To investigate the effect of backfill on roof behavior and the influence of different factors on roof subsidence in paste backfilling mining, this study takes the fully mechanized paste backfilling face of the Weishen Coal Mine as a case study. Combining theoretical analysis, numerical simulation, and field measurements, the spatial interaction mechanism between the roof and backfill was examined. Key factors, including panel width (140~200m), mining height (1.5~3.0m), backfill strength (2.0~3.5MPa), and backfill ratio (80%~95%), were analyzed to determine their influence on roof subsidence. The range analysis method was employed to quantify factor weights, with practical adjustments applied. Theoretical results indicate that when the roof initially contacts the backfill, the roof span is 1.82m. As the face advances, the roof-backfill contact area increases, and the roof subsidence stabilizes at a maximum value of 0.333 m. Increasing panel width and mining height amplify maximum subsidence by 11.8% and 101.9%, respectively, whereas higher backfill strength and backfill ratio reduce it by 29.1% and 22.7%. Range analysis identified mining height as the dominant factor (weight: 49.7%), followed by backfill strength (22.8%), backfill ratio (16.2%), and panel width (11.3%).

In view of the difficulties of updating 3D geological model caused by multi-person collaboration, tedious measurement process and low efficiency in traditional traverse survey of working face, a dynamic revision technology of geological model based on coal-rock boundary geological recording device is proposed. Firstly, the geological model of the working face is constructed by collecting the relevant geophysical exploration, drilling, supplementary exploration data and roadway development information.Then the geological recording device is used to measure the coal rock boundary at the current mining position of the fully mechanized mining face, and the coordinates of the coal rock boundary point on the top and bottom of the coal seam are obtained.Finally, the measurement results of the coal-rock boundary point are imported into the established initial geological model, and the dynamic update of the 3D geological model of the working face is completed through the automatic reconstruction function of the model, and the geological body in a certain range in front of the current mining position of the working face is finally realized.The application of the above method finally meets the demand of adaptive coal cutting in fully mechanized mining face of Coal Mine.

To intelligently control belt conveyors based on coal flow, thereby save energy and reduce consumption, and mitigate equipment wear, we studied a coal flow monitoring and intelligent speed control system for belt conveyors based on algorithm model. The system integrates algorithm model technology to capture and analyze coal flow images on the belt in real time. By employing the U2-Net algorithm, the system accurately segments and recognizes the images to calculate the coal flow. Based on this data, the system intelligently adjusts the operating speed of the belt conveyor according to a preset optimal speed regulation strategy, ensuring transportation efficiency while minimizing energy consumption.

Aiming at the problem of complex failure mechanism and scarcity of fault samples in coal mining machine height adjustment system, this paper proposes and constructs an experimental platform for coal mining machine height adjustment system based on virtual-real linkage, aiming at realizing the effective acquisition of systematic multi-source fault characteristic data.The experimental platform utilizes multi-domain coupled modeling technology to realize high-fidelity mapping of the physical system, and optimizes the design of mechanical structure and sensing layout through spatial adaptation to ensure the safe operation of the physical entity. Relying on the cooperative operation mechanism of hardware and software subsystems, the platform realizes the dynamic coupling between physical entities and virtual simulation models. Based on the platform, typical fault simulation experiments and extreme working condition simulation experiments are carried out, and the consistency of virtual and real fault data is evaluated by the cosine similarity. The experimental results show that the similarity between the real data and the simulated data are all above 0.9, which fully verifies that the platform has good robustness and can generate accurate and effective fault data. At the same time, the platform can generate key fault characterization parameters that are difficult to be directly monitored in the physical entity, which provides reliable multi-dimensional experimental data support and theoretical support for the intelligent fault diagnosis of coal mining machine height adjustment system.

Unlike traditional conveyor corridor that use main steel trusses and profiled steel sheets as enclosure structures, the side panels of prefabricated modular conveyor corridors employ corrugated plates with vertical stiffeners as the primary loadbearing structure. However, there are no specific codes for their mechanical analysis and structural design methods. To address this, the design process and methodology for the side panel structure of prefabricated modular conveyor corridors is detailed. The proposed dimensions for a single side panel are a height of 3000~3800mm and a length of 12000mm. The corrugated plates have a wave height of 50~100mm and a wave pitch of 300 mm. The upper part of the side panel has a curvature radius of 1100 ~1500mm, with a corresponding central angle of 27°~45°. The research results comprehensively consider factors such as load-bearing capacity, stability, and manufacturing difficulty, ensuring rational structural design and dimensions for each part of the side panel to meet the requirements of prefabricated modular trestles.

