Adaptive Sliding Mode Control of Nonlinear Systems Using Neural Network and Disturbance Estimation Technique

신경망과 외란 추정 기법을 이용한 비선형 시스템의 적응 슬라이딩 모드 제어

This paper proposes a neural network(NN)-based adaptive sliding mode controller for discrete-time nonlinear systems. By using disturbance estimation technique, a sliding mode controller is designed, which forces the sliding variable to be zero. Then, NN compensator with hidden-layer-to-output-layer weight update rule is combined with sliding mode controller in order to reduce the error of the estimates of both disturbances and nonlinear functions. The whole closed loop system rejects disturbances excellently and is proved to be ultimately uniformly bounded(UUB) provided that certain conditions for design parameters are satisfied.