Methods to choose the best Hidden Markov Model topology for improving maintenance policyReportar como inadecuado




Methods to choose the best Hidden Markov Model topology for improving maintenance policy - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

1 PRISME - Laboratoire Pluridisciplinaire de Recherche en Ingénierie des Systèmes, Mécanique et Energétique 2 IRAUS PRISME - Laboratoire Pluridisciplinaire de Recherche en Ingénierie des Systèmes, Mécanique et Energétique

Abstract : Prediction of physical particular phenomenon is based on partial knowledge of this phenomenon. Theses knowledges help us to conceptualize this phenomenon according to di erent models. Hidden Markov Models HMM can be used for modeling complex processes. We use this kind of models as tool for fault diagnosis systems. Nowadays, industrial robots living in stochastic environment need faults detection to prevent any breakdown. In this paper, we wish to nd the best Hidden Markov Model topologies to be used in predictive maintenance system. To this end, we use a synthetic Hidden Markov Model in order to simulate a real industrial CMMS. In a stochastic way, we evaluate relevance of Hidden Markov Models parameters, without a priori knowledges. After a brief presentation of a Hidden Markov Model, we present the most used selection criteria of models in current literature. We support our study by an example of simulated industrial process by using our synthetic model. Therefore, we evaluate output parameters of the various tested models on this process: topologies, learning algorithms, observations distributions, epistemic uncertainties. Finally, we come up with the best model which will be used to improve maintenance policy and worker safety.

Keywords : predictive maintenance Hidden Markov Models model selection learning algorithms statistical test uncertainties predictive maintenance.





Autor: Bernard Roblès - Manuel Avila - Florent Duculty - Pascal Vrignat - Stéphane Begot - Frédéric Kratz -

Fuente: https://hal.archives-ouvertes.fr/



DESCARGAR PDF




Documentos relacionados