Since its release, Standard for Design of General Layout and Transportation for Coal Enterprises has effectively promoted the standardization work of the general layout and transportation in the coal industry. Its provisions cover a lot of relevant specification contents, which is convenient for designers to query and use. However, with the development of the specifications in the coal and related industries, many of its provisions are in conflict with the actual situations in practical work, affecting the authority of the standards and specifications. Combining some design experiences, review requirements in practical work and the latest specifications, the author conducts a detailed discussion on the relevant provisions in the standard, providing relevant suggestions for the better application and revision of the standard.

To address the challenge of surrounding rock control in roadway retention under hard roofs during roof cutting, through theoretical analysis, numerical simulation, and engineering practice, a mechanical model for overburden movement in roof-cutting roadway retention and a numerical model for pressure relief roof cutting and gob-side entry retention under thick-hard direct roofs were established. The failure mechanism of surrounding rock in gob-side entries was clarified. The effects of advance pre-splitting pressure relief under different parameters were compared, the stress response characteristics of surrounding rock under varying roof-cutting parameters were analyzed, and the evolution of surrounding rock stress with working face retreat were studied. The research findings indicate: (1) The length and state of the lateral cantilever beam of the roof are key factors affecting the stability of the surrounding rock. Roof cutting actions can significantly reduce roof bending moments, with the subsidence of the roof on the gob side decreasing to 11.4% of that without roof cutting. Under thick-hard roof stratified caving conditions, the support-balanced structure can effectively control roadway deformation. The control direction of 'roof pressure relief + surrounding rock reinforcement coordination' is determined. (2) The response characteristics of surrounding rock stress to different roof cutting angles and height parameters were analyzed. The dynamic evolution characteristics of full-time vertical stress and deviatoric stress in the surrounding rock of gob-side entries under mining influence were obtained. It is clarified that the stress peaks of the solid coal rib adjacent to the retained roadway exhibit a steep-to-gentle negative correlation with both cutting angle and height. (3) A control strategy of 'roof pressure relief and high-strength anchoring; solid coal rib deep anchorage; and gob-side gangue blocking and roof support' was proposed. Field engineering applications demonstrate that under the coordinated control of roof cutting pressure relief and reinforcement support, the displacement change rate of the retained surrounding rock is low, anchor cable forces remain stable, and surrounding rock control effects are effective.

This article takes Ping'anbao Mine as the engineering background, and conducts on-site secondary stress measurement, rock mechanics parameter testing, and numerical simulation analysis of the excavated roadway. The maximum principal stress measured is σ_max=6.68MPa, which is 2.56 times the self weight stress; Secondly, with the help of FLAC^3Ddisplacement inversion, the distribution of secondary stress field after tunnel excavation was clarified, and the horizontal stresses were determined to be σ_x=5.0 MPa and σ_y=4.0 MPa, respectively. Finally, grouting with anchor rods and cable support was proposed. The on-site practice measured that the roof displacement decreased from 300 mm to 239 mm, a decrease of 21%, and the floor heave decreased from 226 mm to 115 mm, a decrease of 49%, effectively controlling the serious deformation problem of high stress tunnels.

To address the rock burst hazard induced by difficult caving of hard roof strata in gently inclined coal seams, this study proposes a hydraulic fracturing roof weakening technology, using the I010206 working face at Kuangou Coal Mine as an engineering case. Through theoretical analysis, numerical simulation, and field monitoring, fracturing parameters were optimized (borehole diameter: 133mm, injection pressure: 25MPa, flow rate: 40m³), employing a segmented hydraulic fracturing process with a double-packer single-clamp system. The results demonstrate that fracturing generates a complex fracture network dominated by horizontal fractures, with an effective radius of 15–30m, significantly compromising roof integrity. The periodic weighting interval of supports shortened to 10.4-11.6m, accompanied by reduced stress concentration coefficients and diminished elastic energy accumulation. Transient electromagnetic surveys and borehole imaging confirmed effective fracture development, achieving a controlled transformation of the roof structure from "strong-hard" to "weak-fragmented." This provides a theoretical foundation and technical support for preventing dynamic disasters in mines under similar geological conditions.

