databases. As a result, when tested on different datasets, overfitted classifier models are not always reliable because their accuracy changes with changes in the domain of speakers. Moreover, personality annotations are often subjective, which creates variability in raters perception during labeling. These problems inhibit the effectiveness of speech personality recognition applications. To reduce the unexplained variance caused by unknown differences in raters perception, a structure that uses Balanced Iterative Reducing and Clustering using Hierarchies (BIRCH) algorithm is proposed. Furthermore, a feature extraction method is proposed to filter out undesirable adulterations be it noise, silence, or uncertain pitch segments, while extracting essential audio features, i.e., signal power roll-off, pitch, and pause rate. Experiments on the standard SSPNet dataset records a relative 4% increase in overall accuracy when log-likelihood based annotations are used. Moreover, improved consistency in accuracy is observed when this method is tested on male and female subsets.

This article concerns the distributed optimal observer design, which aims to estimate the discrete-time nonlinear leader state for all followers with optimum online. The communication constraint and no prior knowledge of the leader’s dynamics cause a challenging task about the observer design. To this end, an adaptive critic design-based distributed optimal observer is developed via the actor–critic framework. The critic network is employed to approximate the cost function. The action network produces the optimal correction policy of the observer. Through convergence analysis, the overall estimation error and the weight estimation errors of the critic network and the action network are demonstrated to be all uniformly ultimately bounded (UUB). The simulation results verify the effectiveness of the developed observer.

In this article, the problem of filtering is studied for a class of nonlinear systems subject to time delays. The dynamics of nonlinear systems are characterized by Takagi–Sugeno (T–S) affine-fuzzy models. First, an extended bounded real lemma is established. In the process of analysis, a novel membership-dependent Lyapunov–Krasovskii functional is constructed, contributing to reducing the conservatism of the obtained results. Then, a fuzzy filter is designed through a linearization procedure such that the filtering error system is stable and satisfies a specified$H_{\infty }$performance level. The research results further deepen and enrich the theory of fuzzy filtering, providing the theoretical basis and the technical support for real applications. Finally, examples are provided to verify the effectiveness of the developed new design methods.

This paper is concerned with the delay-dependent stability analysis of linear systems with a time-varying delay. Two types of improved Lyapunov-Krasovskii functionals (LKFs) are developed to derive less conservative stability criteria. First, a new delay-product-type LKF, including single integral terms with time-varying delays as coefficients is developed, and two stability criteria with less conservatism due to more delay information included are established for different allowable delay sets. Second, the delay-product-type LKF is further improved by introducing several negative definite quadratic terms based on the idea of matrix-refined-function-based LKF, and two stability criteria with more cross-term information and less conservatism for different allowable delay sets are also obtained. Finally, a numerical example is utilized to verify the effectiveness of the proposed methods.

This article investigates H∞synchronization of delayed neural networks under a receding horizon scheme, where two types of interval time-varying delays are considered according to whether the lower bound of the delay derivative is known or not. Note that a receding horizon synchronization law can be regarded as an optimization solution at each timeslot to a minimaxization problem related closely with a certain cost functional. In this article, two cost functionals with some delay-dependent matrices are introduced, respectively, for the two types of time delays. In order to obtain less conservative conditions, a novel inequality on quadratic polynomial functions is established, which includes some existing ones as its special cases. Based on the novel inequality, two sufficient conditions are derived to design the terminal weighting matrices of the cost functionals such that the resulting synchronization error system can be stabilized with a prescribed infinite horizon H∞performance level. Finally, three numerical examples are used to demonstrate the validity of the proposed results.

Based on a hidden Markov model (HMM), the issue of fault detection (FD) is investigated for singularly perturbed systems with their measurements transmitted over a bandwidth-limited communication network. A homogeneous Markov chain is adopted to model packet dropouts and time delays simultaneously, whose mode transition probabilities are assumed to be partially unknown. The discrepancies between the Markov modes and their observed ones have been noted, which are reflected by a hidden Markov process. An HMM-based FD filter (FDF) is aimed to be designed such that the stochastic stability and prescribed H∞performance are ensured for the resulting filtering error dynamics of FD. A new Lyapunov-Krasovskii functional is constructed, which is with the Markov mode and the singular perturbation parameter (SPP). With the aid of up-to-date techniques in handing time delays, a sufficient condition based on linear matrix inequalities (LMIs) is derived which provides a design scheme of such an FDF. The FDF parameters are given and the SPP's admissible bounds are evaluated when the LMIs have feasible solutions. The performance of the designed FDF is demonstrated by two examples.

The weight-adapted convolution neural network (WACNN) is proposed to extract discriminative expression representations for recognizing facial expression. It aims to make good use of the convolution neural network's (CNN's) potential performance in avoiding local optima and speeding up convergence by the hybrid genetic algorithm (HGA) with optimal initial population, in such a way that it realizes deep and global emotion understanding in human-robot interaction. Moreover, the idea of novelty search is introduced to solve the deception problem in the HGA, which can expend the search space to help genetic algorithm jump out of local optimum and optimize large-scale parameters. In the proposal, the facial expression image preprocessing is conducted first, then the low-level expression features are extracted by using a principal component analysis. Finally, the high-level expression semantic features are extracted and recognized by WACNN which is optimized by HGA. In order to evaluate the effectiveness of WACNN, experiments on JAFFE, CK+, and static facial expressions in the wild 2.0 databases are carried out by using k -fold cross validation, and experimental results show the recognition accuracies of the proposal are superior to that of the state-of-the-art, such as local directional ternary pattern and weighted mixture deep neural network (DNN), which aim to extract discriminative and are the DNN-based methods. Moreover, recognition accuracies of the proposal are also higher than the deep CNN without HGA, which indicates that the proposal has better global optimization ability. Meanwhile, preliminary application experiments are also carried out by using the proposed algorithm on the emotional social robot system, where nine volunteers and two-wheeled robots experience the scenario of emotion understanding. Application results indicate that the wheeled robots can recognize basic expressions, such as happy, surprise, and so on.

Single-link flexible-joint manipulator (FJM) is a kind of time-varying nonlinear system with underactuated characteristics. This paper takes the uncertain single-link FJM (USLFJM) as the object, and presents a novel robust control approach based on equivalent input disturbance (EID) method for motion control (i.e., position control and trajectory tracking control) of the USLFJM. Based on the uncertain dynamic model and desired target of this system, an error system is constructed. The error system is considered as a linear system with a nonlinear virtual disturbance. The motion control objective of the USLFJM can be realized by globally asymptotically stabilizing this linear system and compensating the influence of the nonlinear virtual disturbance. Then, an EID-based control system is designed to realize this control objective. Only position measurements are utilized in this paper, and the stability of the control system is proved. The simulation results are presented to illustrate the validity and the robustness of the proposed control method.

