This paper investigates inverse reinforcement learning for continuous-time networked two-dimensional Markov jump systems. In many IoT applications, control policies are generated by expert controllers or cloud-based optimization modules, while the underlying performance objectives are implicit and therefore unavailable to distributed edge nodes. To address this challenge, an inverse reinforcement learning framework is developed to reconstruct mode-dependent cost functions from observed state and input trajectories. By exploiting the coupled algebraic Riccati equation structure associated with two-dimensional Markov jump systems, inverse optimality conditions are reformulated across both propagation dimensions and stochastic modes. The proposed approach establishes asymptotic mean-square stability and convergence of the recovered cost matrices, and it reveals fundamental identifiability and homogeneity properties that characterize reward ambiguity in inverse learning. To improve scalability and reduce model dependence, a fully data-driven inverse reinforcement learning algorithm is further proposed, enabling cost reconstruction without explicit knowledge of system dynamics. Numerical and physics-grounded simulation examples demonstrate the effectiveness of the proposed methods.

With the rapid development of autonomous unmanned vehicle (AUV) technology, the requirements for sensor data integrity and reliability are increasing. Data-driven intrusion detection systems (IDSs) have been widely used as an effective module of defense to ensure AUV security. Once the IDS is destroyed, the impact on the normal driving of the AUV will be unimaginable. Unlike traditional research that seeks to improve the detection accuracy of IDS, this paper discusses the challenges posed by adversarial attacks on autonomous vehicles from the perspective of attackers. In this paper, an generative adversarial-enabled U-shaped network (GEUN) is proposed to generate adversarial sensor attacks in AUVs and reveal vulnerabilities in existing IDSs. Specifically, GEUN consists of a shared feature extraction encoder, an adversarial anomaly reconstruction decoder, a discriminator, and a detector. The feature extraction encoder is used to add multi-scale information to the input to strengthen the multi-scale feature extraction of sensor signals by the network. With the help of discriminators and detectors, the adversarial anomaly reconstruction decoder is used to generate anomalies based on the extracted multi-scale vehicle information. Through experimental comparison with other methods, it is shown that the proposed GEUN can effectively attack various common IDS, which provides guidance for future research and development in the field of security of AUVs.

This paper investigates the resilient dynamic feedback control problem for fuzzy multi-rate systems (FMRS) subject to a novel important-data-based attack (IDBA). In practical engineering systems, physical limitations such as sensor aging, quantization effects, and unstable power supplies often cause discrepancies between measurement outputs and actual system states, leading to multi-rate sampling behaviors. To accurately characterize such sampling inconsistencies, a nonhomogeneous Markov sampling model is introduced, which provides a more realistic description and reduces conservatism compared with traditional homogeneous models. Motivated by the need for stealthy yet destructive cyber attacks, this paper further proposes an IDBA scheme, in which the adversary selectively identifies and disrupts only the most critical data nodes based on their instantaneous impact on system behavior. To mitigate the severe disruptions caused by IDBA, a resilient dynamic output feedback controller is designed, thereby enhancing adaptability under adverse network conditions. Simulation studies, including both numerical and practical examples, demonstrate that the proposed control framework effectively preserves system stability and achieves superior performance in the presence of IDBA.

This article addresses the output feedback control problem for a specific class of discrete-time fuzzy singularly perturbed systems subjected to nonuniform sampling and a round-robin protocol. An innovative method for modeling nonuniform sampling periods through nonhomogeneous sojourn probabilities is proposed, offering a more intuitive and adaptable framework for system design and analysis. The round-robin protocol is applied to nonuniformly sampled outputs, optimizing information transmission efficiency and enhancing overall system performance. To tackle potential limitations in state data acquisition, a token-dependent static output feedback controller is developed that addresses the complexities introduced by nonperiodic sampling and asynchronous premise variables. Sufficient conditions are derived to ensure stochastic stability of the closed-loop system. Finally, two simulation examples are presented to validate and demonstrate effectiveness of the theoretical approach.

This article addresses the challenges posed by multimode denial of service (DoS) and deception attacks in observer-based sliding mode control (SMC) for fuzzy nonlinear systems. A novel multimode DoS attack model is introduced, incorporating time-varying sojourn probabilities to provide a more accurate and computationally efficient representation of the stochastic nature of these attacks. This model overcomes the limitations of traditional Markov-based models by capturing dynamic attack behaviors. Deception attacks are modeled as unbounded nonlinear functions, and adaptive neural networks (NNs) are employed to approximate their complex behaviors, significantly reducing their detrimental impact on system stability. A fuzzy sliding surface is designed based on the switching rule for sojourn probabilities, and an observer-based SMC law is proposed to ensure the mean square estimation upper bound of the fuzzy nonlinear systems, guaranteeing stability despite the presence of cyberattacks. Finally, the validity and superiority of the proposed control strategy are demonstrated through a tunnel diode circuit model.

This article addresses discrete-time Takagi–Sugeno fuzzy switching systems utilizing a dual-channel transmission framework combined with an innovative switching rule. A novel duration-based switching mechanism is proposed, capturing realistic multiple-distribution characteristics by employing a joint distribution function involving both the current mode and its duration. Unlike traditional semi-Markov-based transition probabilities, this method emphasizes sojourn probabilities, significantly reducing the parameter estimation complexity and computational burden. The developed mechanism supports generalized duration distributions, surpassing traditional single-distribution limitations and thus lowering conservatism in the analysis. To improve the modeling accuracy and practical applicability, mode-dependent fuzzy membership functions are adopted. Observer-based feedback control strategies are implemented to effectively estimate state variables, addressing practical challenges in state measurement. In addition, the dual-channel strategy is introduced to mitigate packet loss effects and enhance data transmission reliability. The effectiveness and superiority of the proposed method are demonstrated through simulations on a single-link robotic arm.