Ground L-shaped well gas drainage and pressure relief is an important technical means for gas drainage in coal mining areas. In response to the current problems of low drainage efficiency, difficult well completion and large difficulty in well deviation control during the gas drainage process of ground L-shaped horizontal wells, the technical principle of L-shaped horizontal well gas drainage is analyzed and three key technical points, including well location deployment, key technologies for drilling and well completion, and negative pressure drainage technology, are summarized. According to the gas migration law, the L-shaped well layout range is optimized; the three-casing wellbore structure design is sorted out and proposed, the wellbore trajectory control technology is optimized, the anti-pressing directional drilling technology, well completion and well washing technology, and cementing technology of L-shaped wells are studied, and the L-shaped well drilling technology system is established. According to the characteristics of gas drainage and pressure relief by L-shaped wells, two negative pressure drainage modes and negative pressure drainage control management systems at different stages are proposed. The "flow rate guarantee and negative pressure variation" control method is adopted at each stage. The gas drainage effect of ground L-shaped wells in Huaibei mining area is studied and analyzed. The pure gas drainage volume of Guobei Coal Mine reaches 2.7×106m³, and the pure gas drainage volume of a group of L-shaped horizontal wells implemented in Zhuxianzhuang Coal Mine is up to 5875m³ per day, achieving safe mining. On this basis, the future development direction of L-shaped well technology is proposed, mainly including the precision of design parameters, precise control of horizontal section trajectory, large displacement horizontal well drilling, refined drainage management, and joint ground-surface L-shaped mining-induced well gas drainage technology.

The re-mining of abandoned coal is an effective scheme to improve the utilization rate of coal resources and prolong the service life of the mine. In view of the stability analysis of the remaining pillars of the underlying coal seam under the disturbance of the overlying coal mining in the room-and-pillar goaf. Based on the engineering background of shallow buried thin coal seam mining in Sandaogou Coal Mine, the safety factor of the remaining coal pillars in the underlying coal seam is determined by theoretical calculation. Taking the distribution of deviatoric stress field and the expansion of plastic zone as the indexes, the numerical simulation method is used to explore the influence of the mining parameters of the coal seam and the parameters of the working face on the stability of the remaining coal pillars. The results show that : ( 1 ) The safety factor of the residual coal pillar in the pillar mining of 5^-2 coal seam is 1.541, which can maintain long-term stability ;( 2 ) The spatial distribution characteristics of the failure characteristics of the remaining group columns in the 5^-2 coal seam are ' O 'shaped distribution. The stability of the coal pillars in the central area is obviously inferior to that of the boundary coal pillars. The instability of the coal pillars in the central area has the risk of inducing the instability of the remaining group columns. ( 3 ) The distribution of deviatoric stress field and the expansion of plastic zone in the remaining coal pillars of room-and-pillar mining in 5^-2 coal seam are mainly determined by the mining parameters of the working face of the coal seam. The larger the size of room-and-pillar mining in 5^-2 coal seam is, the stronger the influence of coal pillar stability on the mining disturbance of 4^-4 coal seam is.

To address the severe strata pressure manifestations in impact-prone isolated working faces, this study takes the 3203 isolated working face as an engineering case. [Methods] By integrating theoretical analysis, numerical simulation, and field monitoring, the stress evolution characteristics before and after mining to the square stage were investigated, with a focus on the influence of hydraulic support strength and its adaptability. [Results] The results indicate that the overlying strata load from adjacent goaf transfers to the isolated working face, forming a high-stress concentration zone with an impact risk coefficient of 0.75 (moderate instability potential). When advancing to the square stage, the peak values of advanced and lateral abutment pressures reach 27.0MPa and 50 m in maximum influence range, respectively. Increasing hydraulic support strength effectively reduces roof-to-floor convergence, stabilizing at 31cm when support strength reaches 1.1MPa. Field monitoring demonstrates that the ZF9000/18/34D hydraulic support performs well, with average and maximum working resistances of 7260 kN and 8527 kN during pressure periods, ensuring safe and efficient production. [Conclusion] Enhancing hydraulic support strength effectively controls deformation and guarantees stability in isolated working faces, providing a reference for adaptability studies of hydraulic supports under similar engineering conditions.

