The lithology of the strata in the Gobi region of the Xinjiang autonomous region of China is mainly composed of mudstone, silty mudstone, and other soft rocks. Because of the low strength of the rock mass and the serious effects of physical weathering in this area, the slope stability in open-pit mines is poor, and creep deformation and instability can readily occur. Taking the Dananhu No. 2 open-pit mine as a typical example, the creep test of a mudstone sample under different stress levels was studied. Then, based on a bottom friction experiment and a FLAC3D numerical simulation, the deformation and failure processes of the slope were analyzed. The stress–displacement curve and the displacement–time curve for the monitoring points were plotted to obtain the relationship between the stress and displacement for the slope of the soft rock. The results showed that the long-term strength of the mudstone was between 8.0 and 8.8 MPa, and that stable creep occurred when the slope was under low stress. The potential failure mode for this type of slope is that the front edge creeps along the weak layer and then a crack is formed at the trailing edge of the slope. When the crack penetrates the weak layer, cutting bedding and bedding sliding occur. The deformation process of the stable creep slope includes an initial deformation stage, an initial creep stage, a constant velocity creep stage and a deceleration creep stage.

In light of the complex and dynamic mechanical properties of evolving weak strata in open-pit mines, and the consequent difficulty of determining their mechanical parameters, this study uses the ultimate balance theory, along with the back analysis method combined with monitoring data on field displacement, to carry out parameter inversion using the FLAC3D numerical simulation software. The edge slope of a working pit of the Weijiamao open-pit mine was used as research object to this end. As the results obtained by the constitutive model were consistent with the field monitoring data, the evolving weak strata in the slope and the position of the landslide in the mine could be obtained. The landslide was directed northeast. The mechanism of the edge slope of the working pit was identified as unloading shear failure, and the feasibility of the method of parameter inversion was verified. The internal friction angle ϕ and cohesion C of evolving weak strata in the slope of the open-pit mine were also obtained, where this compensated for the deficiency of laboratory tests and enabled the transformation from qualitative to quantitative analysis. This can provide a reliable basis for the safe operation of open-pit mines.

Quantifying slope mechanical parameters as comprehensive indicators is crucial for predicting slope stability. The Mohr–Coulomb (M-C) criterion, a classical method for determining the relevant parameters of rock mass mechanics, effectively reflects the failure characteristics of rock masses in most types of slopes. Based on this, effective stress and shear strength from the M-C criterion are selected as key indicators, and a characteristic dataset is constructed by integrating these with other influencing factors of slope stability. The safety factor, calculated using the Bishop method within the framework of limit equilibrium analysis, serves as the output variable. Subsequently, a novel Black Kite Algorithm (BKA) was developed to enhance the prediction model of a multilevel perceptron neural network. The results demonstrate that the mean square error (RMSE) of the BKA-MLP model is merely 2.41%, significantly lower than that of alternative models. Additionally, the R² value reaches approximately 95%, indicating a high level of interpretability. The SHAP-based interpretability analysis of the trained model highlights effective stress, shear strength, and slope angle as the three most sensitive features. Based on these findings, targeted landslide prevention measures were proposed, providing a new approach for slope stability analysis and disaster prevention.

The purpose of this study is to accurately calculate the escape velocity of miners under different roadway conditions during mine fire periods. The experiment to examine escape velocity was carried out in the roadway of the Mu Chengjian Coal Mine. In the experiment, the relationships between the miner escape velocity and the inclination of the roadway, the area of the accessible section of the roadway, and the average wind velocity of the roadway were obtained through single factor analysis, and two multiple regression equations of the escape velocity were developed through multivariable linear regression analysis. The escape velocities of the miners were then predicted, and the error was analyzed with multiple regression equations. The experimental results show that the miner escape velocity decreases with an increase in the absolute value of the inclination of the roadway and increases with an increase of the accessible section area of the roadway and the average wind velocity of the roadway. In addition, the multiple regression equations have the strongest significance if the independent variables are the inclination of the roadway, the accessible section area of the roadway, and the type of roadway, and the contribution rate of the inclination of the roadway to the escape velocity is the highest. The predicted results calculated by the multiple regression equations are close to the experimental data, and the prediction errors are less than 10%. Consequently, we conclude that the multiple regression equations can be used to predict the miner escape velocity during periods of mine fires.

In the traditional optimization mathod, the process control parameters for fully mechanized mining face are determined by experts or technicians based on their own experience, which is lack of scientific basis, and need long production adjustment cycle. It is cause large loss, and not conducive to improving mine production efficiency. In order to solve this problem, the study proposes a process control parameter optimization method based on a mixed strategy of artificial neural network and genetic algorithm and uses a cross‐entropy cost function to optimize an artificial neural network, which improves the learning speed and fitting accuracy of the neural network. Using the historical production data of a fully mechanized coal mining face, taking the pulling speed of the shearer, hydraulic support moving speed, chain speed of scraper conveyor, chain speed of stage loader, emulsion pump outlet pressure, and spray pump outlet pressure as the optimization objects and taking the value range of each process control parameter as a constraint condition to establish a mixed strategy optimization model of process control parameters for a fully mechanized mining face, each process control parameter is optimized with the output of coal per minute as the optimization goal. The results show that the method has high accuracy and short optimization process time and can effectively improve the production efficiency of the working face.

Dump in the steep area of the open‐pit mine is essential for safe production. The bedrock with the bumpy‐surface blasting method effectively improves the stabilization of the dumpsite. The effect of the ratio and dispersion degree on the deformation and failure of the dumping bench at the largely inclined area was analyzed. Based on the limit equilibrium method, the equation about the stability factor and the blasted region ratio was deduced. Virtual experiments were performed to address how the ratio and dispersion degree affect deformation and failure. The results showed that the stability factor is a quadratic function of the ratio of the blasted area. The increase in the ratio results in a drastic reduction of displacement, and the direction of displacement significantly changes. The rise in the dispersion degree effectively reduces the displacement and shear strain increment, and the failure mode changes. There is a specific value for the ratio and dispersion degree, making the displacement and shear strain increment little. The research on bumpy surface blasting in this paper provides the theoretical foundation for the dump construction at the site with the large dip angle.