Domain adaptation (DA) techniques are becoming increasingly proficient in cross-domain fault diagnosis tasks. However, DA-based methods are not always applicable due to the target domain data is not always accessible. Although there have been some interesting domain generalization methods for fault diagnosis under unseen conditions, most of them can only be used to mine the fault features on source domain distributions, and the improvement of model generalization performance is limited. To solve this problem, the multiplicative noise Gaussian perturbation strategy and the additive noise linear fusion strategy are proposed to capture fault information beyond source domain distributions. The former is used to randomly perturb feature statistics of multisource domains to simulate the uncertainty of domain shift, while the latter is used to perform the additive noise linear operation on feature statistics of multiple source domains to ensure the authenticity of the generated feature styles. Further, the feature statistics generated by both strategies are mixed with random convex weights to obtain new feature styles, achieving the best compromise between reliability and diversity. The network can learn more fault information from features with diversified styles. Extensive experimental results on both public and real datasets verify the effectiveness of our approach.

This study investigates the problem of adaptive neural network asynchronous control for switching cyber-physical systems under unknown dead zones. A generalized switching rule, instead of a Markov/semi-Markov process, is utilized to scrutinize the switching behavior of subsystems. This approach characterizes the dynamic nature of sojourn probabilities using single-mode-based sojourn time, aiming to decrease computational load while meeting the demands of real-world scenarios. Considering the intricacies of network environments, the unknown dead zone inputs are considered, which can be effectively implemented via the adaptive neural network-based control law. To counteract the adverse effects of unforeseen information, a saturation-based observer is developed, in which the saturation level is dynamically adjusted with the hope of providing greater flexibility. Utilizing a Lyapunov function that correlates with the detected mode and the system mode, sufficient criteria are established to ensure that the closed-loop system remains bounded in probability. Eventually, the practicality and effectiveness of the proposed control methodology are verified through two simulated examples.

This study investigates an asynchronous sliding-mode control (SMC) strategy tailored for interval type-2 (IT2) fuzzy switching systems, specifically addressing challenges posed by cyber-attacks. Distinct from existing stochastic switching strategies, a novel duration-time-based switching rule is proposed that integrates both sojourn probability and mode duration, significantly reducing computational complexity and aligning more closely with practical requirements. To mitigate mode-switching-induced chattering and enhance robustness against uncertainties and disturbances, an innovative fuzzy SMC law with a learning mechanism is developed. Notably, a recursive sliding-mode learning controller is introduced, replacing abrupt switching actions with iterative learning adjustments to progressively guide system states onto the sliding surface, thereby significantly improving control smoothness and reducing chattering. To effectively handle cyber-attacks disrupting mode transmission, a comprehensive mismatched model that dynamically synchronizes the modes of the system and the controller is introduced, offering improved resilience compared to traditional fixed mismatch approaches. Utilizing the proposed learning-based SMC and Lyapunov stability theory, sufficient conditions ensuring mean-square stability of the system are derived. Finally, the practical effectiveness and distinct superiority of the proposed methods are demonstrated through simulations using mass-spring-damper and tunnel diode circuit models.

This article studies the input-to-state stability (ISS) problem of networked control systems (NCSs) subject to both Denial-of-Service (DoS) and unknown deception attacks (DAs). A neural network (NN)-based resilient event-triggered control protocol (RETCP) is first presented to mitigate resource constraints and the adverse effects of cyber attacks, where the NN technology is leveraged to neutralize and approximate the malicious data injected by unknown DAs. Then, we develop a new predictor to compensate for lost signals of NCSs during the DoS threats, so that the NCSs can further tolerate more unfavorable DoS and unknown DAs. It is shown that the resulting NCSs with the designed novel NN-based controller can achieve ISS under the complex attacks. Finally, experimental evaluations are conducted for an uncrewed ground vehicle (UGV) to verify efficacy of the proposed intelligent control protocols.

This article investigates the state estimation problem for 2-D Markov jumping systems subjected to randomly occurring false data injection attack. To address this challenge, a novel probabilistic multi-interval ETP (PMIETP) is proposed, integrated with a time-varying saturation mechanism (TVSM). The PMIETP is designed by combining subinterval triggering thresholds with a probability distribution model, thereby enhancing system performance and adaptability under varying network conditions. To further mitigate the impact of maliciously injected data and improve estimation robustness, a TVSM-based estimator is developed, which employs an adaptive threshold to confine abnormal data within an acceptable range. In addition, a particle swarm optimization algorithm is employed to fine-tune design parameters, thereby reducing the conservativeness of linear matrix inequality conditions. Based on Lyapunov stability theory, sufficient criteria are derived to guarantee mean-square asymptotic stability and prescribed noise attenuation performance. Finally, a numerical simulation example demonstrates the effectiveness and superiorities of the proposed approach over existing methods.

This article addresses the adaptive neural network (NN)-based sliding-mode control (SMC) problem for sampled-data singularly perturbed systems under aperiodic sampling intervals and input dead zone nonlinearities. To accurately characterize the irregularity of sampling intervals, a nonhomogeneous sojourn probability approach is introduced. To accurately characterize the irregularity of sampling intervals, a nonhomogeneous sojourn probability approach is introduced. An adaptive NN scheme is utilized to estimate and effectively compensate for the nonlinear errors induced by input dead zones, thereby significantly enhancing the robustness and performance of the controlled system. Leveraging these considerations, a novel sliding-mode controller, specifically designed to accommodate variations in sampling period modes and singular perturbation parameters, is proposed. This control strategy guarantees the exponential ultimate boundedness of system states in the mean-square sense and ensures the reachability of the predefined sliding surface in the closed-loop system. The validity of the proposed theory is demonstrated through a practical example.

