Title :
PID Controller Based Adaptive GA and Neural Networks
Author :
Sun, Lei ; Mei, Tao ; Yao, Yansheng ; Cai, Linqin ; Meng, Max Q H
Author_Institution :
Center for Biomimetic Sensing & Control Res. Inst. of Intelligent Machines, Chinese Acad. of Sci., Hefei
Abstract :
A self-tuning PID controller based on adaptive genetic algorithm (AGA) and neural networks is presented. AGA optimizes not only the initial weights of the BP neural networks (BPNN) which optimizes parameters of PID, but also the optimum values of the following radial basis function neural networks (RBFNN) parameters: centers, variance and weights of the output layer. RBFNN identifies the Jacobian information of the controlled plant. The influence on the control performance is solved which results from the initial parameters of BPNN and RBFNN. The result of the simulation shows that the method can improve the robust performance of the control system
Keywords :
genetic algorithms; neurocontrollers; radial basis function networks; robust control; self-adjusting systems; three-term control; BP neural networks; Jacobian information; PID parameters optimization; adaptive genetic algorithm; control system; radial basis function neural networks; robust performance; self-tuning PID controller; Adaptive control; Automatic control; Automation; Biomimetics; Control system synthesis; Iterative algorithms; Machine intelligence; Neural networks; Programmable control; Three-term control; PID; RBF; adaptive GA; neural network;
Conference_Titel :
Intelligent Control and Automation, 2006. WCICA 2006. The Sixth World Congress on
Conference_Location :
Dalian
Print_ISBN :
1-4244-0332-4
DOI :
10.1109/WCICA.2006.1714351
