A multi-nets approach for modeling and evaluating rail maintenance strategies
Olivier François, Laurent Bouillaut, Dubois, S · HAL (Le Centre pour la Communication Scientifique Directe) · 2011
In this paper, an assistant tool for the maintenance of rails in an automated metro context for normal steel wheeled trains using an extension of the VirMaLab formalism is proposed. The theory of Dynamic Bayesian Networks offers an interesting frame to solve this specific problem as it allows to use probability distributions to represent degradation process together with stochastic representation of maintenance agents. We present a modular modeling of the current rails' diagnosis. It simulates the rail degradation and the whole maintenance process as the behavior of actors involved in the defect detection, but also the maintenance action decisions. Indicators that are provided by the software are helpful for the determination of optimal maintenance parameters.