Application of dynamic neural networks to approximation and control of nonlinear systems

Author

Amin, S. Massoud ; Rodin, Ervin Y. ; Wu, Alan Y.

Author_Institution

Dept. of Syst. Sci. & Math., Washington Univ., St. Louis, MO, USA

Volume

1

fYear

1997

fDate

4-6 Jun 1997

Firstpage

222

Abstract

Based on a paradigm of neurons with local memory (NLM), we discuss the representation of control systems by neural networks. Using this formulation, the basic issues of controllability and observability for the dynamic system are addressed. A separation principle of learning and control is presented for NLM, showing that the weights of the network do not affect its dynamics. Theoretical issues concerning local linearization via a coordinate transformation and nonlinear feedback are discussed

Keywords

controllability; dynamics; feedback; learning (artificial intelligence); neurocontrollers; nonlinear control systems; observability; controllability; coordinate transformation; dynamic neural networks; local linearization; local memory; nonlinear feedback; nonlinear systems; observability; separation principle; Artificial neural networks; Control systems; Controllability; Mathematics; Neural networks; Neurofeedback; Neurons; Nonlinear control systems; Nonlinear systems; Observability;

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.1997.611790

Filename

611790