Due to the complex geological conditions of coal-rock, the cutting head of coal mine excavation machines experiences severe fluctuations in loads, making it difficult for existing macroscopic controls to accurately capture the microscopic loads on the cutting pick. Therefore, a dynamic simulation and intelligent control model for the cutting head load of an adaptive roadheader based on multi-scale coupled simulation is developed. The study first modifies the classical load model through finite element method to accurately simulate the microscopic interaction between the cutting pick and the rock mass. The non-dominated sorting genetic algorithm II in elite strategy is used to construct a multi-objective optimization model to determine the optimal parameters for cutting head speed and swing speed. Finally, load dynamic control is achieved by combining radial basis function proportional-integral-derivative controller, and multi-body dynamics-discrete element method and proximal policy optimization are introduced to improve the adaptability to complex working conditions. Test results from different operation scenarios showed that the path planning error of the model met high-precision excavation requirements in regular roadways. During the long-term stable operation phase, the energy consumption ratio and energy utilization efficiency were significantly improved compared to traditional solutions. Faced with slight changes in coal-rock hardness, this model provided early warnings effectively. Under single-point fracture failure, load stability was quickly restored. In the constant operating condition performance test, the model demonstrated significant steady-state control accuracy with minimal mean square error and zero overshoot. Furthermore, a pilot engineering application in a high-gas coal mine roadway demonstrated that the relative error between the simulated and measured loads was controlled within 6.5%, validating the practical feasibility of the proposed system. This study can effectively reduce pick failure, improve excavation efficiency, provide core technical support for the "less manpower, unmanned" operation of coal mines, and assist in the safe and efficient upgrading of the coal industry.
Feng et al. (Mon,) studied this question.