Wireless sensor networks (WSNs) are usually deployed in the target area to carry out detecting or monitoring tasks. Sweep coverage is an important concern of WSNs that more targets in the area can be monitored with fewer mobile sensor nodes. With the rapid development of unmanned aerial vehicle (UAV) technology, UAV has been increasingly used in military and civil fields. UAVs can be regarded as sensor nodes to perform specific tasks. Due to the limited battery lifetime of UAV in flight mission, it is difficult to achieve full coverage of all targets in a large-scale monitoring scenario. In this article, we study how to plan the paths of multiple UAVs for sweep coverage. Based on the background of forest fire early warning and monitoring, we consider a min-time max-coverage (MTMC) issue in sweep coverage, where a set of UAVs is dispatched to efficiently patrol the targets in the given area to achieve maximum coverage in minimum time. We establish a mathematical model considering the different coverage quality requirements of the targets in the given area. Then, we analyze the characteristics of the model and propose a heuristic algorithm weighted targets sweep coverage (WTSC) to find the optimal path, which considers the weights of the targets and the performance constraints of UAVs. Finally, we provide various numerical experiments and comparisons with several previous works to validate the superiority of the proposed algorithm.

Internet of Vehicles (IoV) is a typical application of Internet-of-Things (IoT) technology in the field of intelligent transportation systems. In the actual IoV, such as the autonomous vehicle fleet, there exists the problem of heterogeneous multivehicle coordination based on IoT communication. How to ensure the synchronization of multiple vehicles is a hot issue. In particular, when the system can only obtain a partial state of the vehicle, and does not know the dynamic model, including the vehicle itself and the companion model. To overcome these deficiencies, this article deals with the model-free output consensus control problem for a class of partially observable heterogeneous multivehicle systems (MVSs). Using measurable input/output data without any system knowledge, this article develops a Q-function-based adaptive dynamic programming (ADP). First, an adaptive distributed observer is designed to estimate the output of the leader. The augmented state representation is built using historical measurable input/output data instead of the unmeasurable inner system state. Then, a Q-function-based ADP method using measurable input/output data was introduced. The method is used to solve this distributed tracking control problem without the requirement for the MVSs dynamics. The convergence analysis of the proposed method is also given. To facilitate the implementation of the proposed method, an actor-critic framework is adopted to approximate the optimal Q-functions and the optimal control policies. It shows that the approximated control policies achieve the distributed optimal tracking control. Finally, the simulation results verify the effectiveness of the developed method for solving multivehicle formation control problems.

This paper is concerned with the stability and stabilization problems of T-S fuzzy systems with time-varying delays. The purpose is to develop a new state-feedback controller design method with less conservatism. First, a novel Lyapunov-Krasovskii functional is constructed by combining delay-product-type functional method together with the state vector augmentation. By utilizing Wirtinger-based integral inequality and an extended reciprocally convex matrix inequality, a less conservative delay-dependent stability condition is developed. Then, the corresponding controller design method for the closed-loop delayed fuzzy system is derived based on parallel distributed compensation scheme. Finally, two classic numerical examples are given to show the effectiveness and merits of the proposed approaches.

A fuzzy deep neural network with sparse autoencoder (FDNNSA) is proposed for intention understanding based on human emotions and identification information (i.e., age, gender, and region), in which the fuzzy C-means (FCM) is used to cluster the input data, and deep neural network with sparse autoencoder (DNNSA) is designed for emotional intention understanding in human-robot interaction. It aims to make robots capable of recognizing human emotions and understanding related emotional intention, the FCM is suitable for gathering similar information so that the calculations of dimensionality of DNNSA will be reduced, and the sparse autoencoder of DNNSA can make the neuron of DNNSA sparse to reduce the complexity of the network in such a way human-robot interaction is running smoothly. To validate the proposal, simulation experiments based on benchmark databases such as facial expression database of CK+, and speech emotion corpus of CASIA were completed. The experimental results show that the proposal outperforms the baseline algorithms of Softmax regression (SR), DNNSA, FCM-based SR (FSR), Softplus, Gath Geva-based DNNSA (GDNNSA), and ensemble DNNSA (EDNNSA). Preliminary application experiments are performed in the development of emotional social robot system, where volunteers experience the scenario of “drinking at the bar”. The obtained results indicate that the proposed FDNNSA can promote robot understanding of emotional intention of human.

The weight of alloying elements is a decisive factor to determine the grade and quality of alloy steel. It is difficult to control the weight of alloying elements accurately running due to the fluctuations in the feed rate. This article presents a new control system including a controller and a two-level adjustment strategy. First, a mathematical model is built to describe the weighing system based on the analysis of the weighing characteristics. Next, a control system is developed based on the model. Then, a two-level data-based adjustment strategy for the parameters of the controller is devised based on both the real-time data of the current batch and historical data of former batches of weighing. It ensures that the controller adapts to the fluctuations in the feed rate. Finally, the results of real runs show that the method has high accuracy and strong robustness.

This article addresses the control problem of an open-loop unstable linear time-invariant system with an input delay and an unknown disturbance. An observer-predictor-based control method is presented for such a system in which only output information is available. First, the system state is reconstructed and the disturbance is estimated using the equivalent-input-disturbance approach. Next, the future information on the state and the disturbance is predicted to reduce the effect of the input delay. Then, a new predictive control scheme is developed. The closed-loop system is simplified into two subsystems for analysis. Stability conditions are derived for each subsystem separately. Finally, a comparison with previous approaches through simulations shows the superiority of the presented method over others for disturbance rejection.

Sinter ore is the main raw material for ironmaking, and burn-through point (BTP) is one of the significant factors to measure the stability of the sintering process. In this article, through the feature extraction of time-series trend, a fuzzy control strategy is presented for the BTP. First, the Hurst exponent of the time series for the BTP is calculated by resorting to the rescaled range analysis method, by which the trend feature is analyzed. Then, by using the Mann-Kendall test, both global and local trend feature variable of the time series for the BTP are extracted and regarded as the inputs of the fuzzy controller. Next, a fuzzy controller for the BTP is designed to produce the control quantity of the strand velocity. Finally, based on a semiphysical simulation system and the raw data collected from an iron and steel plant, an experiment is carried out to demonstrate the effectiveness of the proposed control strategy.

