A hybrid fuzzy neural network and its control applications

Author

Chuang, C.-H. ; Lee, T.S.

Author_Institution

Sch. of Aerosp. Eng., Georgia Inst. of Technol., Atlanta, GA, USA

fYear

1996

fDate

15-18 Sep 1996

Firstpage

175

Lastpage

180

Abstract

We present an alternative neural network architecture which is similar to the operation of a general fuzzy inference system. This hybrid fuzzy neural network (HFNN) is a modified multilayer feedforward neural network (MFNN) with four different layers. By using the gradient method, learning algorithms are derived. An example is presented to compare the approximation performance of the HFNN with the MFNN. The HFNN is then applied to an inverted pendulum control problem by using temporal backpropagation. The performance of the HFNN controller is illustrated by simulations

Keywords

fuzzy logic; fuzzy neural nets; inference mechanisms; multilayer perceptrons; neurocontrollers; approximation performance; general fuzzy inference system; gradient method; hybrid fuzzy neural network; inverted pendulum control problem; learning algorithms; modified multilayer feedforward neural network; temporal backpropagation; Feedforward neural networks; Fuzzy control; Fuzzy neural networks; Fuzzy systems; Gradient methods; Hafnium; Inference algorithms; Multi-layer neural network; Neural networks; Neurons;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Control, 1996., Proceedings of the 1996 IEEE International Symposium on

Conference_Location

Dearborn, MI

ISSN

2158-9860

Print_ISBN

0-7803-2978-3

Type

conf

DOI

10.1109/ISIC.1996.556197

Filename

556197