The mechanical parameters of surrounding rock are an essential basis for roadway excavation and support design. Aiming at the difficulty in obtaining the mechanical parameters of surrounding rock and large experimental errors, the optimized BP neural network model is proposed in this paper. The mind evolutionary algorithm can adequately search the optimal initial weights and thresholds, while the neural network has the advantage of strong nonlinear prediction ability. So, the optimized BP neural network model (MEA-BP model) takes advantage of the two models. It can not only avoid the local extreme value problem but also improve the accuracy and reliability of the prediction results. Based on the orthogonal test method and finite element analysis method, training samples and test samples are established. The nonlinear relationship between rock mechanical parameters and roadway deformation is established by the BP model and MEA-BP model, respectively. The importance analysis of the three input variables shows that the ∆D is the most important input variable, while ∆BC has the smallest impact. The comparison of prediction performance between the MEA-BP model and BP model demonstrates that the optimized initial weights and thresholds can improve the accuracy of prediction value. Finally, the MEA-BP model has been well applied to predicting the mechanical parameter for the surrounding rock in the Pingdingshan mine area, which proves the accuracy and reliability of the optimized model.

In underground coal mines, high-pressure water jet slotting is effective at improving coal seams’ permeability. The slotting depth determines the effect of pressure relief and permeability enhancement in coal seams. However, there is no effective and feasible way of determining the slotting depth; thus, the operational parameters and borehole layout are unknown. This study determined the effects of key parameters, including the nozzle diameter, jet pressure, rotation speed, and slotting time, on the slotting depth. A water jet slotting depth calculation model was established and verified according to the slotting experiments under different operational conditions. The slotting depths were investigated based on the results of field slotting experiments. The results revealed that there exists an optimal nozzle diameter for a higher jet impact velocity. The slotting depth linearly increased with the jet pressure and decreased as a power function with the increase of the jet translation speed. The slotting depth increased with the slotting time, but the growth rate gradually decreased and tended to be stable. As the rotation speed increased, the slotting depth became greater at the initial period and the limit depth was reached faster. Laboratory and field slotting experiments were conducted to verify the model, and the experimental results are approximately in agreement with the theoretical predictions. The results of this study can be useful as guidelines for the hydraulic parameter selection of water jet slotting and for optimizing the layout of coal gas drainage boreholes.

Coal mining has gradually entered the deep mining era, and large-height mining is an important way to mine thick coal seams in the deep. The high coal wall will inevitably make the distribution of the overburden structure in the coal mining face more complicated, and the large buried depth will also cause more intense mine pressure. The study of the distribution and evolution of the overburden structure and stress in the mining site can provide theoretical guidance for safe mining. In this work, a physical similarity modeling test was carried out based on the physical–mechanical parameters of overburden rock and similarity theory, taking the mining of a deep, large-height working face in Pingdingshan Coal Mine as an example. The results show that the deformation and breakage of overburden rock in deep, large-height workings occurring during mining is persistent and not only in a short period of time. The breakage form of overburden can be categorized into two types based on the deformation characteristics: (I) non-separation-induced type, and (II) separation-induced type. Among these, the breakage induced by separation can be divided into two categories: (i) dominated by self-weight stress, and (ii) affected by shear cracks. It also summarizes the form of the overburden structure and the structural morphology of the stope. The overburden structure shows a “combined cantilever beam structure-articulated rock-slab structure-non-articulated rock-slab structure”. Among these, the periodic breakage of the upper cantilever beam evolved articulated and non-articulated rock-slab structure in the lower part, which weakened the supporting effect of the lower gangue and further aggravated the breakage of the upper overburden rock. The shape of the main structure of the stope mainly depends on the fracture line from the advancing coal wall to the upper overburden: from a rectangular shape without collapse to a trapezoidal shape at the initial stage of collapse, to a trapezoidal shape with multiple steps after the main roof collapse.

High-solid-water material is a kind of soft rock-like material with significant plastic deformation characteristics, and creep performance is its important material property. In order to study the effect of creep on the properties of high-solid-water materials, this paper first conducts creep tests of high-solid-water filling materials under different loading methods, performs creep data analysis based on the Boltzmann superposition principle, carries out the creep experiment of high-solid-water materials under different water contents to analyze the creep characteristics of high-solid-water materials, and then processes the curve of graded loading based on the Boltzmann superposition principle to obtain the strain–time curve of axial creep under different constant stress. Finally, the instantaneous curve is compared with the creep stress–strain curve. It is concluded that the high-solid-water filling materials with water content of 61%, 65% and 69% meet the transportation requirements and filling requirements, and the total coagulation time increases slightly with the increase in water content. The curve treated by the Boltzmann superposition principle has the same trend in the overall creep process and the creep curve loaded separately. With the increase in loading stress, the total strain of the material gradually increases, and with the increase in the water content of the material, the rate of change in the total strain of the material also increases. The long-term strength of high-solid-water materials decreases with the increase in water content. The specimen will eventually cause irreversible failure under long-term stress during the fourth-stage loading.

Establishing the relationship between the deformation of coal samples and acoustic emission response is the basis for the deformation prediction of coal samples. Using a combination of laboratory tests and theoretical analysis, acoustic emission tests of the uniaxial loading process were conducted on coal samples in the study area and the test results were analyzed, focusing on the rule of variation of acoustic emission counts with loading time. Based on the analysis of stress, strain, time, and acoustic-emission parameters variation, the relationship between the deformation of coal samples and acoustic emission response was established and analyzed. The analysis results show that during the loading process, the acoustic emission counts show the characteristics of stage changes, which can be divided into three stages: the initial stage with sporadic acoustic emission events, the middle stage with a stable increase of acoustic emission events, and the final stage with the rapid increase of acoustic emission events. This stage division has good consistency with the deformation stages of coal samples. Moreover, the acoustic emission counts have obvious and easily identifiable characteristics of changes in the deformation process of coal samples. The acoustic emission count can be used as a sensitive indicator in this study area to predict the deformation of coal samples. It provides a reference for the application of acoustic-emission prediction technology in this study area, which is important to improve the accuracy of geohazard prediction.

To improve the effect of gas drainage, with the aim of overcoming the problem of air leakage of conventional sealing materials, this study proposed the concept of gas drainage borehole sealing with active support and developed a new type of sealing material with the properties of permeability, fluidity, expansibility, early strength and compressive resistance through orthogonal tests. Using a specially designed active support testing device, this study analyzed the development law of borehole fracture under the action of active support force, which was then verified via field tests at a mine in Henan Province, China. The results show that the higher the expansion rate, the smaller the internal friction angle and cohesion, which is reflected in the sharp decline in the peak strength of the sealing material. The active support force of the sealing material has a significant time effect. It increases rapidly at first, before its growth rate slows down and tends toward a certain value. The greater the active support force provided by the sealing material, the smaller the radius of the plastic zone and breakage zone; this observation is also true of the displacement around the borehole. The active support force of sealed boreholes can effectively inhibit the development of cracks around the hole and reduce the generation of gas leakage channels. Under the action of the same burial depth and active support force, the larger the mechanical parameters of rock, the smaller the radius of the plastic zone and the breakage zone, as well as the smaller the displacement around the borehole. As has been proven by engineering practice, under the same conditions, the gas drainage concentration of the new sealing material is 47.5%, which is 84.8% higher than that of the original sealing material.