Abstract:To address the problems of low equipment coordination efficiency,insufficient data integration,and incomplete safety monitoring coverage in coal mine production scheduling and safety management,a digital twin-driven integrated ground decision scheduling system for the fully mechanized top-coal caving face was proposed.The system adopted a three-level centralized control architecture consisting of intelligent working face terminals,roadway control nodes,and a ground management and control center.The intelligent working face terminals collected equipment status and environmental parameters in real time,the roadway control nodes performed data cleaning,fusion,and edge preprocessing through explosion-proof servers,and the ground management and control center integrated a digital twin system with an intelligent decision engine to achieve global monitoring and coordinated optimization.By integrating industrial Ethernet and wireless Mesh networks,a highly reliable communication infrastructure was constructed.A digital twin model of fully mechanized top-coal caving face equipment was constructed by combining accurate three-dimensional models with kinematic models,and dynamic synchronization between physical and virtual entities was achieved using a three-dimensional scene automatic construction algorithm.Through multi-source data acquisition and processing,real-time data-driven synchronous mapping,coordinated control of coal cutting and top-coal caving,and multi-system integrated access,coordinated operations of autonomous shearer cutting planning and planned coal caving by hydraulic supports were realized.The application results in an actual coal mine showed that the following rate of the hydraulic supports remained above 97 percent,the automation rate of coal caving exceeded 85 percent,the proportion of manual intervention was lower than 10 percent,and the number of operators per shift was reduced from five to one.The system response latency was less than 200 ms,and the frame rate remained above 30 frames per second,achieving closed-loop management integrating perception,analysis,decision-making,and control.

Abstract:CO released from the oxidation of residual coal in goaf areas causes CO exceedance in the return air corner of coal mines,and clarifying the critical thresholds for CO exceedance in the return air corner and establishing a graded early warning index system are of great significance for the early warning of coal spontaneous combustion in goaf areas.To achieve accurate early warning of coal spontaneous combustion disasters in coal mine goaf areas,a medium-rank bituminous coal was taken as an example,and the oxidation characteristics of coal and the generation patterns of indicator gases under ambient temperature and heating conditions were systematically analyzed by combining laboratory experiments and field observations.Experimental results indicated that coal exhibited a hysteresis phenomenon of O2 consumption and CO generation at ambient temperature,and the background CO volume fraction generated by ambient-temperature oxidation was determined to be 18×10-6.During the heating oxidation stage,the oxygen consumption rate and CO generation rate showed a significant increasing turning point with a sharp increase at 70 ℃,and the characteristic gas C2H4 began to appear at 100 ℃.Based on these results,the low-temperature oxidation process of coal was divided into three stages,namely slow oxidation(30-70 ℃),accelerated oxidation(70-100 ℃),and intense oxidation(＞100 ℃).By integrating experimental data with historical field monitoring data,a four-level early warning index system for coal spontaneous combustion was established with the CO concentration in the return air corner as the core indicator,which provided a theoretical basis and practical guidance for early identification and graded prevention and control of coal spontaneous combustion based on CO concentration in the return air corner.

Abstract:Existing studies on deterministic transport networks for mining lack in-depth discussion of the applicability boundaries of Time-Sensitive Networking(TSN)and Slicing Packet Network(SPN),as well as their potential coordination and technology integration paths.They also fail to combine the realities of multi-service,multi-layer,and highly dynamic network transport in mines to provide technically instructive technology selection and integrated networking solutions.To address this issue,this study systematically analyzed the urgent demand of industrial Ethernet and 5G radio access networks for the mining vertical industry for deterministic transport networks in the context of intelligent mines.It focused on the basic principles and performance characteristics of TSN and SPN.The key technologies of TSN included traffic regulation,deterministic service scheduling,and centralized control,while the key technologies of SPN included sliced Ethernet,fine-granularity slicing,and packet forwarding.Combined with the actual networking architecture and service types of industrial ring networks in mining production environments,the applicability and technical limitations of TSN and SPN in typical scenarios such as underground communication,remote control,video surveillance,and sensor data transmission were further investigated.The results showed that SPN,by virtue of its hard isolation capability,flexible service scheduling,and slicing features for vertical industries,was more consistent with the requirements of mining industrial ring networks for unified multi-service transport and deterministic performance assurance.Finally,this study demonstrates that SPN is an important technological path for the evolution of deterministic networks in the intelligent construction of mines and provides recommendations for the upgrading and deployment of mining industrial ring networks.

