신경망을 이용한 비선형 시스템의 외란 관측기 설계

Abstract

내부 불확실성과 외부외란을 추정하기 위한 NDO 를 설계하는데 파라미터 튜닝법을 이용하였으며, 각각의 파라미터들을 조정하는데 유용함을 보였다.In this paper, a neural disturbance observer(NDO) is developed and its application to the control of a nonlinear system with the internal and/or external disturbances is presented. To construct the NDO, a parameter tuning method is proposed and shown to be useful in adjusting the parameters of the NDO. The tuning method employes the disturbance observation error to guarantee that the NDO monitors unknown disturbances. Each of the nodes of the hidden layer in the NDO network is a radial basis function(RBF). In addition, the relationships between the suggested NDO-based control and the conventional adaptive controls reported in the previous literatures are discussed. And it is shown in a rigorous manner that the disturbance observation error converges to a region of which size can be kept arbitrarily small. Finally, an example and some computer simulation results are presented to illustrate the effectiveness and the applicability of the NDO.