Predictive Maintenance concerns the smart monitoring of machine to avoid possible future failures, since because it is better to intervene before the damage occurs, saving time and money. In this paper, a Predictive Maintenance methodology based on Machine learning approach is presented and it is applied to a real cutting machine, a woodworking machinery in a real industrial group, producing accurate estimations. This kind of strategy is important to deal with maintenance problems given the ever increasing need to reduce downtime and associated costs. The Predictive Maintenance methodology implemented allows dynamical decision rules that have to be considered for maintenance prediction using a combined approach on Azure Machine Learning Studio. The Three models (RF, GBM and XGBM) allowed the accurately predict machine down ever gripped bearing thanks to the pre-processing phases
An event based machine learning framework for predictive maintenance in industry 4.0 / Calabrese, M.; Cimmino, M.; Manfrin, M.; Fiume, F.; Kapetis, D.; Mengoni, M.; Ceccacci, S.; Frontoni, E.; Paolanti, M.; Carrotta, A.; Toscano, G.. - ELETTRONICO. - 9:(2019). (Intervento presentato al convegno ASME 2019 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC-CIE 2019 tenutosi a Orlando, Florida (USA) nel 18-21 August 2019) [10.1115/DETC2019-97917].
An event based machine learning framework for predictive maintenance in industry 4.0
Mengoni M.Supervision
;Ceccacci S.;Frontoni E.;Paolanti M.;
2019-01-01
Abstract
Predictive Maintenance concerns the smart monitoring of machine to avoid possible future failures, since because it is better to intervene before the damage occurs, saving time and money. In this paper, a Predictive Maintenance methodology based on Machine learning approach is presented and it is applied to a real cutting machine, a woodworking machinery in a real industrial group, producing accurate estimations. This kind of strategy is important to deal with maintenance problems given the ever increasing need to reduce downtime and associated costs. The Predictive Maintenance methodology implemented allows dynamical decision rules that have to be considered for maintenance prediction using a combined approach on Azure Machine Learning Studio. The Three models (RF, GBM and XGBM) allowed the accurately predict machine down ever gripped bearing thanks to the pre-processing phasesI documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
