Adaptive neural network control for a class of nonlinear discrete system

Abstract

An adaptive neural network control scheme is presented for a class of nonlinear discrete-time systems. The unknown nonlinear plants are represented by an equivalent model composed of a simple linear submodel plus a nonlinear submodel around operating points, and a simple linear controller is designed based on the linearization of the nonlinear system, a compensation term, which is implemented with a two-layer recurrent neural network during every sampling period, is introduced to control nonlinear systems, the network weight adaptation law is derived by using Lyapunov theory. The proposed design scheme guarantees that all the signals in closed-loop system are bounded, and the filtering tracking error converges to a small neighborhood of the origin.