Article
Computer Science, Artificial Intelligence
Ziwei Li, Zongjie Chen, Ting Fang, Hao Shen
Summary: This paper addresses the extended dissipativity-based synchronization problem of Markov jump neural networks with partially known probability information. It introduces a detector from the hidden Markov model and establishes a criterion for neural networks with partially known probability information. The proposed approach is validated through numerical examples.
Article
Computer Science, Artificial Intelligence
Weizhong Chen, Ming-Zhe Dai, Chaoxu Guan, Zhongyang Fei
Summary: This paper addresses the synchronization problem for semi-Markov jump master-slave neural networks with extended dissipativity performance and partly unknown transition rates. Sufficient stability and dissipativity criteria are established, and a state feedback controller is designed to ensure synchronization. A numerical example is provided to verify the results.
Article
Computer Science, Artificial Intelligence
Ramasamy Saravanakumar, M. Syed Ali
Summary: This study examines the extended dissipative problem for Markovian jump generalized neural networks with asynchronous mode-dependent time-varying interval delayed states and proposes reliable criteria to achieve an extended dissipative performance index.
NEURAL PROCESSING LETTERS
(2022)
Article
Engineering, Mechanical
Zhenyu Wu, Zehui Xiao, Xuexi Zhang, Jie Tao
Summary: This article focuses on event-triggered quasi-synchronization in discrete Markov jump neural networks (MJNNs). By introducing a hidden Markov model, the mode mismatches in real-world applications are described. A more general event-triggered protocol is constructed by developing the threshold parameter as a diagonal matrix to achieve a desired balance between synchronization performance and event-triggered transmission. The sufficient condition for event-triggered quasi-synchronization of MJNNs is proposed using Lyapunov techniques, and a tighter error bound is obtained through an iterative algorithm and linear matrix inequality. A numerical example is provided to demonstrate the effectiveness of the control scheme by comparing the conservatism between the proposed approach and the existing one.
NONLINEAR DYNAMICS
(2023)
Article
Automation & Control Systems
Feng Li, Shengyuan Xu, Hao Shen, Zhengqiang Zhang
Summary: This article discusses the extended dissipativity-based control problem for singularly perturbed systems with Markov jump parameters, considering partial information on the Markov chain. A comprehensive hidden Markov model is established to address the partial information issues, leading to a criterion for analyzing the extended stochastic dissipativity of the systems. The theoretical results are validated through an illustrative example and a vehicle active suspension system.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Jie Tao, Zehui Xiao, Zeyu Li, Jun Wu, Renquan Lu, Peng Shi, Xiaofeng Wang
Summary: This article investigates finite-time dissipative state estimation for Markov jump neural networks, introducing a dynamic event-triggered transmission mechanism and an asynchronous state estimator design to ensure effectiveness in a numerical example.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Mathematics, Applied
B. Visakamoorthi, K. Subramanian, P. Muthukumar
Summary: This paper investigates the dissipativity-based asynchronous sampled-data control design for a class of Takagi-Sugeno fuzzy Markovian jump systems along with time delay, gain fluctuations, and actuator failures. The hidden Markov model is introduced to describe the asynchronization phenomenon, and a novel mode-dependent Lyapunov-Krasovskii functional is constructed to achieve stability conditions and extend the maximum sampling period of fuzzy systems. The study aims to design asynchronous non-fragile reliable control with sampled-data information for stochastically stable and dissipative fuzzy systems. Sufficient conditions in the form of linear matrix inequalities are derived, and less conservative results and desired controllers are obtained by solving the inequalities. Numerical examples are provided to demonstrate the effectiveness and superiority of the proposed design technique.
APPLIED MATHEMATICS AND COMPUTATION
(2022)
Article
Automation & Control Systems
Jie Tao, Muxi Xu, Depeng Chen, Zehui Xiao, Hongxia Rao, Yong Xu
Summary: This article investigates the problem of event-triggered resilient filtering for Markov jump systems. The study uses hidden Markov model to characterize asynchronous constraints between the filters and systems, and employs interval type of gain uncertainties for more accurate modeling. By separating the vertices of the uncertain interval, the number of linear matrix inequalities constraints can be significantly reduced, reducing the difficulty and time of calculation. Additionally, an event-triggered scheme is applied to minimize network resource consumption.
