Predicting the tensile behaviour of cast alloys by a pattern recognition analysis on experimental data
Autor(a) principal: | |
---|---|
Data de Publicação: | 2019 |
Outros Autores: | , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UFRGS |
Texto Completo: | http://hdl.handle.net/10183/196242 |
Resumo: | The ability to accurately predict the mechanical properties of metals is essential for their correct use in the design of structures and components. This is even more important in the presence of materials, such as metal cast alloys, whose properties can vary significantly in relation to their constituent elements, microstructures, process parameters or treatments. This study shows how a machine learning approach, based on pattern recognition analysis on experimental data, is able to o er acceptable precision predictions with respect to the main mechanical properties of metals, as in the case of ductile cast iron and compact graphite cast iron. The metallographic properties, such as graphite, ferrite and perlite content, extrapolated through macro indicators from micrographs by image analysis, are used as inputs for the machine learning algorithms, while the mechanical properties, such as yield strength, ultimate strength, ultimate strain and Young’s modulus, are derived as output. In particular, 3 di erent machine learning algorithms are trained starting from a dataset of 20–30 data for each material and the results o er high accuracy, often better than other predictive techniques. Concerns regarding the applicability of these predictive techniques in material design and product/process quality control are also discussed. |
id |
UFRGS-2_18f733cd6d487ec56c63c7bb3d020300 |
---|---|
oai_identifier_str |
oai:www.lume.ufrgs.br:10183/196242 |
network_acronym_str |
UFRGS-2 |
network_name_str |
Repositório Institucional da UFRGS |
repository_id_str |
|
spelling |
Fragassa, CristianoBabic, MatejBergmann, Carlos PerezMinak, Giangiacomo2019-06-25T02:39:50Z20192075-4701http://hdl.handle.net/10183/196242001094369The ability to accurately predict the mechanical properties of metals is essential for their correct use in the design of structures and components. This is even more important in the presence of materials, such as metal cast alloys, whose properties can vary significantly in relation to their constituent elements, microstructures, process parameters or treatments. This study shows how a machine learning approach, based on pattern recognition analysis on experimental data, is able to o er acceptable precision predictions with respect to the main mechanical properties of metals, as in the case of ductile cast iron and compact graphite cast iron. The metallographic properties, such as graphite, ferrite and perlite content, extrapolated through macro indicators from micrographs by image analysis, are used as inputs for the machine learning algorithms, while the mechanical properties, such as yield strength, ultimate strength, ultimate strain and Young’s modulus, are derived as output. In particular, 3 di erent machine learning algorithms are trained starting from a dataset of 20–30 data for each material and the results o er high accuracy, often better than other predictive techniques. Concerns regarding the applicability of these predictive techniques in material design and product/process quality control are also discussed.application/pdfengMetals. Basel, Suíça. Vol. 9, no. 5 (May 2019), Art. 557, 21 p.Propriedades dos materiaisAnálise de dadosFerro fundidoRedes neurais artificiaisMaterial properties predictionExperimental data analysisductile/spheroidal cast iron (SGI)compact graphite cast iron (CGI)Machine Learning (RF)Pattern recognitionRandom Forest (RF)Artificial Neural Network (NN)k-nearest neighbours (kNN)Predicting the tensile behaviour of cast alloys by a pattern recognition analysis on experimental dataEstrangeiroinfo:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da UFRGSinstname:Universidade Federal do Rio Grande do Sul (UFRGS)instacron:UFRGSTEXT001094369.pdf.txt001094369.pdf.txtExtracted Texttext/plain79915http://www.lume.ufrgs.br/bitstream/10183/196242/2/001094369.pdf.txta946aa9838899ffe6c5ee5fe692aa969MD52ORIGINAL001094369.pdfTexto completo (inglês)application/pdf2412526http://www.lume.ufrgs.br/bitstream/10183/196242/1/001094369.pdf3ced01d6d9f462dbd7390b9f09fea877MD5110183/1962422019-06-26 02:35:01.972711oai:www.lume.ufrgs.br:10183/196242Repositório de PublicaçõesPUBhttps://lume.ufrgs.br/oai/requestopendoar:2019-06-26T05:35:01Repositório Institucional da UFRGS - Universidade Federal do Rio Grande do Sul (UFRGS)false |
dc.title.pt_BR.fl_str_mv |
