Time-Delay Nonlinear System Modelling via Delayed Neural Networks

Author

de Jesus Rubio, Jose ; Yu, Wen ; Li, XiaoOu

Author_Institution

Departamento de Control Automatico, CINVESTAV-IPN, Mexico City

Volume

1

fYear

0

fDate

0-0 0

Firstpage

119

Lastpage

123

Abstract

In this paper, nonlinear systems on-line identification via delayed dynamic neural networks is studied. Dynamic series-parallel neural network model with time delay is presented and the stability conditions are derived using Lyapunov-Krasovskii approach. The conditions for passivity, asymptotic stability are established in some senses. All the results are described by linear matrix inequality (LMI). We conclude that the gradient algorithm for weight adjustment is stable and robust to any bounded uncertainties

Keywords

Lyapunov methods; asymptotic stability; delays; gradient methods; identification; linear matrix inequalities; neurocontrollers; nonlinear systems; Lyapunov-Krasovskii approach; asymptotic stability; delayed neural networks; dynamic series-parallel neural network model; gradient algorithm; linear matrix inequality; nonlinear system online identification; passivity; robust system; time delay; time-delay nonlinear system modelling; weight adjustment; Automation; Delay systems; Intelligent control; Neural networks; Nonlinear systems; identification; neural networks; time-delay;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Control and Automation, 2006. WCICA 2006. The Sixth World Congress on

Conference_Location

Dalian

Print_ISBN

1-4244-0332-4

Type

conf

DOI

10.1109/WCICA.2006.1712374

Filename

1712374