Research on the intelligent coordinated top-coal caving model and key technologies in extra-thick coal seams

LI Dongyin; WANG Zuguang; WANG Shen; LI Huamin; PENG Weiping; LI Hongbin; ZHANG Guopeng; ZHANG Xuhe

doi:10.16186/j.cnki.1673-9787.2024060059

Abstract：Objectives Fully mechanized top-coal caving is a safe and efficient mining method for extra-thick coal seams.However,the complexity of the caving environment,the challenges in coordinating min-ing and caving,and the numerous factors influencing caving parameters have hindered the development of intelligent fully mechanized top-coal caving,particularly in terms of automated coal caving control technol-ogy.Methods To address the challenges of intelligent coal caving control under group caving conditions in fully mechanized top-coal caving faces of extra-thick coal seams,this study employs theoretical analysis,laboratory simulation experiments,computer control software development,and field trials.The research follows the framework of"mechanism of intelligent group caving-theory and methods of mining-caving coor-dination control-decision-making model for coal caving processes-field application of coal caving software."Results The study proposes a multi-outlet group cooperative caving method.Taking the continuous group caving method as an example,the spatial relationship between the top-coal caving body and the coal-rock interface under group cooperative caving is revealed.By analyzing the coordination relationship between mining and caving and the logic of group caving in fully mechanized top-coal caving faces,this study estab-lishes a theoretical framework for intelligent mining-caving coordination control in extra-thick coal seams.A coordinated control model for mining and caving in terms of time,space,and material transport capacity is developed,along with a group caving decision-making method based on reinforcement learning and the Hid-den Markov Random Field(HMRF)model,providing a reliable theoretical foundation for intelligent cav-ing decision-making and precise control.Furthermore,a multi-source information database for fully mecha-nized top-coal caving faces is established by integrating geological information with mining and caving pro-cess parameters,laying the groundwork for intelligent decision-making and digital twin applications.Con-clusions Based on the mining-caving coordination characteristics under group caving conditions,an intelli-gent caving decision-making model is developed,and an intelligent caving decision support system(soft-ware)is independently designed and implemented.Field application of this software has enabled an annual coal production capacity of 15 million tons in intelligent fully mechanized top-coal caving faces.