Accurately inferring the causality among variables is essential for diagnosing the root causes of industrial process faults. The multimode characteristics of industrial processes augment the complexity of fault evolution processes, which presenting challenges to traditional methods. To this end, the continuous causal learning framework is proposed for comprehensive root cause diagnosis of multimode processes. Firstly, the temporal feature interference aided causal discovery network is designed to achieve collaborative quantification of multivariate causality, which can facilitate continuous learning while avoiding pairwise causal modeling. Then, to address the “catastrophic forgetting" issue in continuous learning, an elastic weight consolidation strategy is introduced to balance the newly emerged modes and previously learned modes through adaptive parameter regularization during sequential model updating. Subsequently, the root cause diagnosis index impact score is designed to locate the real root cause according to the causality variations from normal to faults with Cramer-von Mises test. Additionally, the propagation paths are identified through the SL metric by involving causality strength and time lag simultaneously. Finally, the proposed method significantly outperform the existing methods in terms of root cause diagnosis on both simulated and real-world multimode processes.

This paper investigates the sensor fault detection and diagnosis problems for lithium-ion battery systems. A combined model-based and data-driven approach is proposed to detect and diagnose four types of sensor faults, i.e., bias fault, drift fault, accuracy degradation and complete fault. Firstly, an optimal model-based fault detection filter is designed to obtain the residual data, which is utilized to extract the features of the sensor faults. Secondly, a data-driven method is developed to realize the fault detection and diagnosis, which adopts the technique of short-time Fourier transform (STFT) to generate a multi-window STFT-based fault detection and diagnosis algorithm. By employing appropriate multiple windows, the trade-off between time-domain and frequency-domain accuracy is achieved, allowing for a more precise characterization of the faults. Compared with the traditional fault detection and diagnosis techniques, the developed approach is more general and applicable to a broader range of sensor faults. Finally, a physical experiment is conducted for validating the effectiveness and practicality of the proposed method.

This paper presents a gradient-based fault detection method for pitch control systems in avionics. On the basis of the dynamic model of the airplane, the proposed method detects both operator and sensor faults by monitoring the online data. By integrating fault-related behaviors over an extended time window, the method effectively amplifies small changes caused by incipient faults, improving detectability. Theoretical analysis reveals that under normal flight conditions, the gradient has a zero expected value and a finite, analytically tractable variance. These characteristics make the method compatible with traditional fault detection approaches. Sufficient tests on real flight data verify its ability to detect hard-to-identify faults.

Offline reinforcement learning (RL) offers a promising paradigm for learning policies from precollected datasets. Nonetheless, applying it to robotic control poses significant challenges, including non-Markovian dynamics and the scarcity of high-quality demonstrations, both of which can undermine the performance of existing methods. To address these issues, this work introduces the horizon-GreedyQ-ensemblesRegularized decisionTransformer (GQRT), an offline RL algorithm tailored for robotic tasks. GQRT leverages a transformer-based policy for trajectory modeling, thereby enabling effective long-horizon decision-making in non-Markovian settings. To alleviate the lack of expert demonstrations, we develop a multistep horizon-greedy policy evaluation mechanism that stitches suboptimal sequences into improved trajectories. Furthermore, to cope with mixed-quality demonstrations collected from diverse sources, we incorporate aQ-ensemble with lower confidence bound regularization, which ensures more stable and reliable value estimation. Extensive experiments on robotic locomotion and manipulation benchmarks demonstrate that GQRT achieves state-of-the-art performance, validating its robustness in complex robotic scenarios.

In this article, a multiobjective optimization methodology is tailored for energy producers and sellers (Prosumers) and electric vehicle charging service providers (EVCS) in IES. The primary objective is to harmonize economic and safety aspects of system, while addressing uncertainties associated with renewable energy and involvement of electric vehicles (EVs) in integrated demand response (IDR). Initially, an orderly charging model for EVs is developed by driving behavior patterns, taking into account the influence of EVCS aggregating EVs in IDR via photovoltaic-energy storage charging stations. Subsequently, a stochastic programming method with conditional value at risk is utilized to alleviate potential risks from stochastic and intermittent nature of renewable energy outputs. Furthermore, the optimization framework incorporates operating costs of Prosumers and EVCS, and peak-to-valley difference of IES load as multiobjective functions. The optimal solution is determined by technique for order of preference by similarity to ideal solution. Ultimately, case studies confirm that the proposed approach effectively balances economic performance for multiple stakeholders and operational safety, and enhances system robustness under uncertain conditions.

This paper presents a novel and integrated approach for unmanned surface vehicles (USVs) in path planning and trajectory tracking control applications. In order to ensure the optimality and real-time performance of USV’s path planning, the planning algorithm based on reinforcement learning is integrated and improved by fusing the state information of USVs and the environment. To guarantee the smoothness of the generated path curve for the required tracking and control algorithm, the points with large curvature are selected as key points for sampling and quintic spline curve fitting is used. According to the characteristics of USVs during trajectory tracking, a controller is designed to ensure the stability and accuracy of the tracking, and the stability of this controller is proved by Lyapunov function. The validity and feasibility of the proposed method have been verified through simulation experiments.

The global stabilization control issue concerning a class of general upper-triangular nonlinear systems subject to non-parametric uncertainties is dealt with in this paper by constructing a nonsmooth dynamic nonrecursive state-feedback controller. The major challenge in handling such systems is that they cannot be stabilized through the conventional feedback linearization approaches. The investigated strategy does not involve a nested process, commonly seen in existing methods, but rather constructs a homogeneous stabilizer directly via a low-gain design, which greatly facilitates the design of the controller and the analysis of global stability. Meanwhile, by developing a dual-layer adaptive low-gain online updating law, the system with unknown homogeneous nonlinearity growth conditions under consideration can be flexibly stabilized. A numerical simulation and an application to the nonlinear liquid level control resonant circuit system are implemented in this paper to demonstrate the efficacy of the built framework.

