Cross-scale correlation analysis of water-induced deterioration on soft rock in coal mine underground reservoir engineering based on deep learning algorithm

Abstract Soft rock is one of the common geological conditions in coal mine underground water reservoir engineering. The cross-scale correlation analysis of water erosion soft lithology deterioration is very important for the safety and stability of coal mine underground reservoir (CMUR) engineering. To address the issues of grain crowding and segmentation difficulties in cross-scale correlation analysis, as well as the limitations of traditional etching methods, this study proposes an image grain segmentation method based on deep learning algorithms, utilizing scanning electron microscopy and image processing techniques. The method successfully segments crowded grains and eliminates the interference from misplaced particles. In addition, indoor uniaxial compression tests were conducted to obtain the mechanical properties of sandstone samples with different water content. By quantitatively characterizing the macroscopic and microscopic deterioration degree of red sandstone samples with different water contents, the relationship between the strength changes of rock samples and the petrographic parameters such as grain size and grain shape is analyzed, and the influence law of soft lithology deterioration in CMUR engineering is revealed. The results indicate: (1) Water significantly weakens the mechanical properties and stability of soft rock. With increasing water content, the strength of sandstone samples continuously decreases, and the failure mode transitions from brittle to ductile failure. (2) The deterioration of micro-micro structures is the main cause of the decrease in mechanical properties of water-eroded soft rock. Grain size, grain area, and aspect ratio are negatively correlated with water content, indicating that hydrophilic minerals in soft rock dissolve under the action of water, leading to rock damage. (3) Grain size, area, and aspect ratio can serve as significant indicators for quantifying the strength changes of water-eroded soft rock. The research findings can be applied to stability assessment and disaster prevention in CMUR engineering.