Approximate nonlinear system linearization with neural networks

Author

Pei, Hai-Long ; Zhou, Qi-Jie

Author_Institution

Dept. of Autom., South China Univ. of Technol., Guangzhou, China

Volume

1

fYear

1997

fDate

4-6 Jun 1997

Firstpage

821

Abstract

Researches have shown that neural networks have the ability to approximate a function as well as its derivatives. In this paper a novel method of approximate nonlinear system linearization with neural networks is proposed. The network approximator is designed to integrate the involutive equation of a nonlinear system whether the integrability condition is satisfied or not. This result offers a promising opportunity to introduce neural network theory into nonlinear system control

Keywords

approximation theory; control system synthesis; feedforward neural nets; function approximation; integration; linearisation techniques; multilayer perceptrons; nonlinear systems; partial differential equations; approximate nonlinear system linearization; integrability condition; involutive equation; network approximator; neural network theory; nonlinear system control; Artificial neural networks; Automation; Control systems; Linear approximation; Linear systems; Multi-layer neural network; Neural networks; Nonlinear control systems; Nonlinear systems; Partial differential equations;

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.1997.611918

Filename

611918