This paper delves into the constant voltage output regulation problem for delayed inductive power transfer (IPT) systems with linear matrix inequality region constraints. Different from existing works, the proposed approach not only provides a model-free controller design procedure, but also deals with time-varying delays and packet losses. The main contributions are twofold. First, we propose a novel data-based parameterization of delayed systems. Second, data-based sufficient conditions are derived under which the delayed stability and LMI region constraints are guaranteed and then controller is parameterized. Finally, an experimental example is proposed to demonstrate the accuracy of proposed methods and the robustness of the suggested controllers.

Tackling the challenge of open-switch (OS) fault diagnostics in grid-tied three-level neutral point clamped (NPC) inverters with parameter uncertainty, this paper introduces a fault diagnosis method that integrates a variable forgetting factor bias-compensation recursive least squares (VFFBCRLS) algorithm with a novel discrete disturbance sliding mode observer (DSMO) for three-level inverters. The proposed approach initially employs a VFFBCRlS algorithm to obtain the uncertain parameters of the inverter. Building upon this foundation, a novel discrete DSMO is introduced to obtain the output currents rapidly and accurately. Then, an adaptive fault detection variable is constructed based on the norm of the residual between the measured and the estimated currents, ensuring the accuracy and robustness of the detection algorithm. Finally, a precise identification of OS faults in grid-tied inverters is achieved through the establishment of a localization mechanism. The hardware-in-the-loop (HIL) test results provide validation for the efficacy and robustness of the proposed method.

This article introduces an innovative approach to simultaneously estimate time-domain and spatiotemporal faults in nonlinear distributed parameter systems (NDPSs)nonlinear distributed parameter systems (NDPSs) under external disturbances. First, the establishment of an iterative learning observer that accounts for both temporal and spatial changes is presented. Next, a fault estimation law is devised utilizing a distinct full iterative learning (FIL)full iterative learning (FIL) technique, facilitating rapid and precise estimation of fault signals while mitigating the impact of external disturbances. Furthermore, the adoption of the $\lambda $ -norm method aids in simplifying the determination of convergence conditions and gain matrix calculations. Lastly, comprehensive simulation results validate the efficacy of the developed approach, underscoring its adeptness in efficiently and precisely estimating faults across both time and spatiotemporal domains.

Seeking the Pareto-Nash equilibrium in multi-agent, multi-objective general-sum games (MMGSG) poses a significant challenge, particularly in accurately capturing individual preferences and adhering to the fairness principle of the solution. To address this issue, this paper introduces, for the first time, a multi-level distributed fuzzy optimum policy iteration (MDFOPI) method for identifying the Pareto-Nash equilibrium point in MMGSG. This approach is grounded in fuzzy optimal membership degrees, and employs fuzzy measures and$\lambda$-mean classification to construct the coupled multi-objective optimum matrix, utilizing the strategy space as the foundation. The Pareto-Nash equilibrium point is sought through the MDFOPI method, with the multi-objective optimal membership degree matrix used to organize the sampled data and integrate the results of multi-objective evaluations. This work rigorously proves the existence of Nash equilibria in MMGSG and establishes the convergence of the MDFOPI method to a fixed point, specifically a Pareto-Nash equilibrium point. The accuracy and practical applicability of the research findings are verified through simulation experiments.

Focusing on control performance enhancement for a general class of nonlinear systems with mismatched disturbances, an intelligent composite regulator is investigated by integrating disturbance observation, nonrecursive nonsmooth control (NRNSC), and deep reinforcement learning (DRL) techniques in this article. With the help of the self-learning ability delivered by the DRL algorithm, a robust adaptive control scheme is constructed for handling the challenge of parameter configuration difficulty in the traditional NRNSC synthesis approach. A new feature is that the bandwidth factor optimization in both feedforward and feedback loops is simultaneously considered. While ensuring the system maintains certain robustness, the most suitable adaptive bandwidth factors are self-tuned to optimize the control performance. Thereafter, an appropriate tradeoff is promisingly achieved between the two performances. To enhance the persuasiveness of the proposed method in terms of performance improvement, numerical simulations, and experiment tests on a permanent magnet synchronous motor (PMSM) position servo platform are conducted.

The series includes two parts, articulating the two novel avenues of research on intelligent fault diagnosis (FD) for nonlinear feedback control systems. In Part I of the series, we design a novel FD paradigm by elaborating an invertible neural network (INN) for feedback control systems. With the aid of a left manifold, the core idea behind the INN-based FD scheme is as follows: 1) formulation of residual generator used for FD as a projection of system data onto the null space that has the same dimension as system outputs; 2) in a topological space, elaboration of a homeomorphism that delivers an invertible relationship between system outputs and residual signals when the system input is given; and 3) skillful introduction of both the master and slave objective functions to achieve system/parameter identification with information loseless property. Comparing with the existing FD approaches, the three superior strengths of the proposed FD scheme deserving mentation are as follows: 1) it specializes in nonlinear feedback control systems; 2) it can effectively avoid the overfitting problem when approximating or learning nonlinear system dynamics; and 3) control theory guides the whole design, ensuring the interpretability of the learning process. Finally, two studies on nonlinear systems demonstrate the feasibility of the invertible left manifold (ILM)-based FD strategy. Part I would contribute to the future development of machine learning (ML)-based system identification and explainable FD approaches, and also benefits the right manifold-based FD designs in Part II.

The challenge of the exploration-exploitation dilemma persists in off-policy reinforcement learning (RL) algorithms, impeding the improvement of policy performance and sample efficiency. To tackle this challenge, a novel historical decision-making regularized maximum entropy (HDMRME) RL algorithm is developed to strike the balance between exploration and exploitation. Built upon the maximum entropy RL framework, the historical decision-making regularization method is proposed to enhance the exploitation capability of RL policies. The theoretical analysis involves proving the convergence of HDMRME, investigating the tradeoff between exploration and exploitation of HDMRME, examining the disparity between the Q-function learned through HDMRME and the classic one, and analyzing the suboptimality of the trained policy. The performance of HDMRME is evaluated across various continuous-action control tasks from Mujoco and OpenAI Gym platforms. Comparative experiments demonstrate that HDMRME exhibits superior sample efficiency and achieves more competitive performance compared with other state-of-the-art RL algorithms.

