An algorithm based on the YOLOv5 model is proposed to address safety incidents such as tearing and blockage at transfer points on belt conveyors in coal mines caused by foreign objects mixed in with the coal flow. Given the tough underground conditions and images acquired with low quality, recursive filtering and MSRCR image enhancement algorithms were utilized to preprocess the dynamic images collected by underground monitoring devices, substantially enhancing image quality. The YOLOv5 model has been improved by introducing a multi-scale attention module (MSAM) during the channel map slicing, thereby increasing the model’s resistance to interference from redundant image features. Deep separable convolution was utilized in place of conventional convolution to detect, identify, and process large foreign objects on the belt conveyor as well as to increase detection speed. The MSAM-YOLOv5 model was trained before being installed on the NVIDIA Jetson Xavier NX platform and utilized to identify videos gathered from the coal mine belt conveyor. According to the experimental findings, the upgraded MSAM-YOLOv5 model has a greater recognition accuracy than YOLOv5L, with an average recall rate for different foreign objects of 96.27%, an average detection accuracy of 97.35%, and a recognition speed of 44 frames/s. The algorithm assures detection accuracy while increasing detection speed, satisfying the requirements for large foreign object detection on belt conveyors in coal mines.

The presence of gas content in medium- and high-rank coal poses a threat to safety production. Safe gas extraction is based on a correct understanding of the pore structure of coal. This work investigates the pore structure characteristics of medium- and high-rank coal and evaluates their fractal structure. The coal samples were collected from Huainan Coalfield and Qinshui Coalfield, and divided into four types, according to the difference in surface bright characteristics. Through adopting low-temperature liquid nitrogen adsorption and desorption, and applying Kelvin equation, we obtain the main pore structure types and main pore size distribution characteristics of various coal briquettes. Electron microscope scanning structure and scientific analysis were used for special adsorption and desorption curves and hysteresis to find the dynamic reason. According to the different adsorption mechanism and Frenkel–Halsey–Hill-based model, with P/ P₀ = 0.4 as the dividing point of fractal dimension analysis, the pore structure of coal samples is classified into five grades. The fractal evaluation results are consistent with the results of curve analysis and pore size analysis.

Deep-hole presplitting blast technology is an effective method to intensively increase the permeability of coal seam and high-efficiency extract gas. Aimed at the drivage shaft working place of opening No. 13-1 Coal seam influenced by fault in Panyi Coal Mine, this paper comprehensively took advantage of the technology of deep-hole presplitting blast and intensified increasing permeability, the technology of reinforcing coal body using metal skeleton, as well as the technology damming and extracting gas of outside of metal skeleton, diminished the outburst risk only after 18 days, and got the purpose of rapidly diminishing outburst risk. And this provided an effective solution of rapidly diminishing outburst risk and safety opening coal seam for similar conditions.

In this paper, the fractal dimension of coal surfaces was calculated using the fractal theory, and the influence of different surfactants on the fractal dimension of coal surface was studied. Six kinds of sustainable and traditional surfactants used in coal gas desorption processes were compared and analyzed. We used mineral gas fertilizer coal from Huainan Liuzhuang, China, as the research object and studied sodium dodecyl benzene sulfonate (SDBS), cohol diethanolamide (CDEA), nonylphenol polyoxyethylene ether (NP-10), tea saponin, sucrose ester and rhamnolipid surfactants used to modify coal. The methane adsorption capacity of coal before and after surfactant modification was measured by low field nuclear magnetic resonance methane adsorption, and Langmuir volume and Langmuir pressure were obtained according to the Langmuir fitting equation. The results showed that from the perspective of fractal dimensions, the best surfactant in the context of sustainability (in order) is rhamnolipid, CDEA, tea saponin, sucrose ester. According to the two important parameters V_L and P_L in the Langmuir equation, the coal sample modified by sucrose ester had the strongest gas adsorption capacity. According to the numerical analysis of the surface fractal dimension D_S of the coal modified by surfactants, the soluble organic matter in the raw coal samples dissolved, and the micropore morphology evolved to become mesoporous or macroporous, which is more favorable for desorption. The coal samples modified by rhamnolipid and SDBS had the strongest gas desorption ability.