Predicting the tensile behaviour of cast alloys by a pattern recognition analysis on experimental data |
title |
Predicting the tensile behaviour of cast alloys by a pattern recognition analysis on experimental data |
spellingShingle |
Predicting the tensile behaviour of cast alloys by a pattern recognition analysis on experimental data Fragassa, Cristiano Propriedades dos materiais Análise de dados Ferro fundido Redes neurais artificiais Material properties prediction Experimental data analysis ductile/spheroidal cast iron (SGI) compact graphite cast iron (CGI) Machine Learning (RF) Pattern recognition Random Forest (RF) Artificial Neural Network (NN) k-nearest neighbours (kNN) |
title_short |
Predicting the tensile behaviour of cast alloys by a pattern recognition analysis on experimental data |
title_full |
Predicting the tensile behaviour of cast alloys by a pattern recognition analysis on experimental data |
title_fullStr |
Predicting the tensile behaviour of cast alloys by a pattern recognition analysis on experimental data |
title_full_unstemmed |
Predicting the tensile behaviour of cast alloys by a pattern recognition analysis on experimental data |
title_sort |
Predicting the tensile behaviour of cast alloys by a pattern recognition analysis on experimental data |
author |
Fragassa, Cristiano |
author_facet |
Fragassa, Cristiano Babic, Matej Bergmann, Carlos Perez Minak, Giangiacomo |
author_role |
author |
author2 |
Babic, Matej Bergmann, Carlos Perez Minak, Giangiacomo |
author2_role |
author author author |
dc.contributor.author.fl_str_mv |
Fragassa, Cristiano Babic, Matej Bergmann, Carlos Perez Minak, Giangiacomo |
dc.subject.por.fl_str_mv |
Propriedades dos materiais Análise de dados Ferro fundido Redes neurais artificiais |
topic |
Propriedades dos materiais Análise de dados Ferro fundido Redes neurais artificiais Material properties prediction Experimental data analysis ductile/spheroidal cast iron (SGI) compact graphite cast iron (CGI) Machine Learning (RF) Pattern recognition Random Forest (RF) Artificial Neural Network (NN) k-nearest neighbours (kNN) |
dc.subject.eng.fl_str_mv |
Material properties prediction Experimental data analysis ductile/spheroidal cast iron (SGI) compact graphite cast iron (CGI) Machine Learning (RF) Pattern recognition Random Forest (RF) Artificial Neural Network (NN) k-nearest neighbours (kNN) |
description |
The ability to accurately predict the mechanical properties of metals is essential for their correct use in the design of structures and components. This is even more important in the presence of materials, such as metal cast alloys, whose properties can vary significantly in relation to their constituent elements, microstructures, process parameters or treatments. This study shows how a machine learning approach, based on pattern recognition analysis on experimental data, is able to o er acceptable precision predictions with respect to the main mechanical properties of metals, as in the case of ductile cast iron and compact graphite cast iron. The metallographic properties, such as graphite, ferrite and perlite content, extrapolated through macro indicators from micrographs by image analysis, are used as inputs for the machine learning algorithms, while the mechanical properties, such as yield strength, ultimate strength, ultimate strain and Young’s modulus, are derived as output. In particular, 3 di erent machine learning algorithms are trained starting from a dataset of 20–30 data for each material and the results o er high accuracy, often better than other predictive techniques. Concerns regarding the applicability of these predictive techniques in material design and product/process quality control are also discussed. |
publishDate |
2019 |
dc.date.accessioned.fl_str_mv |
2019-06-25T02:39:50Z |
dc.date.issued.fl_str_mv |
2019 |
dc.type.driver.fl_str_mv |
Estrangeiro info:eu-repo/semantics/article |
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/10183/196242 |
dc.identifier.issn.pt_BR.fl_str_mv |
2075-4701 |
dc.identifier.nrb.pt_BR.fl_str_mv |
001094369 |
identifier_str_mv |
2075-4701 001094369 |
url |
http://hdl.handle.net/10183/196242 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.ispartof.pt_BR.fl_str_mv |
Metals. Basel, Suíça. Vol. 9, no. 5 (May 2019), Art. 557, 21 p. |
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/10183/196242/2/001094369.pdf.txt http://www.lume.ufrgs.br/bitstream/10183/196242/1/001094369.pdf |
bitstream.checksum.fl_str_mv |
a946aa9838899ffe6c5ee5fe692aa969 3ced01d6d9f462dbd7390b9f09fea877 |
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_ |
1801224969677438976 |