Practical stability issues in CMAC neural network control systems

Author

Chen, Fu-Chuang ; Chang, Chih-Homg

Author_Institution

Dept. of Control Eng., Nat. Chiao Tung Univ., Hsinchu, Taiwan

Volume

4

Issue

1

fYear

1996

fDate

1/1/1996 12:00:00 AM

Firstpage

86

Lastpage

91

Abstract

The cerebellar model articulation controller (CMAC) neural network is a practical tool for improving existing nonlinear control systems. A typical simulation study is used to clearly demonstrate that CMAC can effectively reduce tracking error, and also destabilize a control system which is otherwise stable. Then quantitative studies are presented to search for the cause of instability in the CMAC control system. Based on these studies, methods are discussed to improve system stability. Experimental results on controlling a real world system are provided to support the findings in simulations

Keywords

cerebellar model arithmetic computers; discrete time systems; learning (artificial intelligence); neurocontrollers; nonlinear control systems; stability; CMAC neural network; cerebellar model articulation controller; discrete time systems; generalisation; learning rate; neural control; nonlinear control systems; quantisation; stability; tracking error; Control systems; Electrical equipment industry; Intelligent networks; Neural networks; Nonlinear control systems; PD control; Pi control; Proportional control; Stability; Three-term control;

fLanguage

English

Journal_Title

Control Systems Technology, IEEE Transactions on

Publisher

ieee

ISSN

1063-6536

Type

jour

DOI

10.1109/87.481771

Filename

481771