Predictive maintenance of transport systems under incomplete and imprecise data
Maintenance prévisionnelle en présence de données incomplètes et imprécises
Maintenance is an important factor for quality, operational safety, to meet deadlines and to attain high productivity in complex industrial facilities. The MAPSYD project proposes an original methodlogy for predictive maintenance to take in account both incomplete and imprecise data collected by sensors. First, we propose a methodology based on the association of hidden Markov chains and the theory of imprecise probabilities. Next, we define a decision making tool in order to build an economic model based on the maintenance policy obtained from the imprecise Markov chain methodology. Finally, we propose to develop a sensor system embedded in a tram or a bus and located on the critical parts implementing the algorithms developed in the proposed methodology.
Research & academic partners