The differential distribution of original rock stress and stress concentration caused by the variation in coal seam depth in karst topography are critical factors influencing the selection of roof-cutting parameters. Based on this, this study explores a method to determine reasonable roof-cutting parameters by incorporating the characteristics of coal seam depth variation in karst mountainous areas. A mechanical model of the cantilever beam structure for roof cutting in gob-side entry retention (GSER) is constructed, and the critical values and reasonable ranges of roof-cutting height and angle under different burial depths are derived. Furthermore, the displacement and stress evolution characteristics of surrounding rocks in gob-side entry retention under different coal seam burial depths, roof-cutting heights, and roof-cutting angles within the reasonable range of roof-cutting parameters are analyzed. The results show that there is a positive correlation between roof-cutting height and tensile stress in the uncut portion of the main roof, while roof-cutting angle and coal seam depth are negatively correlated with tensile stress. From the perspective of impact, roof-cutting height has a greater impact than roof-cutting angle, followed by coal seam depth. As for the distribution characteristics of the reasonable roof-cutting parameter range, the fan-shaped area of reasonable roof-cutting parameters gradually decreases with increasing coal seam depth. Taking the geological conditions of Anshun Coal Mine as an example, when the burial depth increases from 350 m to 550 m, adjusting the roof-cutting height to 6 m, 7 m, and 8 m, respectively, and setting the roof-cutting angle at 10° can effectively achieve the stability of the surrounding rock in the GSER. The research findings can provide a scientific basis and engineering references for selecting roof-cutting parameters in mines with similar geological conditions.

The width of a stop-mining coal pillar is of great significance to the stability of the surrounding rock of the main roadway and the safety of production in the mine. This paper focuses on the west panel of Sihe Coal Mine as the engineering background, analyzes the evolution characteristics of front abutment pressure in the mining area under conditions of rapid advancement and large mining height and its sensitivity to influencing factors, explores the coupling mechanism between the width of the stop-mining coal pillar and the surrounding rock of the main roadway, and analyzes the differences in mining pressure characteristics such as internal stress of the coal pillar, vertical stress, deformation, and failure of the main roadway’s surrounding rock under different coal pillar widths with the influence of mining. The comprehensive results indicate that the influence range of front abutment pressure on the working face is 65 m, and the significance ranking of different mining factors acting on it is as follows: mining height > working face length > advancing speed. The rational width of the stop-mining coal pillar is determined to be 80 m while the stress field of the surrounding rock in the main roadway is in a critical state of mining disturbance. Industrial tests have shown that the relative displacements between the roof and floor as well as the ribs of the main roadway are relatively small, at 105 and 260 mm, respectively, which can effectively maintain the stability of the surrounding rock of the main roadway. The research results can provide a scientific basis and engineering reference for the design of stop-mining coal pillars in mines with similar geological conditions.

After a mine water inrush occurs, it is crucial to quickly identify the source of the water inrush and the key control area, and to formulate accurately efficient water control measures. According to the differences in water chemical characteristics of four aquifers in the Fenyuan coal mine, the concentrations of K⁺~Na⁺, Ca²⁺, Mg²⁺, Cl⁻, SO₄²⁻, and HCO₃⁻ were taken as water source identification indexes. A decision tree classification model based on the C4.5 algorithm was adopted to visualize the chemical characteristics of a single water source and extract rules, and intuitively obtained the discrimination conditions of a single water source with Mg²⁺, Ca²⁺, and Cl⁻ as important variables in the decision tree: Mg²⁺ < 39.585 mg/L, Cl⁻ < 516.338 mg/L and Mg²⁺ ≥ 39.585 mg/L, Ca²⁺ < 160.860 mg/L. Factor analysis and Fisher discriminant theory were used to eliminate the redundant ion variables, and the discriminant function equations of the two, three, and four types of mixed water sources were obtained successively in turn. This paper puts forward MSE, RMSE, and MAE as the evaluation indexes of the water source mixing degree calculation models and obtains the ranking of the pros and cons of the mixed water source mixing degree calculation models. The results show that the minimum inscribed circle analytical method is the optimal model for the calculation of the mixing degree of two types of water sources, and the MSE, RMSE, and MAE are 0.17%, 4.13%, and 4.13%, respectively. The minimum inscribed circle clustering method is the optimal model for the calculation of the mixing degree of three types of water sources, and the minimum distance method is the optimal model for the calculation of the mixing degree of four types of water sources. The method of mine water source identification based on the decision tree C4.5 algorithm and mixing degree calculation has the characteristics of a simple calculation process, high efficiency, objective accuracy, and low cost, which can provide a scientific basis for the development of stope water control measures.