A hybrid multimodel neural network for nonlinear systems identification

Author

Baruch, I. ; Thomas, F. ; Garrido, R. ; Gortcheva, E.

Author_Institution

CINVESTAV-IPN, Mexico City, Mexico

Volume

6

fYear

1999

fDate

36342

Firstpage

4278

Abstract

An improved universal parallel recurrent neural network canonical architecture, named a recurrent trainable neural network (RTNN), suited for state-space systems identification, and an improved dynamic backpropagation method of its learning, are proposed. The proposed RTNN is studied with various representative examples and the results of its learning are compared with other results given in the literature. For a complex nonlinear plants identification, a fuzzy-rule-based system and a fuzzy-neural multimodel, are used. The fuzzy-neural multimodel is applied to a mechanical system with friction identification

Keywords

backpropagation; fuzzy neural nets; identification; large-scale systems; nonlinear systems; recurrent neural nets; state-space methods; complex systems; dynamic backpropagation; fuzzy-neural network; fuzzy-rule-based system; identification; learning; multimodel neural network; nonlinear systems; recurrent neural network; state-space; Electronic mail; Equations; Friction; Learning systems; Neural networks; Nonlinear dynamical systems; Nonlinear systems; Recurrent neural networks; Stability; System identification;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1999. IJCNN '99. International Joint Conference on

Conference_Location

Washington, DC

ISSN

1098-7576

Print_ISBN

0-7803-5529-6

Type

conf

DOI

10.1109/IJCNN.1999.830854

Filename

830854