This paper investigates the asynchronous PID control problem of switched systems under denial-of-service (DoS) attacks and proposes a collaborative framework combining a resilient adaptive event-triggering protocol (RAETP) and robust model predictive control (RMPC). In response to the limitations of the traditional Bernoulli-type DoS attack model, a variable-frequency DoS attack model is innovatively introduced, which describes the dynamic uncertainty of the attack frequency through a random variable, thereby enhancing the ability to characterize real-world network threats. Based on the switching mechanism of piecewise homogeneous sojourn probabilities, an asynchronous PID-RMPC controller is designed, which uses time-varying mode estimation probabilities to compensate for the mode mismatch caused by attacks, and the mean square stability conditions of the closed-loop system are rigorously derived. Simulation experiments show that the proposed RAETP can increase the effective data transmission rate under attacks compared with the static event-triggered (SETP) protocol, and the PID-RMPC strategy has achieved rapid convergence and robust stability in two simulation examples, verifying the engineering applicability of the theoretical method.

Nowadays, transfer learning (TL) is widely used in fault diagnosis of machinery, which greatly broadens its application in scenarios with variable operating conditions. However, existing TL-based fault diagnosis methods usually emphasize on the research of domain adaptation (DA) mechanisms, and neglect the impact of the expressiveness of the classifier on DA. To overcome this limitation of existing DA-based diagnosis methods, the dynamic softmax with angular margin penalty is designed to dynamically adjust the expressiveness of the embeddings learned by the encoder network. In this way, the diagnosis network can learn more representative features, which improves the robustness of the network on the target data. Furthermore, a trend block is designed to learn trend features in the vibration signal, so that the fault features learned by the feature extractor are more abundant. Comprehensive experiments on real and public datasets show that our approach outperforms other well-established cross-domain fault diagnosis algorithms.

In this article, we address the problem of protocol-based sliding mode control for switched systems with multizone probabilistic time-varying delays. To effectively manage the dynamic behavior of stochastic switching systems, a novel switching rule that incorporates both sojourn probability information and sojourn time is proposed. By exploiting the random nature of time-varying transmission delays, a novel multizone probabilistic event-triggered protocol is developed. Unlike the common sliding model control law, by utilizing the coordinate transformation technique, a protocol-based sliding mode control law is implemented to realize the reachability of predetermined sliding domain. Finally, simulations involving a numerical example and an operational amplifier model are provided to validate the feasibility and efficacy of the proposed methodology.

This paper addresses the problem of vehicle platoon control for third-order nonlinear cyber physical vehicle systems (CPVSs) within finite-time under denial-of-service (DoS) attacks. Unlike existing approaches that assume known systematic matrix of the leader vehicle, this study proposes a data-driven learning algorithm to learn unknown systematic matrix of the leader vehicle. Additionally, a finite-time distributed observer is introduced, thereby enabling follower vehicles to achieve finite-time state observation of the leader vehicle under DoS attacks. Moreover, a novel low-pass filter chain is designed to construct a new variable with high-order derivatives. Utilizing the new variable, a finite-time resilient decentralized controller is formulated, incorporating fuzzy adaptive methods and backstepping techniques to achieve finite-time vehicle platoon control under DoS attacks. Finally, simulation experiments validate the effectiveness of the proposed method.

In the case of label space alignment, the existing domain adaptation (DA)-based fault diagnosis approaches have achieved high accuracy. In real industrial scenarios, however, the label space of the target domain is usually a subset of the label space of the source domain, called partial DA (PDA). The main challenge of PDA lies in how to separate common samples from private samples. In existing works, different weights are usually assigned to different samples based on the prediction score of the classifier, but the negative transfer caused by the data distribution alignment of private and common samples is ignored. To address this problem, class-consistency matching is proposed in this article, which uses label consensus score to identify classes in target clusters to discover common and private samples. In addition, parameter-free cosine attention wavelet blocks (PCAWBs) are designed to learn the complementary spatial-domain and frequency-domain features to enrich the domain-invariant features extracted by the shared encoder. Experiments on the real motor system demonstrate that the proposed method significantly outperforms state-of-the-art PDA fault diagnosis approaches.

This study focuses on TSSDC for Takagi-Sugeno (T-S) fuzzy reaction-diffusion neural networks (NNs) under random sampling and network-induced delays. Fuzzy reaction-diffusion NNs extend traditional NNs by incorporating spatial dynamics through reaction-diffusion processes, offering improved modeling capabilities for complex systems. However, the combination of reaction-diffusion terms and fuzzy modeling increases the complexity of dynamic analysis, particularly in synchronization control. To address these challenges, a novel random TSSDC (RTSSDC) framework is developed. The proposed approach integrates random sampling across both temporal and spatial dimensions with an innovative random event-triggered communication scheme to increase resource utilization efficiency and accommodate real-world network conditions. A unified closed-loop model is established by introducing a packet loss scheduling strategy to handle data disorder caused by significant transmission delays. The framework incorporates switching gains to provide additional flexibility and robustness. Ultimately, numerical simulations are conducted to validate the superior synchronization performance and efficient resource utilization under random sampling and network-induced delays.

Modern automobiles consist of several electronic control units (ECUs) that communicate with each other via the control area network (CAN) protocol. However, the CAN bus is susceptible to the risks associated with various attacks caused by the lack of encryption and certification mechanisms. To eliminate potential safety risks in vehicles, this paper proposes an anomaly detection system based on convolutional neural network (CNN) and transformer. Additionally, the ant-lion optimization (ALO) algorithm was introduced to adaptively adjust the receptive field size, thereby better capturing long-term dependencies in the input sequence data. We conducted tests on the car hacking dataset and evaluated the performance of multiple anomaly detection models on four metrics. The experiment shows that the method proposed in this article is efficient in detecting network attacks.