Abstract:Current prediction models for dust concentration in open-pit mines usually rely on predefined indicators and parameters to estimate dust levels.However,the open-pit mining environment is complex and highly variable,and the key factors influencing dust concentration are numerous and difficult to clearly define.As a result,existing prediction models show limitations in prediction accuracy and generalization ability,and they often ignore the deep spatiotemporal features embedded in the data,making it difficult to comprehensively characterize the variation patterns of dust concentration.To address these issues,a dust concentration prediction model for open-pit mines based on a Long Short-Term Memory network(LSTM)-Convolutional Neural Network(CNN)was proposed.Pearson correlation analysis was used to select humidity,noise,stripping volume,and wind speed as input indicators for dust concentration prediction.After preprocessing,these indicators were fed into multiple parallel CNN units with an attention mechanism,which extracted local spatial features at different scales.The attention mechanism was used to weight the extracted features,enhancing feature representations that were more strongly related to dust concentration while suppressing redundant or noisy information.The attention-enhanced features were then reorganized into a time-series format,and the gated mechanism of the LSTM captured the temporal dynamic patterns and long-term dependencies of dust concentration.Finally,dust concentration was predicted through a fully connected layer.Experimental results showed that,compared with single models including LSTM,CNN,and Random Forest(RF),the proposed LSTM-CNN model improved the coefficient of determination R2 by 7.85％,12.91％,and 23.49％,respectively,reduced the Root Mean Square Error(RMSE)by 17.81％,45.76％,and 33.35％,and reduced the Mean Absolute Error(MAE)by 26.48％,25.56％,and 24.52％.Compared with hybrid models RF-SVR and RF-GRU,the LSTM-CNN model improved R2 by 2.89％and 4.79％,reduced RMSE by 9.15％and 14.12％,and reduced MAE by 11.40％and 16.53％,respectively.

Abstract:Electromagnetic radiation monitoring technology is currently used to conduct non-contact directional measurements in roadways,which enables large-scale regional scanning,but in the practice of ultra-thick coal seam extraction it suffers from poor anti-interference performance and the inability to penetrate into the coal-rock mass.To address these problems,a borehole electromagnetic radiation monitoring system suitable for mobile monitoring inside boreholes was developed.The system employed a borehole electromagnetic radiation antenna with a small cross-sectional area and low inductance magnetic core,which exhibited optimal response characteristics in the frequency band of 0-20 kHz and effectively overcame the challenges of complex underground electromagnetic environments and signal attenuation during long-distance transmission,enabling accurate capture of weak electromagnetic radiation signals from deep coal mass.Field measurements of electromagnetic radiation were conducted using the borehole electromagnetic radiation monitoring system at the 1101 working face of Zhundong No.2 Mine of State Grid Energy Xinjiang Zhundong Coal Power Co.,Ltd.along the coal seam dip direction,the working face strike direction,and during the pressure relief process of large-diameter boreholes.The results showed that the intensity and counts of borehole electromagnetic radiation were significantly correlated with the distribution of surrounding rock stress.The spatial distribution patterns of borehole electromagnetic radiation signals along the coal seam dip direction accurately characterized deep surrounding rock stress concentration zones,and the distribution patterns along the working face strike direction effectively delineated the spatial boundaries between the in-situ stress zone and the mining-affected zone,enabling accurate inversion of the surrounding rock stress state during ultra-thick coal seam extraction.The temporal evolution of borehole electromagnetic radiation during the pressure relief process corresponded to three stages,namely the pressure relief silence stage,the stress adjustment and fluctuation stage,and the rheological damage active stage,which effectively characterized the stress evolution of surrounding rock during the pressure relief period.

