Mild steel GMA welds microstructural analysis and estimation using sensor fusion and neural network modeling
שמור ב:
| מחבר ראשי: | |
|---|---|
| Publication Date: | 2021 |
| מחברים אחרים: | , , , , |
| פורמט: | Article |
| שפה: | eng |
| Source: | Repositório Institucional da UnB |
| Download full: | https://repositorio.unb.br/handle/10482/42003 https://doi.org/10.3390/s21165459 https://orcid.org/ 0000-0001-6659-441X https://orcid.org/ 0000-0002-7426-0687 https://orcid.org/ 0000-0002-0361-0555 |
סיכום: | This study aims at evaluating the efficiency of sensor fusion, based on neural networks, to estimate the microstructural characteristics of both the weld bead and base material in GMAW processes. The weld beads of AWS ER70S-6 wire were deposited on SAE 1020 steel plates varying welding voltage, welding speed, and wire-feed speed. The thermal behavior of the material during the process execution was analyzed using thermographic information gathered by an infrared camera. The microstructure was characterized by optical (confocal) microscopy, scanning electron microscopy, and X-ray Diffraction tests. Finally, models for estimating the weld bead microstructure were developed by fusing all the information through a neural network modeling approach. A R value of 0.99472 was observed for modelling all zones of microstructure in the same ANN using Bayesian Regularization with 17 and 15 neurons in the first and second hidden layers, respectively, with 4 training runs (which was the lowest R value among all tested configurations). The results obtained prove that RNAs can be used to assist the project of welded joints as they make it possible to estimate the extension of HAZ. |
| _version_ | 1871442318299496448 |
|---|---|
| author | Caio, Leandro Bruno Alves |
| author2 | Silva, Alysson Martins Almeida Alvarez Bestard, Guillermo Vieira, Lais Soares Carvalho, Guilherme Caribé de Alfaro, Sadek Crisóstomo Absi |
| author2_role | author author author author author |
| author_browse | Alfaro, Sadek Crisóstomo Absi Alvarez Bestard, Guillermo Caio, Leandro Bruno Alves Carvalho, Guilherme Caribé de Silva, Alysson Martins Almeida Vieira, Lais Soares |
| author_facet | Caio, Leandro Bruno Alves Silva, Alysson Martins Almeida Alvarez Bestard, Guillermo Vieira, Lais Soares Carvalho, Guilherme Caribé de Alfaro, Sadek Crisóstomo Absi |
| author_role | author |
| bitstream.checksum.fl_str_mv | efc10544b3f2882e278928d9b08090a6 ba54f8d1c5f5ec8df897ad678916c701 |
| bitstream.checksumAlgorithm.fl_str_mv | MD5 MD5 |
| bitstream.url.fl_str_mv | http://repositorio2.unb.br/jspui/bitstream/10482/42003/1/ARTIGO_MildSteelGMA.pdf http://repositorio2.unb.br/jspui/bitstream/10482/42003/2/license.txt |
| collection | Repositório Institucional da UnB |
| dc.contributor.author.fl_str_mv | Caio, Leandro Bruno Alves Silva, Alysson Martins Almeida Alvarez Bestard, Guillermo Vieira, Lais Soares Carvalho, Guilherme Caribé de Alfaro, Sadek Crisóstomo Absi |
| dc.date.accessioned.fl_str_mv | 2021-09-02T10:56:33Z |
| dc.date.available.fl_str_mv | 2021-09-02T10:56:33Z |
| dc.date.issued.fl_str_mv | 2021-08-13 |
| dc.identifier.citation.fl_str_mv | CAIO, Leandro Bruno Alves et al. Mild steel GMA welds microstructural analysis and estimation using sensor fusion and neural network modeling. Sensors, v. 21, n. 16, 5459, 2021. DOI: https://doi.org/10.3390/s21165459. Disponível em: https://www.mdpi.com/1424-8220/21/16/5459. Acesso em: 02 set. 2021. |
| dc.identifier.doi.pt_BR.fl_str_mv | https://doi.org/10.3390/s21165459 |
| dc.identifier.orcid.pt_BR.fl_str_mv | https://orcid.org/ 0000-0001-6659-441X https://orcid.org/ 0000-0002-7426-0687 https://orcid.org/ 0000-0002-0361-0555 |
