Generative adversarial networks for data augmentation in structural adhesive inspection

Detalhes bibliográficos
Autor(a) principal: Peres, Ricardo Silva
Data de Publicação: 2021
Outros Autores: Azevedo, Miguel, Araújo, Sara Oleiro, Guedes, Magno, Miranda, Fábio, Barata, José
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10362/133127
Resumo: UIDB/- 00066/2020 POCI-01-0247-FEDER-034072
id RCAP_bd23c810bdab30b2084eb2f3f9818e25
oai_identifier_str oai:run.unl.pt:10362/133127
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Generative adversarial networks for data augmentation in structural adhesive inspectionData augmentationDeep learningIndustry 4.0Quality controlStructural adhesiveMaterials Science(all)InstrumentationEngineering(all)Process Chemistry and TechnologyComputer Science ApplicationsFluid Flow and Transfer ProcessesUIDB/- 00066/2020 POCI-01-0247-FEDER-034072The technological advances brought forth by the Industry 4.0 paradigm have renewed the disruptive potential of artificial intelligence in the manufacturing sector, building the data-driven era on top of concepts such as Cyber-Physical Systems and the Internet of Things. However, data availability remains a major challenge for the success of these solutions, particularly concerning those based on deep learning approaches. Specifically in the quality inspection of structural adhesive applications, found commonly in the automotive domain, defect data with sufficient variety, volume and quality is generally costly, time-consuming and inefficient to obtain, jeopardizing the viability of such approaches due to data scarcity. To mitigate this, we propose a novel approach to generate synthetic training data for this application, leveraging recent breakthroughs in training generative adversarial networks with limited data to improve the performance of automated inspection methods based on deep learning, especially for imbalanced datasets. Preliminary results in a real automotive pilot cell show promise in this direction, with the approach being able to generate realistic adhesive bead images and consequently object detection models showing improved mean average precision at different thresholds when trained on the augmented dataset. For reproducibility purposes, the model weights, configurations and data encompassed in this study are made publicly available.DEE - Departamento de Engenharia Electrotécnica e de ComputadoresUNINOVA-Instituto de Desenvolvimento de Novas TecnologiasCTS - Centro de Tecnologia e SistemasDEE2010-C2 Robótica e Manufactura Integrada por ComputadorRUNPeres, Ricardo SilvaAzevedo, MiguelAraújo, Sara OleiroGuedes, MagnoMiranda, FábioBarata, José2022-02-17T23:19:32Z2021-04-012021-04-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10362/133127eng2076-3417PURE: 36679070https://doi.org/10.3390/app11073086info: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:RCAAP2024-05-22T17:59:33Zoai:run.unl.pt:10362/133127Portal AgregadorONGhttps://www.rcaap.pt/oai/openairemluisa.alvim@gmail.comopendoar:71602024-05-22T17:59:33Repositório 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 Generative adversarial networks for data augmentation in structural adhesive inspection
title Generative adversarial networks for data augmentation in structural adhesive inspection
spellingShingle Generative adversarial networks for data augmentation in structural adhesive inspection
Peres, Ricardo Silva
Data augmentation
Deep learning
Industry 4.0
Quality control
Structural adhesive
Materials Science(all)
Instrumentation
Engineering(all)
Process Chemistry and Technology
Computer Science Applications
Fluid Flow and Transfer Processes
title_short Generative adversarial networks for data augmentation in structural adhesive inspection
title_full Generative adversarial networks for data augmentation in structural adhesive inspection
title_fullStr Generative adversarial networks for data augmentation in structural adhesive inspection
title_full_unstemmed Generative adversarial networks for data augmentation in structural adhesive inspection
title_sort Generative adversarial networks for data augmentation in structural adhesive inspection
author Peres, Ricardo Silva
author_facet Peres, Ricardo Silva
Azevedo, Miguel
Araújo, Sara Oleiro
Guedes, Magno
Miranda, Fábio
Barata, José
author_role author
author2 Azevedo, Miguel
Araújo, Sara Oleiro
Guedes, Magno
Miranda, Fábio
Barata, José
author2_role author
author
author
author
author
dc.contributor.none.fl_str_mv DEE - Departamento de Engenharia Electrotécnica e de Computadores
UNINOVA-Instituto de Desenvolvimento de Novas Tecnologias
CTS - Centro de Tecnologia e Sistemas
DEE2010-C2 Robótica e Manufactura Integrada por Computador
RUN
dc.contributor.author.fl_str_mv Peres, Ricardo Silva
Azevedo, Miguel
Araújo, Sara Oleiro
Guedes, Magno
Miranda, Fábio
Barata, José
dc.subject.por.fl_str_mv Data augmentation
Deep learning
Industry 4.0
Quality control
Structural adhesive
Materials Science(all)
Instrumentation
Engineering(all)
Process Chemistry and Technology
Computer Science Applications
Fluid Flow and Transfer Processes
topic Data augmentation
Deep learning
Industry 4.0
Quality control
Structural adhesive
Materials Science(all)
Instrumentation
Engineering(all)
Process Chemistry and Technology
Computer Science Applications
Fluid Flow and Transfer Processes
description UIDB/- 00066/2020 POCI-01-0247-FEDER-034072
publishDate 2021
dc.date.none.fl_str_mv 2021-04-01
2021-04-01T00:00:00Z
2022-02-17T23:19:32Z
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/10362/133127
url http://hdl.handle.net/10362/133127
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 2076-3417
PURE: 36679070
https://doi.org/10.3390/app11073086
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 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 mluisa.alvim@gmail.com
_version_ 1817545847415504896