IEEE TRANSACTIONS ON CYBERNETICS
(2022)
Article
Engineering, Electrical & Electronic
Ting Wang, Baoyong Zhang, Deming Yuan, Yijun Zhang
Summary: This paper investigates the event-based extended dissipative state estimation problem for memristor-based Markovian neural networks with hybrid time-varying delays and sensor nonlinearity. By employing a Markov jump model and an event-triggered scheme, novel conditions are presented to ensure the stability and performance of the system, along with an existence criterion for the desired estimator. Simulation results demonstrate the effectiveness of the proposed method.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS
(2021)
Article
Computer Science, Artificial Intelligence
Chao Ma, Liziyi Hao, Hang Fu
Summary: This paper investigates the synchronization problem of Takagi-Sugeno fuzzy hidden Markov jump complex dynamical networks, proposing an asynchronous synchronization control strategy and utilizing neural networks for unknown function approximation. Sufficient conditions are established for mean-square synchronization performance with disturbances using Lyapunov method, and asynchronous controller gains are designed based on linear matrix inequalities. An illustrative example is provided to demonstrate the effectiveness of the proposed synchronization techniques.
COMPLEX & INTELLIGENT SYSTEMS
(2022)
Article
Automation & Control Systems
Xiaobin Gao, Feiqi Deng
Summary: This article addresses the dissipativity-based finite-time filtering problem for a class of Markov jump systems using an event-triggered mechanism. It introduces Bernoulli sequences to model uncertainty and nonlinearity, and applies a mode-dependent ETM to alleviate communication pressure. A full-order reliable filter is designed based on stochastic finite-time analysis, with conditions given in terms of LMI to guarantee system stability.
INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL
(2021)
Article
Biochemistry & Molecular Biology
Ioannis A. Tamposis, Dimitra Sarantopoulou, Margarita C. Theodoropoulou, Evangelia A. Stasi, Panagiota Kontou, Konstantinos D. Tsirigos, Pantelis G. Bagos
Summary: Hidden Markov Models (HMMs) are successful in predicting protein features, but in some biological problems more information is needed. The combination of HMMs and neural networks in HNNs can improve prediction performance, with topology predictions outperforming other methods.
COMPUTATIONAL AND STRUCTURAL BIOTECHNOLOGY JOURNAL
(2021)
Article
Automation & Control Systems
Yong Xu, Zheng-Guang Wu, Ya-Jun Pan
Summary: This article investigates the filtering problem of Markovian jump neural networks subject to incomplete measurements and deception attacks, adopting an event-triggered communication strategy to reduce communication frequency. The sufficient condition is derived to ensure stochastic stability and dissipativity of the resulting augmented system despite the presence of deception attacks and incomplete information.
IEEE TRANSACTIONS ON CYBERNETICS
(2021)
Article
Computer Science, Artificial Intelligence
Yufeng Tian, Zhanshan Wang
Summary: This study focuses on extended dissipativity analysis for MJNNs with time-varying delay, by constructing a DIDPT Lyapunov functional and removing unnecessary constraints to obtain more general results. The advantages of the proposed method are illustrated through a numerical example.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Computer Science, Information Systems
Jiaxin Luo, Yong Zhao
Summary: This paper investigates the finite-time exponentially extended dissipativity for uncertain stochastic bilinear Markov jump systems based on the hidden Markov model. It establishes sufficient conditions for the closed-loop system to satisfy the finite-time exponentially extended dissipative performance and proposes an asynchronous and robust resilient controller.