This paper is devoted to the sliding mode control issue of switching singularly perturbed systems in the presence of dynamic-memory event-triggered protocol. A novel nonhomogeneous sojourn probability is introduced with the hope of better characterizing the switching behavior of the corresponding system mode, in which the variation of sojourn probabilities is adjusted by a deterministic switching signal. Additionally, aiming at relieving the communication burden and improving improve the system performance, a novel dynamic event-triggered protocol with the merits of utilizing a series of historically launched packets and the singularly perturbed parameter is constructed. Subsequently, a singularly-perturbed-parameter-based sliding mode controller is designed for ensuring the mean-square exponential stability of the switching singularly perturbed systems and the reachability of the specified sliding surface. Finally, two simulation examples are provided to verify the efficiency of the theoretical findings.Note to Practitioners—Sliding mode control has gained broad attention for its cost-saving and reliability. In some practical networked control systems, due to the inner property, they will bring a great burden of computation and data transmission. In this paper, we give a novel dynamic event-triggered protocol with the merits of utilizing a series of historically launched packets and the singularly perturbed parameter. A novel nonhomogeneous sojourn probability is introduced with the hope of better characterizing the switching behavior of the corresponding system mode, in which the variation of sojourn probabilities is adjusted by a deterministic switching signal. A singularly-perturbed-parameter-based sliding mode controller is provided to make the networked control systems keep stable. The results provide a reference for the mean-square exponential stability of the switching singularly perturbed systems and the reachability of the specified sliding surface under sliding mode control.

This article addresses an adaptive neural network (NN) sliding-mode control (SMC) strategy for fuzzy singularly perturbed systems against unrestricted deception attacks and stochastic communication protocol (SCP). Instead of relying on the traditional transition probability, a sojourn-probability-based SCP is efficiently established to characterize the stochastic nature more precisely. In response to unrestricted deception attacks, an NN-based technique is deployed to estimate and counteract their detrimental impacts on system performance. Moreover, the design of the sliding-mode controller integrates the singular perturbation parameter and fuzzy rules, addressing the challenge of imperfect premise matching. The proposed controller guarantees exponential ultimate boundedness in the mean square sense and ensures the reachability of the specified sliding surface for the closed-loop system. Finally, the efficacy of the proposed theoretical framework is validated through two illustrative examples, confirming its practical applicability and robustness.

This article focuses on addressing the asynchronous filtering problem in T-S fuzzy sampled-data systems under the presence of censored measurements and non-uniform sampling. In contrast to existing approaches that rely on Markov processes to govern nonuniform sampling, a sojourn probability strategy is adopted to capture the random behavior of sampling periods. This strategy provides easily measurable information, surpassing the complexities associated with obtaining transition probabilities. Moreover, the variations in nonhomogeneous sojourn probability are controlled by a deterministic switching signal, enabling wider applicability compared to existing methods. The fading degree of transmitted data are assessed through a censoring strategy, and the measurement is modeled using a Tobit model. Considering the presence of nonuniform sampling periods and asynchronous premise variables, a general asynchronous fuzzy filtering method is carried out, and sufficient conditions are derived to ensure the mean-square stability of the resulting system. Finally, the developed methodology is validated through a numerical example, showcasing its applicability and effectiveness.

As an important component of the rotating machinery, rolling bearings usually work under the condition of variable speed and load, and vibration signals in the same health state are significantly different due to the change in operating conditions. To address the problem that the existing deep learning (DL) methods have fixed nonlinear transformations for all input signals in cross-domain fault diagnosis, we propose a new activation function, i.e., parameter-free adaptively rectified linear units (PfAReLU). The proposed activation function performs adaptive nonlinear transformations according to the input data and can better capture the fault features of vibration signals in the same fault state under different operating conditions. Furthermore, the number of PfAReLU parameters is zero, so that the risk of network overfitting is reduced. At the same time, deep parameter-free reconstruction-classification networks with PfAReLU (DPRCN-PfAReLU) are also constructed for cross-domain fault diagnosis. Specifically, DPRCN-PfAReLU consists of a shared encoder, a target domain decoder, and a source domain classifier. The shared encoder adds a parameter-free attention module at the output to enhance the weight of domain-invariant features without increasing network parameters. The shared encoded representation of source domain and target domain is learned by target domain decoder and source domain classifier. Compared with other methods under nine different operating conditions via real experiment studies, the proposed method shows superiority for cross-domain fault diagnosis.

This study is concerned with protocol-based asynchronous filtering for interval type-2 (IT2) fuzzy systems subject to time-varying saturation functions. Two mutually independent Markov processes are proposed to characterize the random manners of intermittently failure and transmission sequence of sensor nodes, and a new joint Markov process is formulated by adopting the merging technique. Aiming at curbing the data collision and improving network utilization in the restricted network, an ETRP is implemented to govern whether to orchestrate the packets and which one to be launched simultaneously. A novel asynchronous filter is formulated under the constraint of saturation with the hope to improve filtering performance. This construction involves the dynamic adaptation of the saturation level in tandem with the estimation error. Additionally, the mismatched modes between the newly joined Markov process and filter are characterized by a hidden Markov model. Eventually, two examples are applied to verify the availability of the theoretical results.

