To reveal the fracture mechanism of overburden aquifers during mining under anticlinal structural zones in western mining areas, this study takes Panel 1309 of the Guojiahe Coal Mine as the engineering background and employs field investigations, physical similarity simulation, and numerical simulation methods to systematically investigate the overburden fracture and crack evolution laws during extra-thick coal seam mining in anticlinal zones. The research results demonstrate the following: (1) The large slope angle of the anticlinal zone and significant elevation difference between slope initiation points and the axis constitute the primary causes of water inrush-induced support failures in working face 1309. The conglomerate of the Yijun Formation serves as the critical aquifer responsible for water inrush, while the coarse sandstone in the Anding Formation acts as the key aquiclude. (2) Influenced by the slope angle, both overburden fractures and maximum bed separation zones during rise mining predominantly develop toward the goaf side. The water-conducting fracture zone initially extends in the advance direction, when its width is greater than its height, and changes to a height greater than its width when the key aquifer fractures and connects to the main aquifer. (3) The height of the collapse zone of the working face is 65 m, and the distribution of broken rock blocks in the collapse zone is disordered; after the fracture of the water-insulating key layer, the upper rock layer is synchronously fractured and activated, and the water-conducting fissure leads to the water-conducting layer of the Yijun Formation. (4) Compared to the periodic ruptures of the main roof, the number of fractures and their propagation speed are greater during the initial ruptures of each stratum. Notably, the key aquiclude’s fracture triggers synchronous collapse of overlying strata, generating the most extensive and rapidly developing fracture networks. (5) The fracture surface on the mining face side and the overlying strata separation zone jointly form a “saddle-shaped” high-porosity area, whose distribution range shows a positive correlation with the working face advance distance. During the mining process, the porosity variation in the key aquiclude undergoes three distinct phases with advancing distance: first remaining stable, then increasing, and finally decreasing, with porosity reaching its peak when the key stratum fractures upon attaining its ultimate caving interval.

In order to solve the problem of support crushing, rib spalling, and partial roof fall in working face crossing fault structure area, taking II1023 working face of Haizi Mine as the engineering background, the numerical simulation, theoretical analysis, and field measurement were used to simulate the rock activity law in the process of working face crossing fault. Based on this, the mechanical model of the interaction between the support and the surrounding rock in the fault area was established, and the calculation formula of the support strength required by the support under different equilibrium criteria was deduced, which provides a basis for the reasonable selection of hydraulic support. The results show that the rock stress of the working face passing through the fault zone is divided into high-stress section when it is gradually close to the fault and low-stress section after passing through the fault. In the high-stress section, the rock stress increases in front of the working face, and the distribution form is similar to the stress distribution of the narrow coal pillar. The roof easily forms a long hanging roof and slip along the fault surface, which is prone to rib spalling and partial roof fall and support crushing. The support strength is mainly related to fault dip angle, fault cohesion, support beam length, length of the main roof rock beam, and the distance between working face and fault. The reasonable support strength should be determined by the calculation results under different equilibrium criteria. When the working face advances in the high-stress section, the required support strength of the support increases with the increase of the fault dip angle and the length of the main roof rock beam and decreases with the increase of the fault cohesion, the length of support beam, and the distance between working face and fault. With the increase of the fault dip angle, the form of rotary instability changes and the probability increases. The field practice shows that during the fault crossing of the II1023 working face, the working resistance of the support shows the characteristics of high-pressure area and low-pressure area, but it does not exceed the rated working resistance of the selected support. The fully mechanized coal face passed through the fault area safely, and there were no accidents such as support crushing, rib spalling, and partial roof fall.

Aiming at the problem of large deformations and difficult maintenance of cross-mining floor roadways, taking the track transportation roadway of the cross-mining east wing floor in Qinan Coal Mine as the engineering background, the stress field distribution of mining stress in floor strata and surrounding rock of floor roadway during the cross-mining process of the working face is studied by combining theoretical analysis with numerical simulation. The results show that the influence of mining stress on the vertical stress of floor strata is reflected in the stress-increasing area in front of the coal wall and the stress-decreasing area in the rear of the coal wall. With the increase in the depth of the floor strata, the peak value of the vertical stress gradually decreases, and the distance from the peak value of the vertical stress to the coal wall and the influence range of the vertical stress gradually increases. When the width of the coal pillar is greater than the influence range of advance abutment pressure of the working face, the development speed of the plastic zone is slow. When the roadway is located in the influence range of advance abutment pressure, the plastic zone of the roadway’s surrounding rock develops rapidly. When the working face crosses the floor roadway more than 10 m, the depth of the plastic zone of the surrounding rock of the roadway is no longer increased; the siltstone above the roadway is the key layer of fracturing, and the deformation of the roadway has been effectively improved after hydraulic fracturing. Through the analysis of numerical simulation results, the fracturing scheme has a significant effect on the stability control of the surrounding rock of the cross-mining floor roadway. This study has certain guiding significance for the maintenance and sustainable utilization of floor roadways in the cross-mining process, which is conducive to ensuring the sustainable mining of underground coal and the safety of personnel and equipment and is of great significance to the sustainable development of the coal mining industry.

