A Digital Twin‐Oriented Simulation Framework for Emergency Evacuation Path Optimisation in Underground Coal Mines Integrating Personnel Positioning and Environmental Monitoring

ABSTRACT

Emergency evacuation in underground coal mines is hindered by the inability of static escape plans to adapt to rapidly changing post‐disaster conditions. This study constructs a digital twin‐oriented simulation framework integrating ultra‐wideband (UWB) personnel positioning with multi‐parameter environmental monitoring, and develops a dynamic evacuation path optimisation algorithm on a time‐varying hazard‐weighted graph. No physical mine is connected, so the framework is exercised entirely in simulation. Internal synchronisation latency remains within 2 s under disaster mode, and a simplified gas dispersion model deviates approximately 8.6% from literature benchmarks. A weighted A* algorithm variant incorporating a risk‐aversion heuristic and roadway capacity constraints is proposed. Under a gas outburst scenario with 260 personnel, the algorithm reduces mean evacuation time by 20.6% and cumulative hazard exposure by 34.2% compared to the static Dijkstra baseline, with a mean planning time of 1.4 s satisfying real‐time requirements. A coupled outburst and collapse case raises the number of hazardous segments from 7 to 11 through reduced dilution. Ablation experiments confirm the synergistic benefit of fusing positioning and environmental data, and sensitivity analyses verify the robustness of key weight parameters. Under combined sensing degradation, the two gains narrow to 18.8% and 31.1%, and they fall to 17.7% and 29.4% when route compliance drops to 70%. The findings provide a methodological reference for intelligent emergency evacuation in underground mines, though field validation with real mine data remains necessary.