Taking the 4303 working face of Shaqu Coal Mine as the engineering background, aiming at the lack of bending resistance of roadway gangue retaining structure, a comparative study of I-steel and retractable U-steel gangue retaining support structure was carried out. Through theoretical analysis, numerical simulation and field application, the supporting structure of gangue retaining wall is compared. Firstly, the force mechanism of the gangue retaining structure is clarified by theoretical analysis. The gangue retaining structure is equivalent to the simply supported beam structure. The mechanical model of the gangue retaining structure is established, and the bending resistance of the two gangue retaining structures is compared and analyzed. Secondly, ABAQUS numerical simulation software is used to establish the model of I-steel and retractable U-steel gangue retaining structure. The bending characteristics of I-steel and retractable U-steel gangue retaining structures under the same stress state are compared. The bending characteristics of retractable U-steel gangue retaining structures with different lap lengths are compared. The results show that the retractable U-steel gangue retaining structure has better bending resistance than the I-steel gangue retaining structure. Increasing the lap length can improve the bending resistance of the gangue retaining structure. Finally, on the basis of the above research, a reasonable field design scheme of retractable U-shaped steel gangue retaining structure is proposed, which has achieved good field application results.

Due to long-term operation in humid, high-temperature, and dusty underground environments, coal mine belt conveyors are prone to various malfunctions, such as belt deviation, slippage, damage, breakage, as well as motor and roller failures, which require the equipment to be shut down for maintenance, resulting in increased coal production costs and decreased production efficiency. Based on the large-scale AI architecture featuring cloud-edge collaboration and on-the-fly edge learning, this paper integrates computer vision, equipment control, and big data analytics technologies to propose an intelligent monitoring algorithm for coal flow transportation systems. It develops key AI model technologies for conveyor belt anomaly detection, ultimately establishing a visual intelligent monitoring and management system for coal transportation. The implementation achieves intelligent speed regulation of conveyor belts based on coal volume monitoring, while forming a closed-loop operational process that encompasses damage tracking, anomaly warning, and incident handling throughout the conveyor belt operation. The application has been successful in Hetaoyu coal mine, belt speed measurement error <±2%, coal volume statistics error < ±5%, 30% reduction in belt idling rate, annual electricity savings of approximately 150,000 kWh per kilometer of conveyor belt, reduced mechanical impact intensity, 40% extension of roller replacement cycle, reducing the number of belt inspection workers for 6 km of the main inclined shaft by 10 times per day, reducing abnormal downtime by 15 minutes per day, extending the service life of the belt, significantly reducing staff and increasing efficiency, and creating a direct economic benefit of RMB 2 million per year and an indirect economic benefits exceeding RMB 10 million per year. The application effect is good.

In order to accurately and dynamically obtain the wind speed and air volume of the underground wind station, a set of anthropomorphic measurement system for roadway wind speed was developed. The system uses the motor as the driving force and the mechanical wind meter as the wind measurement means. The controller, display board, alarm, and camera work together to realize the automatic clutch and zero return of the mechanical wind meter. The mechanical wind meter automatically measures wind according to the six-line trajectory. The dial of the mechanical wind meter is intelligently recognized by AI, and the wind measurement results are released simultaneously underground and above the well. The main body of the wind measuring device is a single supporting cantilever beam structure made of carbon fiber as the main material, which has the characteristics of light weight, easy installation and easy storage. Through simulation and theoretical calculation, the maximum bending subsidence of cantilever beam is determined to ensure that the slider can slide on the slide rail without obstacles. Through the development of mine intrinsically safe actuator, the wireless automatic control of mechanical wind meter counting and zeroing is realized. Based on the dynamic geometric relationship between the wind meter and the motor, a mathematical model of the inverse solution of "wind meter trajectory → motor rotation stroke" is established to realize the autonomous six-line wind measurement of the wind meter. The system has been tested industrially in Cilinshan Coal Mine and Yanbei Coal Mine. Taking the results of tracer gas air volume measurement as the standard value, the feasibility of device wind measurement instead of manual wind measurement is analyzed: The wind measurement results of the device are consistent with the tracer gas air volume measurement results in terms of changing trend and fluctuation, and the average wind measurement error is less than 5%. The anthropomorphic wind measurement system can replace manual wind measurement and realize "one-click wind measurement". Accurately and dynamically obtain the wind speed of the whole section of the tunnel.

