Machine learning for predicting fracture strain in sheet metal forming

Detalhes bibliográficos
Autor(a) principal: Marques, Armando E.
Data de Publicação: 2022
Outros Autores: Dib, Mario A., Khalfallah, Ali, Soares, Martinho S., Oliveira, Marta C., Fernandes, José V., Ribeiro, Bernardete M., Prates, Pedro A.
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10773/35358
Resumo: Machine learning models are built to predict the strain values for which edge cracking occurs in hole expansion tests. The samples from this test play the role of sheet metal components to be manufactured, in which edge cracking often occurs associated with a uniaxial tension stress state at the critical edges of components. For the construction of the models, a dataset was obtained experimentally for rolled ferritic carbon steel sheets of different qualities and thicknesses. Two types of tests were performed: tensile and hole expansion tests. In the tensile test, the yield stress, the tensile strength, the strain at maximum load and the elongation after fracture were determined in the rolling and transverse directions. In the hole expansion test, the strain for which edge cracking occurs, was determined. It is intended that the models can predict the strain at fracture in this test, based on the knowledge of the tensile test data. The machine learning algorithms used were Multilayer Perceptron, Gaussian Processes, Support Vector Regression and Random Forest. The traditional polynomial regression that fits a 2nd order polynomial function was also used for comparison. It is shown that machine learning-based predictive models outperform the traditional polynomial regression method; in particular, Gaussian Processes and Support Vector Regression were found to be the best machine learning algorithms that enable the most robust predictive models.
id RCAP_cef8ffd9a2cb2614bb94e7fa9610ce76
oai_identifier_str oai:ria.ua.pt:10773/35358
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Machine learning for predicting fracture strain in sheet metal formingSheet metal formingMachine learningPredictive regression modelsFracture strainMachine learning models are built to predict the strain values for which edge cracking occurs in hole expansion tests. The samples from this test play the role of sheet metal components to be manufactured, in which edge cracking often occurs associated with a uniaxial tension stress state at the critical edges of components. For the construction of the models, a dataset was obtained experimentally for rolled ferritic carbon steel sheets of different qualities and thicknesses. Two types of tests were performed: tensile and hole expansion tests. In the tensile test, the yield stress, the tensile strength, the strain at maximum load and the elongation after fracture were determined in the rolling and transverse directions. In the hole expansion test, the strain for which edge cracking occurs, was determined. It is intended that the models can predict the strain at fracture in this test, based on the knowledge of the tensile test data. The machine learning algorithms used were Multilayer Perceptron, Gaussian Processes, Support Vector Regression and Random Forest. The traditional polynomial regression that fits a 2nd order polynomial function was also used for comparison. It is shown that machine learning-based predictive models outperform the traditional polynomial regression method; in particular, Gaussian Processes and Support Vector Regression were found to be the best machine learning algorithms that enable the most robust predictive models.MDPI2022-11-29T16:12:28Z2022-10-24T00:00:00Z2022-10-24info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10773/35358eng2075-470110.3390/met12111799Marques, Armando E.Dib, Mario A.Khalfallah, AliSoares, Martinho S.Oliveira, Marta C.Fernandes, José V.Ribeiro, Bernardete M.Prates, Pedro A.info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-02-22T12:08:00Zoai:ria.ua.pt:10773/35358Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:06:22.432499Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv Machine learning for predicting fracture strain in sheet metal forming
title Machine learning for predicting fracture strain in sheet metal forming
spellingShingle Machine learning for predicting fracture strain in sheet metal forming
Marques, Armando E.
Sheet metal forming
Machine learning
Predictive regression models
Fracture strain
title_short Machine learning for predicting fracture strain in sheet metal forming
title_full Machine learning for predicting fracture strain in sheet metal forming
title_fullStr Machine learning for predicting fracture strain in sheet metal forming
title_full_unstemmed Machine learning for predicting fracture strain in sheet metal forming
title_sort Machine learning for predicting fracture strain in sheet metal forming
author Marques, Armando E.
author_facet Marques, Armando E.
Dib, Mario A.
Khalfallah, Ali
Soares, Martinho S.
Oliveira, Marta C.
Fernandes, José V.
Ribeiro, Bernardete M.
Prates, Pedro A.
author_role author
author2 Dib, Mario A.
Khalfallah, Ali
Soares, Martinho S.
Oliveira, Marta C.
Fernandes, José V.
Ribeiro, Bernardete M.
Prates, Pedro A.
author2_role author
author
author
author
author
author
author
dc.contributor.author.fl_str_mv Marques, Armando E.
Dib, Mario A.
Khalfallah, Ali
Soares, Martinho S.
Oliveira, Marta C.
Fernandes, José V.
Ribeiro, Bernardete M.
Prates, Pedro A.
dc.subject.por.fl_str_mv Sheet metal forming
Machine learning
Predictive regression models
Fracture strain
topic Sheet metal forming
Machine learning
Predictive regression models
Fracture strain
description Machine learning models are built to predict the strain values for which edge cracking occurs in hole expansion tests. The samples from this test play the role of sheet metal components to be manufactured, in which edge cracking often occurs associated with a uniaxial tension stress state at the critical edges of components. For the construction of the models, a dataset was obtained experimentally for rolled ferritic carbon steel sheets of different qualities and thicknesses. Two types of tests were performed: tensile and hole expansion tests. In the tensile test, the yield stress, the tensile strength, the strain at maximum load and the elongation after fracture were determined in the rolling and transverse directions. In the hole expansion test, the strain for which edge cracking occurs, was determined. It is intended that the models can predict the strain at fracture in this test, based on the knowledge of the tensile test data. The machine learning algorithms used were Multilayer Perceptron, Gaussian Processes, Support Vector Regression and Random Forest. The traditional polynomial regression that fits a 2nd order polynomial function was also used for comparison. It is shown that machine learning-based predictive models outperform the traditional polynomial regression method; in particular, Gaussian Processes and Support Vector Regression were found to be the best machine learning algorithms that enable the most robust predictive models.
publishDate 2022
dc.date.none.fl_str_mv 2022-11-29T16:12:28Z
2022-10-24T00:00:00Z
2022-10-24
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10773/35358
url http://hdl.handle.net/10773/35358
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 2075-4701
10.3390/met12111799
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv MDPI
publisher.none.fl_str_mv MDPI
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799137718920282112