Aperiodic adaptive control for neural-network-based nonzero-sum differential games: A novel event-triggering strategy. (September 2019)

• Record Type: Journal Article
• Authors: Mu, Chaoxu; Wang, Ke
• Is Part Of: ISA transactions. Volume 92(2019)
• Page Start: 1
• Page End: 13
• Publication Date: 2019-09
• Subjects: Event-triggering -- Nonzero-sum differential game -- Nonlinear dynamics -- Neural network -- Nash equilibrium; Engineering instruments -- Periodicals; Engineering instruments; Periodicals; Electronic journals; 629.805
• DOI: 10.1016/j.isatra.2019.01.025
• Languages: English
• ISSNs: 0019-0578

Abstract

Abstract: Owing to the adoption of aperiodic sampling pattern, the event-triggering control mode has been widely investigated in networked systems to save communication and reduce computation. Recently, there has been some preliminary findings to explore applications of this novel mode and to implement it in neural-network-based nonlinear systems by including an event generator. This motivates our investigation. For the first time, this paper designs triggering rules for neural-network-based nonzero-sum differential games characterized by nonlinear dynamics and quadratic cost functions. The main intention of the event-triggering strategy is to reduce communication between controllers and neural networks, thereby mitigating computational loads of controllers. An adaptive critic algorithm is subsequently applied to learn the required Nash equilibrium on line and meantime an alarm sampling period is proposed to ameliorate the learning accuracy. Furthermore, three simulation cases validate the approximate-optimal control performance and appraise virtues of the proposed event-triggering mode. Highlights: This is the first attempt to study event-triggering nonzero-sum differential games. A triggering threshold is devised to reduce the computational load. An alarm sampling period is proposed to maintain the learning accuracy. The weight convergence and the stability are proved using Lyapunov approach.