Some new results on system identification with dynamic neural networks

Author

Yu, Wen ; Li, XiaoOu

Author_Institution

Dept. de Control Autom., CINVESTAV-IPN, Mexico City, Mexico

Volume

12

Issue

2

fYear

2001

fDate

3/1/2001 12:00:00 AM

Firstpage

412

Lastpage

417

Abstract

Nonlinear system online identification via dynamic neural networks is studied in this paper. The main contribution of the paper is that the passivity approach is applied to access several new stable properties of neuro identification. The conditions for passivity, stability, asymptotic stability, and input-to-state stability are established in certain senses. We conclude that the gradient descent algorithm for weight adjustment is stable in an L_∞ sense and robust to any bounded uncertainties

Keywords

gradient methods; identification; neural nets; nonlinear systems; online operation; stability; L_∞ stability; asymptotic stability conditions; bounded uncertainty robustness; dynamic neural networks; gradient descent algorithm; input-to-state stability conditions; neuro identification; nonlinear system online identification; passivity approach; passivity conditions; stability criteria; stable properties; weight adjustment; Asymptotic stability; Circuit stability; Multilayer perceptrons; Neural networks; Nonlinear control systems; Nonlinear systems; Robustness; Stability analysis; System identification; Uncertainty;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.914535

Filename

914535