Development of a self-organized neuro-fuzzy model by using genetic algorithm for system identification

Chuen Jyh Chen, Shih Ming Yang, Shih Guei Lin

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In neuro-fuzzy applications, it is known that the selections in neural network structure, fuzzy logic membership functions, and fuzzy logic rules are very challenging as they are sensitive to modeling accuracy. A neuro-fuzzy model with genetic algorithm is developed for system identification, where fuzzy logic is to tune the membership functions by three-phase learning and genetic algorithm is to search the optimal parameters of the model. The weight/bias in artificial neural network, the center/width of membership function, and the fuzzy logic rules can all be determined. Performance verification of system identification by a benchmark nonlinear difference equation shows that the neuro-fuzzy model with genetic algorithm is most effective in modeling accuracy.

Original languageEnglish
Pages (from-to)281-290
Number of pages10
JournalJournal of Aeronautics, Astronautics and Aviation
Volume46
Issue number4
DOIs
Publication statusPublished - 2014 Dec 1

Fingerprint

system identification
fuzzy mathematics
membership functions
genetic algorithms
genetic algorithm
Fuzzy logic
logic
Identification (control systems)
Membership functions
Genetic algorithms
Neural networks
difference equations
Difference equations
artificial neural network
Learning algorithms
learning
modeling

All Science Journal Classification (ASJC) codes

  • Aerospace Engineering
  • Space and Planetary Science

Cite this

@article{69130a0fba784f56acac64a18525dcb9,
title = "Development of a self-organized neuro-fuzzy model by using genetic algorithm for system identification",
abstract = "In neuro-fuzzy applications, it is known that the selections in neural network structure, fuzzy logic membership functions, and fuzzy logic rules are very challenging as they are sensitive to modeling accuracy. A neuro-fuzzy model with genetic algorithm is developed for system identification, where fuzzy logic is to tune the membership functions by three-phase learning and genetic algorithm is to search the optimal parameters of the model. The weight/bias in artificial neural network, the center/width of membership function, and the fuzzy logic rules can all be determined. Performance verification of system identification by a benchmark nonlinear difference equation shows that the neuro-fuzzy model with genetic algorithm is most effective in modeling accuracy.",
author = "Chen, {Chuen Jyh} and Yang, {Shih Ming} and Lin, {Shih Guei}",
year = "2014",
month = "12",
day = "1",
doi = "10.6125/14-0508-795",
language = "English",
volume = "46",
pages = "281--290",
journal = "Journal of Aeronautics, Astronautics and Aviation, Series A",
issn = "1990-7710",
publisher = "The Aeronautical and Astronautical Society of the Republic of China",
number = "4",

}

Development of a self-organized neuro-fuzzy model by using genetic algorithm for system identification. / Chen, Chuen Jyh; Yang, Shih Ming; Lin, Shih Guei.

In: Journal of Aeronautics, Astronautics and Aviation, Vol. 46, No. 4, 01.12.2014, p. 281-290.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Development of a self-organized neuro-fuzzy model by using genetic algorithm for system identification

AU - Chen, Chuen Jyh

AU - Yang, Shih Ming

AU - Lin, Shih Guei

PY - 2014/12/1

Y1 - 2014/12/1

N2 - In neuro-fuzzy applications, it is known that the selections in neural network structure, fuzzy logic membership functions, and fuzzy logic rules are very challenging as they are sensitive to modeling accuracy. A neuro-fuzzy model with genetic algorithm is developed for system identification, where fuzzy logic is to tune the membership functions by three-phase learning and genetic algorithm is to search the optimal parameters of the model. The weight/bias in artificial neural network, the center/width of membership function, and the fuzzy logic rules can all be determined. Performance verification of system identification by a benchmark nonlinear difference equation shows that the neuro-fuzzy model with genetic algorithm is most effective in modeling accuracy.

AB - In neuro-fuzzy applications, it is known that the selections in neural network structure, fuzzy logic membership functions, and fuzzy logic rules are very challenging as they are sensitive to modeling accuracy. A neuro-fuzzy model with genetic algorithm is developed for system identification, where fuzzy logic is to tune the membership functions by three-phase learning and genetic algorithm is to search the optimal parameters of the model. The weight/bias in artificial neural network, the center/width of membership function, and the fuzzy logic rules can all be determined. Performance verification of system identification by a benchmark nonlinear difference equation shows that the neuro-fuzzy model with genetic algorithm is most effective in modeling accuracy.

UR - http://www.scopus.com/inward/record.url?scp=84920082858&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84920082858&partnerID=8YFLogxK

U2 - 10.6125/14-0508-795

DO - 10.6125/14-0508-795

M3 - Article

AN - SCOPUS:84920082858

VL - 46

SP - 281

EP - 290

JO - Journal of Aeronautics, Astronautics and Aviation, Series A

JF - Journal of Aeronautics, Astronautics and Aviation, Series A

SN - 1990-7710

IS - 4

ER -