Chattering free sliding mode control based on recurrent neural network

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

4 Scopus Citations
View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Pages (from-to)1726-1731
Journal / PublicationProceedings of the IEEE International Conference on Systems, Man and Cybernetics
Volume2
Publication statusPublished - 1998

Conference

Title1998 IEEE International Conference on Systems, Man, and Cybernetics
PlaceUnited States
CitySan Diego, CA
Period11 - 14 October 1998

Abstract

This paper develops a new sliding mode neural network control scheme for a class of nonlinear discrete systems, which can eliminate a chattering effect. The control system is designed on the basis of the discrete Lyapunov theory which assure the system reaches sliding mode manifolds. The equivalent control is used directly as the control input after reaching sliding mod manifolds. A part of equivalent control is estimated by an on-line estimator, which is realized by a recurrent neural network (RNN). The real-time recurrent learning (RTRL) algorithm is improved and used to train the RNN. Due to its real-time learning ability, the stability of control system are guaranteed. The proposed control scheme eliminates chattering and provides sliding mode motion on the selected manifolds in the state space. The detailed control procedure is given and numerical examples are used to validate the proposed control scheme.