Novel adaptive neural networks control with event-triggered for uncertain nonlinear system

In this paper, the issue of developing an event-triggered adaptive tracking controller for a class of uncertain nonlinear system is investigated. The radial basis function neural networks (RBFNN) is employed to approximate the uncertain parts, where the time-varying approximation errors are combined. However, it causes the dimensionality of RBFNN's weight vector larger, which means more network resources are needed. It is a tough task to develop an adaptive tracking controller for nonlinear systems suffered network resources constraint. To save network resources, an event-triggered scheme is developed. Then, with the aid of adaptive backstepping technique, an event-triggered adaptive tracking control approach is established. With the developed event-triggered adaptive tracking controller, the boundedness of all signals in the closed-loop system can be guaranteed. Moreover, it can achieve the balance of tracking performance and the utilization of network resources. Finally, two simulation examples are given to verify the effectiveness of the proposed control scheme.