As critical nodes in urban transportation networks, the operational resilience of urban tunnels directly affects roadway network efficiency and public safety. Existing studies on tunnel resilience exhibit deficiencies in the attention paid to routine incidents, the interpretability of evaluation methods, and the robustness of underlying data. To address these gaps, this paper constructs a three-layer resilience evaluation framework (pre-event, during-event, and post-event) based on 1123 accident records, hourly traffic flow data, and expert scoring data from 10 urban tunnels in Shanghai in 2024. The framework integrates the Analytic Hierarchy Process (AHP) and min–max normalization to derive comprehensive resilience scores. Furthermore, two explainable artificial intelligence (XAI) techniques—SHAP (SHapley Additive exPlanations) feature importance analysis and K-means clustering—are introduced to identify key drivers of resilience differentiation and typical resilience patterns, respectively. Empirical results reveal that (1) half of the 10 tunnels achieve a B-level rating or above, while C/D-level tunnels still account for 50%, indicating considerable room for improvement; (2) SHAP analysis suggests that during-event absorption capacity contributes most significantly to resilience differences (50.24%), with the average traffic reduction rate being the most influential single indicator within this model; and (3) K-means clustering classifies the tunnels into four patterns: high-resilience balanced type, pre-event weak type, post-event weak type, and during-event weak type, each corresponding to distinct resilience enhancement strategies. The methodological framework developed in this paper effectively enables the quantification, interpretation, and pattern recognition of tunnel resilience, providing data-driven decision support for urban tunnel operation and management. It should be noted that the A–D ratings are sensitive to the normalization method: under an alternative normalization, 7 out of 10 tunnels change grade. The ratings should therefore be interpreted as relative to the selected sample rather than as absolute performance levels.

This study investigates the smoke spread characteristics and occupant evacuation safety of a 15 MW battery electric vehicle (BEV) fire in a 1.5 km small-bore single-lane road tunnel. Owing to its minimized cross-section (a single 3.0 m lane within a 3.7 m inner diameter), no fire protection or evacuation facilities can be accommodated, and its fire safety therefore requires performance-based verification. Fire Dynamics Simulator (FDS) was used to simulate the fire under different longitudinal ventilation velocities, and the smoke temperature, visibility and CO concentration were examined. Based on these indices, the available safe egress time (ASET) was determined, while the required safe egress time (RSET) was obtained from Pathfinder evacuation simulations for a worst-case congestion scenario involving 420 occupants, so as to evaluate whether the evacuation distance of the 1.5 km tunnel is adequate. The results show that under natural ventilation, the upstream section 645–750 m violates the RSET < ASET criterion; under 1 m/s longitudinal ventilation, the failure zone shrinks to 740–750 m; at 2 m/s and 3 m/s, the upstream region remains tenable throughout the 900 s simulation and all occupants can evacuate safely. A longitudinal ventilation velocity of at least 2 m/s is therefore required to ensure safe upstream evacuation in this tunnel. The conclusions are drawn for the present worst-case configuration and are intended for the pre-construction performance-based verification of similar single-lane tunnels without evacuation facilities.