Dynamic system modeling based on wavelet recurrent fuzzy neural network

Author

Ji-Rong Song ; Hong-Bo Shi

Author_Institution

Dept. of Electron. & Commun. Eng., East China Univ. of Sci. & Technol., Shanghai, China

Volume

2

fYear

2011

fDate

26-28 July 2011

Firstpage

766

Lastpage

770

Abstract

In this paper, Combined recurrent neural network and wavelet-based fuzzy neural network, A new wavelet recurrent fuzzy network (WRFNN) is presented. In order to simplify parameters identification and improve model generalization ability, The premise and consequent coefficients are optimized separately. The premise parameters are optimized by LM algorithm, at the same time the consequent coefficients are updated by recursive least square estimation. Simulation results of a nonlinear dynamic system and a CSTR system modeling show that the WRFNN can catch system dynamic real-time.

Keywords

fuzzy neural nets; identification; least squares approximations; modelling; recurrent neural nets; recursive estimation; wavelet transforms; CSTR system modeling; LM algorithm; WRFNN; dynamic system modeling; model generalization ability improvement; nonlinear dynamic system; parameters identification; recursive least square estimation; wavelet recurrent fuzzy neural network; Fuzzy neural networks; Heuristic algorithms; Least squares approximation; Nonlinear dynamical systems; Testing; Training; Wavelet transforms; LM algorithm; modeling; recurrent neural network; recursive least square estimation; wavelet-based fuzzy neural network;

fLanguage

English

Publisher

ieee

Conference_Titel

Natural Computation (ICNC), 2011 Seventh International Conference on

Conference_Location

Shanghai

ISSN

2157-9555

Print_ISBN

978-1-4244-9950-2

Type

conf

DOI

10.1109/ICNC.2011.6022164

Filename

6022164