As a non-explosive low-disturbance rock breaking technology, carbon dioxide phase transition blasting (CDPTB) is widely used in rock breaking projects such as pressure relief and permeability enhancement in coal mines, open-pit mining, road subgrade excavation, foundation pit excavation, etc. In this paper, the principle and equipment of CDPTB are systematically analyzed, and the characteristics of a reusable fracturing tube and disposable fracturing tube are determined. Different energy calculation methods are analyzed to determine the magnitude or equivalent explosive equivalent of CDPTB. According to the characteristics of impact stress wave and high-pressure gas, the cracking mechanism of CDPTB is proposed. Under the action of medium-impact stress, rock mass will produce multi-point cracking, and high-pressure gas will produce a gas wedge effect in the initial fracture, which determines the comprehensive action path of the stress wave and high-pressure gas. In terms of fracture characteristics, the fractal method is used to evaluate the macroscopic crack and fragment, microscopic fracture and pore characteristics. In terms of vibration characteristics, the attenuation law of CDPTB vibration with distance is statistically analyzed, and the Hilbert–Huang transform method is used to analyze the time–frequency characteristics of CDPTB. This rock breaking technology can be widely used in different projects, and the existing problems and future challenges are put forward.

Large-diameter gas extraction borehole is considered an effective method by which to realize coal mine methane exploitation and outburst prevention. Efficient gas extraction can be achieved by selecting the right borehole parameters. In this paper, by comparing several conventional objective weighting methods, the PCA was used to assign the weights to the research indices, the optimization objective was reduced from multi-dimensional to one-dimensional with the help of the gray correlation analysis. The study of gas extraction effect under different borehole parameters based on the response surface model. Numerical simulations were used to analyze the mixed volume of gas extraction, the pure volume of extraction and the concentration in the upper corner after extraction under different schemes. Finally, a genetic algorithm degree model was used to solve the solution and determine the optimal arrangement of borehole parameters. The study shows that (1) the weight shares of borehole stratum, borehole diameter and borehole spacing were 0.385, 0.285 and 0.33, respectively, in the reduced dimensional analysis of the PCA. (2) Using the results of improved gray correlation analysis as a comprehensive evaluation value to measure the effect of gas extraction, the optimal range of the model was 28–30 m borehole level, 190–210 mm borehole diameter and 5.5–6.5 m borehole spacing. (3) Using the genetic algorithm to solve the model, we obtained the borehole layer 28.79 m, borehole diameter 199.89 mm, borehole spacing 5.76 m. The borehole gas extraction effect was good under this parameter. The extraction mixed volume was 129.8 m³/min, the extraction pure volume was 9.16 m³/min, the upper corner concentration was 0.52%, and the prediction accuracy of the model was 97.8%.

Deep mining has started in the Huaibei mining area, and the serious threat of high confined water on the floor to the coal seam is gradually increasing. Based on the deep confined water mining project at working face II633 of the Hengyuan coal mine, this paper theoretically analyzes the damage depth of the floor and the risk of water inrush from the floor. The best proportion of grouting materials was quantitatively optimized by indoor experiments, and an industrial field test was conducted to judge the grouting effect. The results show that the failure depth of the bottom plate calculated by theoretical analysis is 31.73 m; a single factor test and a response surface optimization design method determined the best value of each index: water cement ratio 0.8, bentonite 2%, water reducer 0.6%, sodium silicate 2%. The damage depth of the bottom plate after grouting is 18.83~20 m, according to the field monitoring by the strain method. The optimized slurry significantly reduces the damage depth of the floor, ensures the safe and efficient mining of the coal seam above the high–pressure water, and has a high reference value for the safe mining of the coal seam under similar geological conditions.

Influencing factors and sensitivity analysis of coal permeability are significant for reasonably setting coalbed methane (CBM) extraction parameters and increasing CBM output. Seepage tests were conducted on gassy coal using a seepage test system for damaged coal and rock mass under various conditions of axial pressure, confining pressure, and gas pressure. Moreover, the influences of different factors on the permeability of gassy coal and the sensitivity of permeability to these factors were analyzed. Research results show that under the same confining pressure, the relationship between permeability and axial pressure of gassy coal meets the quadratic polynomial function; under the same axial pressure, the permeability changes with the confining pressure as a power function. The permeability of gassy coal is far more sensitive to confining pressure than to axial pressure during axial seepage. Under the same axial pressure and confining pressure (same stress), the permeability of gassy coal reduces at first and then increases in a V-shaped trend with growing gas pressure. There is a turning point in the seepage tests, that is, the critical gas pressure. When the gas pressure is lower than the critical value, the slippage effect plays the leading role in the variation of permeability of the coal; on the contrary, effective stress plays the dominant role. In the non-isobaric deviatoric stress state, the permeability of gassy coal is most sensitive to the confining pressure, followed successively by gas pressure and axial pressure. The research results provide a theoretical basis for precise gas extraction and control in coal seams.

To address the challenges of low accuracy in coal gangue image recognition and poor segmentation performance under the influence of dust in underground coal mines, a scaled simulation platform was constructed to replicate the longwall top coal caving face. This platform utilized real coal gangue particles as the raw material and employed dust simulation to mimic the dust conditions typically found in coal mines. Images of coal gangue without dust and under varying dust concentrations were then collected for analysis. In parallel, an improved DeeplabV3+ coal gangue image segmentation model is proposed, where ResNeSt is employed as the backbone network of DeeplabV3+, thereby enhancing the model’s capability to extract features of both coal and gangue. Furthermore, two channel attention modules (ECAs) are incorporated to augment the model’s ability to recognize edge features in coal gangue images. A class-label smoothing training strategy was adopted for model training. The experimental results indicate that, compared to the original DeepLabV3+ model, the optimized model achieves improvements of 3.14%, 4.70%, and 3.83% in average accuracy, mean intersection over union (mIoU), and mean pixel accuracy, respectively. Furthermore, the number of parameters was reduced from 44.18 M to 43.86 M, the floating-point operations decreased by 8.33%, and the frames per second (FPS) increased by 45.03%. When compared to other models such as UNet, PSANet, and SegFormer, the proposed model demonstrates superior performance in coal gangue segmentation, accuracy, and parameter efficiency. A method combining dark channel prior and Gaussian weighting was employed for defogging coal gangue images under varying dust concentration conditions. The recognition performance of the coal gangue images before and after defogging was assessed across different dust concentrations. The model’s segmentation accuracy and practical applicability were validated through defogging and segmentation of both indoor and underground dust images. The recognition accuracy of coal and gangue, before and after defogging, improved by 6.8–71.8% and 5.8–45.8%, respectively, as the dust concentration increased, thereby demonstrating the model’s effectiveness in coal gangue image defogging segmentation in underground dust environments.