RDBU| Repositório Digital da Biblioteca da Unisinos

ELFpm: an ensemble-based learning framework for predictive maintenance in industry 4.0

Mostrar registro simples

Autor Dalzochio, Jovani;
Lattes do autor http://lattes.cnpq.br/4598296566128465;
Orientador Kunst, Rafael;
Lattes do orientador http://lattes.cnpq.br/1301443198267856;
Co-orientador Barbosa, Jorge Luis Victória;
Lattes do co-orientador http://lattes.cnpq.br/6754464380129137;
Instituição Universidade do Vale do Rio dos Sinos;
Sigla da instituição Unisinos;
País da instituição Brasil;
Instituto/Departamento Escola Politécnica;
Idioma en;
Título ELFpm: an ensemble-based learning framework for predictive maintenance in industry 4.0;
Resumo The topic of predictive maintenance has great relevance in the search for the rationalization and efficiency of the industrial plants in the context of Industry 4.0. Monitoring equipment parameters and identifying behavior changes that identify a future failure allows for anticipation of maintenance while avoiding unnecessary preventive maintenance. There are numerous works in the literature that work towards the prediction of maintenance of various equipment. However, the same equipment has different behavior depending on the conditions of use or the operating environment, making a tool capable of being trained for new environments is necessary. This work describes the methodology of creating a framework that can be configured to work on predicting equipment failures, that is, regardless of location or condition of use. For this, starting from the initial configuration of the framework, the use of an ontology is applied in the choice of the best prediction technique for each established condition of the initial parameterization.;
Palavras-chave Industry 4.0; Ontology; Machine learning; Predictive maintenance;
Área(s) do conhecimento ACCNPQ::Ciências Exatas e da Terra::Ciência da Computação;
Tipo Dissertação;
Data de defesa 2020-03-17;
Agência de fomento CAPES - Coordenação de Aperfeiçoamento de Pessoal de Nível Superior;
Direitos de acesso openAccess;
URI http://www.repositorio.jesuita.org.br/handle/UNISINOS/9220;
Programa Programa de Pós-Graduação em Computação Aplicada;


Arquivos deste item

Este item aparece na(s) seguinte(s) coleção(s)

Mostrar registro simples

Buscar

Busca avançada

Navegar

Minha conta

Estatística