An input-output based robust stabilization criterion for neural-network control of nonlinear systems

Author

Fernandez de Caflete, J. ; Barreiro, A. ; García-Cerezo, A. ; García-Moral, I.

Author_Institution

Departmento de Ingeneria de Sistemas y Automatica, Malaga Univ., Spain

Volume

12

Issue

6

fYear

2001

fDate

11/1/2001 12:00:00 AM

Firstpage

1491

Lastpage

1497

Abstract

A stabilization method based on the input-output conicity criterion is presented. Conventional learning algorithms are applied to adjust the controller dynamics, and robust stability of the closed-loop system is guaranteed by modifying the training patterns which yield unstable behavior. The methodology developed expands the class of nonlinear systems to be controlled using neural control schemes, so that the stabilization of a broad class of neural-network-based control systems, even with unknown dynamics, is assured. Straightforwardness in the application of this method is evident in contrast to the Lyapunov function approach

Keywords

closed loop systems; input-output stability; neurocontrollers; nonlinear control systems; robust control; stability criteria; closed-loop system; controller dynamics; input-output based robust stabilization criterion; input-output conicity criterion; learning algorithms; neural-network control; nonlinear systems; robust stability; stabilization method; training patterns; unstable behavior; Automatic control; Control systems; Lyapunov method; Nonlinear control systems; Nonlinear dynamical systems; Nonlinear systems; Robust control; Stability analysis; Stability criteria; Training data;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.963785

Filename

963785