This manuscript presents a digital methodology that uses condition-based modeling and Bayesian filters to generate comprehensive overviews of railway track interventions, including required maintenance, scheduling windows, and associated costs for entire railway networks. The approach was tested on a 25 km Swiss regional railway network and shows potential to improve early-stage planning efficiency, optimize preventive maintenance scheduling, and reduce corrective intervention costs.
Hamed Mehranfar,
Bryan T Adey,
Saviz Moghtadernejad,
Claudia Fecarotti
