On applying artificial intelligence techniques to maximise passengers comfort and infrastructure reliability in urban railway systems

Railway infrastructure reliability and availability are key to guarantee an efficient rail service. In particular, track maintenance has a significant impact on the ride quality and train speed, since the reduction of speed limits is imposed in case of poor track condition. This implies consequence for the passengers comfort and delays of travel times. In this context, this research is aimed at developing an integrated model for the identification of track defects and the optimal ordering of maintenance interventions that can reduce operational costs for the infrastructure manager, improving capacity, efficiency as well as passengers' satisfaction. The application of the proposed approach to a real urban railway line is described, showing its effectiveness.