A predictive maintenance approach based on time series segmentation

Detalhes bibliográficos
Autor(a) principal: Coelho, Daniel Filipe Silveira
Data de Publicação: 2021
Tipo de documento: Dissertação
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10773/32120
Resumo: The increase in automation provided by Industry 4.0 combined with the growing competitiveness in the market highlights the importance of intelligent maintenance. Companies must rethink current maintenance strategies in order to detect failures before they occur. This is the motto of predictive maintenance, through the analysis of data from equipment it is possible to predict when failures will occur and act in accordance with the forecast. This project, in addition to developing a platform capable of receiving and processing data in real-time from deferent equipment, also proposes a predictive maintenance approach based on time series segmentation. This new predictive maintenance approach was applied to data from a mechanical press, located in Bosch Thermotechnology, S.A., having achieved an efficiency of 90.91%. Throughout the document, all elements of the developed system are discussed in detail, from the data acquisition systems to sending forecasts on the condition of the equipment to a visualization platform.
id RCAP_a5b7689fafd970001774c7cc13e2af27
oai_identifier_str oai:ria.ua.pt:10773/32120
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling A predictive maintenance approach based on time series segmentationPredictive maintenanceTime series segmentationTime seriesData analysisData processingAnomaly detectionForecastsThe increase in automation provided by Industry 4.0 combined with the growing competitiveness in the market highlights the importance of intelligent maintenance. Companies must rethink current maintenance strategies in order to detect failures before they occur. This is the motto of predictive maintenance, through the analysis of data from equipment it is possible to predict when failures will occur and act in accordance with the forecast. This project, in addition to developing a platform capable of receiving and processing data in real-time from deferent equipment, also proposes a predictive maintenance approach based on time series segmentation. This new predictive maintenance approach was applied to data from a mechanical press, located in Bosch Thermotechnology, S.A., having achieved an efficiency of 90.91%. Throughout the document, all elements of the developed system are discussed in detail, from the data acquisition systems to sending forecasts on the condition of the equipment to a visualization platform.O aumento da automatização proporcionada pela Industria 4.0 aliada à crescente competitividade no mercado destaca a importância de uma manutenção inteligente. As empresas devem repensar as atuais estratégias de manutenção de modo detetar de forma antecipada as avarias. Este é o lema da manutenção preditiva, através da análise dos dados dos equipamentos é possível prever quando as avarias irão ocorrer e agir em conformidade com a previsão. Este projeto, para além de desenvolver uma plataforma capaz de receber e processar dados em tempo real de diversos equipamentos, também propõe uma abordagem de manutenção preditiva baseada na segmentação de series temporais. Esta nova abordagem foi aplicada a dados de uma prensa mecânica da Bosch Thermotechnology, S.A., tendo-se alcançado uma eficiência de 90.91%. Ao longo do documento é abordado em detalhe todos os elementos do sistema desenvolvido, desde os sistemas de aquisição de dados, até ao envio das previsões sobre a condição do equipamento para uma plataforma de visualização.2021-09-15T13:55:39Z2021-07-28T00:00:00Z2021-07-28info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10773/32120engCoelho, Daniel Filipe Silveirainfo: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:RCAAP2024-02-22T12:02:05Zoai:ria.ua.pt:10773/32120Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:03:55.793926Repositório 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 A predictive maintenance approach based on time series segmentation
title A predictive maintenance approach based on time series segmentation
spellingShingle A predictive maintenance approach based on time series segmentation
Coelho, Daniel Filipe Silveira
Predictive maintenance
Time series segmentation
Time series
Data analysis
Data processing
Anomaly detection
Forecasts
title_short A predictive maintenance approach based on time series segmentation
title_full A predictive maintenance approach based on time series segmentation
title_fullStr A predictive maintenance approach based on time series segmentation
title_full_unstemmed A predictive maintenance approach based on time series segmentation
title_sort A predictive maintenance approach based on time series segmentation
author Coelho, Daniel Filipe Silveira
author_facet Coelho, Daniel Filipe Silveira
author_role author
dc.contributor.author.fl_str_mv Coelho, Daniel Filipe Silveira
dc.subject.por.fl_str_mv Predictive maintenance
Time series segmentation
Time series
Data analysis
Data processing
Anomaly detection
Forecasts
topic Predictive maintenance
Time series segmentation
Time series
Data analysis
Data processing
Anomaly detection
Forecasts
description The increase in automation provided by Industry 4.0 combined with the growing competitiveness in the market highlights the importance of intelligent maintenance. Companies must rethink current maintenance strategies in order to detect failures before they occur. This is the motto of predictive maintenance, through the analysis of data from equipment it is possible to predict when failures will occur and act in accordance with the forecast. This project, in addition to developing a platform capable of receiving and processing data in real-time from deferent equipment, also proposes a predictive maintenance approach based on time series segmentation. This new predictive maintenance approach was applied to data from a mechanical press, located in Bosch Thermotechnology, S.A., having achieved an efficiency of 90.91%. Throughout the document, all elements of the developed system are discussed in detail, from the data acquisition systems to sending forecasts on the condition of the equipment to a visualization platform.
publishDate 2021
dc.date.none.fl_str_mv 2021-09-15T13:55:39Z
2021-07-28T00:00:00Z
2021-07-28
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10773/32120
url http://hdl.handle.net/10773/32120
dc.language.iso.fl_str_mv eng
language eng
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
_version_ 1799137694881677312

Registros relacionados