Prediction and parameter optimization are effective methods for mine personnel to control blast-induced ground vibration. However, the challenge of effective prediction and optimization lies in the multi-factor and multi-effect nature of open-pit blasting. This study proposes a hybrid intelligent model to predict ground vibrations using a least-squares support vector machine (LSSVM) optimized by a particle swarm algorithm (PSO). Meanwhile, multi-objective particle swarm optimization (MOPSO) was used to optimize the blast design parameters by considering the vibration of particular areas and the bulk rate of blast fragmentation. To compare the prediction performance of PSO-LSSVM, a genetic-algorithm-optimized BP neural network (GA-BP), unoptimized LSSVM, and BP were used, by applying the same database. In addition, the root-mean-squared error (RMSE), the mean absolute error (MAE), and the correlation coefficient (r) were regarded as the evaluation indicators. Furthermore, the optimization results of the blasting parameters were obtained by quoting the established vibration prediction model and bulk rate proxy model in MOPSO and verified by field tests. The results indicated that the PSO-LSSVM model provided the highest efficiency in predicting vibrations with an RMSE of 1.954, MAE of 1.717, and r of 0.965. Furthermore, the blasting vibration can be controlled by using the two-objective optimization model to obtain the best blasting parameters. Consequently, this study can provide more specific recommendations for vibration hazard control.

Frozen fractured rock mass is often encountered during the implementation of geotechnical engineering in cold regions. The tensile strength parameters of frozen rock play an important role in the construction of rock slopes involving tensile failure. In order to study the tensile characteristics of a frozen fractured rock mass in a cold region, original rock specimens were mined and processed in the Yulong Copper Mine, and artificial, frozen fractured marble specimens were made. The effects of different ice-filled crack angles, lengths, and widths on the force–displacement curve and the tensile strength of frozen rock were studied by laboratory Brazilian splitting experiments and RFPA^3D, and the evolution law of the tensile strength of frozen rock was revealed. At the same time, wing crack initiation and cracking mode after tensile failure were analyzed by high-speed camera; the whole process of the Brazilian splitting of frozen rock was reconstructed, and the development of microcrack initiation in frozen rock was analyzed. The following conclusions were drawn from the test results: the frozen rock specimens have typical brittle-failure characteristics. The tensile strength of frozen rock decreases gradually with the increase in the width and length of ice-filled cracks, and decreases first and then increases with the increase in the angle of the ice-filled crack. The ice-filled crack incurs damage first, and then the wing cracks start from the tip of the ice-filled crack and extend continuously. The tensile strength of frozen rock is significantly affected by the angle and length of ice-filled cracks.

The propagation mechanism of explosion stress waves in frozen rock mass is the main factor affecting the blasting efficiency and safety construction of strip mines in alpine cold regions. In order to study explosion stress wave propagation and crack extension in the blasting process of frozen rock mass with ice-filled cracks, RFPA^2D is adopted to simulate the influence of the geometric parameters of ice-filled cracks (ice-filled crack thickness d, normal distance R from blasting hole to the ice-filled crack, and ice-filled crack angle α), loading intensity and loading rate on the explosion stress wave propagation effect and the damage range. The results show: The attenuation trend of explosion stress waves decreases gradually with an increase of thickness (e.g., In the case of R is 0.2 m, when d is 0.02 m, 0.04 m, and 0.08 m, the calculated attenuation factor of the minimum principal stress peak value is 7.128%, 18.056%, and 30.035%, respectively), and it decreases slightly with an increase of normal distance and ice-filled crack angle. The damage elements range of the ice-filled crack decreases when the ice-filled crack thickness and normal distance increases. The loading intensity and the loading rate have a significant influence on blasting hole fracture patterns. The ice-filled crack has a guiding effect on the growth of blasting cracks at the blasting hole. Nevertheless, the existence of ice-filled cracks inhibits the propagation of explosion stress waves in frozen rock mass.

Borehole breakouts significantly influence drilling operations’ efficiency and economics. Accurate evaluation of breakout size (angle and depth) can enhance drilling strategies and hold potential for in situ stress magnitude inversion. In this study, borehole breakout size is approached as a complex nonlinear problem with multiple inputs and outputs. Three hybrid multi-output models, integrating commonly used machine learning algorithms (artificial neural networks ANN, random forests RF, and Boost) with the Walrus optimization algorithm (WAOA) optimization techniques, are developed. Input features are determined through literature research (friction angle, cohesion, rock modulus, Poisson’s ratio, mud pressure, borehole radius, in situ stress), and 501 related datasets are collected to construct the borehole breakout size dataset. Model performance is assessed using the Pearson Correlation Coefficient (R²), Mean Absolute Error (MAE), Variance Accounted For (VAF), and Root Mean Squared Error (RMSE). Results indicate that WAOA-ANN exhibits excellent and stable prediction performance, particularly on the test set, outperforming the single-output ANN model. Additionally, SHAP sensitivity analysis conducted on the WAOA-ANN model reveals that maximum horizontal principal stress (${\sigma }_H$) is the most influential parameter in predicting both the angle and depth of borehole breakout. Combining the results of the studies and analyses conducted, WAOA-ANN is considered to be an effective hybrid multi-output model in the prediction of borehole breakout size.

A novel numerical experimental method is developed herein to study frost-heaving cracking in fractured rock masses by reproducing the physical experimental frost-heaving process. The failure mode of a preexisting closed and water-saturated single-flaw in a rock mass during the frost-heaving process is affected by the inclination angle, flaw width, crack length, and cooling rate. Additionally, a regression model for predicting secondary crack formation and propagation is established by combining multiple stepwise regressions. Overall, the results indicate that preexisting flaw with various inclination angles, flaw lengths, and cooling rates mainly propagates along the flaw-coplanar direction. The secondary crack failure mode is most affected by the flaw width, and the length of the secondary crack increases with increasing inclination angle, flaw width, and flaw length, but decreases with increasing cooling rate. The contributions of the investigated factors to the secondary crack length follow the order: flaw width > inclination angle > cooling rate > flaw length. The results presented herein provide crucial theoretical guidance for engineering and construction projects in cold regions.

In order to investigate the dynamic mechanical behavior of composite rock in deep-buried tunnels, the dynamic impact tests of the combinations with three lithologies (granite-H, cyan sandstone-S1, and red sandstone-S2) and six kinds of composite forms (H-S1, S1-H, H-S2, S2-H, S1-S2, and S2-S1), were carried out in this study. Additionally, the effects of the combination forms and strain rates on the stress-strain curve, peak stress, energy utilization rate (EUR), failure process, displacement field, and failure mode of the composite sample were analyzed. The results show that the peak stresses of all the combinations are linearly and positively correlated with the strain rate. When the strain rate is close, the peak stress and elastic modulus of the combination with front hard and rear soft (FHRS) rocks are larger. Furthermore, the EUR of different combinations is proportional to the incident energy. The EUR of the front soft and rear hard (FSRH) combination is generally higher than that of the FHRS combination. In general, the rock with low strength always fails first in the composite. When the strength disparity between the two rocks of the composite is small, the failure of the composite with FSRH is relatively small, and the main deformation occurs in the rock with low strength. Finally, the fractal dimension of the fragments after the impact of the FSRH combination is larger, i.e., the lumpiness of fragments is closer.