Rate of penetration (ROP) optimization is crucial for drilling processes due to its vital role in increasing efficiency. This article proposes a new hybrid bat algorithm (HBA) to achieve the maximum ROP accurately. A data-driven ROP model is established by combining the wavelet filtering and optimized support vector regression according to the drilling characteristics. After that, five modifications, namely, iterative local search, stochastic inertia weight, pulse rate and loudness improvement, directional echolocation, and modified local random walk are combined to further improve the global optimization performance of the bat algorithm. Extensive experiment results on the IEEE Congress on Evolutionary Computation 2005 standard benchmark problems show that the proposed algorithm has successful outcomes compared with ten conventional algorithms. Additionally, in the application of the HBA to a real-world drilling process in Shennongjia area, Central China, the ROP has been improved by 34.84%, which is the largest compared with the conventional popular ROP optimization methods.

The accuracy and integrity of the actual production data influence the reliability and stability of sintering process in steel industry. However, the actual production data may encounter various outliers due to noise, sensor failure, and operator negligence existing in this process. To tackle this issue, this article develops an original framework for the detection and correction of abnormal production data in the sintering process. First, an improved kernel-based Fuzzy C-Means algorithm is developed to effectively divide normal production data under multiple operating conditions. Then, different one-class support vector machine (SVM) classifiers are constructed for different operating conditions. According to which operating condition the actual production data belongs to, the one-class SVM under this operating condition is called to accurately detect abnormal production data. Finally, the most similar normal historical data in the operating condition is obtained to correct the abnormal data by using k nearest neighbor algorithm based on the Mahalanobis distance. Simulation results involving actual production data illustrate the effectiveness of the proposed method. By taking two existing models of the sintering process as examples, their prediction performance becomes improved after detecting and correcting the abnormal production data, so that the proposed framework has important engineering application impact.

In this article, the finite-time H∞state estimation problem is addressed for a class of discrete-time neural networks with semi-Markovian jump parameters and time-varying delays. The focus is mainly on the design of a state estimator such that the constructed error system is stochastically finite-time bounded with a prescribed H∞performance level via finite-time Lyapunov stability theory. By constructing a delay-product-type Lyapunov functional, in which the information of time-varying delays and characteristics of activation functions are fully taken into account, and using the Jensen summation inequality, the free weighting matrix approach, and the extended reciprocally convex matrix inequality, some sufficient conditions are established in terms of linear matrix inequalities to ensure the existence of the state estimator. Finally, numerical examples with simulation results are provided to illustrate the effectiveness of our proposed results.

This paper is concerned with the stubborn state estimation of delayed neural networks that subject to a general class of disturbances in measurements, including outliers and impulsive disturbances as its special cases. This class of disturbances may be unbounded, irregular, and assorted; therefore, they can hardly be suppressed by existing identification-based estimation approaches. In this paper, a stubborn state estimator is constructed by intentionally devising a saturation scheme on the injection of output estimation error. The embedded saturation can effectively resist the influences from these measurement disturbances by saturating them. Moreover, the saturation threshold in the designed scheme is not constant but governed by a dynamic equation with parameters to be designed. Benefiting from this adaptiveness, the estimator obtains more freedom in dealing with various disturbances. By combining a novel Lyapunov functional, the generalized sector condition and two latest integral inequalities, a delay-dependent criterion is derived in a less conservative way to check whether the estimation error system with this dynamic saturation is globally stable. A sufficient condition with two tuning scalars is further provided to codesign the gain of the state estimator and the evolution law of the saturation threshold. Finally, two numerical examples are used to illustrate the stubbornness of this state estimator in the presence of measurement outliers or impulsive disturbances.

Two-layer fuzzy support vector regression-Takagi-Sugeno (TLFSVR-TS) model is proposed for emotion understanding in human-robot interaction (HRI), where the real-time dynamic emotion is recognized according to facial expression, and emotional intention understanding is obtained mainly based on human emotions and identification information. It aims to make robots capable of recognizing and understanding human emotions, in such a way that make HRI run smoothly. TLFSVR-TS considers about the priori knowledge inferred from human personal preference to reduce the uncertainty of various people, and multiple support vector regression (SVR) corresponding to different genders/provinces/ages of human to guarantee the local learning ability. Preliminary application experiments are performed in the developing emotional social robot system, where 30 volunteers experience the scenario of “drinking in the bar.” Results show that the proposal receives higher understanding accuracy than that of TLFSVR, kernel fuzzy c-means clustering is fused with SVR, and SVR.

This paper develops a quick and effective continuous state feedback control strategy based on intelligent optimization for a planar three-link passive–active–active (PAA) underactuated system with first-order nonholonomic characteristic. We analyze the integral characteristic of the system and find the passive link will be stabilized at different angle when the two active links of the system are controlled to different angles. Therefore, we design a set of continuous state feedback controllers based on the control targets of the two active links, and then we optimize the target angles of all links and the design parameters of the above controllers by employing intelligent optimization algorithm. In this way, the system can be stabilized at the target point by using these controllers with optimized parameters. Finally, the simulation results demonstrate that the continuous control strategy based on intelligent optimization may make the planar PAA underactuated system be stabilized at any target point from any initial point.

Conventionally, as the system's dynamics is known, the optimal consensus control problem relies on solving the coupled Hamilton-Jacobi-Bellman (HJB) equations. In this paper, with the unknown system dynamics being considered, a local Q-function-based adaptive dynamic programming method is put forward to deal with the optimal consensus control problem for unknown discrete-time nonlinear multiagent systems by approximating the solutions of the coupled HJB equations. First, a local Q-function is defined, which considers the local consensus error and the actions of the agent and its neighbors. Using the Q-function, it is convenient to get the derivatives with regard to the weights of the consensus control policies, even without the model of system dynamics. Then, with the defined local Q-function, a distributed policy iteration technique is developed, which is theoretically proved to be convergent to the solutions of the coupled HJB equations. An actor-critic neural network framework for implementing the developed model-free optimal consensus control method is constructed to approximate the local Q-functions and the control policies. Finally, the feasibility and effectiveness of the developed method are verified by a series of simulations.

This paper presents a control strategy based on model reduction and online intelligent calculation for a planar n-link underactuated manipulator with a passive first joint (PAn-1 for short) to realize its control objective, which is to move its end-point from an initial position to a target position. First, two active links of the planar PAn-1 manipulator are chosen to be the active links of a planar virtual passive-active-active (PAA) manipulator, which guarantees that the geometric reachable range of the planar virtual PAA manipulator is the same as that of the planar PAn-1 manipulator. The planar PAn-1 manipulator is reduced to the planar virtual PAA manipulator by keeping the states of two active links in their initial values and controlling the states of the remaining n - 3 active links to zero. Then, the planar virtual PAA manipulator is equivalent to two planar virtual Acrobots by adopting two-stage control method. Based on two sets of angle constraint relationships corresponding to two planar virtual Acrobots, an online differential evolution algorithm is employed to obtain all link target angles of the planar virtual PAA manipulator. Next, two Lyapunov functions, each of which is constructed based on the active link angle of one planar virtual Acrobot, are used to design controllers to realize the system control objective. Finally, Simulation results of a planar PAA-active manipulator demonstrate the effectiveness of the proposed control strategy.

