Bead geometry prediction in pulsed GMAW welding : a comparative study on the performance of artificial neural network and regression models
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Outros Autores: | , , |
Tipo de documento: | Artigo |
Idioma: | por |
Título da fonte: | Repositório Institucional da UFRGS |
Texto Completo: | http://hdl.handle.net/10183/255611 |
Resumo: | Weld bead geometry is a critical factor for determining the quality of welded joints, for this the welding process input parameters play a key role. In this study, the relationships between welding process variables and the size of the weld bead produced by pulsed GMAW process were investigated by a neural network trained with Bayesian-Regulation Back Propagation algorithm and a second degree regression models. A series of experiments were carried out by applying a Box-Behnken design of experiment. The results showed that both models can predict well the bead geometry. However, the neural network model had a slightly better performance than the second-order regression model. Both models can be used for further analyses and using them may surmount or reduce the need of experimental procedures especially in thermal analysis validations of welding finite element modelling. |
id |
UFRGS-2_10c87f94930eaad4beb9c6892d20367d |
---|---|
oai_identifier_str |
oai:www.lume.ufrgs.br:10183/255611 |
network_acronym_str |
UFRGS-2 |
network_name_str |
Repositório Institucional da UFRGS |
repository_id_str |
|
spelling |
Giarollo, Daniela FátimaHackenhaar, WilliamMazzaferro, Cintia Cristiane PetryMazzaferro, Jose Antonio Esmerio2023-03-11T03:30:00Z20220104-9224http://hdl.handle.net/10183/255611001163102Weld bead geometry is a critical factor for determining the quality of welded joints, for this the welding process input parameters play a key role. In this study, the relationships between welding process variables and the size of the weld bead produced by pulsed GMAW process were investigated by a neural network trained with Bayesian-Regulation Back Propagation algorithm and a second degree regression models. A series of experiments were carried out by applying a Box-Behnken design of experiment. The results showed that both models can predict well the bead geometry. However, the neural network model had a slightly better performance than the second-order regression model. Both models can be used for further analyses and using them may surmount or reduce the need of experimental procedures especially in thermal analysis validations of welding finite element modelling.application/pdfporSoldagem & inspeção. São Paulo, SP. Vol. 27 (2022), e2722Soldagem MIG/MAGRedes neurais artificiaisModelos de regressãoArtificial neural networkRegression modelPulsed GMAWBead geometry prediction in pulsed GMAW welding : a comparative study on the performance of artificial neural network and regression modelsinfo:eu-repo/semantics/articleinfo:eu-repo/semantics/otherinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da UFRGSinstname:Universidade Federal do Rio Grande do Sul (UFRGS)instacron:UFRGSTEXT001163102.pdf.txt001163102.pdf.txtExtracted Texttext/plain40518http://www.lume.ufrgs.br/bitstream/10183/255611/2/001163102.pdf.txt424b21e33a69e873443736c70091376eMD52ORIGINAL001163102.pdfTexto completo (inglês)application/pdf1142745http://www.lume.ufrgs.br/bitstream/10183/255611/1/001163102.pdf681126f7dedfe9b4f9ed4af7847dd825MD5110183/2556112023-11-30 04:23:38.941641oai:www.lume.ufrgs.br:10183/255611Repositório de PublicaçõesPUBhttps://lume.ufrgs.br/oai/requestopendoar:2023-11-30T06:23:38Repositório Institucional da UFRGS - Universidade Federal do Rio Grande do Sul (UFRGS)false |
dc.title.pt_BR.fl_str_mv |
Bead geometry prediction in pulsed GMAW welding : a comparative study on the performance of artificial neural network and regression models |
title |
Bead geometry prediction in pulsed GMAW welding : a comparative study on the performance of artificial neural network and regression models |
spellingShingle |