In order to study the retaining mechanism of gangue filling space in double-shield solid filling mining, the geometric model of retaining filling space was established by combining theoretical analysis with EDEM numerical simulation. The influence of filling height, multi-frame sequential blanking process and blanking step on the accumulation state of filling body was simulated. The results show that the filling operation and space enclosure model in double-shield solid filling mining are established, and the calculation method of filling body volume is obtained. The relationship between filling volume and working face length, support center distance, filling step distance, filling height, gangue rest angle, length of blanking port and length of blanking port is obtained. The annual filling amount of gangue under two kinds of double-shield solid filling mining height and filling height in Hecaogou Coal Mine is calculated theoretically. The increase of filling height will significantly increase the accumulation range, and the filling height has little effect on the accumulation angle of gangue particles. When the filling height increases from 1.0 m to 1.2m, the diameter of gangue accumulation range increases from 3.32m to 3.82m, and the accumulation angle increases from 28.7 ° to 28.9 °; The numerical simulation of the blanking process along the working face and the blanking step along the advancing direction of the working face verifies the rationality of the filling space maintenance geometric model of the double-shield solid filling mining proposed in this paper, and verifies the existence of ' gully ' and ' gully ' in the filling process, which provides a theoretical basis for the efficient process design of double-shield solid filling.

To establish a "mechanism-constrained and data-driven" rockburst monitoring and early warning system, artificial intelligence algorithms are employed to construct nonlinear relational models that deeply explore inherent data patterns, thereby achieving an integrated "location-time-intensity" tripartite early warning framework. A multi-parameter rockburst risk prediction index system was established, incorporating real-time monitoring indicators, mining technical indicators, coal-rock mass strength indicators, and geological condition indicators. By introducing temporal sequence data and spatial location parameters, a spatiotemporally coupled early warning module was developed. Key methodologies include: scalar normalization of indicator parameters using normalization equations; K-means clustering to impute missing target values; correlation analysis and principal component analysis (PCA) to investigate inter-factor relationships and reveal mappings between data and geological/mining conditions, thereby unifying the "mechanism" essence with "data" phenomena. Three multi-parameter comprehensive early warning models—L2-regularized multiple linear regression, BPNN (Backpropagation Neural Network), and RNN-GRU (Recurrent Neural Network with Gated Recurrent Units)—were constructed and comparatively evaluated. Validation results demonstrate that the L2-regularized linear regression model effectively outputs fitting relationships between factors and rockburst risks while providing weight values of indicators for mechanistic studies. In contrast, the RNN-GRU model exhibits superior computational efficiency, faster convergence, and enhanced capability to capture dynamic features in time-series data through its GRU architecture. By integrating One-Hot encoding of monitoring point coordinates and improved K-means clustering for spatial risk localization, the model achieves spatiotemporal distribution prediction of rockburst hazards. Field validation at a rockburst-prone mine in Hujierte Mining District demonstrated, predicted magnitudes closely benchmarked against actual events, achieving <2.5-hour temporal MAE and <50-meter spatial RMSE, with spatiotemporal prediction reliability reaching 85% confidence level.

When the gently inclined coal seam working face is mined to the fault affected area, the pressure distribution of the support is unbalanced, and the deformation and damage of the surrounding rock of the mining roadway are serious. In order to systematically study the failure law of the overburden rock of the working face near the fault, this paper takes the working face 250602 of Zaoquan Coal Mine as the background, adopts the method of combining theoretical analysis, numerical simulation and field measurement, and simplifies the overburden structure of the working face into three mechanical models according to whether there is a fault in the working face and the spatial location relationship between the working face and the fault, which are fixed at both ends, fixed at one end, simply supported at one end, and cantilever beam structure. Based on the three mechanical models, the analytical solutions of the roof deflection of the three models were solved by using the superposition principle, and the buckling calibration method was introduced to analyze whether the roof of the working face had buckling effect. On the basis of theoretical analysis, the UDEC discrete element numerical method is used to compare and analyze the development height, basic roof subsidence, and overburden failure mode of the "two zones" of overburden rock, so as to reveal the failure law of overburden mining in the gently inclined coal seam working face in the fault affected area. The results show that when the working face is located on the upper wall side of the fault, the basic top subsidence is higher than that of conventional mining, and the rock layer collapse form in the fault affected area is a "pile-up" structure. When the working face is located on the lower side of the fault, the basic top subsidence is larger, and the failure form of overall slip is present near the fault. At the same time, the reliability of the numerical simulation is verified by the roof drilling. The research results provide a theoretical basis for solving the problems of mine pressure control and roadway surrounding rock support under the influence of faults.