This paper studies the dissipativity of singular time-delay systems. The objective is to derive a less conservative criterion with less computational demand. Throughout this paper, the augmented Lyapunov-Krasovskii functional (LKF) and the free-matrix-based integral inequality are used to realize less conservativeness. On the basis of these techniques, a less conservative criterion is first given. Then, by decomposing singular time-delay systems into differential equations and algebraic ones, state vectors of the systems are divided into two parts. To reduce redundant decision variables, each part of the state vectors is considered independently to construct a special augmented LKF with less decision variables. As a result, an improved criterion is deduced, and thus less conservativeness and less computational demand are achieved at the same time. Moreover, the presented state decomposition method provides a new research idea for singular time-delay systems not yet reported in the literatures. Finally, the above statements are demonstrated by a numerical example.

A plant is controlled remotely on a network for a networked control system. Disturbances from the network and surroundings may deteriorate the control performance of such a system. To solve this problem, this paper presents a new method of suppressing an exogenous disturbance for those control systems. The control system has a state observer to estimate the state of the plant and an equivalent-input-disturbance (EID) estimator to produce an estimate of the disturbance on the control input channel in a real-time fashion. The system is divided into two subsystems for the analysis of system stability. A stability condition of the control system with a time-varying delay is presented in terms of a linear matrix inequality. Simulations demonstrate the validity of the method. And a comparative study shows the superior of our method to a conventional Smith-EID control method.

Effective influential spreaders prediction in online social networks is critical for a variety of network services such as viral marketing, online recommendation, and many more. The conventional machine learning methods mainly adopted various hand-crafted features in the prediction models. However, their effectiveness relies on the domain knowledge heavily, and thus it is difficult to generalize these models to different domains. In this paper, we propose an Influence Deep Learning (IDL) model to learn users' latent feature representation for predicting influence spread. Our IDL model is fully data-driven, and it takes sampling subnetworks as input to the deep neural networks for learning users' latent vector representation. Moreover, we design a strategy to incorporate user-specific features and network structure into the graph convolutional neural network to overcome the imbalance problem of labeled training data. The experimental results show that our model outperforms other baselines in online social networks, and our model is more practical in large-scale data sets.

A method to suppress exogenous disturbances in a nonlinear system is presented based on equivalent-input-disturbance (EID) approach. The nonlinear term is considered to be useful and should not be rejected in this paper. The method has two exceptional merits: it is a output-feedback control method, and the only restriction of the nonlinear term is used to ensure the stability of the NEID-based control system. Finally, the design procedure is illustrated by a numerical example.

One of the keys for the success of sweep coverage is to organize the participants to patrol effectively in large-scale target areas in order to satisfy the quality requirements of the sweep tasks. In this article, we first analyze the possibility of applying crowdsensing technology for sweep coverage and propose a framework to solve the problem of arranging participants to sweep large-scale target areas when the quality requirements change dynamically over time. First, this problem is formulated as a task assignment problem with the goal of maximizing social welfare. Then, we establish a sweep coverage quality model for the area, which is a different approach from conventional methods that focus on the point of interest (PoI), and we propose a participant incentive model that considers the sustainability of the crowdsensing platform. Since determining the optimal assignment solution is an NP-hard problem, we design two approximate algorithms to arrange participants with the goal of maximizing social welfare; these are the participant-task oriented search (PTOS) algorithm based on a two-stage greed search and the bipartite graph-based participant search (BGPS) algorithm. We evaluate our methods using a population density map dataset from real-world cities as the large-scale target area and create dynamic task requirements for the sweep coverage. The experimental results show that the performance of our two algorithms is significantly better than the performance of the baseline algorithm.

One of the keys to making cloud data-centers (CDCs) proliferate impressively is the implementation of efficient task scheduling. Since all the resources of CDCs, even including operating systems (OSes) and application programs, can be stored and managed on remote data-centers, this study first analyzed the task scheduling problem for CDCs and established a mathematical model of the scheduling of two-stage tasks. The Johnson's rule was combined with the genetic algorithm to create a Johnson's-rule-based genetic algorithm (JRGA), which takes into account the characteristics of multiprocessor scheduling in CDCs. New crossover and mutation operations were devised to make the algorithm converge more quickly. In the decoding process, the Johnson's rule is used to optimize the makespan for each machine. Simulations were used to compare the performance of the JRGA with that of the list scheduling algorithm and an improved list scheduling algorithm. The results demonstrate the validity of the JRGA.

Many artificial benchmark problems have been proposed for different kinds of continuous optimization, e.g., global optimization, multimodal optimization, multiobjective optimization, dynamic optimization, and constrained optimization. However, there is no unified framework for constructing these types of problems and possible properties of many problems are not fully tunable. This will cause difficulties for researchers to analyze strengths and weaknesses of an algorithm. To address these issues, this paper proposes a simple and intuitive framework, which is able to construct different kinds of problems for continuous optimization. The framework utilizes the k -d tree to partition the search space and sets a certain number of simple functions in each subspace. The framework is implemented into global/multimodal optimization, dynamic single objective optimization, multiobjective optimization, and dynamic multiobjective optimization, respectively. Properties of the proposed framework are discussed and verified with traditional evolutionary algorithms.

This paper investigates the problem of robust H∞control for a class of nonlinear systems with state and input time-varying delays. The nonlinearity is presented by a continuous-time Takagi-Sugeno (T-S) fuzzy model with parameter uncertainties. A sufficient asymptotic stability condition is first proposed by constructing a delay-product-type augmented Lyapunov-Krasovskii functional and utilizing an extended reciprocally convex matrix inequality together with a Wirtinger-based integral inequality. Then, a state feedback controller is derived that guarantees the closed-loop fuzzy system being asymptotically stable with an H∞performance index. Finally, four numerical examples are given to reveal the effectiveness and merits of the developed new design techniques.

This paper investigates the problem of extended dissipativity for Markovian jump neural networks (MJNNs) with a time-varying delay. The objective is to derive less conservative extended dissipativity criteria for delayed MJNNs. Toward this aim, an appropriate Lyapunov-Krasovskii functional (LKF) with some improved delay-product-type terms is first constructed. Then, by employing the extended reciprocally convex matrix inequality (ERCMI) and the Wirtinger-based integral inequality to estimate the derivative of the constructed LKF, a delay-dependent extended dissipativity condition is derived for the delayed MJNNs. An improved extended dissipativity criterion is also given via the allowable delay sets method. Based on the above-mentioned results, the extended dissipativity condition of delayed NNs without Markovian jump parameters is directly derived. Finally, three numerical examples are employed to illustrate the advantages of the proposed method.

