Neural Adaptive Dynamic Surface Asymptotic Tracking Control for a Class of Uncertain Nonlinear System

Abstract

In this paper, by incorporating the neural network into an adaptive dynamic surface control (DSC) framework, a neural adaptive DSC algorithm is developed for a class of uncertain nonlinear system to ensure the asymptotic output tracking. Neural network is used to approximate the unknown nonlinear term in the system such that the requirements for known nonlinear term in control laws design procedure are released. In order to eliminate the boundary layer effects, which are caused by the linear filters at each step in the DSC procedure, the nonlinear filters with the compensation term are designed skillfully. The proposed neural adaptive DSC algorithm not only avoids the inherent problem of “explosion of complexity” in the backstepping procedure, but also has its own advantages: (1) releasing the requirements for known nonlinear term in control laws design procedure; (2) holding the asymptotic output tracking performance. Some simulations are shown to demonstrate the effectiveness and advantages of the proposed controller.