In coal engineering such as coal mining and roadway excavation, complex underground environment leads to damage and deformation of coal body. It is of great significance to study the response mechanism of mechanical characteristics during coal disaster damage to maintain the stability of coal mining. In this paper, the large-size coal body is taken as the research object, and the conventional triaxial compression test is carried out to monitor the mechanical behavior of coal body under different confining pressures. The conditions and laws of the sub-instability stage of coal body are found, and the failure mechanism of coal body under triaxial compression is revealed. The results show that : ( 1 ) The thresholds of the five stages of the full stress-strain curve increase with the increase of confining pressure, and the peak strain has a high correlation with confining pressure. ( 2 ) The power law equation has a good fitting effect on the axial strain rate in the accelerated growth stage of coal disaster. ( 3 ) When the test environment is close to the real state of coal underground, the sub-instability will occur ; the quasi-static and quasi-dynamic stages account for 37.5 % and 62.5 % of the total time of sub-instability, and the stress and radial strain evolution in the quasi-dynamic stage is more intense. ( 4 ) The sensitivity of residual strength is higher than that of peak strength, and the strength attenuation coefficient gradually decreases with the increase of confining pressure. ( 5 ) The coal body is mainly shear failure accompanied by tensile failure, and the crack width is different at different positions. The research results have theoretical significance for the identification of sub-instability stage, and provide theoretical support for the occurrence mechanism, early warning and prevention of coal engineering disasters.

Accurate sensing of shaft wind speed is the core link to realize the intelligent ventilation system, but at present, mine shafts are affected by airflow fluctuations caused by turbulence disturbance, and there are large errors in the wind speed monitoring results. In order to eliminate such errors, this paper proposes an adaptive and accurate sensing algorithm for shaft wind speed. The algorithm continuously optimizes the wind speed estimation and reduces the data noise by predicting and updating steps, combined with adaptive adjustment of the model error, so as to eliminate the influence of turbulence. Six types of shaft wind speeds, 0.15 m/s, 0.50 m/s, 2.00 m/s, 5.00 m/s, 10.00 m/s, and 15.00 m/s, were monitored continuously for 600 seconds, and the monitoring data were corrected using the algorithm studied in this paper. The analysis results show that the corrected data of this algorithm can be significantly close to the expected value compared with the monitoring data, and the accuracy has been improved by 73.56%, 65.04%, 56.24%, 61.38%, 71.04% and 69.63%, respectively. This algorithm provides accurate and reliable data support for the intelligent ventilation system and promotes the development of mine intelligence.

Accurate and quantitative prediction of coal caving gas emission was one of the important contents of mine gas emission prediction. The current prediction formula of gas emission rate in coal caving mining did not fully consider the mining parameters and gas seepage process in coal block, which leaded to the prediction accuracy of gas emission rate in coal caving mining.Based on Darcy seepage theory, taking the actual gas parameters of 5301 coal face of Sihe Coal Mine as the data source, the mathematical and physical model of coal block gas seepage and emission was constructed. Based on the UDS interface of fluent, the gas emission process of coal blocks with different sizes and shapes was simulated, and the general calculation formula of gas emission rate of coal blocks with equivalent radius, surface area volume ratio and time as independent variables was established by numerical analysis method. Combined with the actual mining coal transportation process and mining coal cutting process, considering the distribution of mining coal geometric parameters, the mathematical modeling method was used to build the calculation model of coal mining coal gas emission and the calculation model of coal mining coal gas emission. The gas emission data of 5301 working face in Sihe coal mine were measured, and the relative error between the calculated results and the measured results was 10.96%.The research showed that the calculation model had a certain field practicability.

In the process of coal mine roadway excavation, the tunneling path of Tunnel Boring Machine (TBM) may deviate from the predetermined axis due to the uncertainty and complexity of the environment. In order to improve the accuracy of TBM pose prediction, this paper proposes a TBM tunneling pose prediction model based on optimized deep learning algorithm. The collected TBM tunneling parameters are extracted and cleaned, and the spatial features of the data are extracted by convolutional neural network (CNN). Bidirectional long short-term memory network (BiLSTM) is used to learn the time dependence of the data. In order to further optimize the performance of the model, the Sparrow Optimization Algorithm with Sine Cosine and Cauchy Mutation (SCSSA) is used to optimize the hyperparameters of the CNN-BiLSTM model. The results show that the optimized model has a significant improvement in multiple error indicators, including mean absolute error (MAE), mean absolute percentage error (MAPE), mean square error (MSE) and root mean square error (RMSE). At the same time, the performance indicators such as correlation coefficient (R) and coefficient of determination (R2) are also improved. Specifically, when the SCSSA-CNN-BiLSTM model predicts the pose parameters such as rolling angle, pitch angle, azimuth angle and horizontal deviation of TBM tunneling, the determination coefficient R2 reaches 0.9982,0.9944,0.9936 and 0.9865, respectively, which verifies the efficiency and accuracy of the model in the prediction of TBM tunneling pose in coal mine roadway.

