Search

To address the challenges of fracture recognition in the CT scanning images of coal or rock, particularly the interference of gangue and the recognition of fractures at different scales, proposed and implemented a network model for coal-rock fracture extraction based on deep learning (MCSN). According to the U-Net architecture, the model utilized its encoder-decoder structure and skip connections to segment the fracture structure images from complex coal-rock body images. Firstly, the fracture structures in the CT scanning images were annotated manually using the internal scan images captured by a coal industrial CT scanning system. And the annotated original data was augmented to create a coal-rock CT fracture dataset. Subsequently, to make the extraction network of main features have a stronger extraction capability of fracture structure features, the weights of a pre-trained VGG16 model were transferred to the U-Net encoder through a transfer learning technique. Simultaneously, the decoder part of the U-Net model was improved using the deep separable dilated convolutional modules (DCAC) and residual modules to effectively boost the recognition capability of fracture structures in the CT images, demonstrating a superior segmentation accuracy and robustness. To validate the effectiveness of the coal-rock fracture extraction network model proposed, the results obtained by the MCSN were compared with those of classical convolutional neural networks and threshold segmentation methods. Experimental comparisons revealed a significant advantage of the model proposed in both qualitative and quantitative analyses. The proposed model, employing a multi-scale fusion strategy, demonstrated the capability to effectively extract fractures in complex coal-rock images, thereby enhancing the efficiency and accuracy of fracture identification. The model was applied to the identification of fractures in roadway surrounding rock based on borehole imaging. Fracture extraction was performed through the analysis of borehole videos and planar unfolded images collected by a borehole imaging instrument. The results from both sources were cross-validated to obtain an accurate distribution of fractures in roadway surrounding rock. Furthermore, the model provides guidelines for the injection and sealing of boreholes, increasing volume fraction of coal seam gas extraction.

Using an impact damage-percolation experimental system for gas-bearing coal or rock, the authors carry out various gas-bearing coal impact experiments with in-situ seepage tests to reveal the law of dynamic mechanical characteristics, fracture expansion, and permeability changes of gas-bearing coal under different impact loads and gas pressures loading. Using an industrial CT scanning system, the authors conduct a 3D reconstruction of the fracture structure in order to analyze the internal fracture expansion characteristics of gas-bearing coal and the influence law on gas permeation patterns. The results show that both the impact load and gas pressure play an important role in the dynamic mechanical properties, deformation process, fracture expansion, and gas permeation patterns of gas-bearing coal: ① Under the coupling of impact load and gas pressure, the stress-strain curve of gas-bearing coal has an inconspicuous compaction stage due to the influence of confining pressure and axial pressure. The deformation process of gas-bearing coal includes elastic deformation stage, strain strengthening stage, and failure stage. ② The increase of impact load will increase the dynamic mechanical parameter value of gas-bearing coal, while the increase of gas pressure will reduce the value. The greater the impact load, the higher the gas pressure, and the more sufficient the fracture expansion of gas-bearing coal. At the same time, the fracture structure is more complex. ③ The seepage law of gas-bearing coal is controlled by fracture expansion. Under the coupling of impact load and gas pressure, three types of gas flow exist in gas-bearing coal: pore flow, coexistence of pore flow and fracture flow, and fracture flow. After the impact failure of gas-bearing coal, the gas flow pattern can transition from pore flow to coexistence of pore flow and fracture flow, and eventually to fracture flow, as the gas pressure increases and the influence of gas wedges intensifies. Fracture expansion and flow patterns jointly affect the seepage law of gas-bearing coal. The permeability of gas-bearing coal generally exhibits a trend of initially increasing and then decreasing with the increase of gas pressure.

With the development of coal seam fracturing technology, promote the gas extraction by liquid nitrogen cold soaking fracturing coal has attracted widespread attention. In order to study the effect of liquid nitrogen cold soaking on the microstructures of different coals (lean coal, fat coal and anthracite) before and after liquid nitrogen cold soaking, the scanning electron microscopy (SEM), pore size distribution instrument and physical adsorption instrument were jointly characterized. The influence of liquid nitrogen cold soaking on the distribution of pore volume and specific surface area of different coal samples was comparatively analyzed. The results show that the thermal stress generated during the liquid nitrogen cold soaking destroys the microstructure of the coal or causes the initiation of micro-cracks, After liquid nitrogen cold soaking, the total pore volume and specific surface area of coal samples increase. The total pore volume growth rate of fat coal is the lowest, followed by anthracite, and the lean coal’s is the highest. The volume of micropores, micropores, meso-pores and macropores/fractures in the coal samples increase. cold leaching of liquid nitrogen causes macropores to pass through and form macropores/fissures in coal samples, resulting in the reduction of pore volume of macropores. After liquid nitrogen cold soaking, the pore specific surface area of each coal sample concentrate in the range of 10 − 100 nm, and has obvious peak characteristics. Liquid nitrogen cold soaking can increase the adsorption capacity of lean coal, fat coal and anthracite coal samples, and the adsorption capacity difference is the largest in the middle high pressure region (0.4 < p/p0 < 1.0). Liquid nitrogen cold soaking can effectively transform the internal microstructure of different coals. The research results are helpful to reveal the spatial expansion and connectivity of macroscopic and microscopic pore fractures in coal reservoirs during liquid nitrogen cracking.

Using an impact damage-percolation experimental system for gas bearing coal or rock and an industrial CT scanning system, the authors design and carry out a series of dynamic compression-seepage tests for loading at different impact velocities under triaxial prestressed states and reconstruct the three-dimensional crevices structure of the impact-damaged sandstone in order to reveal the law of damage features and permeability of the gas bearing sandstone under different impact loads. The experimental results of dynamic stress-strain curve characteristics, energy dissipation laws, damage and permeability evolution features under different impact velocities loading of fluid-solid coupling sandstone samples show that as the impact loading velocity increases, the strain rate of the gas bearing sandstone increases. The incident wave energy, reflection wave energy, transmission wave energy and absorption energy increase simultaneously as well. The peak stress and peak strain of gas bearing sandstone increase with the impact velocity as well, and the compaction stage in the dynamic stress-strain curve is constantly compressed until it disappears completely. The failure form of gas bearing sandstone is mainly shear failure under the condition of triaxial static and gas-solid coupling. With the increase of impact velocity, the number of tensile cracks under the combination of impact load and gas pressure increases continuously. Poisson's ratio effect and eccentric compression form two types of tensile cracks along the axial direction or perpendicular to the sample. The two types of tensile cracks are connected along the outer edge of the specimen, showing a grid shape. Nascent cracks are interconnected, which drives macroscopic through cracks formation. The absorption energy of gas bearing sandstone directly determines the degree of damage. The increasing absorption energy not only increases the damage degree of gas bearing sandstone after damage, but also greatly improves the permeability. The permeability of gas bearing sandstone after impact damage follows a linear positive correlation with its crack rate.