Digital twin-driven integrated ground decision scheduling system for fully mechanized top-coal caving face

To address the problems of low equipment coordination efficiency, insufficient data integration, and incomplete safety monitoring coverage in coal mine production scheduling and safety management, a digital twin-driven integrated ground decision scheduling system for the fully mechanized top-coal caving face was proposed. The system adopted a three-level centralized control architecture consisting of intelligent working face terminals, roadway control nodes, and a ground management and control center. The intelligent working face terminals collected equipment status and environmental parameters in real time, the roadway control nodes performed data cleaning, fusion, and edge preprocessing through explosion-proof servers, and the ground management and control center integrated a digital twin system with an intelligent decision engine to achieve global monitoring and coordinated optimization. By integrating industrial Ethernet and wireless Mesh networks, a highly reliable communication infrastructure was constructed. A digital twin model of fully mechanized top-coal caving face equipment was constructed by combining accurate three-dimensional models with kinematic models, and dynamic synchronization between physical and virtual entities was achieved using a three-dimensional scene automatic construction algorithm. Through multi-source data acquisition and processing, real-time data-driven synchronous mapping, coordinated control of coal cutting and top-coal caving, and multi-system integrated access, coordinated operations of autonomous shearer cutting planning and planned coal caving by hydraulic supports were realized. The application results in an actual coal mine showed that the following rate of the hydraulic supports remained above 97 percent, the automation rate of coal caving exceeded 85 percent, the proportion of manual intervention was lower than 10 percent, and the number of operators per shift was reduced from five to one. The system response latency was less than 200 ms, and the frame rate remained above 30 frames per second, achieving closed-loop management integrating perception, analysis, decision-making, and control.