矿业科学学报 (Aug 2022)

Technology path and assumptions of intelligent surrounding rock control at longwall working face

  • Yang Shengli,
  • Wang Jiachen,
  • Li Ming

DOI
https://doi.org/10.19606/j.cnki.jmst.2022.04.002
Journal volume & issue
Vol. 7, no. 4
pp. 403 – 416

Abstract

Read online

The intelligent surrounding rock control at longwall working face is the necessary condition to realize the intelligent mining of working face. This paper redefined the connotation of the surrounding rock system at longwall working face and clarified the scope of surrounding rock control and clarified the scope of surrounding rock control, which includes small structure of support surrounding rock within its basic topic range in the vertical direction, and the far field rock layer that will have an effect on surrounding rock control at longwall working face. The factors of surrounding rock system at longwall working face are classified, there are "controllable factors" and "uncontrollable factors" according to the mode of action. The points and basic principles of intelligent surrounding rock control are determined. Multi-parameter intelligent detection, precise analysis of pattern discriminations, self-determination, quick implementation and dynamic evaluation of control effects which is technological framework for intelligent control is established. Furthermore, scientific issues and critical technical problems of intelligent surrounding rock control at longwall working face are elaborated. The four key technology assumptions based on this are "intelligent mining system at working face", "adaptive intelligent control technology of equipment-surrounding rock", "intelligent control of complex conditions surrounding rock", and "stability analysis of surrounding rock system at longwall working face under unified coordinate system". The extractability of the information on the working conditions of support is analyzed with the actual case, and the intelligent prediction of mine pressure at longwall working face is realized by the stacked LSTM algorithm.

Keywords