Adaptive fuzzy wavelet neural network control for a class of nonlinear systems using sliding-mode approach

In this paper, an adaptive fuzzy wavelet neural network control (AFWNNC) system composed of a neural controller and a robust compensator is proposed. The neural controller using a fuzzy wavelet neural network (FWNN) is designed to approximate an ideal controller, and the robust compensator is designed to ensure system stable. In many previous published papers, to ensure the stability of the intelligent control system, a switching compensator is designed to dispel the approximation error introduced by the neural controller. However, the switching compensator usually causes chattering phenomena. The proposed robust compensator is designed to eliminate the approximation error without occurring chattering phenomena. Moreover, a proportional-integral-derivative (PID) type adaptation tuning mechanism is derived to speed up the convergence of the tracking error and controller parameters. Finally, the proposed AFWNNC system is applied to a chaotic system and a DC motor. The simulation and experimental results verify the system stabilization, favorable tracking performance and no chattering phenomena can be achieved by the proposed AFWNNC system.