Multiagent reinforcement learning (RL) training is usually difficult and time-consuming due to mutual interference among agents. Safety concerns make an already difficult training process even harder. This study proposes a safe adaptive policy transfer RL approach for multiagent cooperative control. Specifically, a pioneer and follower off-policy policy transfer learning (PFOPT) method is presented to help follower agents acquire knowledge and experience from a single well-trained pioneer agent. Notably, the designed approach can transfer both the policy representation and sample experience provided by the pioneer policy in the off-policy learning. More importantly, the proposed method can adaptively adjust the learning weight of prior experience and exploration according to the Wasserstein distance between the policy probability distributions of the pioneer and the follower. Case studies show that the distributed agents trained by the proposed method can complete a collaborative task and acquire the maximum rewards while minimizing the violation of constraints. Moreover, the proposed method can also achieve satisfactory performance in terms of learning speed and success rate.

In this article, a distributed fault estimation (DFE) approach for switched interconnected nonlinear systems (SINSs) with time delays and external disturbances is proposed using a novel segmented iterative learning scheme (SILS). First, through the utilization of interrelated information among subsystems, a distributed iterative learning observer is developed to enhance the accuracy of fault estimation results, which can realize the fault estimation of all subsystems under time delays and external disturbances. Simultaneously, to facilitate rapid fault information tracking and significantly reduce sensitivity to interference, a new SILS-based fault estimation law is constructed by combining the idea of segmented design with the method of variable gain. Then, an assessment of the convergence of the established fault estimation methodology is conducted, and the configurations of observer gain matrices and iterative learning gain matrices are duly accomplished. Finally, simulation results are showcased to demonstrate the superiority and feasibility of the developed fault estimation approach.

Federated learning (FL)-based fault diagnosis is being widely developed. However, most of the existing FL methods may suffer from two drawbacks: 1) they are limited to a single diagnosis task, and this may be insufficient when comprehensive health status information is needed and 2) most of them work offline, thus neglecting the useful information contained in newly collected operation data. For this end, this article proposes a multitask federated incremental learning (multitask-FIL) framework. First of all, a multitask feature sharing network is established by assigning the extracted general features to different downstream tasks, so that the joint loss function is obtained for subsequent collaborative training. Then, Q-learning algorithm is used to select the incremental sequences for all the parties from real-time running data, which can facilitate the model performance by involving additional data information and preferred parties. After that, the incremental weight of each party is dynamically adjusted according to the loss depth and sample size in each round of communication, so that the effects of different parties can be quantified throughout the model iteration and aggregation process. Finally, experiments on three challenging cases are performed to show that the proposed method has strong multitask collaboration capability.

This article addresses a finite-time trajectory tracking control problem for autonomous underwater vehicles with parametric uncertainties, external disturbances, thruster faults, and saturation. First, considering the unpredictable oceanic environment with the thruster faults and model uncertainties, an event-triggered finite-time generalized extended state observer (ETFTGESO) is developed to estimate the synthetic failure and unmeasured velocities simultaneously. Triggered position data is used as feedback in the correction terms of ETFTGESO, which consequently reduces unnecessary communication or computational burden. The observer order is expanded by two additional states, which enhance the estimation accuracy. Then, a homogeneous output feedback controller is proposed to achieve finite-time stability of the vehicle. To improve the convergence rate of the position and velocity trajectories, the finite-time control law is updated by integrating a homogeneous integral sliding surface. Rigorous theoretical analysis verifies fast convergence, the influence of control parameters on bounded stable region, and accurate dynamic positioning. Finally, numerical simulations are carried out to demonstrate the superiority of the proposed control scheme.

This article addresses the fault detection (FD) problem for traction drive systems with stochastic noises and deterministic disturbances. A traction drive system with sensor and actuator faults is first described as a dynamic process. Then, the disturbance-decoupling residual generator is developed by constructing a subspace for deterministic disturbances. Based on the generated residual signals, the corresponding ambiguity sets are constructed to characterize the distributional uncertainties of noises. Moreover, the design of the target FD system is formulated as a distributionally robust optimization (DRO) problem. By solving the DRO problem, a robust FD approach is developed. It is worth noting that this method not only delivers satisfactory detection performances, but also enhances robustness against both deterministic disturbances and distributional uncertainties of stochastic noises. The reliability and validity of the developed method are illustrated by a numerical simulation and an experimental study on an actual traction drive system.

In this article, a novel visionary policy iteration (VPI) framework is proposed to address the continuous-action reinforcement learning (RL) tasks. In VPI, a visionary Q-function is constructed by incorporating the successor state into the standard Q-function. Due to the introduction of the successor state, the proposed visionary Q-function captures information about state transitions within the Markov decision process (MDP), thereby providing a forward-looking perspective that enables a more accurate and foresighted evaluation of potential action outcomes. The relationship between the visionary Q-function and the standard Q-function is analyzed. Subsequently, both the policy evaluation and policy improvement rules in VPI are designed based on the proposed visionary Q-function. The convergence proof for VPI is provided, ensuring that the iterative policy sequence in VPI will converge to the optimal policy. By combining the VPI framework with the twin delayed deep deterministic policy gradient (TD3) algorithm, a visionary TD3 (VTD3) algorithm is developed. The evaluation of VTD3 is performed on multiple continuous-action control tasks from Mujoco and OpenAI Gym platforms. The results of comparative experiments demonstrate that VTD3 can achieve more competitive performance than other state-of-the-art (SOTA) RL approaches. Additionally, the experimental results indicate that VPI enhances decision-making capability, reduces Q-function estimation bias, and improves sample efficiency, thereby boosting the performance of existing RL algorithms.

