Disturbance estimation combined with new adaptive RBF neural network for uncertain system with disturbance

Abstract

In this work, we propose a new adaptive neural network controller combined with disturbance estimation for a class of nonlinear systems. The approach uses Radial Basis Functions, RBF neural network. An adaptive scheme for the RBF neural network is developed to approximate unknown system functions and to estimate disturbances consisting of both approximation errors and external disturbances. An adaptive law is then applied to update the parameters of controller instead of choosing fixed controller's parameters which are coefficients of Hurwitz polynomial. Thanks to Lyapunov's theory, asymptotic stability is established with the tracking errors converging to a neighborhood of the origin. Finally, an example, coupled tank liquid system, is presented to illustrate the proposed methods.