This paper deals with the finite-horizon quantized H∞state estimation problem for a class of discrete timevarying genetic regulatory networks with quantization effects under stochastic communication protocols (SCPs). To better reflect the data-driven flavor of today's biological research, the network measurements (typically gigabytes in size by highthroughput sequencing technologies) are transmitted to a remote state estimator via two independent communication networks of limited bandwidths. To lighten the communication loads and avoid undesired data collisions, the measurement outputs are quantized and then transmitted under two SCPs introduced to schedule the large-scale data transmissions. The purpose of this paper is to design a time-varying state estimator such that the error dynamics of the state estimation satisfies a prescribed H∞performance requirement over a finite horizon in the presence of nonlinearities, quantization effects, and SCPs. By utilizing the completing-the-square technique, sufficient conditions are derived to ensure the H∞estimation performance and the parameters of the state estimator are designed by solving coupled backward recursive Riccati difference equations. A numerical example is given to illustrate the effectiveness of the design scheme of the proposed state estimator.

This paper investigates the H∞state estimation problem for a class of discrete-time nonlinear singularly perturbed complex networks (SPCNs) under the Round-Robin (RR) protocol. A discrete-time nonlinear SPCN model is first devised on two time scales with their discrepancies reflected by a singular perturbation parameter (SPP). The network measurement outputs are transmitted via a communication network where the data transmissions are scheduled by the RR protocol with hope to avoid the undesired data collision. The error dynamics of the state estimation is governed by a switched system with a periodic switching parameter. A novel Lyapunov function is constructed that is dependent on both the transmission order and the SPP. By establishing a key lemma specifically tackling the SPP, sufficient conditions are obtained such that, for any SPP less than or equal to a predefined upper bound, the error dynamics of the state estimation is asymptotically stable and satisfies a prescribed H∞performance requirement. Furthermore, the explicit parameterization of the desired state estimator is given by means of the solution to a set of matrix inequalities, and the upper bound of the SPP is then evaluated in the feasibility of these matrix inequalities. Moreover, the corresponding results for linear discrete-time SPCNs are derived as corollaries. A numerical example is given to illustrate the effectiveness of the proposed state estimator design scheme.

This paper addresses the exponential synchronization problem for neural networks with time-varying delays. First, a novel controller is presented by combining intermittent control with dynamic output feedback control. Next, a sufficient criterion is established based on the Lyapunov-Krasovskii functional approach and the lower bound lemma for reciprocally convex technique to ensure exponential stability of the resultant closed-loop system. Then, some solvable conditions of the proposed control problem are derived in terms of linear matrix inequalities. Notably, our results here extend the existing ones to the relaxed case because the derivative of time-varying delays is now an arbitrary bounded real number. Finally, a numerical simulation is provided to demonstrate the effectiveness of the proposed method.

Wind power now is taken as an essential alternative to burning fossil fuels for humans and begin to be used in our daily life. However, the wind power is hard to predict since the wind speed is a highly fluctuating resource. This paper presents a multiple wind speeds fusion method to improve the accuracy of short-term wind power prediction based on a k - nearest neighbors-based support vector regression ( k NN-SVR) model. First, a k NN algorithm is devised to select the historical wind speed points that is nearest to the prediction point from the historic data set. Then, a SVR model is built to obtain the fusion wind speed based on three independent numerical weather predictions at the nearest historic prediction point, which improves the accuracy of the wind speed prediction. Finally, the fusion wind speed is employed to predict the wind power by using an back propagation neural network (BPNN) model. Experimental results that are on the basis of the data from an actual wind farm in Shanxi Province, China, show the efficiency of the fusion method.

This paper is concerned with energy-to-peak state estimation on static neural networks (SNNs) with interval time-varying delays. The objective is to design suitable delay-dependent state estimators such that the peak value of the estimation error state can be minimized for all disturbances with bounded energy. Note that the Lyapunov-Krasovskii functional (LKF) method plus proper integral inequalities provides a powerful tool in stability analysis and state estimation of delayed NNs. The main contribution of this paper lies in three points: 1) the relationship between two integral inequalities based on orthogonal and nonorthogonal polynomial sequences is disclosed. It is proven that the second-order Bessel-Legendre inequality (BLI), which is based on an orthogonal polynomial sequence, outperforms the second-order integral inequality recently established based on a nonorthogonal polynomial sequence; 2) the LKF method together with the second-order BLI is employed to derive some novel sufficient conditions such that the resulting estimation error system is globally asymptotically stable with desirable energy-to-peak performance, in which two types of time-varying delays are considered, allowing its derivative information is partly known or totally unknown; and 3) a linear-matrix-inequality-based approach is presented to design energy-to-peak state estimators for SNNs with two types of time-varying delays, whose efficiency is demonstrated via two widely studied numerical examples.

A three-layer weighted fuzzy support vector regression (TLWFSVR) model is proposed for understanding human intention, and it is based on the emotion-identification information in human-robot interaction. The TLWFSVR model consists of three layers, including adjusted weighted kernel fuzzy c-means for data clustering, fuzzy support vector regressions (FSVR) for information understanding, and weighted fusion for intention understanding. It aims to guarantee the quick convergence and satisfactory performance of the local FSVR via adjusting the weights of each feature in each cluster, in such a way that importance of different emotion-identification information is represented. Moreover, smooth human-oriented interaction can be obtained by endowing robot with human intention understanding capability. Experimental results show that the proposed TLWFSVR model obtains higher intention understanding accuracy and less computational time than that of two-layer fuzzy support vector regression, support vector regression, and back propagation neural network (BPNN), respectively. Additionally, the preliminary application experiments are performed in the developing human-robot interaction system, called emotional social robot system, where 12 volunteers and 2 mobile robots experience a scenario of “drinking at a bar.” Application results indicate that the bartender robot is able to understand customers' order intentions.

This brief is concerned with global asymptotic stability of a neural network with a time-varying delay. First, by introducing an auxiliary vector with some nonorthogonal polynomials, a slack-matrix-based integral inequality is established, which includes some existing one as its special case. Second, a novel Lyapunov-Krasovskii functional is constructed to suit for the use of the obtained integral inequality. As a result, a less conservative stability criterion is derived, whose effectiveness is finally demonstrated through two well-used numerical examples.