In recent years, significant achievements have been made on fault diagnosis methods based on deep learning. However, in practical applications, it is often difficult to obtain a sufficient number of labeled samples to meet the model's learning requirements. In order to solve this problem, a multi-dimensional global attention siamese network (MGASN) is proposed to achieve the few-shot fault diagnosis. First, the multidimensional global attention (MGA) is introduced to fully integrate and extract key information from vibration signals in spatial and channel dimensions. In this way, the model can more accurately capture fault features. Second, a siamese network is constructed based on MGA to implement contrastive learning. Through this approach, the model jointly learns the feature mappings of fault samples with a limited number of labeled data. This enables MGASN to have high learning ability even with fewer samples. Experimental results show that MGASN based on MGA has good fault diagnosis and classification performance in few-shot situations. This provides an effective solution for fault detection and diagnosis in practical industrial applications.

This article addresses the dynamic positioning control problem of a nonlinear unmanned marine vehicle (UMV) system subject to network communication constraints and deny-of-service (DoS) attack, where the dynamics of UMV are described by a Takagi-Sugeno (T-S) fuzzy system (TSFS). In order to save limited communication resource, a new intelligent event-triggering mechanism is proposed, in which the event triggering threshold is optimized by a Q -learning algorithm. Then, a switched system approach is proposed to deal with the aperiodic DoS attack occurring in the communication channels. With a proper piecewise Lyapunov function, some sufficient conditions for global exponential stability (GES) of the closed-loop nonlinear UMV system are derived, and the corresponding observer and controller gains are designed via solving a set of matrix inequalities. A benchmark nonlinear UMV system is adopted as an example in simulation, and the simulation results validate the effectiveness of the proposed control method.

This paper is concerned with the intelligent event-triggering-based positioning control of networked unmanned marine vehicle (UMV) systems with hybrid attacks, where the UMV and control station is connected by a communication network and the DoS attack and Deception attack are studied. Firstly, a stochastic switched Takagi-Sugeno (T-S) fuzzy system model is proposed for the networked nonlinear UMV systems subject to aperiodic DoS attack and random Deception attack. Then, a novel asynchronous advantage actor-critic (A3C) learning-based event-triggering approach is introduced to alleviate the communication load. By using the Lyapunov stability theory and switched system analysis method, the mean-square exponential stability condition of the closed-loop system and the design method of observer-based controller are devised. Finally, an example of a networked UMV system is given to verify the effectiveness of the proposed resilient control strategy.

Currently, numerical optimization methods are used to solve distributed optimal power allocation (OPA) problems for islanded microgrid (MG) systems. Most of them are developed based on rigorous mathematical derivation. However, the complexity of such optimization algorithms inevitably creates a gap between theoretical analysis and real-time implementation. In order to bridge such a gap, in this article we provide a new distributed learning-based framework to solve the real-time OPA problem. Specifically, inspired by the human-thinking scheme, distributed deep neural networks (DNNs) together with a dynamic average consensus algorithm are first employed to obtain an approximate OPA solution in a distributed manner. Then a distributed balance generation and demand algorithm is designed to fine-tune it to obtain the final optimal feasible solution. In addition, it is theoretically proved that the proposed DNN can well approximate one existing OPA algorithm (Guo et al. 2018), where quantitative numbers of at most how many hidden layers and neurons are provided. Several experimental case studies show that our proposed distributed learning framework can achieve similar optimal results to those obtained by using typical existing distributed numerical optimization methods while it is superior in terms of simplicity and real-time capability.

In order to ensure that the power system frequency and tie-line power remain at the nominal value when the load fluctuates, while reducing the release number of decentralized sensor, this work presents a novel adaptive event-triggered scheme for the load frequency regulation via designing the decentralized dynamic output feedback controller (DOFC), where the communication delay issue is also considered due to communication constraints. Distinct from the existing ones, the proposed adaptive event-triggered strategy automatically tunes the threshold according to the local extremum of the system output signal, which can significantly reduce the number of unnecessary signal transmissions to ensure system performance. First, the proposed adaptive event-triggered transmission scheme is integrated with the decentralized DOFC and communication delays under the framework of a linear time-delay system. Then, the asymptotic stability of the closed-loop power system is analyzed through the Lyapunov stability theory and a procedure is given for the design of decentralized dynamic output load frequency controllers by solving some linear matrix inequalities (LMIs). Finally, a three-area power system is used to verify the effectiveness and usefulness of the proposed results.

This article presents a novel dynamic event-triggered scheme for the load frequency regulation with periodic denial-of-service (DoS) attacks and deception attacks via decentralized output-based control algorithm. Compared with the existing event-triggered strategy, the proposed one automatically changes the parameters of the triggered condition by detecting the frequency trend of the DoS attack to change the release frequency, which can ensure the stability of the power system while increasing the probability of effective transmission subject to DoS attack and thus, reducing network bandwidth usage. First, the proposed dynamic event-triggered strategy combined with the decentralized output-based controller is presented in a unified framework to deal with deception attacks and DoS attacks in the multiarea power system. Then, we utilize the Lyapunov stability theory to analyze the exponential stability in the mean-square sense and the robustness of the power system. By solving a set of linear matrix inequalities (LMIs), a procedure is given for the design of output-based load frequency controllers. Finally, a three-area power system is exploited as a simulation to verify the effectiveness of the proposed results.

As large-scale power systems are more and more closely integrated with remote transmission technologies, they are also affected by malicious factors in the cyber and physical layers when bringing convenience. In this article, we propose a novel adaptive event-triggered strategy and apply to the multi-area power system to deal with the load frequency control (LFC) problem with network-induced delay and stochastic sensor faults based on the discrete-time sliding mode control (DSMC) technique. Compared with existing event-triggered strategies, the proposed event-triggered strategy dynamically adjusts the threshold according to system state fluctuations, which can improve the system's tolerance for sensor faults and reduce the number of transmitted packets. Firstly, a dynamic LFC model combining network-induced delay, sensor faults, adaptive event-triggered strategy and DSMC is proposed by using the analysis method of time-delay system. Then we devise an appropriate discrete-time sliding surface for each subsystem in the networked power systems. The Lyapunov stability theory is used to analyze the asymptotic stability and robustness of each subsystem, and the decentralized controller design method is derived. Finally, some simulation examples are introduced to confirm the effectiveness of the proposed adaptive event-triggered DSMC approach.

