Process mining approach for recovery of realized train paths and route conflict identification

摘要

Data records from train describer systems are a valuable source of information for analyzing railway opera3tions performance and assessing railway timetable quality. This paper presents a tool based on process min4ing event data records from the Dutch train describer system TROTS. The underlying algorithms automat5ically identify route conflicts with conflicting trains, determine accurate arrival and departure times/delaysat stations, and reconstruct the train paths on track section and blocking time level. Graphical user inter7face and visualizations of the time-distance diagrams and blocking time diagrams support and simplify theanalysis of running times, dwell times, incidents, track obstructions, disruptions, and structural errors in thetimetable design. The case study of a one day of traffic on a busy railway corridor in the Netherlands ispresented, as well as the examples to describe the graphical user interface.