A two-layer fuzzy kernel regression (TLFKR) model is proposed for understanding human emotional intention in human-robot interaction, where TLFKR model consists of two layers, including fuzzy c-means (FCM) with kernel ridge regression (Kernel 1) for information analysis layer, fuzzy support vector regressions (FSVR) (Kernel 2) for intention understanding layer. TLFKR model represents the weight impact for each emotional information and aims to improve smooth human-robot interaction by endowing robot with human emotional intention understanding capability. Experimental Results show that the proposal obtains an intention understanding accuracy of 65.67%/68.33%/80.67% with the clusters number c=2/3/6 (according to different genders/ages/nationalities), which are 7.34%/7.18%/8.67% and 18.67%/21.33%/33.67% higher than that of TLFSVR and SVR, respectively. Additionally, preliminary application experiments are performed in the developing emotional social robot system, where two mobile robots and volunteers experience a scenario of “drinking at a bar”, and social robots are able to express basic emotions and understand human order intention.

To ensure that people can supplement enough water at the right time, an initiative service method based on intention understanding for drinking service robot is proposed. Firstly, individual factors and environmental factors which are associated with personal intentions are collected. Secondly, users' intention and desire degree for intention are obtained by an improved Fuzzy-Context-specific Intention Inference method. Then the relationship between personal intention and human demands is established by an initiative service model. Finally, robots provide drinking water service initiatively according to humans' demands. Drinking service experiments are performed in a laboratory scenario using a humans-robots interaction system. The experimental results show that the drinking time of actual situation lags behind the initiative service time 25 minutes on average, and the initiative service renders drinking service 2 times more than actual situation on average, which demonstrates the feasibility of the proposal. In prospect, the initiative service method could be applied to many occasions in our daily life, e.g., family service, caring for the elderly, and medical rehabilitation.

In networked load frequency control (LFC) systems, time-varying delays could come from two aspects: measurements' transmission from power plant to control center and control signals from the control center to plant side, because of the use of open communication networks. Those delays can affect the dynamic performance and the stability of the system. In this paper, the two delays are considered in one-area LFC system, instead of combining these two delays into one, when the delay-dependent stability analysis is carried out by using Lyaponuvtheory and linear matrix inequality (LMI) technique. Moreover, the dynamic delay interval method is employed to derive less conservative delay-dependent stability criteria for such time-delay system compared with the existing results. Finally, the effectiveness of the proposed criteria are verified by two case studies.

Coverage issue in directional sensor networks (DSNs) is different from traditional omni-directional wireless sensor networks (WSNs) due to the limited angle of view and adjustable working direction. This paper sets up a model of monitoring area and a model of sensing area according to the unique characteristics of directional sensor and then derives an optimization model for area coverage ratio maximization. A new method based on particle swarm optimization (PSO) is proposed to solve the model. The algorithm makes the directional sensor nodes adjust their sensing direction to get personal best and global best to optimize the coverage of DSNs. The simulation results under different circumstances show that the algorithm has good performance and high efficiency in real situations.

This paper presents a trajectory tracking control strategy based on the finite element method for a planar three-link underactuated manipulator with a passive third joint. From the mechanical structure, the manipulator can be thought of as composed of two parts. The first part is the first link of the manipulator, which is a single link manipulator system. The second part consists of the remaining two links, which can be seen as a plananr Pendubot. First, a finite element model of the planar Pendubot is built by using COMSOL, and the coupling relationship between its active link and its passive link is analyzed. Then, two servo controllers (A and B) with the same structure are designed for two active links of the manipulator, respectively. The servo controller A is directly applied to control the angular velocity of the first link of the manipulator rotating with a constant speed, which makes the end-point of the manipulator move along the trajectory direction. Next, a fuzzy system is designed based on the coupling relationship of the planar Pendubot to calculate the target angular velocity of the second link of the manipulator according to the tracking error and its change rate. The servo controller B is applied to control the angular velocity of the second link of the manipulator, which makes the tracking error converge to zero. Finally, Simulation results demonstrate the effectiveness and the robustness of the proposed control strategy.

This paper investigates the stability of linear systems with a time-varying delay. We propose a new approach to construct Lyapunuv-Krasovskii functional (LKF). Compared with other traditional approach, the proposed one can provide a higher time-delay upper bound and lower computation complexity. Six stability criteria by linear matrix inequalities (LMIs) are established by proposed two novel LKFs in this paper. Based on one numerical example, the advantages of the proposed approach are illustrated.

Adaptive dynamic programming (ADP) is a prevalent way to solve the coupled Hamilton-Jacobi-Bellman (HJB) equations of the optimal consensus control for multi-agent systems (MAS). Neural networks (NNs) are normally used to approximate the value functions in ADP. However, NNs with manually designed features may influence the approximation ability. In this study, kernel-based methods which do not need to set the value function model structure in advance are adopted for value functions approximation. Moreover, to overcome the deficiency that most of the system dynamics are unknown, or the system is too complex to obtain the accurate dynamics. Local action value functions are defined, and kernel-based methods are used to approximate the local action value functions. Thus, an action dependent heuristic dynamic programming (ADHDP) approach using kernel-based local action value functions approximation is developed to achieve the optimal consensus control model-freely. The developed approach uses historical sample data to learn the system dynamics, and avoids the traditional system identification scheme. Simulation results are provided to demonstrate the effectiveness of the presented approach.

This letter describes the improvement of two methods of detecting high-frequency oscillations (HFOs) and their use to localize epileptic seizure onset zones (SOZs). The wavelet transform (WT) method was improved by combining the complex Morlet WT with Shannon entropy to enhance the temporal-frequency resolution during HFO detection. And the matching pursuit (MP) method was improved by combining it with an adaptive genetic algorithm to improve the speed and accuracy of the calculations for HFO detection. The HFOs detected by these two methods were used to localize SOZs in five patients. A comparison shows that the improved WT method provides high specificity and quick localization and that the improved MP method provides high sensitivity.

Contour is a critical feature for image description and object recognition in many computer vision tasks. However, detection of object contour remains a challenging problem because of disturbances from texture edges. This letter proposes a scheme to handle texture edges by implementing contour integration. The proposed scheme integrates structural segments into contours while inhibiting texture edges with the help of the orientation histogram-based center-surround interaction model. In the model, local edges within surroundings exert a modulatory effect on central contour cues based on the co-occurrence statistics of local edges described by the divergence of orientation histograms in the local region. We evaluate the proposed scheme on two well-known challenging boundary detection data sets (RuG and BSDS500). The experiments demonstrate that our scheme achieves a high [Formula: see text]-measure of up to 0.74. Results show that our scheme achieves integrating accurate contour while eliminating most of texture edges, a novel approach to long-range feature analysis.

This paper is concerned with the stability analysis of discrete-time neural networks with a time-varying delay. Assessment of the effect of time delays on system stability requires suitable delay-dependent stability criteria. This paper aims to develop new stability criteria for reduction of conservatism without much increase of computational burden. An extended reciprocally convex matrix inequality is developed to replace the popular reciprocally convex combination lemma (RCCL). It has potential to reduce the conservatism of the RCCL-based criteria without introducing any extra decision variable due to its advantage of reduced estimation gap using the same decision variables. Moreover, a delay-product-type term is introduced for the first time into the Lyapunov function candidate such that a delay-variation-dependent stability criterion with the bounds of delay change rate is established. Finally, the advantages of the proposed criteria are demonstrated through two numerical examples.