Article
Automation & Control Systems
Xiang Liu, Yuanqing Wu
Summary: This article studies the broad learning system (BLS) of intelligent vehicles in different target environments. The target recognition image data is provided and training and detection are performed using an automated guided vehicle (AGV) mobile platform to capture recognition images from various angles and backgrounds. Data normalization and data enhancement are used to expand the dataset and avoid data generalization. The shared convolution layer is employed to extract feature images, and region proposal network (RPN) prefiltering algorithm is used to filter objects in the candidate box. The system achieves stable target recognition in different environmental conditions with an accuracy of about 95%.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Automation & Control Systems
Yongkang Lu, Shenghuang He, Yanzhou Li, Yuanqing Wu, Wenjian Zhong
Summary: This paper studies a spatial-speed decoupled planning method for real-time trajectory generation in the on-road environment. The method includes optimization-based lateral planning and selection-based longitudinal speed planning. Experimental results demonstrate that the proposed algorithm has good real-time property and practical validity.
IET CONTROL THEORY AND APPLICATIONS
(2023)
Article
Automation & Control Systems
Jiabin Hu, Dan Zhang, Zheng-Guang Wu, Hongyi Li
Summary: A novel second-order sliding mode control scheme based on neural network is proposed to solve the trajectory tracking problem for robotic manipulators with dynamic uncertainty, external disturbance, and input saturation. The control method improves the control accuracy and robustness of the robotic manipulator by designing the model and estimating the unknown uncertainties.
Article
Automation & Control Systems
Yong Xu, Zheng-Guang Wu, Jian Sun
Summary: This article addresses the security-based passivity problem of discrete-time Markov jump systems in the presence of deception attacks. It proposes an asynchronous control method and a resilient asynchronous event-triggered control scheme to overcome network disruption and reduce data transmission frequency. By developing triggering conditions for different jumping modes and deriving a stability criterion, the passivity of the system is ensured.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Engineering, Civil
Yong Xu, Zheng-Guang Wu, Ya-Jun Pan
Summary: This paper investigates the resilient distributed secure output path following control problem of heterogeneous autonomous ground vehicles (AGVs) subject to cyber attacks based on reinforcement learning algorithm. The study considers multiple communication channels launched by different attackers and proposes a predictor-acknowledgement clock algorithm to judge the attacked communication channels. A resilient distributed predictor and a resilient local control protocol are developed for predicting and controlling the path following problem. The optimal control problem is solved using discounted algebraic Riccati equations (AREs) and an off-policy reinforcement learning (RL) algorithm is proposed to learn the solution online.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Automation & Control Systems
Donghui Zhang, Zehua Ye, Dan Zhang, Qun Lu
Summary: In this paper, a new intelligent dynamic METC algorithm is proposed to reduce the amount of transmission data and decrease the communication burden in networked control systems. The proposed algorithm optimizes the memory event-triggered function by applying the A3C-GS learning algorithm. Simulation results show that the proposed algorithm reduces the number of triggers by about 40% compared with traditional event-triggered algorithms.
TRANSACTIONS OF THE INSTITUTE OF MEASUREMENT AND CONTROL
(2023)
Article
Automation & Control Systems
Zheng-Guang Wu, Liqing Wang
Summary: In this article, the l(1)-induced performance of the stochastic switched Boolean control network is investigated. Asynchronous state feedback control is studied to achieve the control objective. Sufficient conditions are obtained for system stabilization and prescribed performance level using matrix algebra and inequalities. Examples are presented to demonstrate the effectiveness of the results.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Computer Science, Artificial Intelligence
Zhitao He, Yongyi Chen, Hui Zhang, Dan Zhang
Summary: Connected and automated vehicles (CAVs) are crucial in transforming human mobility, addressing road congestion and enhancing road safety. However, their reliability heavily relies on the security, accuracy, and stability of sensor readings and network data. To tackle the issue of anomaly detection in intelligent transportation systems (ITS), we propose a Wavelet Kernel Network with Omni-Scale Convolutional (WKN-OC) model that adapts scales optimally and processes high-frequency signals more effectively. The model demonstrates strong generalization performance and achieved 96.78% average accuracy in mixed anomaly experiments and 96.13% accuracy in multi anomaly experiments on the Safe Pilot Model Deployment (SPMD) dataset.
