Title :
Neural network adaptive control with fuzzy rules confirming initial weights
Author :
Guiyong, Ren ; Yancheng, Qu ; Changhong, Wang
Author_Institution :
Harbin Inst. of Technol., China
Abstract :
A method, based on fuzzy rules, is presented to learn the initial values of a neural network´s weight array. This neural network is used in an adaptive control architecture. Using the prior knowledge efficiently, it can ensure the stability of the adaptive control during the learning period of the neural network. Simulation results demonstrate the feasibility of this method
Keywords :
adaptive control; fuzzy control; learning (artificial intelligence); model reference adaptive control systems; neurocontrollers; stability; adaptive control architecture; fuzzy rules; initial values; learning period; neural network adaptive control; prior knowledge; weight array; Adaptive control; Fuzzy control; Fuzzy neural networks; Neural networks; Stability;
Conference_Titel :
Intelligent Control and Automation, 2000. Proceedings of the 3rd World Congress on
Conference_Location :
Hefei
Print_ISBN :
0-7803-5995-X
DOI :
10.1109/WCICA.2000.863369