Demands for cloud video surveillance systems are growing rapidly. Addressing to the issue of low energy-efficiency in cloud video datacenters, a task scheduling method using a time-clustering-based genetic algorithm is proposed. Firstly, an off-line scheduling model with SLA (service level agreement) time constraint is proposed after the analysis of the constrain relationship between the SLA and surveillance tasks. Then, a time-clustering-based genetic algorithm (TCGA) is proposed to solve the model for an optimal energy-efficient solution. According to the solution, the service quality is guaranteed and the total operating time of virtual machines is minimized. Meanwhile, idle virtual machines are shut down to reduce energy consumption. Simulations of large scale tasks scheduling are conducted. Several comparison experiments verify that the proposed method can improve the resource utilization greatly and achieve energy saving extremely.

This paper investigates delay-dependent stability for continuous neural networks with a time-varying delay. This paper aims at deriving a new stability criterion, considering tradeoff between conservativeness and calculation complexity. A new Lyapunov-Krasovskii functional with simple augmented terms and delay-dependent terms is constructed, and its derivative is estimated by several techniques, including free-weighting matrix and inequality estimation methods. Then, the influence of the techniques used on the conservativeness and the complexity is analyzed one by one. Moreover, useful guidelines for improving criterion and future work are briefly discussed. Finally, the advantages of the proposed criterion compared with the existing ones are verified based on three numerical examples.

Active vibration control has been widely investigated in civil engineering. This study considers the problem of selecting a norm for an evaluation criterion for the planning of the placement of active damping devices (ADDs) in a structure in active vibration control. Using a 4-degree-of-freedom system as an example, we compare the commonly used 2-norm and ∞-norm, and show that the 2-norm is a suitable choice for the performance index of the placement planning of ADDs.

To guarantee the control performance of a fuzzy control system for the combustion process in a coke oven, the parameters of the fuzzy controller need to be optimized so that the controller can handle large changes in the operating state of the oven. This paper describes an online optimization method for this purpose. In this method, the distance and angle of the trend of the change are used to select data, and just-in-time learning is used to create a dynamic sample base and to build a radial-basis-function neural-network model of the process. A variable-universe fuzzy logic controller controls the process, and an adaptive differential evolution algorithm optimizes the universe parameters. This enables the controller to adapt to changes in the operating state in a timely fashion. Simulation results demonstrate the effectiveness of the method.

This study deals with the problem of H∞tracking control for a sampled-data networked control system based on a Takagi-Sugeno fuzzy model. An error model is established by combining the input delay and parallel distributed compensation techniques so as to transform the sampling period of a sampler, a signal transmission delay, and data packet dropouts to the refreshing interval of a zero-order hold. The method introduces a new augmented Lyapunov-Krasovskii functional to derive a sufficient condition to ensure a prescribed H∞tracking performance with less conservativeness than others. A fuzzy controller can easily be designed using the condition. A numerical example demonstrates the validity of the method.

It is an urgent need to find an objective way to estimate the degree of fatigue of employees. In this study, we designed a monitoring and estimation system for the degree of fatigue. This paper explains a long-term pedaling experiment that we use it to explore the possibility to use only the time sequence data of head movement during pealing to estimate the fatigue. While we show the possibility for this through experimental data, it is clear that we need to collect more data to establish an estimation method.

The passivity of neural networks with a time-varying delay and norm-bounded parameter uncertainties is investigated in this paper. A complete delay-decomposing approach is employed to construct a Lyapunov-Krasovskii functional. Then, by utilizing a segmentation technique to consider the time-varying delay and its derivative and introducing some free-weighting matrices to express the relationship between the time-varying delay and its varying interval, some improved passivity criteria are derived. Finally, two numerical examples are given to show the effectiveness and the merits of the proposed method.

This paper investigates the delay-dependent stability for generalized continuous neural networks with time-varying delays. A novel Lyapunov-Krasovskii functional (LKF) that considers more information on activation functions of delayed neural networks and delay upper bounds is developed. Simultaneously, most commonly used techniques for treating the derivative of the LKF are reviewed and compared with each other. With the way of introducing slack matrices, those techniques are classified into two categories, including free-weighting matrix (FWM)-based techniques and reciprocally convex combination-based techniques. It is found that the introduced slack matrices play an important role in conservatism reducing and those four types of FWM-based methods lead to same results and are equivalent. Moreover, the obtained criteria are extended to the system with a single time-varying delay. Two numerical examples are given to verify the effectiveness of the proposed method.

SUMMARY The curse of dimensionality is a ubiquitous problem for multiagent reinforcement learning, which means the learning and storing space grows exponentially with the number of agents and hinders the application of multiagent reinforcement learning. To relieve this problem, we propose a new framework named as optimal tracking agent (OTA). The OTA views the other agents as part of the environment and uses a reduced form to learn the optimal decision. Although merging other agents into the environment may reduce the dimension of action space, the environment characterized by such form is dynamic and does not satisfy the convergence of reinforcement learning (RL). Thus, we develop an estimator to track the dynamics of the environment. The estimator obtains the dynamic model, and then the model‐based RL can be used to react to the dynamic environment optimally. Because the Q‐function in OTA is also a dynamic process because of other agents’ dynamics, different from traditional RL, in which the learning is a stationary process and the usual action selection mechanisms just suit to such stationary process, we improve the greedy action selection mechanism to adapt to such dynamics. Thus, the OTA will have convergence. An experiment illustrates the validity and efficiency of the OTA.Copyright © 2012 John Wiley & Sons, Ltd.

This paper presents a hierarchical intelligent control system (HICS) based on soft-sensing of burn-through point(BTP) and vertical sintering speed (VSS) for the sintering process, which has a two-level hierarchical configuration (intelligent control level and basic automation level), and is being used in an iron and steel plant. At the intelligent control level, first, BTP and VSS soft-sensing models are established, respectively. Next, the BTP mechanical control model and fuzzy controller are designed. The basic automation level contains a distributed control system (DCS), which performs process control including stable tracking control of the strand velocity; and a communication interface, which enables the intelligent controller and the DCS to exchange data on process information. The real-world application results show that the system not only sufficiently suppresses the fluctuation, but also effectively improve the utilization factor of the sintering machine and the quality and quantity of the sinters.

