In order to study the fractal characteristics of the pomegranate biotite schist under the effect of blasting loads, a one-dimensional SHPB impact test was carried out to test the dynamic compressive strength, damage morphology, fracture energy dissipation density, and other parameters of the rocks under different strain rates; besides, sieve tests were conducted to count the mass fractal characteristics of the crushed masses under different strain rates to calculate the fractal dimension of the crushed rock . Finally, the relationships between fractal dimension and dynamic compressive strength, crushing characteristics, and energy dissipation characteristics were analysed. The results show that under different impact loads, the strain rate effect of the rock is significant and the dynamic compressive strength increases with the increasing strain rate, and they show a multiplicative power relationship. The higher the strain rate of the rock, the deeper the fragmentation and the higher the fractal dimension, and the fractal dimension and rock crushing energy density are multiplied by a power relationship. By performing the comparative analysis of the pomegranate biotite schist, a reasonable strain rate range of 78.75 s^-1~82.51 s^-1 and a reasonable crushing energy consumption density range of 0.78 J·cm^-3~0.92 J·cm^-3 were determined. This research provides a great reference for the analysis of dynamic crushing mechanism, crushing block size distribution, and crushing energy consumption of the roadway surrounding rock.

In order to effectively reduce the disturbance of the precrack blasting vibration on slope rock mass, except paying attention to the damping effect of the precrack, it is also necessary to optimize the blasting parameters and initiation mode of the precrack itself. Based on the blasting theory and empirical formula, the parameters of presplitting blasting such as the hole diameter, hole spacing, charge decoupling coefficient, and line charge density were determined, and field tests of conventional pre-splitting blasting and presplitting blasting with precise delay and hole-by-hole initiation were carried out on the west slope of Buzhaoba. Regression analysis was carried out on the vibration monitoring data, and the blasting vibration attenuation regularity of slope particles was obtained. By comparing the monitored vibration velocity of the two presplitting blasting tests and the forecast results of theoretical calculation, the average reduction rate of the conventional same row blasting vibration is 26.40%, while that of the hole-by-hole blasting vibration can reach 41.45% with a half hole rate of 80.7% and an irregularity of about 130 mm. Results show that the effect of precise delay initiation between preholes based on the digital electronic detonator is better than that of the simultaneous initiation of preholes. Therefore, it is suggested that the hole-by-hole presplitting blasting technology should be applied in the excavation of boundary slope and the treatment of high and steep slope.

Temperature’s influence on the physical and mechanical properties of rocks is a crucial concern for the rational design of deep rock engineering structures and the assurance of their long-term stability. To systematically comprehend the impact of the evolution of mineral composition and micro characteristics on the physical and mechanical behavior of thermally damaged granite, we observed the microscopic structural defects inside the rocks with a polarizing microscope and revealed the thermal damage mechanism of granite from a microscopic perspective by combining ultrasound detection and XRD phase characteristic analysis. The results show that the physical properties of the specimens changed significantly at three characteristic temperature points: 400 °C, 800 °C, and 1000 °C. Under high temperature conditions, the diffraction intensity of all minerals in granite, except for quartz, generally decreased, and stable minerals decomposed. Albite and potash feldspar decomposed to form anorthoclase, thereby reducing the structural stability of the rock material. In addition, the peak width of various minerals decreased to varying degrees with increasing temperature. The increase in mineral volume further damaged the internal structure of the rock material while promoting the transformation from grain boundary to intergranular cracks and from intragranular cracks to transgranular cracks, ultimately forming a interconnected crack network. Thermal damage significantly reduced the longitudinal wave velocity, uniaxial compressive strength, and elastic modulus of the specimens, while the stress–strain curve relationship indicated that the specimens underwent two opposite processes of transformation from brittleness to ductility and then from ductility to brittleness. The thermal damage threshold of granite in this study was 600 °C.

Fragmentation size is an important indicator for evaluating blasting effectiveness. To address the limitations of conventional blasting fragmentation size prediction methods in terms of prediction accuracy and applicability, this study proposes an NRBO-CNN-LSSVM model for predicting mean fragmentation size, which integrates Convolutional Neural Networks (CNN), Least Squares Support Vector Machines (LSSVM), and the Newton-Raphson Optimizer (NRBO). The study is based on a database containing 105 samples derived from both previous research and field collection. Additionally, several machine learning prediction models, including CNN-LSSVM, CNN, LSSVM, Support Vector Machine (SVM), and Support Vector Regression (SVR), are developed for comparative analysis. The results showed that the NRBO-CNN-LSSVM model achieved remarkable prediction accuracy on the training dataset, with a coefficient of determination (R²) as high as 0.9717 and a root mean square error (RMSE) as low as 0.0285. On the test set, the model maintained high prediction accuracy, with an R² value of 0.9105 and an RMSE of 0.0403. SHapley Additive exPlanations (SHAP) analysis revealed that the modulus of elasticity (E) was a key variable influencing the prediction of mean fragmentation size. Partial Dependence Plots (PDP) analysis further disclosed a significant positive correlation between the modulus of elasticity (E) and mean fragmentation size. In contrast, a distinct negative correlation was observed between the powder factor (P_f) and mean fragmentation size. To enhance the convenience of the model in practical applications, we developed an interactive Graphical User Interface (GUI), allowing users to input relevant variables and obtain instant prediction results.