Using Gaussian Processes for Metamodeling in Robust Optimization Problems
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | The Journal of Engineering and Exact Sciences |
Texto Completo: | https://periodicos.ufv.br/jcec/article/view/17809 |
Resumo: | This article proposes an approach based on Gaussian Processes for building metamodels for robust optimization problems that seek to reduce the computational effort required to quantify uncertainties. The approach is applied to two cases: a low-dimensional benchmark problem and a high-dimensional structural design, which consists of minimizing the mass of a structure formed by bars of different materials and diameters, subjected to point loads in different locations. The cases are modeled as robust optimization problems, where the objective function is estimated by a Gaussian Process and the optimization procedure uses a population meta-heuristic. The results indicate that the proposed approach is effective in reducing the number of objective function evaluations required to obtain a robust solution, with no significant statistical differences in the quality of solutions achieved. |
id |
UFV-6_43633352a0c8323679b56fdcc16674b2 |
---|---|
oai_identifier_str |
oai:ojs.periodicos.ufv.br:article/17809 |
network_acronym_str |
UFV-6 |
network_name_str |
The Journal of Engineering and Exact Sciences |
repository_id_str |
|
spelling |
Using Gaussian Processes for Metamodeling in Robust Optimization ProblemsUso de Processos Gaussianos para a Metamodelagem em Problemas de Otimização RobustaGaussian. Process. Metamodels. Optimization. RobustProcessos. Gaussianos. Metamodelagem. Otimização. Robusta. This article proposes an approach based on Gaussian Processes for building metamodels for robust optimization problems that seek to reduce the computational effort required to quantify uncertainties. The approach is applied to two cases: a low-dimensional benchmark problem and a high-dimensional structural design, which consists of minimizing the mass of a structure formed by bars of different materials and diameters, subjected to point loads in different locations. The cases are modeled as robust optimization problems, where the objective function is estimated by a Gaussian Process and the optimization procedure uses a population meta-heuristic. The results indicate that the proposed approach is effective in reducing the number of objective function evaluations required to obtain a robust solution, with no significant statistical differences in the quality of solutions achieved. Este artigo propõe uma abordagem baseada em Processos Gaussianos para a construção de metamodelos para problemas de otimização robusta que busca diminuir o esforço computacional requerido para quantificar incertezas. A abordagem é aplicada em dois casos: um problema de benchmark de baixa dimensão e um de projeto estrutural, de alta dimensão, que consiste em minimizar a massa de uma estrutura formada por barras de diferentes materiais e diâmetros, submetida a cargas pontuais em diferentes locais. Os casos são modelados como problemas de otimização robusta, onde a função objetivo é estimada por um Processo Gaussiano e o procedimento de otimização é conduzido empregando-se uma meta-heurística populacional. Os resultados indicam que a abordagem proposta é eficaz na redução do número de avaliações de função objetivo necessárias para a obtenção de uma solução robusta, não havendo diferenças estatísticas significativas na qualidade das soluções alcançadas. Universidade Federal de Viçosa - UFV2023-12-29info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://periodicos.ufv.br/jcec/article/view/1780910.18540/jcecvl9iss10pp17809The Journal of Engineering and Exact Sciences; Vol. 9 No. 10 (2023); 17809The Journal of Engineering and Exact Sciences; Vol. 9 Núm. 10 (2023); 17809The Journal of Engineering and Exact Sciences; v. 9 n. 10 (2023); 178092527-1075reponame:The Journal of Engineering and Exact Sciencesinstname:Universidade Federal de Viçosa (UFV)instacron:UFVenghttps://periodicos.ufv.br/jcec/article/view/17809/9115Copyright (c) 2023 The Journal of Engineering and Exact Scienceshttps://creativecommons.org/licenses/by/4.0info:eu-repo/semantics/openAccessCruz, Claudemir Mota daLobato, Fran SérgioLibotte, Gustavo Barbosa2024-03-26T17:18:00Zoai:ojs.periodicos.ufv.br:article/17809Revistahttp://www.seer.ufv.br/seer/rbeq2/index.php/req2/oai2527-10752527-1075opendoar:2024-03-26T17:18The Journal of Engineering and Exact Sciences - Universidade Federal de Viçosa (UFV)false |