In this paper, an attack-defense framework is proposed for the remote H ∞ state estimation of delayed recurrent neural networks (RNNs). Firstly, an important-data-based (IDB) attack strategy is constructed, which can identify the important packets that play essential roles in the estimation and selectively attack them based on their importance degree from the perspective of the attackers. By targeting the important packets, larger attack damages can be achieved. Then, a resilient state estimator that can resist IDB attacks is developed from the defenders' point of view. Notably, some unrealistic assumptions (e.g., the attacker knowing the system structure and full parameters, the defender knowing the attack rate/parameters) are removed, which makes the proposed method easy to implement. At last, simulation results are presented to show the larger destructive effect of the constructed IDB attack and the efficiency of the proposed resilient H ∞ state estimator .

In this work, we address the issue of asynchronous deconvolution filter design for 2-D Markov jump systems with random packet losses. First, the considered plant is established by a well-known Fornasini-Marchesini model. Then, an asynchronous 2-D deconvolution filter is proposed to reconstruct the 2-D signal with measurement noise to satisfy a prescribed performance specification. The asynchronization phenomenon between the system modes and filter modes is characterized by a hidden Markov model. Besides, in practical applications, the congestion of the transmission channel between the system and the filter may lead to data losses, which may make the system performance degraded or even unstable. For this, an improved 2-D single exponential smoothing scheme is proposed to generate some predictions of the lost information to compensate for lost packets. By means of the 2-D Lyapunov stability theory, some sufficient conditions are acquired, which can make the resultant system asymptotic mean-square stable and satisfies an$\mathcal{H}_{\infty}$disturbance attenuation performance. At last, an example concerning image processing is adopted to verify the correctness of the presented asynchronous 2-D deconvolution filtering scheme.Note to Practitioners—In practical applications, many dynamics may suffer from undergoing sudden structural or parameter changes, resulting in a system that is difficult to describe clearly. The Markov jump systems, consisting of states and modes, can handle this problem satisfactorily. Considering the effects of some unfavorable factors, i.e., delay, quantization, and environmental noise, a hidden Markov model is employed to handle the asynchronous problem between the system and the filter. On the other hand, the emergence of 2-D systems effectively solves the problem of the system’s state evolving in two directions. In addition, the congestion of the transmission channel between the system and the filter may lead to data loss. To compensate for the impact of data packet loss, an improved 2-D single exponential smoothing scheme is proposed.

This paper studies a novel quality-oriented efficient distributed framework for nonlinear plant-wide industrial quality-related process monitoring. In this strategy, process variables contained in the local unit are divided into quality-related and quality-unrelated parts using the elastic network. Then, the least absolute shrinkage and selection operator technique is utilized to select the communication variables that are highly relevant to the quality-related part of the local unit from neighboring units, which not only improves the quality-oriented process monitoring performance but also reduces redundant communications. Then, for the reorganized quality-related part of the local unit, a reasonable orthogonal decomposition is developed to cope with the inherent flaws of kernel partial least squares. This decomposition further divides the process variable space into two orthogonal parts. For the remaining quality-unrelated part of the local unit, the kernel principal component analysis with a combined index is used to monitor it. Finally, the Bayesian fusion is used to improve the monitoring efficiency. The proposed scheme and the existing methods are compared using the Tennessee Eastman benchmark process, demonstrating the superiority and effectiveness of the proposed method.Note to Practitioners—For plant-wide process monitoring, a novel quality-oriented efficient distributed monitoring strategy is developed in this paper, which not only considers the monitoring of the quality variables within systems but also emphasizes the communication efficiency between local units and neighboring units. By using the proposed strategy, local unit and neighboring unit variables can be initially filtered by applying a combination of the elastic network and the least absolute shrinkage and selection operator technique, which not only takes into account the correlation between local units and neighboring units but also reduces unnecessary information transfer from neighboring units. As a result, it improves the efficiency of distributed monitoring and ensures the accuracy of quality-related fault detection. Furthermore, the supervised process monitoring for quality variables is realized with the help of the proposed strategy. By utilizing the monitoring results, practitioners can accurately determine whether the fault type is quality-related or quality-unrelated. This information facilitates the design of a more targeted fault-tolerant control scheme, reducing unnecessary fault-tolerant control actions and enhancing the efficient utilization of the control system, ultimately leading to energy savings. Finally, the incorporation of the Bayesian fusion strategy enables the generation of both global fault and local fault detection indicators. This feature proves beneficial for designing subsequent visualization platforms, providing comprehensive information for fault analysis and system visualization.

This paper investigates the${H}_{\infty}$tracking control problem for the series-parallel (SP)-inductive power transfer (IPT) system with coil misalignment. To describe the nonlinear characteristic caused by large-scale coil misalignment, a Takagi-Sugeno (T-S) fuzzy modeling approach is successfully applied to the SP-IPT system. By introducing an integrator related to the error between the actual and the reference system output signals, an augmented T-S fuzzy-based SP-IPT system model is established. Then an${H}_{\infty}$parallel distributed compensation (PDC) fuzzy control strategy with a valid event-triggering scheme (ETS) is put forward to guarantee desired tracking control performance and decrease unnecessary packet transmission at the same time. To ensure the asymptotic stability of the augmented T-S fuzzy-based SP-IPT system and the disturbance suppression index, sufficient conditions are employed by utilizing an extended Lyapunov functional method. Finally, a simulation example with regard to the SP-IPT system is developed, which demonstrates that the event-based${H}_{\infty}$PDC fuzzy control strategy proposed in this paper can maintain the constant output voltage of the SP-IPT system while saving communication resources.Note to Practitioners—For IPTs, the coil misalignment phenomenon unavoidably affects their desired performance, such as constant voltage and current output, constant power output, maximum efficiency tracking, and so on. Therefore, the corresponding tracking controllers have brought wide attention in the power transmission research. The proposed control strategies have been utilized to suppress the negative influence caused by coil misalignment, whereas it is difficult for these strategies to ensure the robustness and the stabilization under large-scale coil misalignment. To deal with this problem, this paper is devoted to design a T-S fuzzy-based${H}_{\infty}$control strategy with an ETS to guarantee the stabilization of practical inductive power transfer systems. It is worth mentioning that the proposed robust control strategy is proposed based on the IPT system with T-S fuzzy rules and the ETS, which can simultaneously guarantee desired tracking control performance and decrease unnecessary packet transmission in real applications. In this paper, only constant voltage tracking control are considered for the IPT system with coil misalignment, but some other tracking performance still need to be researched in practice. Therefore, we will take the tracking performance indexes of constant current and constant power into account in the future research.

