Identification and Control for Discrete Dynamics Systems using Space State Recurrent Fuzzy Neural Networks

Author

Monroy, Paul Erick Mendez ; Pérez, Héctor Benítez

Author_Institution

Univ. Nacional Autonoma de Mexico, Mexico City

fYear

2007

fDate

25-28 Sept. 2007

Firstpage

112

Lastpage

117

Abstract

This work presents a structure for modelling and control non linear systems based upon states space recurrent fuzzy neural network (SSRFNN). SSRFNN model has space state structure which is identified since input output data. Fuzzy rules are automatic added through cluster method. Consequent parameter are estimated by using time backpropagation algorithm. An extra observer algorithm is design in order to obtain necessary states measurements. There after control strategy is proposed they some multiple interconnected systems.

Keywords

backpropagation; discrete systems; fuzzy set theory; interconnected systems; nonlinear control systems; recurrent neural nets; discrete dynamics systems; fuzzy rules; interconnected systems; nonlinear systems; space state recurrent fuzzy neural networks; time backpropagation; Automatic control; Backpropagation algorithms; Control system synthesis; Control systems; Fuzzy control; Fuzzy neural networks; Linear systems; Observers; Parameter estimation; State-space methods; Interconnected Systems.; Recurrent Neural Networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Electronics, Robotics and Automotive Mechanics Conference, 2007. CERMA 2007

Conference_Location

Morelos

Print_ISBN

978-0-7695-2974-5

Type

conf

DOI

10.1109/CERMA.2007.4367670

Filename

4367670