This article is concerned with the co-design of fault detection and consensus control protocol for a class of multi-agent systems (MASs) subject to Denial-of-Service attack, where the attack behavior is hidden to the defender as the adversary may launch the attack with different durations but the defender may not know the real situation at each time instant. Due to the complicated attack behavior, a hidden semi-Markov process is introduced where only the observed attack modes emitted by the inaccessible ones are available. The probability density functions of sojourn time and the semi-Markov kernel are adopted to help analyze the combined fault detection and consensus control system. Sufficient conditions on the σ-error mean square stability of MASs with mixed H∞/H-performance are established by using a set of Lyapunov functions that depend on the hidden and the observed attack modes. Moreover, the gain matrices of controller and detector are obtained by solving an optimization problem with some matrix inequality constraints. Finally, the simulation of autonomous unmanned underwater vehicles is used to show the effectiveness of the proposed results.

The adversarial attack methods based on gradient information can adequately find the perturbations, that is, the combinations of rewired links, thereby reducing the effectiveness of the deep learning model-based graph embedding algorithms, but it is also easy to fall into a local optimum. Therefore, this article proposes a momentum gradient attack (MGA) against the graph convolutional network (GCN) model, which can achieve more aggressive attacks with fewer rewiring links. Compared with directly updating the original network using gradient information, integrating the momentum term into the iterative process can stabilize the updating direction, which makes the model jump out of poor local optimum and enhances the method with stronger transferability. Experiments on node classification and community detection methods based on three well-known network embedding algorithms show that MGA has a better attack effect and transferability.

Predicting the potential relations between nodes in networks, known as link prediction, has long been a challenge in network science. However, most studies just focused on link prediction of static network, while real-world networks always evolve over time with the occurrence and vanishing of nodes and links. Dynamic network link prediction (DNLP) thus has been attracting more and more attention since it can better capture the evolution nature of networks, but still most algorithms fail to achieve satisfied prediction accuracy. Motivated by the excellent performance of long short-term memory (LSTM) in processing time series, in this article, we propose a novel encoder-LSTM-decoder (E-LSTM-D) deep learning model to predict dynamic links end to end. It could handle long-term prediction problems, and suits the networks of different scales with fine-tuned structure. To the best of our knowledge, it is the first time that LSTM, together with an encoder-decoder architecture, is applied to link prediction in dynamic networks. This new model is able to automatically learn structural and temporal features in a unified framework, which can predict the links that never appear in the network before. The extensive experiments show that our E-LSTM-D model significantly outperforms newly proposed DNLP methods and obtain the state-of-the-art results.

This article proposes a targeting posture control approach with dynamic obstacle avoidance of differential-drive wheeled mobile robot (WMR) systems in the presence of unknown skidding, slipping, input disturbances, model uncertainties, and torque saturation. First, a nonlinear model predictive control (NMPC) scheme is presented to generate a feasible trajectory from a starting posture to a targeting posture where dynamic obstacles in the environment and physical constraints of the robots are considered. Second, a robust virtual control law at the kinematic level is introduced for the robots to follow the trajectory. Third, taking the consideration of the unknown skidding, slipping, input disturbances, and model uncertainties in the dynamic model being lumped as a total disturbance, which is estimated by the linear extended state observer (LESO), a disturbance compensation-based saturation controller is designed to make the real velocity of the robot converge to the virtual velocity command. Finally, the effectiveness of the proposed control strategy is verified by simulation results.

This paper investigates the leader-follower robust H∞consensus of heterogeneous multiagent systems with denial of service attack, where different attack intensities are considered. A switched system model is introduced to model such an attack phenomenon. Then, sufficient conditions to guarantee the solvability of the robust output consensus problem are obtained, and the quantitative relationship between the consensus performance and attack parameter is established. It is shown that the consensus protocol design problem can be transformed into two static output feedback (SOF) control problems. It is also shown that the SOF controller gains can be determined by solving some linear matrix inequalities without the knowledge of the probability information of each attack. Finally, the effectiveness of the control protocol is demonstrated by a simulation study.

This article addresses the distributed secure platoon control of connected vehicles with denial-of-service (DoS) attack phenomena, which may occur at some sampling time instant. First, a switched time-delay system model is introduced, which captures the time-varying sampling and the DoS attack phenomena simultaneously. Then, sufficient conditions are obtained based on the Lyapunov stability theory, the Jensen’s Inequality method, and the topology matrix decoupling technique, such that the vehicle platoon system under consideration achieves an exponential tracking performance. In this article, the presented system design conditions establish several quantitative relationships between attack parameters and system performance. Moreover, the critical values of attack frequency (AF) and the sampling interval (SI) are also derived, respectively. Finally, both of the simulation and experiment studies on a network of four vehicles are introduced to validate the design.

In this paper, the problem of asynchronous output feedback control is investigated for a class of Takagi-Sugeno fuzzy switched systems subject to intermittent measurements. The Bernoulli process is employed to model the phenomenon of stochastic intermittent measurements. Based on the hidden Markov model and output measurements, an asynchronous controller is designed. Then, sufficient conditions for the existence of an asynchronous controller are proposed, which ensure the stochastic stability of the closed-loop system with desired extended dissipative performance. Finally, an example is presented to illustrate the effectiveness and advantages of the proposed new design techniques.