Accurate fault detection and localization are essential for single-phase three-level (SPTL) rectifier systems with high reliability requirements. However, power switch faults, grid-side current sensor (CS) faults, and DC-link voltage sensor (VS) faults can all contribute to distorted output in the rectifier system, posing challenges for existing diagnostic methods tailored for single-type faults, as they struggle to distinguish between these various faults. Therefore, this study proposes a comprehensive diagnosis technology for open-circuit (OC) faults, CS faults, and VS faults of SPTL rectifiers on the basis of a reduced-order observer. To achieve this, the method begins by expanding and transforming the state equation of the rectifier with faults, ensuring complete decoupling of the OC fault vector from the initial system states and sensor faults. Subsequently, an assessment of the initial system state, CS faults, and VS faults is achieved via the design of a reduced-order observer. Using these estimation results, fault detection variable and its adaptive thresholds is designed, along with fault-distinguishing variables to differentiate between sensor faults and OC faults. Simultaneously, sensor fault identification method and OC fault location method are introduced. Finally, the validity and resilience of the comprehensive diagnostic approach are confirmed through hardware-in-the-loop (HIL) test results under diverse scenarios.

Fault-tolerant control (FTC) is vital for the safety and reliability of automatic systems. Most of the existing FTC methods are developed for open-loop systems subject to additive faults, regardless of the widely present control loops and multiplicative faults within systems. In this article, a performance-based FTC strategy is proposed for the closed-loop systems with multiplicative faults. Considering the high efforts in modeling complex systems, the proposed FTC strategy is realized in the data-driven context. Specifically, a nominal feedback-feedforward controller is first established for the fault-free systems. By selecting the system stability and reference tracking behavior as the key performance indices, two performance evaluators are constructed to detect and classify the occurred multiplicative faults based on the fault-induced effects on the system performance. Then, with the aid of the coprime factorization technique, the multiplicative faults, in the form of additive perturbations to the system coprime factors, are estimated utilizing the closed-loop process data. Furthermore, based on the fault knowledge, a hierarchical fault-tolerant tracking controller is developed according to the levels of system performance degradations, where the functional controller parameters are reconfigured with different priorities. Finally, case studies are provided to validate the effectiveness of the proposed method.

This study focuses on building an intelligent decision-making attention mechanism in which the channel relationship and conduct feature maps among specific deep Dense ConvNet blocks are connected to each other. Thus, develop a novel freezing network with a pyramid spatial channel attention mechanism (FPSC-Net) in deep modeling. This model studies how specific design choices in the large-scale data-driven optimization and creation process affect the balance between the accuracy and effectiveness of the designed deep intelligent model. To this end, this study presents a novel architecture unit, which is termed as the "Activate-and-Freeze" block on popular and highly competitive datasets. In order to extract informative features by fusing spatial and channel-wise information together within local receptive fields and boost the representation power, this study constructs a Dense-attention module (pyramid spatial channel (PSC) attention) to perform feature recalibration, and through the PSC attention to model the interdependence among convolution feature channels. We join the PSC attention module in the activating and back-freezing strategy to search for one of the most important parts of the network for extraction and optimization. Experiments on various large-scale datasets demonstrate that the proposed method can achieve substantially better performance for improving the ConvNets representation power than the other state-of-the-art deep models.

In this article, we consider the problem of switched-command-filtered-based adaptive fuzzy output-feedback funnel control for switched nonlinear multi-input multi-output (MIMO) delayed systems. A switched MIMO high-gain state observer is constructed for each subsystem to estimate unavailable system states. Compared with the conventional command filter technique, the main advantage is that the improved error-compensating signals are designed for each switched subsystem to remove the filtered errors and avoid an explosion of complexity and the singularity problem. Different from the traditional Lyapunov--Krasovskii functional method, design obstacles stemming from unknown time delays are overcome for the switched delayed systems by using appropriate multiple Lyapunov--Krasovskii functions and combining with the approximation capability of the fuzzy logic systems. Under a category of switching signals with mode-dependent average dwell time, all signals in the closed-loop switched system are semiglobally uniformly ultimate bounded under the output-feedback control; meanwhile, the tracking errors can remain in prespecified performance funnels. Case studies illustrate the flexibility and effectiveness of the proposed control approach.

In this article, we study the fault detection problem of unmanned surface vehicles through the implementation of fuzzy multiprocessors. By employing the Takagi–Sugeno fuzzy technique, the linear approximation of unmanned surface vehicles is obtained, and a fuzzy multiprocessor architecture is proposed to estimate the state of unmanned surface vehicles. With the residual signal generated by multiprocessors, a detection logic is designed to realize the fault detection. Based on the Lyapunov method, sufficient conditions are given to ensure that the error dynamic system is asymptotically stable and meets the given$H_{\infty }$and$H\_$performance. Assisted by genetic algorithms, a two-step optimization algorithm is proposed to optimize the mixed$H_{\infty }$and$H\_$performance. Finally, case studies are provided to verify the effectiveness and superiority of the proposed method.

