Title :
Practical stability issues in CMAC neural network control systems
Author :
Chen, Fu Chuang ; Chang, Chih Horng
Author_Institution :
Dept. of Control Eng., Nat. Chiao Tung Univ., Hsinchu, Taiwan
fDate :
29 June-1 July 1994
Abstract :
The CMAC neural network is a practical tool for improving existing nonlinear control systems. Although many researchers report that it has good performance, our results suggest that the CMAC control system can go unstable. The unstable phenomena are quantitatively studied, and some methods for improving the stability are suggested.
Keywords :
cerebellar model arithmetic computers; neurocontrollers; nonlinear control systems; stability; CMAC neural network control systems; cerebellar model articulation controller; nonlinear control systems; stability; unstable phenomena; Control engineering; Control systems; Discrete event simulation; Error correction; Intelligent networks; Neural networks; Proportional control; Quantization; Robot control; Stability;
Conference_Titel :
American Control Conference, 1994
Print_ISBN :
0-7803-1783-1
DOI :
10.1109/ACC.1994.735109
