Naïve Bayesian Classifier for On-line Remaining Useful Life Prediction of Degrading Bearings

Francesco Di Maio (1) , Selina S. Y. Ng (2) , Kwok-Leung Tsui (2) , Enrico Zio (3)

1 Dipartimento di Energia [Milano]
2 Department of Manufacturing Engineering and Engineering Management
3 SSEC - Chaire Sciences des Systèmes et Défis Energétiques EDF/ECP/Supélec

In this paper, the estimation of the Residual Useful Life (RUL) of degraded thrust ball bearings is made resorting to a data-driven stochastic approach that relies on an iterative Naïve Bayesian Classifier (NBC) for regression task. NBC is a simple stochastic classifier based on applying Bayes' theorem for posterior estimate updating. Indeed, the implemented iterative procedure allows for updating the RUL estimation based on new information collected by sensors located on the degrading bearing, and is suitable for an on-line monitoring of the component health status. The feasibility of the approach is shown with respect to real world vibration-based degradation data.

Mots clés: Residual Useful Life; Naïve Bayesian Classifier; Thrust Ball Bearings; Degradation; Prognostics; Condition Monitoring

Domaines: Autre

Francesco Di Maio, Selina S. Y. Ng, Kwok-Leung Tsui, Enrico Zio. Naïve Bayesian Classifier for On-line Remaining Useful Life Prediction of Degrading Bearings. MMR2011, Jun 2011, China. pp.1-14. ⟨hal-00658069⟩