Nonlinear H∞ control for continuous-time recurrent neural networks

Author

Suykens, J.A.K. ; Vandewalle, J. ; De Moor, B.

Author_Institution

Dept. of Electr. Eng., Katholieke Univ. Leuven, Leuven, Belgium

fYear

1997

fDate

1-7 July 1997

Firstpage

459

Lastpage

463

Abstract

In this paper we investigate the nonlinear H_∞ control problem for recurrent neural network models connected to a recurrent neural network controller. Conditions for dissipativity with finite L₂-gain are derived and expressed as matrix inequalities, based on a two-hidden layer recurrent neural network in standard plant form. The matrix inequalities are obtained from a storage function of quadratic form or quadratic form plus integral terms. Narendra´s dynamic backpropagation procedure for training on a set of specific reference inputs is modified with a dissipativity condition.

Keywords

H^∞ control; continuous time systems; neurocontrollers; nonlinear control systems; recurrent neural nets; Narendra dynamic backpropagation procedure; continuous-time recurrent neural networks; dissipativity condition; finite L₂-gain; integral term; nonlinear H_∞ control; quadratic form; recurrent neural network controller; storage function; two-hidden layer recurrent neural network; Backpropagation; Control systems; Linear matrix inequalities; Nonlinear systems; Recurrent neural networks; Standards; LMIs; Neural nets; nonlinear H∞ control;

fLanguage

English

Publisher

ieee

Conference_Titel

Control Conference (ECC), 1997 European

Conference_Location

Brussels

Print_ISBN

978-3-9524269-0-6

Type

conf

Filename

7082137