Adaptive control and identification using one neural network for a class of plants with uncertainties

Author

Tsuji, Toshio ; Xu, Bing Hong ; Kaneko, Makoto

Author_Institution

Dept. of Ind. & Syst. Eng., Hiroshima Univ., Japan

Volume

28

Issue

4

fYear

1998

fDate

7/1/1998 12:00:00 AM

Firstpage

496

Lastpage

505

Abstract

This paper proposes a new neural adaptive control method that can perform adaptive control and identification for a class of controlled plants with linear and nonlinear uncertainties. This method uses a single neural network for both control and identification, and a sufficient condition of the local asymptotic stability is derived. Then, in order to illustrate the applicability of the proposed method, it is applied to the torque control of a flexible beam that includes linear and nonlinear structural uncertainties

Keywords

adaptive control; asymptotic stability; backpropagation; flexible structures; identification; multilayer perceptrons; neurocontrollers; torque control; uncertain systems; adaptive control; asymptotic stability; backpropagation; flexible beam; identification; multilayer perceptron; neural network; neurocontrol; sufficient condition; torque control; uncertain systems; Adaptive control; Control systems; Error correction; Multi-layer neural network; Neural networks; Neurofeedback; Programmable control; Stability; Sufficient conditions; Uncertainty;

fLanguage

English

Journal_Title

Systems, Man and Cybernetics, Part A: Systems and Humans, IEEE Transactions on

Publisher

ieee

ISSN

1083-4427

Type

jour

DOI

10.1109/3468.686711

Filename

686711