Early-Warning Hazard Prediction for Railway Traffic Management under Radio-Based Signalling with Satellite-Based Train Integrity Monitoring

Preprint (2025)
Author(s)

Nina D. Versluis (TU Delft - Civil Engineering & Geosciences)

Egidio Quaglietta (TU Delft - Civil Engineering & Geosciences)

Miquel Garcia-Fernandez (Universitat Politécnica de Catalunya)

Rob M. P. Goverde (TU Delft - Civil Engineering & Geosciences)

Research Group
Transport, Mobility and Logistics
DOI related publication
https://doi.org/10.36227/techrxiv.175322640.00621430/v1 Final published version
More Info
expand_more
Publication Year
2025
Language
English
Research Group
Transport, Mobility and Logistics
Journal title
International Journal of Transportation Science and Technology
Publisher
TechRxiv
Downloads counter
26

Abstract

Radio-based signalling with onboard train integrity monitoring (TIM) is considered a key enabler for increasing railway capacity and improving operational efficiency. In this context, continuous and reliable information on the physical integrity of the train is essential.
Satellite-based technologies are among the most promising solutions for onboard TIM. However, degradation in satellite signals might lead to potentially hazardous traffic conditions that require specific operational management. This paper introduces an early-warning hazard prediction framework to support railway dispatchers in proactively mitigating risks originating from satellite and/or radio signal degradation. The proposed framework extends the core railway traffic management framework by incorporating methods for real-time monitoring and prediction of positioning errors under degraded conditions. Its effectiveness is demonstrated through a case study focused on a representative operational use case for European Train Control System (ETCS) Level 2.
Early identification of potentially hazardous conditions and timely warnings enable dispatchers to act proactively to mitigate the impacts on operational performance; the demonstrated application of the framework leads to a 48% reduction in the impact period and a 41% decrease in additional delays, due to the avoidance of an unplanned stop.