Maintenance policy: degradation laws versus hidden Markov model availability indicator

Pascal Vrignat (1) , Manuel Avila (1) , Florent Duculty (1) , Sébastien Aupetit (2) , Mohamed Slimane (2) , Frédéric Kratz (1)

1 PRISME - Laboratoire Pluridisciplinaire de Recherche en Ingénierie des Systèmes, Mécanique et Energétique
2 LIFAT - Laboratoire d'Informatique Fondamentale et Appliquée de Tours

Today, maintenance strategies and their analyses remain a worrying problem for companies. Socio economic stakes depending on competitiveness of each strategy are even more linked to activity and quality of maintenance interventions. A series of specific events can eventually warn the expert of an imminent breakdown. Our study aims at understanding such "signature" thanks to hidden Markov models. On that purpose, two methods for damage level estimation of maintained system are proposed to expert. The first one consists in using a non parametric and semi-parametric degradation laws (which will be used as references). The second one consists in using a markovian approach. All proposals are illustrated on two studies corresponding to two real industrial situations (continuous system for food processing and moulded products in aluminum alloys for the automotive industry).

Mots clés: diagnosis; maintenance management; assessment; degradation laws; Hidden Markov Model

Domaines: Automatique

Pascal Vrignat, Manuel Avila, Florent Duculty, Sébastien Aupetit, Mohamed Slimane, et al.. Maintenance policy: degradation laws versus hidden Markov model availability indicator. Proceedings of the Institution of Mechanical Engineers, Part O: Journal of Risk and Reliability, 2012, 226(2) (1748006X11406335), pp.137-155. ⟨hal-00628931⟩