Abstract:Most existing dispatching methods for coal mine power systems adopt a single-objective optimization framework that takes minimization of operating cost as the sole objective and mainly considers static security constraints.However,in practical operation of coal mine energy systems,both dynamic and static security requirements need to be satisfied,and reasonable trade-offs among multiple competing objectives must be achieved.The PID-Based Search Algorithm(PSA)has strong optimization potential,but it is prone to falling into local optima and is difficult to adapt to the complex and variable optimization environment of coal mine microgrids.To address this issue,an adaptive parameter adjustment mechanism was introduced,based on which an Adaptive PID-Based Search Algorithm(APSA)was proposed,and a collaborative optimization model of source-grid-load-storage for coal mine microgrids based on APSA was constructed.The model included multiple objective functions such as operating cost,renewable energy utilization rate and penetration rate,and comprehensive voltage deviation index.A three-layer nested solution framework based on hierarchical sequential optimization was designed,in which constraints were imposed layer by layer to search for the optimal solution set,enabling gradual reduction of the solution space and ensuring the convergence rate and computational efficiency of the algorithm.Experimental results showed that,compared with the pre-optimization case,the daily operating cost of the system was reduced by 44.9％,the renewable energy utilization rate was increased to 98.5％,and the comprehensive voltage deviation index was reduced to 1.8 p.u.after APSA optimization.Compared with commonly used particle swarm optimization algorithms and genetic algorithms,APSA exhibits significant advantages in solution stability and convergence accuracy,and it effectively solves the collaborative optimization problem of source-grid-load-storage for coal mine microgrids,providing an effective solution for safe,green,and economical operation of mining areas.

Abstract:To address the limitation in measurement accuracy of existing ultrasonic time difference anemometry caused by the inability of transducer installation positions to dynamically adapt to different roadway cross-sections,this study investigated two ultrasonic transducer installation positions for different roadway cross-sections(such as rectangle,trapezoid,arch,et al).Fluent numerical simulations and underground manual measurements were conducted to verify the existence of an average wind velocity line parallel to the roadway floor.On this basis,by combining turbulent stress decomposition theory with Prandtl's mixing length theory and introducing a modified coefficient,the height function of the average wind speed line from the roadway floor for different roadway sections was derived.Together with the determination of the velocity measurement interval,the installation positions of the two ultrasonic transducers were determined.Simulation and field test results showed that:① compared with the traditional fixed-height transducer installation method,the proposed transducer installation position determination method achieved higher measurement accuracy under the same operating conditions.② The installed transducers performed best in rectangular roadways,with a relative error of 4.486％compared with manual measurements,followed by arched roadways with a relative error of 4.935％,while trapezoidal roadways showed the largest relative error of 5.579％.③ Using standard deviation as the evaluation criterion rsingstandard deviation as the evaluation criterion,the standard deviation of wind velocity measurements obtained by the installed ultrasonic transducers was smaller than that of manual measurements,indicating more stable data acquisition in underground environments.

Abstract:Under deep high-intensity mining conditions,the spatiotemporal evolution pattern of pressure-relief gas emission in the fully mechanized top-coal caving working face is unclear,while traditional high-level drainage roadway construction is costly and exhibits low gas extraction efficiency.At present,research on staged precise gas control over the full time scale from the opening cut to mining termination(i.e.,the full lifecycle),based on the coupling relationship between the dynamic evolution of mining-induced overburden and gas emission stages,remains insufficient.To address these issues,taking the 307 working face of Wangjialing Mine as the engineering case,the feasibility of replacing high-level drainage roadways with high-level directional long boreholes at different strata for pressure-relief gas extraction was evaluated,and a"staged and differentiated"precise control method was proposed.① A permeability distribution model of the deep mining-induced fracture field with three zones of"penetrating-vertical-horizontal"was established,which clarified that the horizontal storage-transport zone was the dominant migration and enrichment area for pressure-relief gas.② The concept of the"full lifecycle"of mining-induced pressure-relief gas emission was proposed,and based on the dynamic coupling relationship between roof weighting characteristics and gas emission,the process was divided into four stages:occurrence stage,bursting stage,fluctuation stage,and stable stage.The gas source composition,emission characteristics,and proportion of each stage were clarified,providing a theoretical basis for staged precise gas control.③ For the initial mining stage(occurrence stage and bursting stage),a"bow-shaped"directional borehole trajectory was designed to achieve precise interception of gas buoyant migration paths;for the normal mining stage(fluctuation stage),a"high-middle-low"multi-layer horizontal directional borehole optimized layout was constructed to comprehensively cover the pressure-relief gas storage and transport zones within the mining-induced overburden space.Field test results showed that this method increased the extracted gas volume fraction of the working face to over 8％,stably controlled the gas volume fraction in the return airflow below 0.4％,effectively solved the problem of gas exceeding the limit in the return air corner,and achieved precise and controllable gas extraction.

