Title: Use of HMM for evaluation of maintenance activities

Authors: Pascal Vrignat, Manuel Avila, Florent Duculty, Frederic Kratz

Addresses: PRISME Institute – MCDS Team, Orleans University, IUT de l'Indre, 2, Av. Francois Mitterrand, 36000 Chateauroux, ENSI, 88 Boulevard Lahitolle, 18020 Bourges Cedex, France. ' PRISME Institute – MCDS Team, Orleans University, IUT de l'Indre, 2, Av. Francois Mitterrand, 36000 Chateauroux, ENSI, 88 Boulevard Lahitolle, 18020 Bourges Cedex, France. ' PRISME Institute – MCDS Team, Orleans University, IUT de l'Indre, 2, Av. Francois Mitterrand, 36000 Chateauroux, ENSI, 88 Boulevard Lahitolle, 18020 Bourges Cedex, France. ' PRISME Institute – MCDS Team, Orleans University, IUT de l'Indre, 2, Av. Francois Mitterrand, 36000 Chateauroux, ENSI, 88 Boulevard Lahitolle, 18020 Bourges Cedex, France

Abstract: This paper deals with a tool which may help maintenance managers to schedule maintenance activities. To help them, we show that by using events which can be observed on a process, like maintenance events, we can predict failures before they occur. Principles are based on hypothesis that failure is preceded by a typical sequence of events. We also show that hidden Markov models can be used according to the right choice of parameters.

Keywords: preventive maintenance; maintenance planning; hidden Markov model; HMM; failure detection; maintenance management; maintenance scheduling; failure prediction.

DOI: 10.1504/IJAIS.2010.034801

International Journal of Adaptive and Innovative Systems, 2010 Vol.1 No.3/4, pp.216 - 232

Published online: 23 Aug 2010 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article