dc.title.none.fl_str_mv |
Using Gaussian Processes for Metamodeling in Robust Optimization Problems Uso de Processos Gaussianos para a Metamodelagem em Problemas de Otimização Robusta |
title |
Using Gaussian Processes for Metamodeling in Robust Optimization Problems |
spellingShingle |
Using Gaussian Processes for Metamodeling in Robust Optimization Problems Cruz, Claudemir Mota da Gaussian. Process. Metamodels. Optimization. Robust Processos. Gaussianos. Metamodelagem. Otimização. Robusta. |
title_short |
Using Gaussian Processes for Metamodeling in Robust Optimization Problems |
title_full |
Using Gaussian Processes for Metamodeling in Robust Optimization Problems |
title_fullStr |
Using Gaussian Processes for Metamodeling in Robust Optimization Problems |
title_full_unstemmed |
Using Gaussian Processes for Metamodeling in Robust Optimization Problems |
title_sort |
Using Gaussian Processes for Metamodeling in Robust Optimization Problems |
author |
Cruz, Claudemir Mota da |
author_facet |
Cruz, Claudemir Mota da Lobato, Fran Sérgio Libotte, Gustavo Barbosa |
author_role |
author |
author2 |
Lobato, Fran Sérgio Libotte, Gustavo Barbosa |
author2_role |
author author |
dc.contributor.author.fl_str_mv |
Cruz, Claudemir Mota da Lobato, Fran Sérgio Libotte, Gustavo Barbosa |
dc.subject.por.fl_str_mv |
Gaussian. Process. Metamodels. Optimization. Robust Processos. Gaussianos. Metamodelagem. Otimização. Robusta. |
topic |
Gaussian. Process. Metamodels. Optimization. Robust Processos. Gaussianos. Metamodelagem. Otimização. Robusta. |
description |
This article proposes an approach based on Gaussian Processes for building metamodels for robust optimization problems that seek to reduce the computational effort required to quantify uncertainties. The approach is applied to two cases: a low-dimensional benchmark problem and a high-dimensional structural design, which consists of minimizing the mass of a structure formed by bars of different materials and diameters, subjected to point loads in different locations. The cases are modeled as robust optimization problems, where the objective function is estimated by a Gaussian Process and the optimization procedure uses a population meta-heuristic. The results indicate that the proposed approach is effective in reducing the number of objective function evaluations required to obtain a robust solution, with no significant statistical differences in the quality of solutions achieved. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-12-29 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://periodicos.ufv.br/jcec/article/view/17809 10.18540/jcecvl9iss10pp17809 |
url |
https://periodicos.ufv.br/jcec/article/view/17809 |
identifier_str_mv |
10.18540/jcecvl9iss10pp17809 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
https://periodicos.ufv.br/jcec/article/view/17809/9115 |
dc.rights.driver.fl_str_mv |
Copyright (c) 2023 The Journal of Engineering and Exact Sciences https://creativecommons.org/licenses/by/4.0 info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
Copyright (c) 2023 The Journal of Engineering and Exact Sciences https://creativecommons.org/licenses/by/4.0 |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Universidade Federal de Viçosa - UFV |
publisher.none.fl_str_mv |
Universidade Federal de Viçosa - UFV |
dc.source.none.fl_str_mv |
The Journal of Engineering and Exact Sciences; Vol. 9 No. 10 (2023); 17809 The Journal of Engineering and Exact Sciences; Vol. 9 Núm. 10 (2023); 17809 The Journal of Engineering and Exact Sciences; v. 9 n. 10 (2023); 17809 2527-1075 reponame:The Journal of Engineering and Exact Sciences instname:Universidade Federal de Viçosa (UFV) instacron:UFV |
instname_str |
Universidade Federal de Viçosa (UFV) |
instacron_str |
UFV |
institution |
UFV |
reponame_str |
The Journal of Engineering and Exact Sciences |
collection |
The Journal of Engineering and Exact Sciences |
repository.name.fl_str_mv |
The Journal of Engineering and Exact Sciences - Universidade Federal de Viçosa (UFV) |
repository.mail.fl_str_mv |
|
_version_ |
1808845241491390464 |