Bayesian Feature Discovery for Predictive Maintenance

Amir Dib (1, 2, 3, 4) , Charles Truong (1, 2, 3, 4) , Laurent Oudre (1, 2, 3, 4) , Mathilde Mougeot (1, 2, 3, 4) , Nicolas Vayatis (1, 2, 3, 4) , Heloïse Nonne (5, 6)

1 ENS Paris Saclay - Ecole Normale Supérieure Paris-Saclay
2 CB - CB - Centre Borelli - UMR 9010
3 Université Paris-Saclay
4 CNRS - Centre National de la Recherche Scientifique
5 ITNOVEM
6 SNCF

This paper considers predictive maintenance, which is the task of predicting rare and anomalous events (typically, system failures) using event logs data, which are series of timestamped symbolic codes emitted at regular or irregular intervals by a monitored system. Our objective is to find small sets of codes (called itemsets or patterns) that occur shortly before failures. Current prediction methods either produce patterns at a high computational cost or resort to kernel approaches which are often difficult to interpret. We introduce Bayesian Pattern Feature Discovery (BPFD), a new generic algorithm for pattern discovery. Our method, based on a pattern mining technique, produces informative and explainable features and is computationally efficient. The performance of BPFD is highlighted on real-world data sets, showing that enriching the feature space with the discovered patterns improves significantly the prediction power of a broad range of predictors and offers useful insight on the predictive maintenance task.

Mots clés: Bayesian learning; pattern mining; predictive maintenance; variational inference

Domaines: Mathématiques [math]; Probabilités [math.PR]; Statistiques [stat]

Amir Dib, Charles Truong, Laurent Oudre, Mathilde Mougeot, Nicolas Vayatis, et al.. Bayesian Feature Discovery for Predictive Maintenance. 2021. ⟨hal-03154496⟩