Publicação

A comparison of machine learning approaches for predicting in-car display production quality

Ver documento

Detalhes bibliográficos
Resumo:In this paper, we explore eight Machine Learning (ML) approaches (binary and one-class) to predict the quality of in-car displays, measured using Black Uniformity (BU) tests. During production, the industrial manufacturer routinely executes intermediate assembly (screwing and gluing) and functional tests that can signal potential causes for abnormal display units. By using these intermediate tests as inputs, the ML model can be used to identify the unknown relationships between intermediate and BU tests, helping to detect failure causes. In particular, we compare two sets of input variables (A and B) with hundreds of intermediate quality measures related with assembly and functional tests. Using recently collected industrial data, regarding around 147 thousand in-car display records, we performed two evaluation procedures, using first a time ordered train-test split and then a more robust rolling windows. Overall, the best predictive results (92%) were obtained using the full set of inputs (B) and an Automated ML (AutoML) Stacked Ensemble (ASE). We further demonstrate the value of the selected ASE model, by selecting distinct decision threshold scenarios and by using a Sensitivity Analysis (SA) eXplainable Artificial Intelligence (XAI) method.
Autores principais:Matos, Luís Miguel
Outros Autores:Domingues, André; Moreira, Guilherme; Cortez, Paulo; Pilastri, André Luiz
Assunto:Anomaly Detection One-class learning Automated Machine Learning Deep Learning Explainable artificial intelligence Supervised Learning
Ano:2021
País:Portugal
Tipo de documento:comunicação em conferência
Tipo de acesso:acesso aberto
Instituição associada:Universidade do Minho
Idioma:inglês
Origem:RepositóriUM - Universidade do Minho
_version_ 1866877395315720192
author Matos, Luís Miguel
author2 Domingues, André
Moreira, Guilherme
Cortez, Paulo
Pilastri, André Luiz
author2_role author
author
author
author
author_facet Matos, Luís Miguel
Domingues, André
Moreira, Guilherme
Cortez, Paulo
Pilastri, André Luiz
author_role author
contributor_name_str_mv Universidade do Minho
country_str PT
creators_json_txt [{\"Person.name\":\"Matos, Luís Miguel\"},{\"Person.name\":\"Domingues, André\"},{\"Person.name\":\"Moreira, Guilherme\"},{\"Person.name\":\"Cortez, Paulo\"},{\"Person.name\":\"Pilastri, André Luiz\"}]
datacite.contributors.contributor.contributorName.fl_str_mv Universidade do Minho
datacite.creators.creator.creatorName.fl_str_mv Matos, Luís Miguel
Domingues, André
Moreira, Guilherme
Cortez, Paulo
Pilastri, André Luiz
datacite.date.Accepted.fl_str_mv 2021-01-01T00:00:00Z
datacite.date.available.fl_str_mv 2021-11-26T09:35:08Z
datacite.date.embargoed.fl_str_mv 2021-11-26T09:35:08Z
datacite.rights.fl_str_mv http://purl.org/coar/access_right/c_abf2
datacite.subjects.subject.fl_str_mv Anomaly Detection
One-class learning
Automated Machine Learning
Deep Learning
Explainable artificial intelligence
Supervised Learning
datacite.titles.title.fl_str_mv A comparison of machine learning approaches for predicting in-car display production quality
dc.contributor.none.fl_str_mv Universidade do Minho
dc.creator.none.fl_str_mv Matos, Luís Miguel
Domingues, André
Moreira, Guilherme
Cortez, Paulo
Pilastri, André Luiz
dc.date.Accepted.fl_str_mv 2021-01-01T00:00:00Z
dc.date.available.fl_str_mv 2021-11-26T09:35:08Z
dc.date.embargoed.fl_str_mv 2021-11-26T09:35:08Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv https://hdl.handle.net/1822/74781
dc.language.none.fl_str_mv eng
dc.publisher.none.fl_str_mv Springer
dc.rights.cclincense.fl_str_mv http://creativecommons.org/licenses/by/4.0/
dc.rights.none.fl_str_mv http://purl.org/coar/access_right/c_abf2
dc.rights.rights.copyright.fl_str_mv openAccess
dc.subject.none.fl_str_mv Anomaly Detection
One-class learning
Automated Machine Learning
Deep Learning
Explainable artificial intelligence
Supervised Learning
dc.title.fl_str_mv A comparison of machine learning approaches for predicting in-car display production quality
dc.type.none.fl_str_mv http://purl.org/coar/resource_type/c_5794
description In this paper, we explore eight Machine Learning (ML) approaches (binary and one-class) to predict the quality of in-car displays, measured using Black Uniformity (BU) tests. During production, the industrial manufacturer routinely executes intermediate assembly (screwing and gluing) and functional tests that can signal potential causes for abnormal display units. By using these intermediate tests as inputs, the ML model can be used to identify the unknown relationships between intermediate and BU tests, helping to detect failure causes. In particular, we compare two sets of input variables (A and B) with hundreds of intermediate quality measures related with assembly and functional tests. Using recently collected industrial data, regarding around 147 thousand in-car display records, we performed two evaluation procedures, using first a time ordered train-test split and then a more robust rolling windows. Overall, the best predictive results (92%) were obtained using the full set of inputs (B) and an Automated ML (AutoML) Stacked Ensemble (ASE). We further demonstrate the value of the selected ASE model, by selecting distinct decision threshold scenarios and by using a Sensitivity Analysis (SA) eXplainable Artificial Intelligence (XAI) method.
