Parameter estimation of nonlinear system based on hybrid intelligent method

Author

Juang, Jih-Gau ; Lin, Bo-Shian ; Li, Chien-Kuo

Author_Institution

Dept. of Commun. & Guidance Eng., Nat. Taiwan Ocean Univ., Keelung, Taiwan

Volume

4

fYear

2004

fDate

10-13 Oct. 2004

Firstpage

3365

Abstract

Parameter estimation of nonlinear system using hybrid intelligent method is presented. A recursive least squares estimation combined with genetic algorithm is used in this study. A recurrent neural network for system identification and a conventional parameter estimation using recursive least-squares method are also given for comparison. After test, the proposed scheme has better performance on parameter estimation than the conventional least-squares estimation and the recurrent neural network.

Keywords

genetic algorithms; least squares approximations; nonlinear control systems; recurrent neural nets; recursive estimation; genetic algorithm; hybrid intelligent method; nonlinear system; parameter estimation; recurrent neural network; recursive least squares estimation; system identification; Genetics; Neural networks; Neurofeedback; Neurons; Nonlinear systems; Parameter estimation; Recurrent neural networks; Recursive estimation; Resonance light scattering; System identification;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man and Cybernetics, 2004 IEEE International Conference on

ISSN

1062-922X

Print_ISBN

0-7803-8566-7

Type

conf

DOI

10.1109/ICSMC.2004.1400862

Filename

1400862