Probability forecasting is a powerful tool for quantifying uncertainty in short-term load forecasting. However, its performance may be hampered by excessive feature redundancy and the quantile crossing phenomenon. To overcome these challenges, this study proposes a novel deep noncrossing quantile method with multi-information fusion for day-ahead load probabilistic density forecasting. This method extracts different types of input features through distinct neural networks, and can reduce the redundancy of feature information. Based on the positive differences among output values from neural networks, a novel quantile noncrossing strategy is introduced. This strategy, integrated within the neural network, eliminates quantile crossing phenomena and enhances the interpretability of model during the training process. Experimental results show that the proposed model reduces the quantile loss by 11% to 31%, produces prediction intervals with higher quality, precision, and no crossovers.

In industrial processes, quality variables are typically sampled at a considerably lower frequency than system inputs due to technical or cost constraints. Dynamic soft sensors utilize temporal prediction to bridge these sampling gaps, thus enabling real-time closed-loop control. However, existing approaches primarily focus on one-step prediction accuracy, potentially leading to significant deviations in long-term predictions. In addition, these methods are incapable of evaluating the reliability of prediction results, subsequently increasing the potential risk of closed-loop systems. To tackle these challenges, this study presents a novel regression modeling approach based on the conditional variational autoencoder (CVAE) framework. In contrast to traditional regression approaches, this method focuses on modeling the transition probability distribution of the system, allowing the model to produce a range of credible quality variable predictions via Monte Carlo (MC) sampling. Based on the CVAEs, the sequential MC method is further employed to simulate diverse potential system state trajectories, thereby achieving multistep soft measurement prediction. Compared with traditional soft measurement techniques, the proposed method demonstrates lower prediction biases and the capacity to assess the credibility of prediction results from a probabilistic standpoint. When online quality variables are assessed by the laboratory, this method can update predictions utilizing the resampling scheme. Two case studies are offered to validate the effectiveness of the proposed scheme.

Dynamic target tracking technology has a broad application prospect in marine transportation, intelligent marine monitoring, border and coastal defense, etc. However, most target tracking guidance systems designed for unmanned surface vehicles (USVs) lack automatic obstacle avoidance capabilities, which limits their tracking performance. To address this challenge, this paper investigates target tracking guidance for USVs in the presence of obstacles. In order to track the target, the sensors fixed on the bow of the USVs need to be oriented toward the target, especially when the USV is sufficiently close to the target. For this purpose, a bias proportional navigation guidance law with look angle constraints is presented for guiding the follower USVs to orient and approach the moving target. In order to navigate the USVs along a safe route to avoid obstacles, the obstacle profile angle constraint is formulated into the guidance law by solving the bias function with final angle boundary conditions. The field experimentation takes place in a 40-meter-wide and 80-meter-long section of the Huchuntang River. Here, a USV equipped with the proposed guidance law effectively tracks a moving target while navigating around obstacles. Results indicate that the proposed guidance law is capable of tracking the object, avoiding obstacles, and orienting the USV to the target at the final time. The experimental test video is presented in (https://youtu.be/l5SQf2ZgcxM).

The increased complexity and intelligence of automation systems require the development of intelligent fault diagnosis (IFD) methodologies. By relying on the concept of a suspected space, this study develops explainable data-driven IFD approaches for nonlinear dynamic systems. More specifically, we parameterize nonlinear systems through a generalized kernel representation for system modeling and the associated fault diagnosis. An important result obtained is a unified form of kernel representations, applicable to both unsupervised and supervised learning. More importantly, through a rigorous theoretical analysis, we discover the existence of a bridge (i.e., a bijective mapping) between some supervised and unsupervised learning-based entities. Notably, the designed IFD approaches achieve the same performance with the use of this bridge. In order to have a better understanding of the results obtained, both unsupervised and supervised neural networks are chosen as the learning tools to identify the generalized kernel representations and design the IFD schemes; an invertible neural network is then employed to build the bridge between them. This article is a perspective article, whose contribution lies in proposing and formalizing the fundamental concepts for explainable intelligent learning methods, contributing to system modeling and data-driven IFD designs for nonlinear dynamic systems.

Over the last decade, transfer learning has attracted a great deal of attention as a new learning paradigm, based on which fault diagnosis (FD) approaches have been intensively developed to improve the safety and reliability of modern automation systems. Because of inevitable factors such as the varying work environment, performance degradation of components, and heterogeneity among similar automation systems, the FD method having long-term applicabilities becomes attractive. Motivated by these facts, transfer learning has been an indispensable tool that endows the FD methods with self-learning and adaptive abilities. On the presentation of basic knowledge in this field, a comprehensive review of transfer learning-motivated FD methods, whose two subclasses are developed based on knowledge calibration and knowledge compromise, is carried out in this survey article. Finally, some open problems, potential research directions, and conclusions are highlighted. Different from the existing reviews of transfer learning, this survey focuses on how to utilize previous knowledge specifically for the FD tasks, based on which three principles and a new classification strategy of transfer learning-motivated FD techniques are also presented. We hope that this work will constitute a timely contribution to transfer learning-motivated techniques regarding the FD topic.

Cross-scenario monitoring requires domain generalization (DG) for changed knowledge when auxiliary information is unavailable and only one source scenario is involved. In this article, a latent representation generalizing network (LRGN) is proposed to learn transferable knowledge through generalizing the latent representations for cross-scenario monitoring in perimeter security. LRGN is composed of a sequential-variational generative adversarial network (SVGAN), a coupled SVGAN (Co-SVGAN), and a knowledge-aggregated SVGAN. First, the Co-SVGAN can learn domain-invariant latent representations to model dual-domain joint distribution of background data, which is usually sufficient in the source and target scenarios. Deceptive domain shifts are generated based on the domain-invariant latent representations without auxiliary information. Then, SVGAN models the changing knowledge by estimating the distribution of domain shifts. Furthermore, the knowledge-aggregated SVGAN can transfer the learned domain-invariant knowledge from Co-SVGAN for generalizing the latent representations through approximating the distribution of domain shifts. Accordingly, LRGN is trained by a four-phase optimization strategy for DG through generating target-scenario samples of concerned events based on the generalized latent representations. The feasibility and effectiveness of the proposed method are validated through real-field experiments of perimeter security applications in two scenarios.