dirty 0
eu_rights_str_mv openAccess
format conferencePaper
fulltext.url.fl_str_mv https://prod-dspace.uminho.pt/bitstreams/dc61b962-2f8e-4b33-ba02-1a3177c371fc/download
id rum_928fdff3a36c0efbc1bf05b38b4e8cb8
identifier.url.fl_str_mv https://hdl.handle.net/1822/74781
instacron_str repositorium
institution Universidade do Minho
instname_str Universidade do Minho
language eng
network_acronym_str rum
network_name_str RepositóriUM - Universidade do Minho
oai_identifier_str oai:repositorium.uminho.pt:1822/74781
organization_str_mv urn:organizationAcronym:repositorium
person_str_mv Matos, Luís Miguel
Domingues, André
Moreira, Guilherme
Cortez, Paulo
Pilastri, André Luiz
publishDate 2021
publisher.none.fl_str_mv Springer
reponame_str RepositóriUM - Universidade do Minho
repository_id_str urn:repositoryAcronym:rum
service_str_mv urn:repositoryAcronym:rum
spelling engSpringerporIn this paper, we explore eight Machine Learning (ML) approaches (binary and one-class) to predict the quality of in-car displays, measured using Black Uniformity (BU) tests. During production, the industrial manufacturer routinely executes intermediate assembly (screwing and gluing) and functional tests that can signal potential causes for abnormal display units. By using these intermediate tests as inputs, the ML model can be used to identify the unknown relationships between intermediate and BU tests, helping to detect failure causes. In particular, we compare two sets of input variables (A and B) with hundreds of intermediate quality measures related with assembly and functional tests. Using recently collected industrial data, regarding around 147 thousand in-car display records, we performed two evaluation procedures, using first a time ordered train-test split and then a more robust rolling windows. Overall, the best predictive results (92%) were obtained using the full set of inputs (B) and an Automated ML (AutoML) Stacked Ensemble (ASE). We further demonstrate the value of the selected ASE model, by selecting distinct decision threshold scenarios and by using a Sensitivity Analysis (SA) eXplainable Artificial Intelligence (XAI) method.application/pdfporA comparison of machine learning approaches for predicting in-car display production qualityMatos, Luís MiguelDomingues, AndréMoreira, GuilhermeCortez, PauloPilastri, André LuizHostingInstitutionOrganizationalUniversidade do Minhoe-mailmailto:repositorium@usdb.uminho.ptrepositorium@usdb.uminho.ptISBNIsPartOf978-3-030-91607-7ISSNIsPartOf0302-9743DOIIsPartOf10.1007/978-3-030-91608-4_12021-11-26T09:35:08Z20212021-01-01T00:00:00ZHandlehttps://hdl.handle.net/1822/74781http://purl.org/coar/access_right/c_abf2open accessAnomaly DetectionOne-class learningAutomated Machine LearningDeep LearningExplainable artificial intelligenceSupervised Learning1044296 bytesother research producthttp://purl.org/coar/resource_type/c_5794conference paper2021http://creativecommons.org/licenses/by/4.0/openAccesshttp://purl.org/coar/access_right/c_abf2application/pdffulltexthttps://prod-dspace.uminho.pt/bitstreams/dc61b962-2f8e-4b33-ba02-1a3177c371fc/download
spellingShingle A comparison of machine learning approaches for predicting in-car display production quality
Matos, Luís Miguel
Anomaly Detection
One-class learning
Automated Machine Learning
Deep Learning
Explainable artificial intelligence
Supervised Learning
status SINGLETON
subject.fl_str_mv Anomaly Detection
One-class learning
Automated Machine Learning
Deep Learning
Explainable artificial intelligence
Supervised Learning
title A comparison of machine learning approaches for predicting in-car display production quality
title_full A comparison of machine learning approaches for predicting in-car display production quality
title_fullStr A comparison of machine learning approaches for predicting in-car display production quality
title_full_unstemmed A comparison of machine learning approaches for predicting in-car display production quality
title_short A comparison of machine learning approaches for predicting in-car display production quality
title_sort A comparison of machine learning approaches for predicting in-car display production quality
topic Anomaly Detection
One-class learning
Automated Machine Learning
Deep Learning
Explainable artificial intelligence
Supervised Learning
topic_facet Anomaly Detection
One-class learning
Automated Machine Learning
Deep Learning
Explainable artificial intelligence
Supervised Learning
url https://hdl.handle.net/1822/74781
visible 1