Weiwei Zhao

The increasingly severe state of coal burst disaster has emerged as a critical factor constraining coal mine safety production, and it has become a challenging task to enhance the accuracy of coal burst disaster prediction. To address the issue of insufficient exploration of the spatio-temporal characteristic of microseismic data and the challenging selection of the optimal time window size in spatio-temporal prediction, this paper integrates deep learning methods and theory to propose a novel coal burst spatio-temporal prediction method based on Bidirectional Long Short-Term Memory (Bi-LSTM) network. The method involves three main modules, including microseismic spatio-temporal characteristic indicators construction, temporal prediction model, and spatial prediction model. To validate the effectiveness of the proposed method, engineering application tests are conducted at a high-risk working face in the Ordos mining area of Inner Mongolia, focusing on 13 high-energy microseismic events with energy levels greater than 10⁵ J. In terms of temporal prediction, the analysis indicates that the temporal prediction results consist of 10 strong predictions and 3 medium predictions, and there is no false alarm detected throughout the entire testing period. Moreover, compared to the traditional threshold-based coal burst temporal prediction method, the accuracy of the proposed method is increased by 38.5%. In terms of spatial prediction, the distribution of spatial prediction results for high-energy events comprises 6 strong hazard predictions, 3 medium hazard predictions, and 4 weak hazard predictions.

In response to the increasingly severe situation of main roadway shock in coal seams, with a focus on the strong-bump coal seam in main roadways under an asymmetric goaf in a certain mine, theoretical analysis, numerical simulation, and engineering practices were employed. This study investigated factors influencing main roadway roof shock damage, changes in roof stress, and characteristics of overlying strata movement. This research unveiled the mechanism and prevention of roof shock in main roadways of strong-bump coal seams in an asymmetric goaf. The research results indicate that the influencing factors of main roadway roof shock damage can be divided into two categories: “strata-support” structure strength and surrounding rock stress. For the determination of the “strata-support” structure, in the case of strong bumps in coal seam roadways influenced by the asymmetric goaf, the key factors contributing to shock damage are the side abutment pressure on the coal pillar in the goaf and the activity level of the roof strata. The distribution of roof stress in the main roadway undergoes continuous changes as district faces are sequentially mined. When the goaf area on the west side gradually increases towards the south, the roof stress in the main roadway consistently rises, and the stress increment follows a pattern of initial increase followed by a decrease. The strata structure of the main roadway roof gradually transforms from an “asymmetric T” shape to a “symmetric T” shape in the transverse profile, and with the evolution of the roof rock layer structure, the mutual feedback effect of strata activity on both sides of the roadway gradually strengthens. Affected by the asymmetric goaf, the main roadway in the district undergoes three different stages: one side of subcritical mining influence → both sides of subcritical mining influence → one side of subcritical mining and one side of critical mining influence. In addition, comprehensively considering the impact of various factors in different stages, the theoretical criteria for roof shock failure in the main roadway are determined. The formulation of an optimized position for the main roadway and a scheme for depressurization through deep-hole blasting in the roof reduce the stress level in the surrounding rock of the main roadway, effectively preventing the occurrence of roof shock in the asymmetric goaf of the coal seam main roadway.

There is a very thick water-bearing key strata above the coal seam in the Binchang mining area. When the mining scale is large, it easily breaks and leads to rockburst with a surge of water gushing in the panel. Adopting the layout pattern of a small panel and a large coal pillar can improve the stability of the main key strata, but at present, the research on the layout pattern of a small panel and a large coal pillar under extra-thick water-bearing key strata is still not perfect. Therefore, taking the second and third panels of a mine in Binchang as the engineering background, the width of the coal pillar and the mining scale of the panel are optimized by means of theoretical analysis, field measurement, and numerical simulation to prevent rockburst and control water inflow. The results show: (1) through theoretical calculation, it is deduced that the critical width of instability of the isolated coal pillar in the current mining scale is 257 m, and the critical mining scale of breaking and instability of the main key strata in the third panel is 537 m; (2) considering the bearing capacity of the isolated coal pillar and the recovery rate of coal resources, the reasonable width of the isolated coal pillar is 210~270 m, and when the width is 200 m and 250 m, the reasonable mining scale of the third panel is 490~550 m and 640~700 m, respectively; (3) the field practice shows that the actual width of the coal pillar between the second and third panels is less than the reasonable width, and the stress concentration in the isolated coal pillar area is relatively high, so the roof deep hole blasting and large-diameter drilling in coal seam are adopted to relieve pressure. After taking pressure relief measures, the stress concentration in the isolated coal pillar area is effectively reduced, and the pressure relief effect is remarkable.