Title :
The model reference adaptive control based on the genetic algorithm
Author :
Jia, Lei ; Jingping, Jiang
Author_Institution :
Dept. of Electr. Eng., Zhejiang Univ., Hangzhou, China
Abstract :
A control method that is a model reference adaptive control method (MRAC) based on the combination of PID control and the genetic algorithm is introduced. It implements the the genetic algorithm´s global optimization to optimize the PID´s three control parameters: Kp, Ki, Kd, to obtain the best control effect. This paper gives an example using this method to control a nonlinear system-continuous stirred tank reactor system (CSTR). Because the state of the CSTR system can not be obtained, a neural network is used to estimate the value of the state. This neural network is trained by the GA. Simulation results are given
Keywords :
chemical technology; digital simulation; genetic algorithms; learning (artificial intelligence); model reference adaptive control systems; neural nets; nonlinear control systems; process control; state estimation; three-term control; CSTR; PID control; continuous stirred tank reactor system; genetic algorithm; global optimization; model reference adaptive control; nonlinear system; Adaptive control; Biological cells; Communication system control; Continuous-stirred tank reactor; Control systems; Encoding; Genetic algorithms; Neural networks; Nonlinear control systems; Three-term control;
Conference_Titel :
Neural Networks,1997., International Conference on
Conference_Location :
Houston, TX
Print_ISBN :
0-7803-4122-8
DOI :
10.1109/ICNN.1997.616122