To address the challenge of preventing spontaneous combustion of residual coal in goafs of thick coal seams, a long-acting composite retardant solution with MgCl₂ -Vc-SDS as the core was developed. Experiments show that the optimized formulation (MgCl₂ 7.5%, Vc 2.5%, SDS 0.025%) significantly increases the critical temperature for coal spontaneous combustion. The production temperatures of CO and C₂H₄ are delayed by 10℃ and 20℃, respectively, with an average retardation rate of 53%. The contact angle of the retardant solution is reduced by 35%, and its reverse capillary rise height is 1.5 times that of pure water, indicating significantly enhanced wetting performance. Long-term performance tests over 20 days showed a fluctuation in the retardation rate of 3.6% to 5.4%. Thermogravimetric and infrared analysis confirmed that the retardant solution functions through dual mechanisms of physical oxygen isolation and chemical modification, increasing the critical temperature of coal samples by 22℃ and the dry cracking temperature by 35.9℃. It reduces oxygen-containing functional groups by 18% and increases hydroxyl groups by 18%, establishing a dual retardation mechanism of “physical oxygen isolation-chemical inhibition”.

Aiming at difficulties for actual seismic design of shaft tower structure. The theoretical analysis method was used to explore the seismic response of the shaft tower under the interaction mechanism of piles, soil, well bore, and shaft tower. Based on the Winkler foundation beam theory, Penzien centralized quality theory and elastic half-space theory of foundation vibration, the theoretical analysis simplified model of piles-soil-well bore-shaft tower system is constructed. Combined with the structural dynamics theory, the dynamic motion equation in the time domain under earthquake action is established. Based on the MATLAB software platform, the seismic response analysis and solution system of the shaft tower is developed. Finally, the piles-soil-well bore-shaft tower system of a large mine is taken as the research object. The influence of site category, foundation and foundation form and seismic wave on the seismic response of the shaft tower is compared. The results show that, the enhancement coefficients of the tower acceleration of shaft tower are concentrated within 1.72~2.12, 1.23~1.71 and 1.02~1.51 respectively under Ⅱ、Ⅲ and Ⅳ site categories. The softer the site, the smaller the tower acceleration enhancement coefficients of the shaft tower. In the design of pile-raft foundation shaft tower, it is necessary to consider the interaction of piles-soil-well bore-shaft tower, which is crucial to ensure the stability and safety of the shaft tower structure．

Coal mining-induced subsidence causes surface deformation and soil erosion, yet their connection is not well-studied. To enhance the ecological restoration strategies in mining regions, it is essential to investigate how subsidence may influence soil erosion. This research focuses on the multi-ore composite mining region in Ordos, employing differential interferometric synthetic aperture radar (D-InSAR) technology alongside the revised universal loss equation (RUSLE) to assess surface subsidence and soil erosion rates quarterly from 2018 to 2021. It examines the spatiotemporal evolution characteristics and quantitatively evaluates the changes in soil erosion within subsidence and non-subsidence areas. The findings indicate:(1) The cumulative subsidence in Ordos' s multi-ore composite mining area increased steadily from 2018 to 2021, with substantial variations in subsidence rates and seasonal trends across different subsidence areas. Specifically, subsidence areas 2 and 3 experienced the highest subsidence, reaching maximum cumulative amounts of 1.04 m and 1.06 m over four years, with a noticeable acceleration in subsidence rates during autumn. (2) The soil erosion rate in the region exhibited clear seasonal variations from 2018 to 2021. Erosion was minimal in summer and winter, characterized primarily by micro-erosion, with rates nearly zero in spring and peaking in autumn. Notably, the maximum soil erosion rate in the subsidence area occurred in 2021, at 26. 51?t?? hm2 ? a1, marking a critical phase for controlling soil and water loss in the mining zone. (3) Mountain mining does not consistently enhance soil erosion; in some instances, subsidence may inhibit erosion. Topographic features significantly influence soil erosion, particularly in mountainous regions, which are highly susceptible to erosion. Open-pit mining exacerbates soil erosion and provokes a more pronounced erosion response in subsiding areas. This study uncovers the relationship between surface deformation and soil erosion in Ordos' s multi-ore composite mining area. It investigates the potential effects of surface deformation on soil erosion, providing a scientific foundation for soil erosion management and ecological restoration in these mining regions.

