Development of global function approximations for desgin optimization using evolutionary fuzzy modeling

Seungjin Kim, Jongsoo Lee

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

This paper introduces the application of evolutionary fuzzy modeling (EFM) in constructing global function approximations to subsequent use in non-gradient based optimization strategies. The fuzzy logic is employed for express the relationship between input and output training patterns in form of linguistic fuzzy rules. EFM is used to determine the optimal values of membership function parameters by adapting fuzzy rules available. In the study, genetic algorithms (GA's) treat a set of membership function parameters as design variables and evolve them until the mean square error between defuzzified outputs and actual target values are minimized. We also discuss the enhanced accuracy of function approximations, comparing with traditional response surface methods by using polynomial interpolation and backpropagation neural networks in its ability to handle the typical benchmark problems.

Original languageEnglish
Pages (from-to)1206-1215
Number of pages10
JournalKSME International Journal
Volume14
Issue number11
Publication statusPublished - 2000 Nov 1

Fingerprint

Fuzzy rules
Membership functions
Backpropagation
Linguistics
Mean square error
Fuzzy logic
Interpolation
Genetic algorithms
Polynomials
Neural networks

All Science Journal Classification (ASJC) codes

  • Mechanical Engineering

Cite this

@article{1cdc76cd3b324ae6bb6f4bf339c4c42f,
title = "Development of global function approximations for desgin optimization using evolutionary fuzzy modeling",
abstract = "This paper introduces the application of evolutionary fuzzy modeling (EFM) in constructing global function approximations to subsequent use in non-gradient based optimization strategies. The fuzzy logic is employed for express the relationship between input and output training patterns in form of linguistic fuzzy rules. EFM is used to determine the optimal values of membership function parameters by adapting fuzzy rules available. In the study, genetic algorithms (GA's) treat a set of membership function parameters as design variables and evolve them until the mean square error between defuzzified outputs and actual target values are minimized. We also discuss the enhanced accuracy of function approximations, comparing with traditional response surface methods by using polynomial interpolation and backpropagation neural networks in its ability to handle the typical benchmark problems.",
author = "Seungjin Kim and Jongsoo Lee",
year = "2000",
month = "11",
day = "1",
language = "English",
volume = "14",
pages = "1206--1215",
journal = "KSME Journal",
issn = "1738-494X",
publisher = "Korean Society of Mechanical Engineers",
number = "11",

}

Development of global function approximations for desgin optimization using evolutionary fuzzy modeling. / Kim, Seungjin; Lee, Jongsoo.

In: KSME International Journal, Vol. 14, No. 11, 01.11.2000, p. 1206-1215.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Development of global function approximations for desgin optimization using evolutionary fuzzy modeling

AU - Kim, Seungjin

AU - Lee, Jongsoo

PY - 2000/11/1

Y1 - 2000/11/1

N2 - This paper introduces the application of evolutionary fuzzy modeling (EFM) in constructing global function approximations to subsequent use in non-gradient based optimization strategies. The fuzzy logic is employed for express the relationship between input and output training patterns in form of linguistic fuzzy rules. EFM is used to determine the optimal values of membership function parameters by adapting fuzzy rules available. In the study, genetic algorithms (GA's) treat a set of membership function parameters as design variables and evolve them until the mean square error between defuzzified outputs and actual target values are minimized. We also discuss the enhanced accuracy of function approximations, comparing with traditional response surface methods by using polynomial interpolation and backpropagation neural networks in its ability to handle the typical benchmark problems.

AB - This paper introduces the application of evolutionary fuzzy modeling (EFM) in constructing global function approximations to subsequent use in non-gradient based optimization strategies. The fuzzy logic is employed for express the relationship between input and output training patterns in form of linguistic fuzzy rules. EFM is used to determine the optimal values of membership function parameters by adapting fuzzy rules available. In the study, genetic algorithms (GA's) treat a set of membership function parameters as design variables and evolve them until the mean square error between defuzzified outputs and actual target values are minimized. We also discuss the enhanced accuracy of function approximations, comparing with traditional response surface methods by using polynomial interpolation and backpropagation neural networks in its ability to handle the typical benchmark problems.

UR - http://www.scopus.com/inward/record.url?scp=0034311217&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034311217&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0034311217

VL - 14

SP - 1206

EP - 1215

JO - KSME Journal

JF - KSME Journal

SN - 1738-494X

IS - 11

ER -