Coal is the main energy source in China, but coal mining is a high-risk industry, making the prevention and control of coal mining hazards an important topic. Constrained by the complexity and unpredictability of underground spaces, current research on coal mining disaster prevention and control technologies mainly focuses on the characteristics of overlying strata and the laws of mine pressure, resulting in significant deficiencies in accuracy. Given this, a data-driven pressure prediction method is proposed, which uses deep learning models to learn the patterns in existing data and generate the required predictions. This approach avoids the challenges of accurately extracting rock mass physical and mechanical parameters and geological structure modeling, thereby improving the accuracy of disaster prevention and control. The stage of working face pressure exertion is a period prone to disasters during coal mining. To achieve accurate prediction of working face pressure, the task is divided into three steps: the first step is to predict support resistance data ahead of the working face, the second step is to classify the pressure labels of coordinate units, and the third step is to predict the characteristic parameters of pressure exertion. Deep learning models were designed and trained separately for each of the three steps: For the first step, a deep Spatiotemporal sequence model was selected, and the trained model achieved a mean absolute error of 4.65 kN in prediction. For the second step, an image segmentation-based classification model was chosen, with the trained model reaching a classification accuracy of 97.77%. For the third step, a fusion model consisting of three LSTM (Long Short-Term Memory) networks was designed. The trained model achieved a mean absolute error of 0.17 for the dynamic pressure coefficient, a maximum resistance error of 810.93 kN during the pressure period, an error of 9.96 cycles for the pressure duration, and a classification accuracy of 92.35% for the pressure type. Simulating the actual situation of application scenarios, the input data for the second and third steps were set as the output data from the previous step, and the model was evaluated. The model achieved a mean absolute error of 1035.21 kN for the prediction of support resistance and classification accuracy of 82.90% for the pressure labels of coordinate units. In the simulated scenario, there were 9922 instances of pressure exertion, and the model predicted 10,336 instances, with 9046 of them matching the actual instances. The prediction of characteristic parameters was evaluated for 4946 instances of pressure exertion, which included three complete pressure exertion cycles. The mean absolute error for the dynamic pressure coefficient was 0.21, the maximum resistance error during the pressure period was 1218.31 kN, the error for the duration of the pressure cycle was 11.03 cycles, and the classification accuracy for the pressure exertion type was 91.75%.

In order to avoid the problem of repeated repair of roadways in the upper mining area of upward mining in the integrated mine, taking the roadways in the 302 mining area of Shancheng Coal Mine as the research object, the failure characteristics of overlying strata and the evolution characteristics of roadway plastic zone in the mining process of underlying coal seam were studied by combining theoretical analysis, numerical simulation, and engineering measurement. The influence law of underlying coal seam mining on the integrity of 3# coal seam and the stability of roadways in the 302 mining area was revealed, and the repair opportunity of roadways in the upper coal seam and the reasonable position of open-off cut in the lower coal seam working face were determined. The research shows that due to the influence of the mining of the working face in the underlying coal seam, the plastic failure of the overlying strata is serious during the upward mining of Shancheng Coal Mine, but there is no step dislocation, but the overall subsidence is presented. The plastic zone range of roadway in 302 mining area first increases and then tends to be stable with the mining of 97308 working face in underlying coal seam, and the roadway repair should be carried out after 280 m advance of 97308 working face. Based on the coordination between the influence of the cutting position of the underlying coal seam on the variation characteristics of the plastic zone of the upper roadway and the saving of coal resources, it is determined that the cutting position of the underlying 153308 working face is advanced to 340 m. The field engineering application shows that the deformation of roadway surrounding rock meets the production requirements by implementing the above mining parameters, and the rerepair of roadway surrounding rock deformation in 302 mining area of 3# coal seam is avoided.

The extremely soft coal seam roadway has the problems of low surrounding rock strength and difficult support. Based on the engineering background of the mining roadway in the extremely soft coal seam of the Quandian coal mine, this paper adopts the research method combining numerical simulation and field measurement. The stress field, displacement field, support force, and loading arch structure characteristics of roadway surrounding rock under bolt-mesh-cable support and existing shed-cable support are compared, and the control principle of bolt-mesh-cable in extremely soft coal seam roadway is expounded. Our study indicated that compared with nonsupport and shed-cable support, the pressure stress range of the surrounding rock in extremely soft coal seam increases, and the stress gradient decreases when bolt-mesh-cable support is used. The roadway displacement and displacement difference decrease. The components of the support achieve stress coordination. The thickness of the loading arch formed in the surrounding rock is large, and the compressive stress in the arch is evenly distributed. The bolt-mesh-cable significantly improves the stress environment and the stability of the roadway. The field practice shows that the roadway deformation is small after the bolt-mesh-cable support is adopted, and the roadway section during excavation and mining meets the requirements of safety production.