Coal mine safety may be able to be ensured via the real-time identification of cracks in rock and coal surfaces. Traditional crack identification methods have the disadvantages of slow speed and low precision. This work suggests an improved You Only Look Once version 5 (YOLOv5) detection model. In this study, we improved YOLOv5 from the perspective of three aspects: a Ghost module was introduced into the backbone network to lighten the model; a coordinate attention mechanism was added; and ECIOU_Loss is proposed as a loss function in this paper to achieve the co-optimization of crack detection speed and accuracy and to meet the deployment requirements in the embedded terminal. The results demonstrate that the improved YOLOv5 has a 92.8% mean average precision (mAP) with an 8 MB model size, and the speed of recognition was 103 frames per second. Compared to the original method, there was a 53.4% reduction in the number of parameters, a detection speed that was 1.9 times faster, and a 1.7% improvement in the mAP. The improved YOLOv5 can effectively locate cracks in real time and offers a new technique for the early warning of coal and rock dynamic hazards.

Rock burst is a sudden disaster that is influenced by various factors. Accurately identifying and predicting rock burst risks is of great significance for improving mine safety. In order to improve the accuracy of rock burst prediction from the perspective of data structure, this paper constructs a two-level prediction model based on six rock burst features. The first-level model uses Box-Cox, Yeo-Johnson, and uniform transformations for data scaling and extends the data using the CTGAN architecture, followed by feature dimension optimization. The second-level model uses the K-Means algorithm to reconstruct labels and enhance inter-class differences, and visualizes clustering effects using ISOMAP. At the algorithm optimization level, an ensemble model stacked with 8 algorithms and a deep forest are used for prediction. The results show that data transformation, increasing model complexity, and appropriate feature expansion can effectively improve prediction accuracy. The single model achieved a maximum accuracy of 81.25%, and the established two-level model outperformed a single machine learning method, with an accuracy improvement of 17.3%. Feature dimension optimization had the highest accuracy improvement of 6.3%. Through comparison, it was found that the deep forest has a prediction accuracy of 98.6%, which is superior to other models such as Gradient Boosting and Multilayer Perceptron. In addition, the SHAP value and 7 evaluation indicators were used to evaluate the model and further explain the prediction results. The proposed two-level rock burst prediction model provides a certain reference value for accurately predicting rock bursts.

With the gradual shift of coal mining to deeper levels in recent years, rock burst has become one of the primary dynamic hazards faced in deep mining. It has been shown that the pore structure in rocks affects the mechanical properties, but the relationship with the rock burst phenomenon still needs to be clarified. In this paper, we investigated the causes and effects of pore structure on impact mechanical properties using RFPA2D numerical simulation software, established several numerical models with different porosities and pore diameters, and analyzed the stress-strain curves, the relationships between porosity and pore diameter and each the bursting liability indices of the coal rock body were elaborated, and the fitting equations in the range of porosity (0%~10%) and pore diameter (0.25~2.0 mm) were obtained. The results showed that the increase in porosity and pore diameter effectively attenuated the bursting ability of coal rocks, which has some reference significance for the study of early warning and prevention of rock burst phenomenon.

Fractured coal in the residual-strength stage is a primary medium for gas migration and drainage in deep mining areas. To investigate the hydro–mechanical seepage response of post-peak fractured coal under constant-pressure-difference conditions, triaxial CO₂ seepage tests were conducted on coal specimens collected from the Xinyuan Coal Mine. A Weibull-based damage constitutive model was established to characterize the confining-pressure-induced hysteresis in the damage-evolution path. The flow-rate evolution and Reynolds number analysis indicated that gas flow remained within the linear Darcy regime. A controlled-variable analysis was used to examine the competing effects governing permeability evolution. Mechanical compaction induced an exponential decrease in permeability, whereas the decrease in permeability with increasing pore pressure was interpreted, within the proposed model framework, as the combined effect of possible adsorption-induced matrix swelling and weakened gas slippage. To address the limitations of conventional constant-slip-factor models, a pressure-dependent slip modulation coefficient was introduced into a composite permeability equation incorporating effective stress, adsorption-related deformation, and dynamic gas slippage. Global nonlinear fitting yielded R² = 0.97 and an RMSE of 0.1909, with the residuals generally distributed around zero, supporting the fitting reliability of the model within the investigated stress–pressure range. Response-surface analysis identified mechanical compaction as the dominant controlling mechanism, while adsorption-related deformation and gas slippage acted as secondary correction mechanisms. The proposed framework provides a quantitative basis for distinguishing the mechanical and fluid-related effects governing permeability evolution in post-peak fractured coal.

The paper introduces a new type of large-scale coal mine dust monitoring and efficient treatment technology, which realizes online continuous monitoring and control of mine dust concentration, and can transmit the dust concentration at the detection point to the underground control system in real time, realizing intelligent coal mine dust management, When the dust concentration exceeds the set standard, the coal shearer and road header can automatically carry out high-pressure spraying to reduce dust. Compared with the traditional technology, the dust removal efficiency is increased by more than 80%.