Article
Computer Science, Artificial Intelligence
Yuezu Lv, Jialing Zhou, Guanghui Wen, Xinghuo Yu, Tingwen Huang
Summary: This article focuses on the consensus problem of nonlinear multiagent systems under directed graphs and proposes fully distributed adaptive attack-free protocols. The fixed-time observer is introduced to estimate both local state and consensus error, and the adaptive gains are designed to estimate unknown neural network constant weight matrix and upper bound of residual error vector. An extra adaptive gain is introduced to estimate communication connectivity information, leading to fully distributed adaptive attack-free consensus protocol.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Jing Zhang, Shuai Liu, Xianfu Zhang, Jianwei Xia
Summary: This article investigates the observer-based adaptive neural network (NN) event-triggered distributed consensus tracking problem for nonlinear multiagent systems with quantization. The limited communication capacity between agents is considered, and event-trigger mechanism and dynamic uniform quantizers are set up to reduce information transmission. An NN-based state observer is designed for each agent to estimate the unmeasurable states, and a distributed control protocol with estimated information of neighbors is designed to address the coupling effects and ensure distributed consensus tracking without Zeno behavior.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Automation & Control Systems
Fei Gao, Weisheng Chen, Zhiwu Li, Jing Li, Rui Yan
Summary: This paper studies a neural network-based distributed cooperative identification strategy with event-triggered communication for a group of coupled identical nonlinear systems. By developing a distributed cooperative learning law in this context, it is proven that the estimated weights of all radial basis function NNs converge to a small neighborhood of their optimal values.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Wei Wang, Yongming Li, Shaocheng Tong
Summary: The study focuses on the event-triggered consensus control problem for nonstrict-feedback nonlinear systems with a dynamic leader. Neural networks are used to approximate unknown dynamics, and an adaptive event-trigger condition and controller are developed. The proposed method successfully achieves bounded leader-following consensus and reduces data communication and frequency of controller updates.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Peijun Wang, Guanghui Wen, Tingwen Huang, Wenwu Yu, Yuezu Lv
Summary: This paper investigates the asymptotical consensus problem for multi-agent systems (MASs) with unknown nonlinear dynamics under directed switching topology using a neural network (NN) adaptive control approach. It designs an observer for each follower to reconstruct the states of the leader, and proposes a discontinuous consensus controller and an NN adaptive law based on the idea of discontinuous control. The paper proves theoretically that asymptotical neuroadaptive consensus can be achieved in the considered MAS if the average dwell time (ADT) is larger than a positive threshold.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Automation & Control Systems
Wei-Wei Che, Lili Zhang, Chao Deng, Zheng-Guang Wu
Summary: The neural network-based adaptive backstepping method is an effective tool for solving the cooperative tracking problem in nonlinear multiagent systems (MASs). However, it cannot be directly applied to cases without continuous communication due to discontinuous signals caused by the absence of continuous communication. To address this issue, a hierarchical design scheme involving distributed cooperative estimators and neural network-based decentralized tracking controllers is proposed. The proposed method uses dynamic event-triggered mechanism to estimate unknown parameters and design a backstepping-based decentralized neural network tracking controller, achieving asymptotic tracking and bounded signals in the closed-loop systems.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Engineering, Multidisciplinary
Gang Wang
Summary: This paper addresses the challenge of designing a consensus algorithm under switching topologies by proposing a novel higher-order filter and distributed consensus controller. It can handle consensus problems of heterogeneous nonlinear multiagent systems with minimal local feedback requirement.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2022)
Article
Computer Science, Artificial Intelligence
Bin Hu, Xinghuo Yu, Zhi-Hong Guan, Jurgen Kurths, Guanrong Chen
Summary: This study introduces a gradient-descent adaptation law for neural adaptive tracking control in hybrid dynamical systems. The proposed control scheme ensures a stable closed-loop error system and demonstrates uniformly exponential stability of the tracking error.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Zhongguo Li, Bo Liu, Zhengtao Ding
Summary: This article proposes a distributed algorithm for training neural networks with private data sets, utilizing constant learning rates to enhance tracking ability and establishing convergence by exploring error dynamics of connected agents. Simulation results validate the effectiveness of the algorithm.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Acoustics
Hossein Chehardoli
Summary: This paper studies the leader-following adaptive optimal neural network consensus of second-order multi-agent systems with nonlinear uncertainties and unknown time delay. The controller consists of a linear part based on state feedback control and a nonlinear part based on neural network to compensate for the uncertainties and disturbances. Appropriate adaptive rules are presented to estimate the neural network gains. The Lyapunov stability criterion is employed to prove the asymptotic stability of the system, ensuring consensus is achieved.
JOURNAL OF VIBRATION AND CONTROL
(2023)
Article
Automation & Control Systems
Ning Wang, Guanghui Wen, Ying Wang, Fan Zhang, Ali Zemouche
Summary: This work addresses the distributed consensus tracking problem for a class of high-order nonlinear multiagent networks over a directed graph. By incorporating a power integrator methodology into the distributed protocol and designing a novel performance function, the proposed design ensures closed-loop stability and allows for preselection of transient-state and steady-state metrics. The consensus tracking error converges to a residual set with adjustable size to desired parameters, while maintaining closed-loop stability and preassigned performances.
IEEE TRANSACTIONS ON CYBERNETICS
(2022)
Article
Engineering, Multidisciplinary
Yilun Shang
Summary: This paper investigates the constrained consensus of a group of continuous-time dynamical agents over state-dependent networks. By utilizing Lyapunov stability theory and robustness analysis, convergence conditions have been obtained and nonlinear control protocols and opinion dynamics models have been proposed, further validating the theoretical results.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2022)
Article
Automation & Control Systems
Deyuan Meng, Jingyao Zhang
Summary: This article introduces a distributed control protocol for cooperative learning in networked multiagent systems, allowing robust tracking of prescribed references regardless of nonlinearities, initial state shifts, and disturbances. A convergence analysis approach is provided by investigating properties of stochastic matrices associated with switching digraphs, ensuring the effectiveness of cooperative learning.
IEEE TRANSACTIONS ON AUTOMATIC CONTROL
(2021)
Article
Engineering, Electrical & Electronic
Jeongju Jee, Girim Kwon, Hyuncheol Park
Summary: Network densification is crucial for future wireless networks to increase capacity over a given area, and user-centric networks are a promising solution. However, hardware impairments such as nonlinear power amplifiers can disrupt network scalability and interfere with user association and cooperative beamforming. This paper proposes a deep learning-based framework for cooperative beamforming in distributed networks with nonlinear power amplifiers to optimize performance.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2023)
Article
Automation & Control Systems
Guoxing Wen, Bin Li
Summary: An optimized leader-follower consensus control is proposed for a class of second-order unknown nonlinear dynamical multiagent system. The control is derived using reinforcement learning, making it simple and effective.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2022)