Predictive maintenance on sensorized stamping presses by time series segmentation, anomaly detection, and classification algorithms
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: | http://hdl.handle.net/10773/35458 |
Resumo: | Sheet metal forming tools, like stamping presses, play an ubiquitous role in the manufacture of several products. With increasing requirements of quality and efficiency, ensuring maximum uptime of these tools is fundamental to marketplace competitiveness. Using anomaly detection and predictive maintenance techniques, it is possible to develop lower risk and more intelligent approaches to maintenance scheduling, however, industrial implementations of these methods remain scarce due to the difficulties of obtaining acceptable results in real-world scenarios, making applications of such techniques in stamping processes seldom found. In this work, we propose a combination of two distinct approaches: (a) time segmentation together with feature dimension reduction and anomaly detection; and (b) machine learning classification algorithms, for effective downtime prediction. The approach (a)+(b) allows for an improvement rate up to 22.971% of the macro F1-score, when compared to sole approach (b). A ROC AUC index of 96% is attained by using Randomized Decision Trees, being the best classifier of twelve tested. An use case with a decentralized predictive maintenance architecture for the downtime forecasting of a stamping press, which is a critical machine in the manufacturing facilities of Bosch Thermo Technology, is discussed. |
id |
RCAP_10781e894acbca8288c34734a7731096 |
---|---|
oai_identifier_str |
oai:ria.ua.pt:10773/35458 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Predictive maintenance on sensorized stamping presses by time series segmentation, anomaly detection, and classification algorithmsPredictive MaintenanceAnomaly DetectionMachine LearningTime SegmentationSheet metal forming tools, like stamping presses, play an ubiquitous role in the manufacture of several products. With increasing requirements of quality and efficiency, ensuring maximum uptime of these tools is fundamental to marketplace competitiveness. Using anomaly detection and predictive maintenance techniques, it is possible to develop lower risk and more intelligent approaches to maintenance scheduling, however, industrial implementations of these methods remain scarce due to the difficulties of obtaining acceptable results in real-world scenarios, making applications of such techniques in stamping processes seldom found. In this work, we propose a combination of two distinct approaches: (a) time segmentation together with feature dimension reduction and anomaly detection; and (b) machine learning classification algorithms, for effective downtime prediction. The approach (a)+(b) allows for an improvement rate up to 22.971% of the macro F1-score, when compared to sole approach (b). A ROC AUC index of 96% is attained by using Randomized Decision Trees, being the best classifier of twelve tested. An use case with a decentralized predictive maintenance architecture for the downtime forecasting of a stamping press, which is a critical machine in the manufacturing facilities of Bosch Thermo Technology, is discussed.Elsevier2022-12-19T16:16:36Z2022-01-01T00:00:00Z2022info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10773/35458eng1877-050910.1016/j.procs.2022.01.318Coelho, DanielCosta, DiogoRocha, Eugénio M.Almeida, DuarteSantos, José P.info: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:RCAAP2024-02-22T12:08:07Zoai:ria.ua.pt:10773/35458Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:06:24.628063Repositório 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 |
Predictive maintenance on sensorized stamping presses by time series segmentation, anomaly detection, and classification algorithms |
title |
Predictive maintenance on sensorized stamping presses by time series segmentation, anomaly detection, and classification algorithms |
spellingShingle |
Predictive maintenance on sensorized stamping presses by time series segmentation, anomaly detection, and classification algorithms Coelho, Daniel Predictive Maintenance Anomaly Detection Machine Learning Time Segmentation |
title_short |
Predictive maintenance on sensorized stamping presses by time series segmentation, anomaly detection, and classification algorithms |
title_full |
Predictive maintenance on sensorized stamping presses by time series segmentation, anomaly detection, and classification algorithms |
title_fullStr |
Predictive maintenance on sensorized stamping presses by time series segmentation, anomaly detection, and classification algorithms |
title_full_unstemmed |
Predictive maintenance on sensorized stamping presses by time series segmentation, anomaly detection, and classification algorithms |
title_sort |
Predictive maintenance on sensorized stamping presses by time series segmentation, anomaly detection, and classification algorithms |
author |
Coelho, Daniel |
author_facet |
Coelho, Daniel Costa, Diogo Rocha, Eugénio M. Almeida, Duarte Santos, José P. |
author_role |
author |
author2 |
Costa, Diogo Rocha, Eugénio M. Almeida, Duarte Santos, José P. |
author2_role |
author author author author |
dc.contributor.author.fl_str_mv |
Coelho, Daniel Costa, Diogo Rocha, Eugénio M. Almeida, Duarte Santos, José P. |
dc.subject.por.fl_str_mv |
Predictive Maintenance Anomaly Detection Machine Learning Time Segmentation |
topic |
Predictive Maintenance Anomaly Detection Machine Learning Time Segmentation |
description |
Sheet metal forming tools, like stamping presses, play an ubiquitous role in the manufacture of several products. With increasing requirements of quality and efficiency, ensuring maximum uptime of these tools is fundamental to marketplace competitiveness. Using anomaly detection and predictive maintenance techniques, it is possible to develop lower risk and more intelligent approaches to maintenance scheduling, however, industrial implementations of these methods remain scarce due to the difficulties of obtaining acceptable results in real-world scenarios, making applications of such techniques in stamping processes seldom found. In this work, we propose a combination of two distinct approaches: (a) time segmentation together with feature dimension reduction and anomaly detection; and (b) machine learning classification algorithms, for effective downtime prediction. The approach (a)+(b) allows for an improvement rate up to 22.971% of the macro F1-score, when compared to sole approach (b). A ROC AUC index of 96% is attained by using Randomized Decision Trees, being the best classifier of twelve tested. An use case with a decentralized predictive maintenance architecture for the downtime forecasting of a stamping press, which is a critical machine in the manufacturing facilities of Bosch Thermo Technology, is discussed. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-12-19T16:16:36Z 2022-01-01T00:00:00Z 2022 |
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/10773/35458 |
url |
http://hdl.handle.net/10773/35458 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
1877-0509 10.1016/j.procs.2022.01.318 |
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_ |
1799137718967468032 |