| dc.identifier.uri.fl_str_mv | https://repositorio.unb.br/handle/10482/42003 |
| dc.language.iso.fl_str_mv | eng |
| dc.publisher.none.fl_str_mv | MDPI |
| dc.rights.driver.fl_str_mv | info:eu-repo/semantics/openAccess |
| dc.source.none.fl_str_mv | reponame:Repositório Institucional da UnB instname:Universidade de Brasília (UnB) instacron:UNB |
| dc.subject.keyword.pt_BR.fl_str_mv | GMAW Estimativa de microestrutura Redes neurais Fusão de sensores |
| dc.title.pt_BR.fl_str_mv | Mild steel GMA welds microstructural analysis and estimation using sensor fusion and neural network modeling |
| dc.type.driver.fl_str_mv | info:eu-repo/semantics/article |
| dc.type.status.fl_str_mv | info:eu-repo/semantics/publishedVersion |
| description | This study aims at evaluating the efficiency of sensor fusion, based on neural networks, to estimate the microstructural characteristics of both the weld bead and base material in GMAW processes. The weld beads of AWS ER70S-6 wire were deposited on SAE 1020 steel plates varying welding voltage, welding speed, and wire-feed speed. The thermal behavior of the material during the process execution was analyzed using thermographic information gathered by an infrared camera. The microstructure was characterized by optical (confocal) microscopy, scanning electron microscopy, and X-ray Diffraction tests. Finally, models for estimating the weld bead microstructure were developed by fusing all the information through a neural network modeling approach. A R value of 0.99472 was observed for modelling all zones of microstructure in the same ANN using Bayesian Regularization with 17 and 15 neurons in the first and second hidden layers, respectively, with 4 training runs (which was the lowest R value among all tested configurations). The results obtained prove that RNAs can be used to assist the project of welded joints as they make it possible to estimate the extension of HAZ. |
| eu_rights_str_mv | openAccess |
| format | article |
| id | UNB_5568ef3b2d083f41fe35d3a83a45ea13 |
| identifier_str_mv | CAIO, Leandro Bruno Alves et al. Mild steel GMA welds microstructural analysis and estimation using sensor fusion and neural network modeling. Sensors, v. 21, n. 16, 5459, 2021. DOI: https://doi.org/10.3390/s21165459. Disponível em: https://www.mdpi.com/1424-8220/21/16/5459. Acesso em: 02 set. 2021. |
| instacron_str | UNB |
| institution | UNB |
| instname_str | Universidade de Brasília (UnB) |
| language | eng |
| network_acronym_str | UNB |
| network_name_str | Repositório Institucional da UnB |
| oai_identifier_str | oai:repositorio.unb.br:10482/42003 |
| publishDate | 2021 |
| publishDateSort | 2021 |
| publisher.none.fl_str_mv | MDPI |
| reponame_str | Repositório Institucional da UnB |
| repository.mail.fl_str_mv | repositorio@unb.br |
| repository.name.fl_str_mv | Repositório Institucional da UnB - Universidade de Brasília (UnB) |
| repository_id_str | |
| spelling | Caio, Leandro Bruno AlvesSilva, Alysson Martins AlmeidaAlvarez Bestard, GuillermoVieira, Lais SoaresCarvalho, Guilherme Caribé deAlfaro, Sadek Crisóstomo Absi2021-09-02T10:56:33Z2021-09-02T10:56:33Z2021-08-13CAIO, Leandro Bruno Alves et al. Mild steel GMA welds microstructural analysis and estimation using sensor fusion and neural network modeling. Sensors, v. 21, n. 16, 5459, 2021. DOI: https://doi.org/10.3390/s21165459. Disponível em: https://www.mdpi.com/1424-8220/21/16/5459. Acesso em: 02 set. 2021.https://repositorio.unb.br/handle/10482/42003https://doi.org/10.3390/s21165459https://orcid.org/ 0000-0001-6659-441Xhttps://orcid.org/ 0000-0002-7426-0687https://orcid.org/ 0000-0002-0361-0555MDPICopyright: © 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https:// creativecommons.org/licenses/by/ 