Using supervised and one-class automated machine learning for predictive maintenance
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Outros Autores: | , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | https://hdl.handle.net/1822/81437 |
Resumo: | Predictive Maintenance (PdM) is a critical area that is benefiting from the Industry 4.0 advent. Recently, several attempts have been made to apply Machine Learning (ML) to PdM, with the majority of the research studies assuming an expert-based ML modeling. In contrast with these works, this paper explores a purely Automated Machine Learning (AutoML) modeling for PdM under two main approaches. Firstly, we adapt and compare ten recent open-source AutoML technologies focused on a Supervised Learning. Secondly, we propose a novel AutoML approach focused on a One-Class (OC) Learning (AutoOneClass) that employs a Grammatical Evolution (GE) to search for the best PdM model using three types of learners (OC Support Vector Machines, Isolation Forests and deep Autoencoders). Using recently collected data from a Portuguese software company client, we performed a benchmark comparison study with the Supervised AutoML tools and the proposed AutoOneClass method to predict the number of days until the next failure of an equipment and also determine if the equipments will fail in a fixed amount of days. Overall, the results were close among the compared AutoML tools, with supervised AutoGluon obtaining the best results for all ML tasks. Moreover, the best supervised AutoML and AutoOneClass predictive results were compared with two manual ML modeling approaches (using a ML expert and a non-ML expert), revealing competitive results. |
id |
RCAP_7cebd3943e4d58acd1ec535a3ebf01d8 |
---|---|
oai_identifier_str |
oai:repositorium.sdum.uminho.pt:1822/81437 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Using supervised and one-class automated machine learning for predictive maintenanceAutomated machine learningOne-class learningPredictive maintenanceSupervised learningScience & TechnologyPredictive Maintenance (PdM) is a critical area that is benefiting from the Industry 4.0 advent. Recently, several attempts have been made to apply Machine Learning (ML) to PdM, with the majority of the research studies assuming an expert-based ML modeling. In contrast with these works, this paper explores a purely Automated Machine Learning (AutoML) modeling for PdM under two main approaches. Firstly, we adapt and compare ten recent open-source AutoML technologies focused on a Supervised Learning. Secondly, we propose a novel AutoML approach focused on a One-Class (OC) Learning (AutoOneClass) that employs a Grammatical Evolution (GE) to search for the best PdM model using three types of learners (OC Support Vector Machines, Isolation Forests and deep Autoencoders). Using recently collected data from a Portuguese software company client, we performed a benchmark comparison study with the Supervised AutoML tools and the proposed AutoOneClass method to predict the number of days until the next failure of an equipment and also determine if the equipments will fail in a fixed amount of days. Overall, the results were close among the compared AutoML tools, with supervised AutoGluon obtaining the best results for all ML tasks. Moreover, the best supervised AutoML and AutoOneClass predictive results were compared with two manual ML modeling approaches (using a ML expert and a non-ML expert), revealing competitive results.This work was executed under the project Cognitive CMMS - Cognitive Computerized Maintenance Management System, NUP: POCI-01-0247-FEDER-033574, co-funded by the Incentive System for Research and Technological Development , from the Thematic Operational Program Competitiveness of the national framework program - Portugal2020. We wish to thank the anonymous reviewers for their helpful comments.ElsevierUniversidade do MinhoFerreira, LuísPilastri, AndréRomano, FilipeCortez, Paulo2022-12-012022-12-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/1822/81437engFerreira, L., Pilastri, A., Romano, F., & Cortez, P. (2022, December). Using supervised and one-class automated machine learning for predictive maintenance. Applied Soft Computing. Elsevier BV. http://doi.org/10.1016/j.asoc.2022.1098201568-494610.1016/j.asoc.2022.109820https://www.sciencedirect.com/science/article/pii/S1568494622008699info: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:RCAAP2023-07-21T11:58:42Zoai:repositorium.sdum.uminho.pt:1822/81437Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T18:48:28.386351Repositório 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 |
Using supervised and one-class automated machine learning for predictive maintenance |
title |
Using supervised and one-class automated machine learning for predictive maintenance |
spellingShingle |
Using supervised and one-class automated machine learning for predictive maintenance Ferreira, Luís Automated machine learning One-class learning Predictive maintenance Supervised learning Science & Technology |
title_short |
Using supervised and one-class automated machine learning for predictive maintenance |
title_full |
Using supervised and one-class automated machine learning for predictive maintenance |
title_fullStr |
Using supervised and one-class automated machine learning for predictive maintenance |
title_full_unstemmed |
Using supervised and one-class automated machine learning for predictive maintenance |
title_sort |
Using supervised and one-class automated machine learning for predictive maintenance |
author |
Ferreira, Luís |
author_facet |
Ferreira, Luís Pilastri, André Romano, Filipe Cortez, Paulo |
author_role |
author |
author2 |
Pilastri, André Romano, Filipe Cortez, Paulo |
author2_role |
author author author |
dc.contributor.none.fl_str_mv |
Universidade do Minho |
dc.contributor.author.fl_str_mv |
Ferreira, Luís Pilastri, André Romano, Filipe Cortez, Paulo |
dc.subject.por.fl_str_mv |
Automated machine learning One-class learning Predictive maintenance Supervised learning Science & Technology |
topic |
Automated machine learning One-class learning Predictive maintenance Supervised learning Science & Technology |
description |
Predictive Maintenance (PdM) is a critical area that is benefiting from the Industry 4.0 advent. Recently, several attempts have been made to apply Machine Learning (ML) to PdM, with the majority of the research studies assuming an expert-based ML modeling. In contrast with these works, this paper explores a purely Automated Machine Learning (AutoML) modeling for PdM under two main approaches. Firstly, we adapt and compare ten recent open-source AutoML technologies focused on a Supervised Learning. Secondly, we propose a novel AutoML approach focused on a One-Class (OC) Learning (AutoOneClass) that employs a Grammatical Evolution (GE) to search for the best PdM model using three types of learners (OC Support Vector Machines, Isolation Forests and deep Autoencoders). Using recently collected data from a Portuguese software company client, we performed a benchmark comparison study with the Supervised AutoML tools and the proposed AutoOneClass method to predict the number of days until the next failure of an equipment and also determine if the equipments will fail in a fixed amount of days. Overall, the results were close among the compared AutoML tools, with supervised AutoGluon obtaining the best results for all ML tasks. Moreover, the best supervised AutoML and AutoOneClass predictive results were compared with two manual ML modeling approaches (using a ML expert and a non-ML expert), revealing competitive results. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-12-01 2022-12-01T00:00:00Z |
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 |
https://hdl.handle.net/1822/81437 |
url |
https://hdl.handle.net/1822/81437 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Ferreira, L., Pilastri, A., Romano, F., & Cortez, P. (2022, December). Using supervised and one-class automated machine learning for predictive maintenance. Applied Soft Computing. Elsevier BV. http://doi.org/10.1016/j.asoc.2022.109820 1568-4946 10.1016/j.asoc.2022.109820 https://www.sciencedirect.com/science/article/pii/S1568494622008699 |
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.publisher.none.fl_str_mv |
Elsevier |
publisher.none.fl_str_mv |
Elsevier |
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 |
|
_version_ |
1799132246482878464 |