Dynamic input/output linearization using recurrent neural networks

Author

Delgado, A. ; Kambhampati, C. ; Warwick, K.

Author_Institution

Dept. of Cybern., Reading Univ., UK

Volume

3

fYear

1996

fDate

3-6 Jun 1996

Firstpage

1721

Abstract

A dynamic recurrent neural network (DRNN) is used to input/output linearize a control affine system in the globally linearizing control (GLC) structure. The network is trained as a part of a closed loop that involves a PI controller, the goal is to use the network, as a dynamic feedback, to cancel the nonlinear terms of the plant. The stability of the configuration is guarantee if the network and the plant are asymptotically stable and the linearizing input is bounded

Keywords

asymptotic stability; closed loop systems; feedback; linearisation techniques; neurocontrollers; nonlinear control systems; recurrent neural nets; stability criteria; two-term control; PI controller; asymptotic stability; closed loop; control affine system; dynamic feedback; dynamic input/output linearization; dynamic recurrent neural network; globally linearizing control; Control system synthesis; Control systems; Cybernetics; Electronic mail; Neural networks; Neurofeedback; Neurons; Nonlinear dynamical systems; Recurrent neural networks; State feedback;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1996., IEEE International Conference on

Conference_Location

Washington, DC

Print_ISBN

0-7803-3210-5

Type

conf

DOI

10.1109/ICNN.1996.549160

Filename

549160