IEEE TRANSACTIONS ON INTELLIGENT VEHICLES
(2023)
Article
Automation & Control Systems
Yongyi Chen, Dan Zhang, Hongjie Ni, Jun Cheng, Hamid Reza Karimi
Summary: In this paper, a new fault diagnosis framework based on a Multi-scale Split Dual Calibration Network with Periodic Information (PI-MSDCN) is proposed to address the problem of fault diagnosis under low signal-to-noise ratio (SNR). The proposed method utilizes a neural network to learn the periodic information of vibration signals and combines it with the raw vibration signal as input data. Experimental results show that the average accuracy of the proposed method is 92.91%, surpassing existing results in literature.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Engineering, Electrical & Electronic
Yanyan Ye, Zhengjie Huang, Liangyin Zhang, Qianqian Cai, Yuanqing Wu
Summary: This paper investigates consensus of networked fractional-order systems over directed graphs and proposes an intermittent sampled position measurement distributed algorithm to reduce operation time and update rates of controllers. It derives necessary and sufficient conditions for consensus using fractional Laplace transform and stability theory and emphasizes the importance of fulfilling certain inequalities to achieve consensus. Simulation examples are provided to verify the theoretical results.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS
(2023)
Article
Automation & Control Systems
Yongyi Chen, Dan Zhang, Kunpeng Zhu, Ruqiang Yan
Summary: In this article, a new activation function called Parameter-free Adaptively Swish (PASwish) is developed to improve the flexibility and generalization ability of deep learning frameworks in industrial scenarios with changing operating conditions. Additionally, deep parameter-free cosine networks with PASwish are proposed to adjust network weights based on domain-specific and domain-invariant features. The proposed method achieves better performance in cross-domain fault diagnosis compared to current studies, with an average accuracy of 95.16% (+/- 1.76%) on 72 transfer tasks.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2023)
Article
Automation & Control Systems
Yong-Sheng Ma, Wei-Wei Che, Chao Deng, Zheng-Guang Wu
Summary: This article investigates the problem of model-free adaptive resilient control (MFARC) for nonlinear cyber-physical systems (CPSs) under aperiodic jamming attacks. The MFARC framework is established and an intermediate variable method is introduced to address the issue of unavailable time-varying parameters. A MFARC scheme is devised to track the desired output and solve a feasibility problem, with controller parameters obtained using linear matrix inequality technique. Additionally, a novel attack compensation mechanism is developed to mitigate the impact of aperiodic jamming attacks.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Computer Science, Artificial Intelligence
Yongyi Chen, Dan Zhang, Ruqiang Yan
Summary: Rolling bearings are important components of rotating machinery and typically operate under variable speed and load conditions. Vibration signals in the same health state exhibit significant differences due to changes in operating conditions. To address fixed non-linear transformations in existing deep learning methods for cross-domain fault diagnosis, a new activation function called parameter-free adaptively rectified linear units (PfAReLU) is proposed. PfAReLU performs adaptive non-linear transformations based on input data and effectively captures fault features of vibration signals under different operating conditions. Furthermore, a deep parameter-free reconstruction-classification network with PfAReLU (DPRCN-PfAReLU) is constructed, which outperforms other methods for cross-domain fault diagnosis in real experiment studies under nine different operating conditions.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Dezhi Yuan, Ting Luo, Dan Zhang, Kunpeng Zhu
Summary: This article proposes a physics-assisted online learning method for tool wear prediction, which combines knowledge from data and physical domain and adjusts the offline basic model with online data. The method has been found to have the lowest mean square error and time complexity, demonstrating good accuracy and generalization.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Automation & Control Systems
Jun Cheng, Shan Liu, Huaicheng Yan, Zheng-Guang Wu, Dan Zhang
Summary: This paper focuses on the sliding mode control of switching singularly perturbed systems in the presence of dynamic-memory event-triggered protocol. By introducing a novel nonhomogeneous sojourn probability and a dynamic event-triggered protocol, a singularly-perturbed-parameter-based sliding mode controller is designed and its efficiency is verified through simulation examples.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2023)