Hybrid adaptive learning control of nonlinear system

Author

Zhang, Ping ; Sankai, Yoshiyuki ; Ohta, Michio

Author_Institution

Graduate Sch. in Eng., Tsukuba Univ., Ibaraki, Japan

Volume

4

fYear

1995

fDate

21-23 Jun 1995

Firstpage

2744

Abstract

A hybrid adaptive learning control for nonlinear dynamical systems is proposed. Feedforward multilayer neural networks are used to construct a controller. Parameters of the neural networks are adjusted by a dynamic backpropagation algorithm and a genetic algorithm. The genetic algorithm manages to escape local minima and reach the neighborhood of the global minimum on the squared error surface. The dynamic backpropagation algorithm is used to search the global minimum from its neighborhood. Computer simulations show that the tracking control performance of nonlinear dynamical systems can be enhanced by the proposed method

Keywords

adaptive control; backpropagation; feedforward neural nets; genetic algorithms; learning systems; multilayer perceptrons; neurocontrollers; nonlinear control systems; nonlinear dynamical systems; dynamic backpropagation algorithm; feedforward multilayer neural networks; genetic algorithm; global minimum; hybrid adaptive learning control; nonlinear dynamical systems; nonlinear system; squared error surface; tracking control performance; Adaptive control; Backpropagation algorithms; Control systems; Genetic algorithms; Multi-layer neural network; Neural networks; Nonlinear control systems; Nonlinear dynamical systems; Nonlinear systems; Programmable control;

fLanguage

English

Publisher

ieee

Conference_Titel

American Control Conference, Proceedings of the 1995

Conference_Location

Seattle, WA

Print_ISBN

0-7803-2445-5

Type

conf

DOI

10.1109/ACC.1995.532348

Filename

532348