The trial-and-error method for calibrating rock mechanics parameters has the disadvantages of complexity, being time-consuming, and difficulty in ensuring accuracy. Harnessing the repeatability and scalability intrinsic to numerical simulation calculations and amalgamating them with the data-driven attributes of machine learning methods, this study uses the finite element analysis software RS2 to establish 252 sets of sandstone sample data. The recursive feature elimination and cross-validation method is employed for feature selection. The shear strength parameters of sandstone are predicted using machine learning models optimized by the particle swarm optimization (PSO) algorithm, including the backpropagation neural network, Bayesian ridge regression, support vector regression (SVR), and light gradient boosting machine. The predicted value of cohesion is proposed as the input feature to predict the friction angle. The results indicate that the optimal input characteristics for predicting cohesion are elastic modulus, Poisson's ratio, peak stress, and peak strain, while the optimal input characteristics for predicting friction angle are peak stress and cohesion. The PSO-SVR model demonstrates the best performance. The maximum error between the predicted values of cohesion and friction angle and the calculated results of RSData program are 3.5% and 4.31%, respectively. The finite element calculation is in good agreement with the stress–strain curve obtained in the laboratory. The sensitivity analysis indicates that SVR's prediction performance for cohesion and friction angle tends to be stable when the sample size is >25. These results offer a valuable reference for accurately predicting rock mechanics parameters.

Rock cleavages consist of the cracks between blocks and the internal faults in blocks. The built-in modeling module in the Three-dimension Distinct Element Code (3DEC) cannot accurately describe the internal structure and the cleavage development characteristics of rock. This study combined 3D Voronoi block elements and scanning electron microscope (SEM) images, to construct a numerical model equivalent to the rock meso structures. Three strategies are proposed to refine the initial model by block subdivision to achieve a function that allows cleavages in the model to cross through the blocks. A physical uniaxial compression test was performed in the laboratory to calibrate the mechanical parameters of the siltstone and the calibrated parameters then were validated by a Brazilian disc test. Sensitivity analysis was conducted to investigate the relationship between the meso-parameters and the model's macro-response, and a calibration procedure was established for accurate replication of rock mechanical behavior. The statistics and analyses of failure characteristics for joints in the model showed that when the compressive and tensile strength values peaked, the percentages of tensile failures were approximately 37% and 10%, respectively. Comparing the cleavages after sample failure in lab tests with the cleavage development paths predicted by the models, the compressive and tensile characteristics were analyzed and the results confirmed the reliability of applying the 3D Voronoi block and subdivision modeling method in the numerical simulation study of the mechanical properties of the rock.

Stress concentration in partially caved goaf is the main cause of dynamic pressure accident in the lower seam mining. Aimed at the characteristics of caving in shallow partially caved goaf (PCG) and the specificity of interior load‐bearing structures, a classification criterion of goaf caving was proposed. The characteristics of cooperative load‐bearing in pillar group and gob pile were revealed by numerical calculation, physical simulation, and theoretical analysis. Taking intermittent mining as an example, combined with the deformation behaviors of the main roof and the loading characteristics of waster rock mass, the characteristics of the load‐bearing of gob piles were described in the form of a piecewise function. A FLAC3D model of intermittent mining is modeled to evaluate the stability of pillars, the long‐term stability and distribution laws of overlying loads were revealed through a refined model. The results show that the width of the caved zone bearing the load in the intermittent goaf is about 20 m, and the maximum load‐bearing capacity is 1.055 MPa. The maximum depth of the plastic region in one side of the pillar is 1.48 m, and the load on elastic zone is about 11.33 MPa. This study provides a method for the study of the caving characteristics and load uncertainty in PCG, and the results provide important theoretical values for the safe mining of lower coal seams.

The accurate prediction of surface subsidence is a significant foundation for the damage assessment of coal seam mining and ecological environment reclamation in loess donga. However, conventional models are very problematic, and the reliability of prediction is usually low. Therefore, we propose a method for predicting surface subsidence of coal seam mining in loess donga that is based on the probability integration model, combined with the movement principle of rock and soil layers in the respective study area, and considering the influence of slope stability and additional mining slip on mining subsidence. The feasibility of our new method was verified by a case study in the N1114 working face of the Ningtiaota coal mine (China) that is situated in an area with abundant loess dongas. The results show that slope slippage is the source of error in the prediction of subsidence in loess donga. The prediction idea of “dividing the surface of loess donga into horizontal strata area and slope sub-area, and predicting the subsidence value of the two areas, respectively” is put forward. A method for predicting the subsidence value of two regions is established. First, based on the theory of probability integral and rock formation movement, the probability integral parameters of the horizontal stratum area are determined, and the subsidence basins in the area are superimposed and calculated. Secondly, according to the slope stability and slip principle, the additional displacement of subsidence in the slope area with mining instability coefficient G_cs > 0.87 is calculated. Finally, combined with the subsidence prediction results of the strata area and the slope sub-area, and the position of the slope, the accurate prediction of the surface subsidence in loess donga is realized. Our results show that the agreement between the curves predicted from our calculations and from the measured data are between 88.7–97.8%. The calculated error of the additional displacement of slope mining slip is between 1.0–9.8%. The excellent correlation between the modelled and measured data documents that our method provides, demonstrated a new efficient and valuable tool for the precise prediction of damages induced by mining of underground coal seams in loess donga.

The mechanism and fracture aperture of thick hard roof failure were theoretically analyzed from the perspective of elastoplastic mechanics. A uniform load cantilever beam was established by considering the voussoir beam structure and stress condition. According to the stress inverse principle in solving the plane strain problem, the internal stress component analytic solution was deduced. Considering the lateral thrust and shear force and by applying the Mohr‐Coulomb failure criterion, the plastic zone boundary equation was obtained. Further analysis of the equivalent stress, equivalent strain, elastic energy density, distortion energy density, and strain energy density was studied with blocks of four different lengths, combined with the rotation angles after failure, to analyze the fissure aperture between straight and curved fracture traces. The theoretical analysis reveals that the deviatoric effect plays the lead role in rupture initiation and propagation; the cracks will deflect during failure, and the fracture trace presents a curved shape. The variation of fracture aperture exhibits a tendency to increase first, then decrease, and then increase along the fracture trace. The analytical approach presented in this paper provides a theoretical basis for determining the main seepage channel flow in underground mining.