Bead geometry prediction in pulsed GMAW welding : a comparative study on the performance of artificial neural network and regression models Giarollo, Daniela Fátima Soldagem MIG/MAG Redes neurais artificiais Modelos de regressão Artificial neural network Regression model Pulsed GMAW |
title_short |
Bead geometry prediction in pulsed GMAW welding : a comparative study on the performance of artificial neural network and regression models |
title_full |
Bead geometry prediction in pulsed GMAW welding : a comparative study on the performance of artificial neural network and regression models |
title_fullStr |
Bead geometry prediction in pulsed GMAW welding : a comparative study on the performance of artificial neural network and regression models |
title_full_unstemmed |
Bead geometry prediction in pulsed GMAW welding : a comparative study on the performance of artificial neural network and regression models |
title_sort |
Bead geometry prediction in pulsed GMAW welding : a comparative study on the performance of artificial neural network and regression models |
author |
Giarollo, Daniela Fátima |
author_facet |
Giarollo, Daniela Fátima Hackenhaar, William Mazzaferro, Cintia Cristiane Petry Mazzaferro, Jose Antonio Esmerio |
author_role |
author |
author2 |
Hackenhaar, William Mazzaferro, Cintia Cristiane Petry Mazzaferro, Jose Antonio Esmerio |
author2_role |
author author author |
dc.contributor.author.fl_str_mv |
Giarollo, Daniela Fátima Hackenhaar, William Mazzaferro, Cintia Cristiane Petry Mazzaferro, Jose Antonio Esmerio |
dc.subject.por.fl_str_mv |
Soldagem MIG/MAG Redes neurais artificiais Modelos de regressão |
topic |
Soldagem MIG/MAG Redes neurais artificiais Modelos de regressão Artificial neural network Regression model Pulsed GMAW |
dc.subject.eng.fl_str_mv |
Artificial neural network Regression model Pulsed GMAW |
description |
Weld bead geometry is a critical factor for determining the quality of welded joints, for this the welding process input parameters play a key role. In this study, the relationships between welding process variables and the size of the weld bead produced by pulsed GMAW process were investigated by a neural network trained with Bayesian-Regulation Back Propagation algorithm and a second degree regression models. A series of experiments were carried out by applying a Box-Behnken design of experiment. The results showed that both models can predict well the bead geometry. However, the neural network model had a slightly better performance than the second-order regression model. Both models can be used for further analyses and using them may surmount or reduce the need of experimental procedures especially in thermal analysis validations of welding finite element modelling. |
publishDate |
2022 |
dc.date.issued.fl_str_mv |
2022 |
dc.date.accessioned.fl_str_mv |
2023-03-11T03:30:00Z |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/other |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10183/255611 |
dc.identifier.issn.pt_BR.fl_str_mv |
0104-9224 |
dc.identifier.nrb.pt_BR.fl_str_mv |
001163102 |
identifier_str_mv |
0104-9224 001163102 |
url |
http://hdl.handle.net/10183/255611 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.ispartof.pt_BR.fl_str_mv |
Soldagem & inspeção. São Paulo, SP. Vol. 27 (2022), e2722 |
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.source.none.fl_str_mv |
reponame:Repositório Institucional da UFRGS instname:Universidade Federal do Rio Grande do Sul (UFRGS) instacron:UFRGS |
instname_str |
Universidade Federal do Rio Grande do Sul (UFRGS) |
instacron_str |
UFRGS |
institution |
UFRGS |
reponame_str |
Repositório Institucional da UFRGS |
collection |
Repositório Institucional da UFRGS |
bitstream.url.fl_str_mv |
http://www.lume.ufrgs.br/bitstream/10183/255611/2/001163102.pdf.txt http://www.lume.ufrgs.br/bitstream/10183/255611/1/001163102.pdf |
bitstream.checksum.fl_str_mv |
424b21e33a69e873443736c70091376e 681126f7dedfe9b4f9ed4af7847dd825 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFRGS - Universidade Federal do Rio Grande do Sul (UFRGS) |
repository.mail.fl_str_mv |
|
_version_ |
1801225083157479424 |