A PID-like controller for nonlinear systems

Author

Jin, Wang ; Wenzhong, Gao ; Fuli, Wang

Author_Institution

Dept. of Autom. Control, Northeastern Univ., ShenYang, China

Volume

3

fYear

1997

fDate

4-6 Jun 1997

Firstpage

1558

Abstract

This paper presents an adaptive PID-like controller (PIDLC) using a modified neural network (MNN) for learning the characteristics of a dynamic system. The PIDLC can adapt parameters variation and uncertainty in the controlled plant through online learning. The MNN´s learning algorithm is considerably faster because of the introduction of recursive least squares algorithm. The simulation results show that this kind of control algorithm is very effective especially when there are variations in the plant dynamics

Keywords

adaptive control; learning (artificial intelligence); least squares approximations; neurocontrollers; nonlinear systems; recurrent neural nets; three-term control; PID-like controller; adaptive control; learning algorithm; nonlinear systems; recurrent neural network; recursive least squares algorithm; system dynamics; Adaptive control; Control systems; Least squares methods; Multi-layer neural network; Neural networks; Nonlinear control systems; Nonlinear dynamical systems; Nonlinear systems; Programmable control; Uncertainty;

fLanguage

English

Publisher

ieee

Conference_Titel

American Control Conference, 1997. Proceedings of the 1997

Conference_Location

Albuquerque, NM

ISSN

0743-1619

Print_ISBN

0-7803-3832-4

Type

conf

DOI

10.1109/ACC.1997.610826

Filename

610826