A predictive-based maintenance approach for rolling stocks vehicles

摘要: In this paper, a model-based maintenance approach is developed for rolling stocks vehicles operating along railway networks. By considering the high management costs in modern and complex railways fleets as primary requirement, key goal of proposed consists efficiently integrating actions with capability to satisfactorily keep services. Here, achieved by means multi-layer that combine into single framework following ingredients: interpolation procedures, machine learning algorithms prediction arguments take advantage an accurate model description stock dynamics. Experiments on PV7 EVO - Matisa, owned Italian Railways Network, have been conducted aim show effectiveness architecture.