Neural-based fixed-time composite learning control for multiagent systems with intermittent faults

• Published in: Neurocomputing (Amsterdam) Vol. 599; p. 128135
• Main Authors: Zheng, Xiaohong, Ren, Hongru, Zhou, Qi, Wang, Xinzhong
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 28.09.2024
• Subjects: Composite learning control; Consensus control; Fixed-time control; Intermittent actuator faults; Multiagent systems (MASs); Consensus control; Fixed-time control; Multiagent systems (MASs); Intermittent actuator faults; Composite learning control
• ISSN: 0925-2312; 1872-8286
• DOI: 10.1016/j.neucom.2024.128135

In this paper, a distributed fixed-time composite learning control problem is addressed for nonlinear multiagent systems (MASs) subject to intermittent actuator faults. First, a distributed estimator is constructed for followers that are unable to communicate directly with the leader. Then, instead of using the traditional adaptive neural network (NN) algorithm, a predictor-based composite learning technique is proposed, which incorporates the prediction error into the NN update law to enhance the estimation accuracy of the unknown nonlinearity. Furthermore, an adaptive fault-tolerant control compensation mechanism is developed for intermittent faults that may occur indefinitely and frequently. To guarantee that all signals of the closed-loop system are bounded in fixed time, a nonsingular fixed-time fault-tolerant controller in the form of quadratic function is established. Finally, simulation results confirm the effectiveness of the presented algorithm. •This paper presents a singularity-free fixed-time NN algorithm for nonlinear MASs, and a composite learning algorithm is established to improve the approximation accuracy of nonlinear functions by introducing a prediction error into NN update law.•For followers without access to the leader, a local estimator is utilized to estimate the leader information. Therefore, the present control method avoids the emergence of coupling terms between agents during the controller design.•This paper considers intermittent actuator faults that may occur indefinitely and frequently, posing significant challenges.