n the field of industry 4.0, one of the sectors in which research is particularly active is the area of Predictive Maintenance(PdM), the purpose of which is to improve the industrial production process. This type of maintenance aims to predict a possible failure event, reduce non-production times and increase the quality of the processing result. The objective of this paper is to select the best Machine Learning models for a PdM application. In particular, such a model should allow making a prediction based on a real dataset, obtained by monitoring a turning process, with the aim of making the classification of the chip shape. The criteria used to choose the best model are accuracy and prediction speed (to reduce the inference time). Indeed it is crucial to spot any potential machine fault in the shortest time possible, in order to intervene before the machine fails. Hence, our goal is to choose the ML models with a lesser inference time while still maintaining high accuracy.

Comparison of Machine Learning Models for Predictive Maintenance Applications / Lazzaro, A.; D'Addona, D. M.; Merenda, Massimo. - 546 LNNS:(2022), pp. 657-666. (Intervento presentato al convegno 6th International Conference on System-Integrated Intelligence, SysInt 2022) [10.1007/978-3-031-16281-7_62].

Comparison of Machine Learning Models for Predictive Maintenance Applications

D'Addona D. M.;
2022

Abstract

n the field of industry 4.0, one of the sectors in which research is particularly active is the area of Predictive Maintenance(PdM), the purpose of which is to improve the industrial production process. This type of maintenance aims to predict a possible failure event, reduce non-production times and increase the quality of the processing result. The objective of this paper is to select the best Machine Learning models for a PdM application. In particular, such a model should allow making a prediction based on a real dataset, obtained by monitoring a turning process, with the aim of making the classification of the chip shape. The criteria used to choose the best model are accuracy and prediction speed (to reduce the inference time). Indeed it is crucial to spot any potential machine fault in the shortest time possible, in order to intervene before the machine fails. Hence, our goal is to choose the ML models with a lesser inference time while still maintaining high accuracy.
2022
978-3-031-16280-0
978-3-031-16281-7
Comparison of Machine Learning Models for Predictive Maintenance Applications / Lazzaro, A.; D'Addona, D. M.; Merenda, Massimo. - 546 LNNS:(2022), pp. 657-666. (Intervento presentato al convegno 6th International Conference on System-Integrated Intelligence, SysInt 2022) [10.1007/978-3-031-16281-7_62].
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11588/902223
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? 2
social impact