4.0/).info:eu-repo/semantics/openAccessMild steel GMA welds microstructural analysis and estimation using sensor fusion and neural network modelinginfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleGMAWEstimativa de microestruturaRedes neuraisFusão de sensoresThis study aims at evaluating the efficiency of sensor fusion, based on neural networks, to estimate the microstructural characteristics of both the weld bead and base material in GMAW processes. The weld beads of AWS ER70S-6 wire were deposited on SAE 1020 steel plates varying welding voltage, welding speed, and wire-feed speed. The thermal behavior of the material during the process execution was analyzed using thermographic information gathered by an infrared camera. The microstructure was characterized by optical (confocal) microscopy, scanning electron microscopy, and X-ray Diffraction tests. Finally, models for estimating the weld bead microstructure were developed by fusing all the information through a neural network modeling approach. A R value of 0.99472 was observed for modelling all zones of microstructure in the same ANN using Bayesian Regularization with 17 and 15 neurons in the first and second hidden layers, respectively, with 4 training runs (which was the lowest R value among all tested configurations). The results obtained prove that RNAs can be used to assist the project of welded joints as they make it possible to estimate the extension of HAZ.engreponame:Repositório Institucional da UnBinstname:Universidade de Brasília (UnB)instacron:UNBORIGINALARTIGO_MildSteelGMA.pdfARTIGO_MildSteelGMA.pdfapplication/pdf10807263http://repositorio2.unb.br/jspui/bitstream/10482/42003/1/ARTIGO_MildSteelGMA.pdfefc10544b3f2882e278928d9b08090a6MD51open accessLICENSElicense.txtlicense.txttext/plain163http://repositorio2.unb.br/jspui/bitstream/10482/42003/2/license.txtba54f8d1c5f5ec8df897ad678916c701MD52open access10482/420032023-05-24 20:21:42.571open accessoai:repositorio.unb.br:10482/42003U3VibWlzc8OjbyBlZmV0aXZhZGEgcG9yIGludGVncmFudGUgZGEgZXF1aXBlIGRvIFJlcG9zaXTDs3JpbyBJbnN0aXR1Y2lvbmFsIGRhIFVuQiBkZSBhY29yZG8gY29tIGxpY2Vuw6dhIGNvbmNlZGlkYSBwZWxvIGF1dG9yIGUvb3UgZGV0ZW50b3IgZG9zIGRpcmVpdG9zIGF1dG9yYWlzLg==Repositório InstitucionalPUBhttps://repositorio.unb.br/oai/requestrepositorio@unb.bropendoar:2023-05-24T23:21:42Repositório Institucional da UnB - Universidade de Brasília (UnB) |
| spellingShingle | Mild steel GMA welds microstructural analysis and estimation using sensor fusion and neural network modeling Caio, Leandro Bruno Alves GMAW Estimativa de microestrutura Redes neurais Fusão de sensores |
| status_str | publishedVersion |
| title | Mild steel GMA welds microstructural analysis and estimation using sensor fusion and neural network modeling |
| title_full | Mild steel GMA welds microstructural analysis and estimation using sensor fusion and neural network modeling |
| title_fullStr | Mild steel GMA welds microstructural analysis and estimation using sensor fusion and neural network modeling |
| title_full_unstemmed | Mild steel GMA welds microstructural analysis and estimation using sensor fusion and neural network modeling |
| title_short | Mild steel GMA welds microstructural analysis and estimation using sensor fusion and neural network modeling |
| title_sort | Mild steel GMA welds microstructural analysis and estimation using sensor fusion and neural network modeling |
| topic | GMAW Estimativa de microestrutura Redes neurais Fusão de sensores |
| url | https://repositorio.unb.br/handle/10482/42003 https://doi.org/10.3390/s21165459 https://orcid.org/ 0000-0001-6659-441X https://orcid.org/ 0000-0002-7426-0687 https://orcid.org/ 0000-0002-0361-0555 |