Abstract:At present,studies on the disaster-inducing mechanism of high-position thick and hard key strata mainly focus on the fracture behavior of key strata and their influence on strong ground pressure in the mining face,while relatively little attention is paid to the effect of variations in the distance between the key strata and the coal seam(interlayer distance)on the transformation of fracture modes of high-position key strata and the associated strain energy"accumulation-release"process.To address this issue,theoretical analysis,numerical simulation,and similarity simulation experiments were comprehensively employed to reveal the transformation mechanism of fracture modes of high-position key strata and the evolution laws of energy accumulation and dissipation,to compare the attenuation characteristics of ground pressure intensity on the working face after weakening of high-position key strata at different horizons,and to clarify the weakening and disaster-mitigation effects of high-position thick and hard key strata.The results showed that an increase in the distance between the key strata and the coal seam led to changes in the area of the suspended region of the key stratum,altered the magnitude and growth pattern of bending moments at the strike and dip boundaries of the key stratum,and promoted the transformation of its fracture mode from vertical fracture to horizontal fracture.Due to its strong bearing capacity,a typical high-position thick and hard key stratum had a larger suspended area and a greater accumulation of elastic strain energy than low-position key strata,and the rapid release of elastic strain energy during fracture posed a higher risk of inducing strong ground pressure disasters.The hydraulic fracturing method significantly altered the fracture step distance of the key strata and the intensity of ground pressure manifestation in the working face.After hydraulic fracturing weakening of a high-position key stratum located 125 m above the coal seam,the fracture step distance was reduced by 40.94％compared with the unweakened condition,the accumulated elastic strain energy was reduced by 98.40％,and the roof pressure of the working face was reduced by 48.77％,effectively controlling the strong ground pressure manifestation induced by fracture of high-position thick and hard key strata.

Abstract:To address the difficulty of accurately and efficiently recognizing coal gangue caused by complex environmental factors such as high dust concentration and highly variable illumination in mines,this study improved the YOLOv12 network model and proposed an intelligent coal gangue recognition method based on improved YOLOv12.A Dual-Scale Sparse Attention(DSSA)mechanism was designed to enhance the model's attention to multi-scale coal gangue target regions and its spatial perception capability.A Multi-Condition Feature Refinement(MCFR)mechanism was designed to perform condition-guided fusion of deep and shallow features,which effectively enhanced the discriminative representation between coal and coal gangue.A Dynamic Multi-Task Balance Loss(DMTBL)function was constructed to achieve adaptive weight adjustment among localization,classification,and confidence,thereby strengthening the model's learning capability for hard sample regions.Experimental results showed that the improved YOLOv12 achieved a precision,recall,and mAP of 96.5％,94.9％,and 95.8％,respectively,in the coal gangue recognition task,representing improvements of 3.8％,4.5％,and 4.5％over the original YOLOv12,which effectively addressed issues such as missed detection,false positives,and blurred boundaries while maintaining a high inference speed of 47.7 frames per second.Visualization results of activation heatmaps showed that the improved YOLOv12 accurately focused on the target object regions when processing coal gangue with different structures and texture complexities,with no obvious background interference,and the activated regions basically cover the main contours of coal blocks and coal gangue.

