Reliability-based MOGA design optimization using probabilistic response surface method and Bayesian neural network

Juhee Lim, Jongsoo Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, an effective optimization approach, which integrated the probabilistic surrogate model, non-dominated sorting genetic algorithm, and reliability index method, is proposed to multi-objective reliability-based design optimization. To reduce the computational cost and improve the efficiency of the optimization process, the problem can be surrogated by probabilistic response surface method and Bayesian neural network as high fidelity metamodel with statistical modelling method. After verification through the simulation results on numerical test problem, these techniques have been applied to engineering problem in optimizing simultaneously multi-performances or objective functions subject to reliability constraints.

Original languageEnglish
Title of host publicationGECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion
PublisherAssociation for Computing Machinery, Inc
Pages219-220
Number of pages2
ISBN (Electronic)9781450367486
DOIs
Publication statusPublished - 2019 Jul 13
Event2019 Genetic and Evolutionary Computation Conference, GECCO 2019 - Prague, Czech Republic
Duration: 2019 Jul 132019 Jul 17

Publication series

NameGECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion

Conference

Conference2019 Genetic and Evolutionary Computation Conference, GECCO 2019
CountryCzech Republic
CityPrague
Period19/7/1319/7/17

Fingerprint

Response Surface Method
Probabilistic Methods
Bayesian Networks
Neural Networks
Neural networks
Reliability Index
Surrogate Model
Sorting algorithm
Statistical Modeling
Process Optimization
Metamodel
Modeling Method
Probabilistic Model
Statistical method
Fidelity
Test Problems
Computational Cost
Objective function
Genetic Algorithm
Engineering

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Theoretical Computer Science
  • Software

Cite this

Lim, J., & Lee, J. (2019). Reliability-based MOGA design optimization using probabilistic response surface method and Bayesian neural network. In GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion (pp. 219-220). (GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion). Association for Computing Machinery, Inc. https://doi.org/10.1145/3319619.3321901
Lim, Juhee ; Lee, Jongsoo. / Reliability-based MOGA design optimization using probabilistic response surface method and Bayesian neural network. GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion. Association for Computing Machinery, Inc, 2019. pp. 219-220 (GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion).
@inproceedings{984ac2bbfb004222baeb93ea27a44fc6,
title = "Reliability-based MOGA design optimization using probabilistic response surface method and Bayesian neural network",
abstract = "In this paper, an effective optimization approach, which integrated the probabilistic surrogate model, non-dominated sorting genetic algorithm, and reliability index method, is proposed to multi-objective reliability-based design optimization. To reduce the computational cost and improve the efficiency of the optimization process, the problem can be surrogated by probabilistic response surface method and Bayesian neural network as high fidelity metamodel with statistical modelling method. After verification through the simulation results on numerical test problem, these techniques have been applied to engineering problem in optimizing simultaneously multi-performances or objective functions subject to reliability constraints.",
author = "Juhee Lim and Jongsoo Lee",
year = "2019",
month = "7",
day = "13",
doi = "10.1145/3319619.3321901",
language = "English",
series = "GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion",
publisher = "Association for Computing Machinery, Inc",
pages = "219--220",
booktitle = "GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion",

}

Lim, J & Lee, J 2019, Reliability-based MOGA design optimization using probabilistic response surface method and Bayesian neural network. in GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion. GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion, Association for Computing Machinery, Inc, pp. 219-220, 2019 Genetic and Evolutionary Computation Conference, GECCO 2019, Prague, Czech Republic, 19/7/13. https://doi.org/10.1145/3319619.3321901

Reliability-based MOGA design optimization using probabilistic response surface method and Bayesian neural network. / Lim, Juhee; Lee, Jongsoo.

GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion. Association for Computing Machinery, Inc, 2019. p. 219-220 (GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Reliability-based MOGA design optimization using probabilistic response surface method and Bayesian neural network

AU - Lim, Juhee

AU - Lee, Jongsoo

PY - 2019/7/13

Y1 - 2019/7/13

N2 - In this paper, an effective optimization approach, which integrated the probabilistic surrogate model, non-dominated sorting genetic algorithm, and reliability index method, is proposed to multi-objective reliability-based design optimization. To reduce the computational cost and improve the efficiency of the optimization process, the problem can be surrogated by probabilistic response surface method and Bayesian neural network as high fidelity metamodel with statistical modelling method. After verification through the simulation results on numerical test problem, these techniques have been applied to engineering problem in optimizing simultaneously multi-performances or objective functions subject to reliability constraints.

AB - In this paper, an effective optimization approach, which integrated the probabilistic surrogate model, non-dominated sorting genetic algorithm, and reliability index method, is proposed to multi-objective reliability-based design optimization. To reduce the computational cost and improve the efficiency of the optimization process, the problem can be surrogated by probabilistic response surface method and Bayesian neural network as high fidelity metamodel with statistical modelling method. After verification through the simulation results on numerical test problem, these techniques have been applied to engineering problem in optimizing simultaneously multi-performances or objective functions subject to reliability constraints.

UR - http://www.scopus.com/inward/record.url?scp=85070575699&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070575699&partnerID=8YFLogxK

U2 - 10.1145/3319619.3321901

DO - 10.1145/3319619.3321901

M3 - Conference contribution

AN - SCOPUS:85070575699

T3 - GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion

SP - 219

EP - 220

BT - GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion

PB - Association for Computing Machinery, Inc

ER -

Lim J, Lee J. Reliability-based MOGA design optimization using probabilistic response surface method and Bayesian neural network. In GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion. Association for Computing Machinery, Inc. 2019. p. 219-220. (GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion). https://doi.org/10.1145/3319619.3321901