Freight transportation using railways offers an efficient solution for moving large volumes of goods over a diverse range of distances, while reducing road congestion and environmental impact. The maintenance of the wheelsets from freight vehicles is vital to make this process safe and cost-effective. However, not enough efforts have been made to improve the maintenance of freight wagons. Consequently, this paper addresses a critical gap in identifying the most appropriate lifetime variable for wheelsets from freight wagons, by comparing time, mileage and gross ton mileage since maintenance. The methods used in this comparative study are regression analysis to model wear trajectories, survival analysis to model damage trajectories and reinforcement learning to model decision policies. The findings demonstrate that gross ton mileage is the most reliable variable for the maintenance of wheelsets from freight wagons. This paper underscores the critical role of gross ton mileage in predictive maintenance, offering actionable insights to enhance decision making and reduce costs, while improving reliability and safety of degrading assets.
Braga et al. (Sun,) studied this question.