Over the past decade, representation learning has received particular attention in the intelligent inspection and maintenance of complex systems thanks to its overwhelming advantages in discovering and mining hidden knowledge representations. The room for in-depth investigations of representation learning-related topics remains open, especially explainable approaches for intelligent inspection and maintenance of complex systems. The primary objective of this special issue, entitled “Explainable Representation Learning-based Intelligent Inspection and Maintenance of Complex Systems,” of IEEE Transactions on Neural Networks and Learning Systems is to provide the related latest achievements made by researchers and practitioners on the one hand and to identify critical issues and challenges for future investigation on the other hand.

This article is concerned with data-driven realization of fault detection (FD) for nonlinear dynamic systems. In order to identify and parameterize nonlinear Hammerstein models using dynamic input and output data, a stacked neural network-aided canonical variate analysis (SNNCVA) method is proposed, based on which a data-driven residual generator is formed. Then, the threshold used for FD purposes is obtained via quantiles-based learning, where both estimation errors and approximation errors are considered. Compared with the existing work, the main novelties of this study include: 1) SNNCVA provides a new parameterization strategy for nonlinear Hammerstein systems by utilizing input and output data only; 2) the associated residual generator can ensure FD performance where both the system model and its nonlinearity are unknown; and 3) with consideration of modeling-induced errors, the quantiles are invoked and used to provide a reliable FD threshold in situations where only limited samples are available. Studies on a nonlinear hot rolling mill process demonstrate the effectiveness of the proposed method.

Missing values are ubiquitous in industrial data sets because of multisampling rates, sensor faults, and transmission failures. The incomplete data obstruct the effective use of data and degrade the performance of data-driven models. Numerous imputation algorithms have been proposed to deal with missing values, primarily based on supervised learning, that is, imputing the missing values by constructing a prediction model with the remaining complete data. They have limited performance when the amount of incomplete data is overwhelming. Moreover, many methods have not considered the autocorrelation of time-series data. Thus, an adaptive-learned median-filled deep autoencoder (AM-DAE) is proposed in this study, aiming to impute missing values of industrial time-series data in an unsupervised manner. It continuously replaces the missing values by the median of the input data and its reconstruction, which allows the imputation information to be transmitted with the training process. In addition, an adaptive learning strategy is adopted to guide the AM-DAE paying more attention to the reconstruction learning of nonmissing values or missing values in different iteration periods. Finally, two industrial examples are used to verify the superior performance of the proposed method compared with other advanced techniques.

In order to achieve fault diagnosis and prognosis, one needs a sufficient and valid life-cycle data. However, this requirement is difficult for current high-reliable manufacturing system. Good thing is that the technique of accelerated degradation testing can be used to address this issue. Bad thing is that it needs a reliable testing/measuring technique to build an accurate model for accelerated degradation testing. However, in practical applications, data acquisition is obtained by sensors or measurement devices, which cannot guarantee perfect working condition under the influence of external environment and stresses, resulting in unreliable signals. Furthermore, since traditional models require complex differentiation and cannot obtain analytical expressions when considering unreliable signals, traditional models rarely reflect well this situation. Motivated by these facts, an accurate model for the accelerated degradation testing is proposed in this study with considering the unreliable signals. Based on the proposed model, a closed-form expression for the useful life analysis is derived. The Metropolis–Hastings (M-H) sampling method is used to estimate the unknown parameters used in the proposed model. For illustration, the electrical connector dataset is analyzed with the proposed model and the traditional models. Comparing the obtained results, the proposed model is more accurate in the useful life analysis than the traditional accelerated degradation testing models by considering the unreliable signals.

Features of incipient faults are tiny in high-speed trains’ electrical drive systems. Noises and disturbances in the external environment and sensors can mask incipient faults. Therefore, fault detection (FD) of incipient faults is a challenge. This paper proposes a new FD scheme using a novel manifold learning method named local linear generalized autoencoder (LLGAE). The prominent characteristics of the LLGAE-based FD method are three-fold: 1) it can realize FD for electric drive systems even without the physical model or expertise; 2) it still has good results for non-Gaussian electrical drives; 3) it entirely takes into account the locally linear structure of samples. Mathematical derivations have proved the proposed method. Through an experimental platform of high-speed trains, the proposed method is validated.

To ensure the safety of an automation system, fault detection (FD) has become an active research topic. With the development of artificial intelligence, model-free FD strategies have been widely investigated over the past 20 years. In this work, a hybrid FD design approach that combines data-driven and model-based is developed for nonlinear dynamic systems whose information is not known beforehand. With the aid of a Takagi-Sugeno (T-S) fuzzy model, the nonlinear system can be identified through a group of least-squares-based optimization. The associated modeling errors are taken into account when designing residual generators. In addition, statistical learning is adopted to obtain an upper bound of modeling errors, based on which an optimization problem is formulated to determine a reliable FD threshold. In the online FD decision, an event-triggered strategy is also involved in saving computational costs and network resources. The effectiveness and feasibility of the proposed hybrid FD method are illustrated through two simulation studies on nonlinear systems.

Recently, canonical correlation analysis (CCA) has been explored to address the fault detection (FD) problem for industrial systems. However, most of the CCA-based FD methods assume both Gaussianity of measurement signals and linear relationships among variables. These assumptions may be improper in some practical scenarios so that direct applications of these CCA-based FD strategies are arguably not optimal. With the aid of neural networks, this work proposes a new nonlinear counterpart called a single-side CCA (SsCCA) to enhance FD performance. The contributions of this work are four-fold: 1) an objective function for the nonlinear CCA is first reformulated, based on which a generalized solution is presented; 2) for the practical implementation, a particular solution of SsCCA is developed; 3) an SsCCA-based FD algorithm is designed for nonlinear systems, whose optimal FD ability is illustrated via theoretical analysis; and 4) based on the difference in FD results between two test statistics, fault diagnosis can be directly achieved. The studies on a nonlinear three-tank system are carried out to verify the effectiveness of the proposed SsCCA method.