This paper is concerned with the problem of asynchronous and reliable filter design with performance constraint for nonlinear Markovian jump systems which are modeled as a kind of Takagi-Sugeno fuzzy switched systems. The nonstationary Markov chain is adopted to represent the asynchronous situation between the designed filter and the considered system. By using the mode-dependent Lyapunov function approach and the relaxation matrix technique, a sufficient condition is proposed to ensure the filtering error system, which is a dual randomly switched system, is stochastically stable and satisfies a given l2-l∞performance index simultaneously. Two different approaches are developed to construct the asynchronous and reliable filter. Owing to the Finsler's lemma, the second approach has fewer decision variables and less conservatism than the first one. Finally, two examples are provided to show the correctness and effectiveness of the proposed methods.

This paper investigates the dissipative filtering problem for a class of discrete-time switched fuzzy systems with missing measurements. The fuzzy plant under consideration incorporates characteristics of Takagi-Sugeno fuzzy systems and switched systems simultaneously. The occurrence of missing measurements is described by a stochastic variable that satisfies the Bernoulli binary distribution, which characterizes the effect of data loss in information transmission between the plant and the filter. Utilizing the Lyapunov function technique, sufficient conditions are developed to ensure that the resultant filtering error system is exponentially stable and strictly dissipative. Two simulation examples are presented to illustrate the validity of the proposed method.

The problem of asynchronous and resilient filtering for discrete-time Markov jump neural networks subject to extended dissipativity is investigated in this paper. The modes of the designed resilient filter are assumed to run asynchronously with the modes of original Markov jump neural networks, which accord well with practical applications and are described through a hidden Markov model. Due to the fluctuation of the filter parameters, a resilient filter taking into account parameter uncertainty is adopted. Being different from the norm-bound type of uncertainty which has been studied in a considerable number of the existing literatures, the interval type of uncertainty is introduced so as to describe uncertain phenomenon more accurately. By means of convex optimal method, the gains of filter are derived to guarantee the stochastic stability and extended dissipativity of the filtering error system under the wave of the filter parameters. Considering the limited computing power of MATLAB solver, a relatively simple simulation is exploited to verify the effectiveness and merits of the theoretical findings where the relationships among optimal performance index, uncertain parameter σ , and asynchronous rate are revealed.

In this paper, the robust output consensus problem for a class of heterogeneous linear multiagent systems (MASs) in presence of aperiodic sampling and random deny-of-service (DoS) attack is investigated. A novel distributed output-feedback control strategy is proposed so that the controlled MAS achieves the objective of output consensus in spite of aperiodic sampling and DoS attack. By assuming that the sampling process is nonuniform and the consecutive attack duration is upper bounded, the closed-loop control system is first described as a discrete-time switched stochastic delay system. Some sufficient conditions are then obtained for the solvability of the secure consensus problem. Furthermore, a constructive design procedure for the proposed controller is then presented. Finally, a simulation example is introduced to illustrate the effectiveness of controller design.

A new globally exponentially synchronization criterion for complex dynamical networks is proposed in this paper taking account of discrete time communications units and time delay is considered, in which globally exponential convergence is achieved. By introducing larger decision matrices to gain time-delay synchronization criterion, it not only inherits the benefits of full utilization of available information, but also has less conservatism. At the same time, except for original system parameters, no more new decision variables are increased. A time-dependent Lyapunov functional approach is proposed to prove the effectiveness of the criterion. Some simulation results hold the feasibility of the theory.

The distributed filtering problem is addressed in this paper for the discrete-time Takagi–Sugeno (T–S) fuzzy systems with incomplete measurements. The system under consideration includes various network-induced uncertainties, e.g., sensor saturation, quantization error, communication delay, and packet dropouts. Specifically, all these uncertainties are assumed to occur in a stochastic way. In addition, the measurement scheduling issue is also addressed such that only a portion of measurements are broadcasting due to the communication constraints. The main focus is on the design of distributed filters based on the information received locally and from the neighborhood such that the desired estimation performance is guaranteed in terms of the decay rate and disturbance attenuation level. Based on the Lyapunov stability theory, the existence condition for such filters is first proposed and the filter gain parameters are then determined by solving an optimization problem. A simulation example is finally presented to illustrate the effectiveness of the new filtering techniques.

The containment control problem for generally linear multiagent systems with aperiodic sampling intervals and measurement size reduction is considered in this paper. Under the assumption that the sampling interval changes from a finite set, an improved protocol is proposed, such that a larger sampling interval can be obtained to achieve containment. By using the properties of Laplacian matrix and the newly developed protocol, the containment control problem is transformed into the stability problem of a discrete-time switched linear system. A sufficient condition is obtained that ensures all the followers converge to the convex hull formed by the state of leaders, and such a sufficient condition is presented in terms of linear matrix inequalities, which are independent of the node of network. To further reduce the communication among agents, a switching-type measurement size reduction scheme is introduced. An optimization problem is proposed for the corresponding controller design. Finally, two simulation studies are conducted to show the effectiveness and advantage of the proposed control algorithms.

This paper is concerned with the asynchronous state estimation for a class of discrete-time switched complex networks with communication constraints. An asynchronous estimator is designed to overcome the difficulty that each node cannot access to the topology/coupling information. Also, the event-based communication, signal quantization, and the random packet dropout problems are studied due to the limited communication resource. With the help of switched system theory and by resorting to some stochastic system analysis method, a sufficient condition is proposed to guarantee the exponential stability of estimation error system in the mean-square sense and a prescribed performance level is also ensured. The characterization of the desired estimator gains is derived in terms of the solution to a convex optimization problem. Finally, the effectiveness of the proposed design approach is demonstrated by a simulation example.

