Understanding Incident Effects on Subway Operations: Clustering Analysis of Severity Patterns

Abstract

Incidents pose challenges to the reliable operation of urban rail transit systems. Given the high frequency of subway services, even minor incidents can cause cascading delays across multiple trains. Understanding incident effects is crucial for improving response time and enabling efficient recovery strategies. This study uses operational records from the Montreal subway system to quantify the overall impact of incidents including the number of affected trains and total delay time. The proposed approach involves integrating operational records with incident data to identify the source of delays and subsequent knock-on effects. To recognize distinct propagation patterns among various incident types, K-means clustering is applied to categorize incidents into three clusters. Cluster 1 represents incidents with the lowest impacts, affecting only one direction of a subway line and imposing an average total delay time of 16 min. Cluster 2, which comprises most incidents, causing moderate operational impacts with an average total delay time of 52 min. Cluster 3 includes severe incidents, affecting an average of 26 trains and causing a total delay time of 273 min. Peak hour analysis indicates that morning and evening peak hours have the highest average number of affected trains, emphasizing the impact of peak hours on incident severity. Investigation into the causes of incidents highlights that the most frequent incidents fall into Cluster 2, implying moderate impacts on subway operations. This research provides valuable insights into subway incident management, laying the groundwork for further studies aimed at enhancing the performance of urban rail transit systems during service disruptions.