In order to realize high efficiency flotation of hard-to-float coking coal, a composite collector (B2) was prepared by mixing kerosene (B1) with isomeric alcohol ethoxylates 1305 (TO-5). Comparative study on the flotation effect, flotation kinetic properties and frothing performance under multi-stage flotation of B1 and B2 on hard-to-float coking coal. Comparison test results of B1 and B2 flotation effect show that: B1 dosage of 3000 g/t in the low level of foaming agent flotation index decreased significantly, while B2 of only 1000 g/t dosage can be obtained with similar ash content but higher yield of clean coal products compared to B1. The flotation kinetic tests and fitting results showed that the R2 of the fitting using the classical first-order kinetic model under different reagents regimes were all above 0.999. The k value of B1 was 1.3439 at 3000 g/t, and the k value was 1.5809 and 1.7203 at 1000 g/t and 3000 g/t of B2,respectively, indicating that the flotation rate of B2 was faster. The timed-release test curves predict that B2 can achieve higher clean coal yields when B1 and B2 have the same clean ash. Surface tension tests revealed that B1 was unable to reduce the surface tension at the gas/liquid interface, while B2 significantly reduced the surface tension at the gas/liquid interface due to the addition of surfactant TO-5. A visual observation study of the bubbles distributed in the range of 10-1000 μm using a high-speed camera system revealed that the number of bubbles in B1-generated bubbles was little and the size of bubbles was large; the number of bubbles generated with B2 increased significantly. The combination of B2 and 2-octanol improves the probability of collision between bubbles and coal particles by generating smaller and denser flotation bubbles. Laser particle size testing of the bubbles revealed that the volume fraction of microbubbles in the size range of 0.1-1 μm increased significantly for B2 compared with that of B1. B2 enhanced the flotation effect of hard-to-float coking coal by changing the bubble characteristics during flotation. The study provides a reference for the research and development of highly efficient trapping agents for hard-to-float coking coal.

Aiming at difficulties for coal roadway supporting in three soft coal seams of Zhengzhou mining area, occurrence characteristics and formation mechanism of three soft coal seam is explained, and the causes for supporting instability in three soft coal roadway is analyzed. The mechanism of bolt support is revealed based on the principle of composite arch beam, and it’s proposed that, coal seam bolt performance, bolt preload, mesh strength, quick installation process and immediate support are the key for three soft coal roadway supporting. On this basis, the thick coal seam bolt-mesh supporting is designed for 22011A coal face transport roadway of Chaohua Coal Mine. The result shows that maximum roof separation at shallow and deep basis points are 48 mm and 52 mm, the maximum roof-to-floor and side-to-side convergence are 372 mm and 310mm, the supporting section of roadway is maintained．

In order to enhance the anti-impact displacement performance of the anti-impact support bracket to reduce the impact pressure hazard caused by deep coal mining, the numerical simulation of vertical compression of the existing pre-creased components was based on, the reaction force elevation and wall strain evolution were linked together, followed by the study of the changes in wall strain after setting ribs, embedded tubes, and circular collars, exploring the law of influence of different structural parameters on the energy absorption effect of the reinforced components, and then using the NSGA-Ⅱ genetic algorithm for optimization and solution, finally determining the optimal dimensions: rib thickness of 3.00 mm, embedded tube thickness of 2.45 mm, and circular collar thickness of 4.31 mm; furthermore, through the simulation and analysis of the results, it was found that: the optimized component is better than the original component in terms of anti-impact performance, with the peak value of the reaction force rising by 8.16%, the average counterforce increasing by 46.8%，the coefficient of load fluctuation dropping by 26.3%, the total energy absorption rising by 57.08%, and the energy absorption performance being better and the reaction force fluctuation being more stable. The research results can provide useful references for the design of anti-impact energy-absorbing components.