This paper deals with the problem of uniform stability and asymptotical stability for nonlinear time delay systems. Some new sufficient conditions are established guaranteeing uniformly stability and asymptotical stability, which show that the derivative of the Lyapunov function relaxes to be indefinite instead of negative definite in the literature. A result for determining input to state stability of nonlinear time delay systems is also reported in this paper.

Emotional states based three-dimensional (3-D) Fuzzy Atmosfield (FA) is proposed to express the feeling between humans and robots in communication, and is built with 3-D coordinates, i.e. "friendly-hostile", "lively-calm", and "casual formal" axes. The FA aims to be an effective tool to proceed with the communication paying attention to the atmosphere generated by individual emotional state which is calculated from bimodal communication cues namely emotional-speech and emotional gesture by using weighted fusion and fuzzy inference. A novel emotion recognition approach is presented which consists of two steps, i.e., classification of six basic emotions for initial emotional states in the Affinity-Pleasure-Arousal emotion space, and emotional transition from prior state by using fuzzy logic. Home party enjoying demonstration confirms FA's availability empirically by questionnaires from unrelated persons of authors' group, where smooth communication between four humans and five eye robots is realized in Mascot Robot System.

To cope with the curse of dimensionality, an ubiquitous problem in multi-agent reinforcement learning, this paper deals with the multi-agent learning in a new perspective and proposes a new algorithm, the optimal tracking agent (OTA). The OTA treats the other agents as a part of the system and uses an estimator to track the dynamics of the system. Thus, it obtains the dynamic model with limit accuracy and uses the model-based reinforcement learning to react optimally to the system. All the processes are just from one agent's perspective, then the searching space for action is just its own and not exponential with the number of agents any more. Thus, the curse of dimensionality is relieved from action space. Experiment illustrates the validity and efficiency of the proposed method.

This paper is concerned with the problem of stability of neural networks with time-varying delays. A novel Lyapunov-Krasovskii functional decomposing the delays in all integral terms is proposed. By exploiting all possible information and considering independent upper bounds of the delay derivative in various delay intervals, some new generalized delay-dependent stability criteria are established, which are different from the existing ones and improve upon previous results. Numerical examples are finally given to demonstrate the effectiveness and the merits of the proposed method.

This paper presents a unified treatment of the motion control of underactuated two-link manipulators, including acrobots and pendubots. The motion space is divided into two areas: swing-up and attractive; and control laws are designed for each. First, a control law based on a weak-control Lyapunov function (WCLF) is employed to increase the energy of and control the posture of the actuated link in the swing-up area. Next, one parameter of the WCLF is chosen to be a nonlinear function of the state to avoid singularities. Then, another parameter of the control law is adjusted based on the state to improve the control performance. Finally, an optimal control law is designed for the attractive area. Stability is guaranteed in the swing-up area by the use of a WCLF based on LaSalle's invariance principle. Moreover, the global stability of the control system is guaranteed by integrating the WCLF and a nonsmooth Lyapunov function.

In this paper, we consider delayed bidirectional associative memory (BAM) neural networks (NNs) with Lipschitz continuous activation functions. By applying Young's inequality and Hoelder's inequality techniques together with the properties of monotonic continuous functions, global exponential stability criteria are established for BAM NNs with time delays. This is done through the use of a new Lyapunov functional and an M-matrix. The results obtained in this paper extend and improve previous results.

This correspondence paper focuses on the problem of exponential stability for neural networks with a time-varying delay. The relationship among the time-varying delay, its upper bound, and their difference is taken into account. As a result, an improved linear-matrix-inequality-based delay-dependent exponential stability criterion is obtained without ignoring any terms in the derivative of Lyapunov-Krasovskii functional. Two numerical examples are given to demonstrate its effectiveness.

This paper addresses the problem of controlling the temperature of the combustion process in a billet regenerative reheating furnace, and presents a method of optimizing the parameters of a fuzzy-neural-network decoupling controller (FNNDC) through the combination of an immune clone and a self-adaptive mutation rate. First, a recurrent neural network is built to model the process based on data from actual runs. Then, the number and parameters of hidden neurons in the FNNDC are determined by means of a fuzzy c-means clustering strategy. Finally, an algorithm for immune-clone evolution (ICE) is combined with a self-adaptive mutation rate to optimize the connecting weights of the FNNDC. This method features global optimization and high precision in local searches. Simulation results demonstrate the validity of this method and its superiority over genetic algorithms.

This letter is concerned with the stability analysis of neural networks (NNs) with time-varying interval delay. The relationship between the time-varying delay and its lower and upper bounds is taken into account when estimating the upper bound of the derivative of Lyapunov functional. As a result, some improved delay/interval-dependent stability criteria for NNs with time-varying interval delay are proposed. Numerical examples are given to demonstrate the effectiveness and the merits of the proposed method.

This paper presents a novel control strategy based on a non-smooth Lyapunov function to guarantee the stability of the system in the whole motion space. Three control laws that are derived based on three Lyapunov functions are applied successively in three stages of motion control to achieve a suitable posture and increase the energy so as to make the acrobot move into the area around the unstable inverted equilibrium position, and to stabilize it at that position. These three Lyapunov functions are combined into one non-smooth function, which theoretically guarantees the stability of the acrobot in the whole motion space. Simulation results have demonstrated the validity of this strategy

This paper presents a comprehensive unified control strategy for underactuated two-link manipulators, including acrobots and pendubots. The motion space is divided into two areas: swing-up and attractive; and control laws are designed for each. First, a control law based on a weak control Lyapunov function (WCLF) is employed to increase the energy and control the posture of the actuated link in the swing-up area. Next, one of the parameters of the WCLF is chosen to be a nonlinear function of the state so as to avoid any singularities. Then, another parameter in the control law is adjusted based on the state to improve the control performance. Stability is guaranteed in the swing-up area by the use of a WCLF based on the LaSalle invariant theorem. Finally, the global stability of the control system is guaranteed by the use of a non-smooth Lyapunov function integrated with a minimum-switching strategy. Simulation results for a pendubot and an acrobot show this control scheme to be very effective

A new Lyapunov-Krasovskii functional is constructed for delayed cellular neural networks, and the S-procedure is employed to handle the nonlinearities. An improved global asymptotic stability criterion is also derived that is a generalization of, and an improvement over, previous results. Numerical examples demonstrate the effectiveness of the criterion.

In this letter, the delay-dependent state estimation problem for neural networks with time-varying delay is investigated. A delay-dependent criterion is established to estimate the neuron states through available output measurements such that the dynamics of the estimation error is globally exponentially stable. The proposed method is based on the free-weighting matrix approach and is applicable to the case that the derivative of a time-varying delay takes any value. An algorithm is presented to compute the state estimator. Finally, a numerical example is given to demonstrate the effectiveness of this approach and the improvement over existing ones.