This paper is concerned with the energy-efficient distributed filtering in sensor networks, and a unified switched system approach is proposed to achieve this goal. For the system under study, the measurement is first sampled under nonuniform sampling periods, then the local measurement elements are selected and quantized for transmission. Then, the transmission rate is further reduced to save constrained power in sensors. Based on the switched system approach, a unified model is presented to capture the nonuniform sampling, the measurement size reduction, the transmission rate reduction, the signal quantization, and the measurement missing phenomena. Sufficient conditions are obtained such that the filtering error system is exponentially stable in the mean-square sense with a prescribed H∞ performance level. Both simulation and experiment studies are given to show the effectiveness of the proposed new design technique.

This paper investigates the problem of sensor-network-based distributed control for large-scale networked control systems, in which the communication constraint and topology switching problems are addressed. In the considered system, a discrete-time interconnected process is controlled by a network of sensors, controllers, and actuators that collect information about the plant, and apply control actions to manage the plant dynamics. The motivation for this paper is that the communication between the plant network and the controller network can be exploited for the system-wide purpose. To deal with the communication constraint problem, strategies such as the event-based communication and logarithmic quantization are applied. Furthermore, in a networked environment, the real-time information of the topology switching is not always available at the controller network side, hence a bunch of synchronous/asynchronous controllers are designed such that the closed-loop system is exponentially stable and achieves a prescribed H∞disturbance attenuation level. Finally, an illustrative example on a benchmark continuous stirred-tank reactor system is presented to demonstrate the effectiveness of the proposed new control technique.

This paper is concerned with the state estimation problem for a class of nonlinear cyber-physical systems (CPSs) where the nonlinear dynamical physical process is approximated by a Takagi-Sugeno fuzzy model. The physical plant is measured by a set of wireless sensors and the sensors communicate with the remote estimator via a communication channel. In the considered CPS, the randomly occurring sensor saturation, signal quantization, packet dropouts as well as the medium access constraint are studied in a unified framework. We develop a sufficient condition such that the filtering error system is asymptotically stable in the mean-square sense and also with a prescribed H∞performance level. The filter gain parameters are determined by solving a convex optimization problem. Finally, the simulation study on the networked truck-trailer system is presented to show the effectiveness of the proposed estimator design.

This paper is concerned with the leader-follower consensus of multiagent systems with wireless communications with the main objective of reducing the power consumption. First, by assuming that the sampling period jumps from one to another only from a given set, a new stochastic sampling approach is introduced to reduce the sampling frequency of each agent. Then, only 1-D of the sampled data is selected, and transmitted to its neighboring agents. Finally, each agent is scheduled to communicate with others intermittently. A unified Markovian system model is proposed to capture the above stochastic sampling, measurement selection scheme and intermittent transmission process, and such a novel protocol can significantly reduce the power consumption. Based on the Lyapunov stability theory and the Markovian jump system approach, the distributed consensus-based controller gain is obtained by solving an optimization problem. The advantage of the proposed consensus protocol is verified by two simulation examples. The simulation results explicitly show our result is more energy-efficient than that of existing one.

The outlier detection problem for dynamic systems is formulated as a matrix decomposition problem with low rank and sparse matrices, and further recast as a semidefinite programming problem. A fast algorithm is presented to solve the resulting problem while keeping the solution matrix structure and it can greatly reduce the computational cost over the standard interior-point method. The computational burden is further reduced by proper construction of subsets of the raw data without violating low-rank property of the involved matrix. The proposed method can make exact detection of outliers in case of no or little noise in output observations. In case of significant noise, a novel approach based on under-sampling with averaging is developed to denoise while retaining the saliency of outliers, and so-filtered data enables successful outlier detection with the proposed method while the existing filtering methods fail. Use of recovered "clean" data from the proposed method can give much better parameter estimation compared with that based on the raw data.

This paper is concerned with the nonfragile distributed H∞filtering problem for a class of discrete-time Takagi-Sugeno (T-S) systems in sensor networks. Additive filter gain uncertainties that reflect imprecision in filter implementation are considered. Based on the robust control approach, sufficient conditions are obtained to ensure that the filtering error system is asymptotically stable with a prescribed H∞performance level and the eigenvalues of the filtering error system in a given circular region. The filter parameters are determined by solving a set of linear matrix inequalities. A simulation study on the nonlinear tunnel diode circuit system is presented to show the effectiveness of the proposed design method.

This paper is concerned with the H∞filtering for networked systems with multiple time-varying transmissions and random packet dropouts. We design a remote H∞filter for these two networked issues such that the filtering error system is exponentially stable and achieves a prescribed H∞performance level. A switched system approach is used to model the multiple time-varying transmission process, and a set of stochastic variables are employed to describe the random packet dropout phenomenon. By the switched system theory and some stochastic analysis methods, a sufficient condition for the existence of the H∞filter is derived in terms of linear matrix inequalities (LMIs). Moreover, the filter gains are determined by solving an optimization problem. Two numerical examples are given to illustrate the effectiveness of the proposed design method.

This note aims to point out one typographical error and one calculation error in the above paper (ibid., vol. 23, no. 5, pp. 827-834, May 2012).

This brief deals with the estimator design problem for discrete-time switched neural networks with time-varying delay. One main problem is the asynchronous-mode switching between the neuron state and the estimator. Our goal is to design a mode-dependent estimator for the switched neural networks under average dwell time switching such that the estimation error system is exponentially stable with a prescribed l2 gain (in the H∞ sense) from the noise signal to the estimation error. A new Lyapunov functional is constructed that may increase during the mismatched switchings. New results on the stability and l2 gain analysis are then obtained. The admissible estimator gains are computed by solving a set of linear matrix inequalities. The relations among the switching law, the maximal delay upper bound, and the optimal H∞ disturbance attenuation level are established. The effectiveness of the proposed design method is finally illustrated by a numerical example.