This article addresses the event-triggered asynchronous fault detection (FD) problem of fuzzy-model-based nonlinear Markov jump systems (MJSs) with partially unknown transition probabilities. For this objective, the nonlinear plant is modeled as an interval type-2 (IT2) fuzzy MJS with the aid of the IT2 fuzzy sets capturing the uncertainties of the membership functions. An adaptive event-triggered scheme is introduced to bring down the costs of the communication network from the system to the fuzzy fault detection filter (FDF), in which the triggering parameter can be adaptively tuned with the system dynamics. A hidden Markov model (HMM) is employed to characterize the asynchronous phenomenon between the system and the FDF. Unlike the existing results, the transition probabilities of the plant and the FDF are allowed to be partially known. By using the Lyapunov and the membership-function-dependent methods, the existence conditions of the FDF are derived. Finally, the proposed FD methods are verified by a numerical simulation.

Recently, to ensure the reliability and safety of high-speed trains, detection and diagnosis of faults (FDD) in traction systems have become an active issue in the transportation area over the past two decades. Among these FDD methods, data-driven designs, that can be directly implemented without a logical or mathematical description of traction systems, have received special attention because of their overwhelming advantages. Based on the existing data-driven FDD methods for traction systems in high-speed trains, the first objective of this paper is to systematically review and categorize most of the mainstream methods. By analyzing the characteristic of observations from sensors equipped in traction systems, great challenges which may prevent successful FDD implementations on practical high-speed trains are then summarized in detail. Benefiting from theoretical developments of data-driven FDD strategies, instructive perspectives on this topic are further elaborately conceived by the integration of model-based FDD issues, system identification techniques, and new machine learning tools, which provide several promising solutions to FDD strategies for traction systems in high-speed trains.

Soft sensors have been extensively developed and applied in the process industry. One of the main challenges of the data-driven soft sensors is the lack of labeled data and the need to absorb the knowledge from a related source operating condition to enhance the soft sensing performance on the target application. This article introduces deep transfer learning to soft sensor modeling and proposes a deep probabilistic transfer regression (DPTR) framework. In DPTR, a deep generative regression model is first developed to learn Gaussian latent feature representations and model the regression relationship under the stochastic gradient variational Bayes framework. Then, a probabilistic latent space transfer strategy is designed to reduce the discrepancy between the source and target latent features such that the knowledge from the source data can be explored and transferred to enhance the target soft sensor performance. Besides, considering the missing values in the process data in the target operating condition, the DPTR is further extended to handle the missing data problem utilizing the strong generation and reconstruction capability of the deep generative model. The effectiveness of the proposed method is validated through an industrial multiphase flow process.

With the aid of neural networks, this article develops two data-driven designs of fault detection (FD) for dynamic systems. The first neural network is constructed for generating residual signals in the so-called finite impulse response (FIR) filter-based form, and the second one is designed for recursively generating residual signals. By theoretical analysis, we show that two proposed neural networks via self-organizing learning can find their optimal architectures, respectively, corresponding to FIR filter and recursive observer for FD purposes. Additional contributions of this study lie in that we establish bridges that link model- and neural-network-based methods for detecting faults in dynamic systems. An experiment on a three-tank system is adopted to illustrate the effectiveness of two proposed neural network-aided FD algorithms.

High-speed trains have become one of the most important and advanced branches of intelligent transportation, of which the reliability and safety are still not mature enough for keeping up with other aspects. The first objective of this paper is to present a comprehensive review on the fault detection and diagnosis (FDD) techniques for high-speed trains. The second purpose of this work is, motivated by the pros and cons of the FDD methods for high-speed trains, to provide researchers and practitioners with informative guidance. Then, the application of FDD for high-speed trains is presented using data-driven methods which are receiving increasing attention in transportation fields over the past ten years. Finally, the challenges and promising issues are speculated for the future investigation.

Incipient faults in high-speed trains are usually masked by noises and disturbances from process and sensors, which severely increases the difficulty of incipient fault detection and diagnosis. By introducing Hellinger distance into multivariate statistical analysis framework, this paper develops a robust detection and diagnosis method for incipient faults under the principal component analysis. The proposed method can detect all incipient sensor faults in traction systems of high-speed trains in real time by comparing reference probability density functions (PDFs) with the online estimated PDFs. According to the fault detection information, an accurate fault diagnosis can be achieved online through Bayesian inference. Key advantages of the proposed method are its salient robustness to unknown noises and disturbances, as well as the high sensitivity to incipient faults. In addition, the proposed method does not require any information on system models of high-speed trains or any human intervention. The effectiveness of the proposed method has been firstly proven by mathematical derivations and then been verified by numerical simulations. Finally, the proposed method has been applied to the practical experiment platform of the high-speed trains.

Hot spots are common abnormalities in photovoltaic (PV) energy systems. Their presence can potentially cause damage to PV modules, such as performance degradation or even unexpected fire to PV energy systems. By sufficiently mining the information hidden in the test data collected from PV modules, this paper develops a space-to-space projection method, which at its core is a linear approach via preserving the locally geometrical structure with respect to time series. Based on the nonlinear model of PV modules established via the proposed projection, data-driven detection of hot spots in PV energy systems can be directly achieved with three key advantages: 1) its implementation does not depend on any mathematical model or physical knowledge of PV energy systems; 2) it is of high-computational efficiency especially in the online detection phase; and 3) it can capture the dynamic characteristic because the local structure of samplings regarding time is given sufficient consideration. The effectiveness and feasibility of the proposed approach are first presented by theoretical analysis and, then, convictively demonstrated via 15 sets of hot spot experiments on practical PV modules.