Abstract:The spontaneous combustion process of coal is influenced by multiple factors.Existing studies mainly investigate coal spontaneous combustion characteristics from aspects such as coal metamorphic degree,oxygen concentration,air supply rate,air humidity,particle size,and moisture content rate.However,the sulfur content in coal is also one of the important factors affecting coal spontaneous combustion.To investigate the effects of sulfur content on the spontaneous combustion characteristics and oxidation kinetic parameters of anthracite,oxidation processes of five coal samples with different sulfur contents were tested using a programmed temperature-rise experiment system with a tube furnace.The effects of different sulfur contents on CO and CO2 gas release characteristics and characteristic temperatures of spontaneous combustion during the low-temperature oxidation process of coal were quantitatively analyzed.By calculating the oxygen consumption rates of coal samples with different sulfur contents under different temperature conditions,the variation pattern of the oxygen consumption rate with temperature was quantitatively examined.Based on chemical reaction kinetics,the apparent activation energies of coal samples under different sulfur contents were calculated,and the variation pattern of apparent activation energy with sulfur content was quantitatively analyzed.The results showed that when the sulfur content remained constant,the concentrations of CO and CO2 and the oxygen consumption rate increased exponentially with increasing temperature,while the apparent activation energy gradually decreased.With increasing sulfur content,the concentrations of CO and CO2 and the oxygen consumption rate at each temperature point first increased and then decreased,reaching maximum values at a sulfur content of 5.14％.In contrast,the characteristic temperature of spontaneous combustion and the apparent activation energy showed opposite trends and reached minimum values at a sulfur content of 5.14％,at which point the coal sample exhibited the strongest spontaneous combustion tendency.Therefore,the critical sulfur content affecting the spontaneous combustion tendency of anthracite was 5.14％.

Abstract:As shallow coal resources become increasingly depleted,deep coal mining is key to ensuring national energy security.In deep mining,the spatiotemporal correlation characteristics of coal and gas outbursts and coal-rock-gas coupled dynamic disasters become more complex,with significantly enhanced chain effects and coupling behaviors,which makes mine ventilation and safety control more difficult.Based on an analysis of the advantages of quantum computing in information representation,information storage,and computational paradigms,as well as the challenges faced by complex mine ventilation and safety control in deep coal mining such as multiphysics coupling solutions and high-dimensional computation,this study explores the potential advantages of a full-chain technical system empowered by quantum computing for complex mine ventilation and safety control from microscopic mechanisms to macroscopic systems.These advantages include ① revealing microscopic disaster-inducing mechanisms of multiphysics coupling through quantum simulation,② rapidly solving high-dimensional models through quantum parallel computation,③ efficiently addressing combinatorial optimization problems in mine ventilation and safety systems through quantum combinatorial optimization algorithms while accelerating model training and deeply mining and integrating multi-source heterogeneous precursor information through quantum machine learning,④ building an intelligent computing platform for mine ventilation and safety systems through the integration of artificial intelligence and quantum computing.The challenges of engineering applications of quantum computing are analyzed,including short quantum coherence time,susceptibility to environmental interference,limitations in the applicability of quantum algorithms,and constraints of quantum hardware facilities.Future research directions are identified as exploring feasibility through multi-instance verification,the superiority of engineering applications,and adaptability across multiple scenarios.This study aims to provide a theoretical reference for promoting the development of intelligent mine ventilation and safety systems toward the integration of artificial intelligence,quantum computing,and quantum artificial intelligence.

Abstract:This study aims to investigate the influence of underlying goaf groups on slope stability under the open-pit-underground combined mining mode.Taking the composite slope of the west dump and pit of the Dameigou Open-pit Coal Mine as the research object,six underlying goafs of working faces beneath the W1 section and four underlying goafs beneath the W2 section were selected as calculation sections.UDEC numerical simulation software was used to sequentially simulate and analyze the displacement and shear strain evolution of overburden after the formation of each working face goaf,and the development characteristics of the caving zone,fracture zone,and bending subsidence zone formed by the goaf group were identified.Based on the distribution characteristics of the"three zones"an engineering geological model of the slope was established,and the slope stability coefficients with and without considering the influence of the"three zones"were calculated using the limit equilibrium method.Based on the Mohr-Coulomb criterion,numerical simulations of slope stability were conducted to reveal the landslide mechanism under the influence of goaf groups.The results indicated that the overlying strata above the goafs exhibited trapezoidal caving,and with an increase in the number of goafs,a superposition effect occurred,significantly expanding the caving range of the overlying strata.The potential landslide modes of the slopes along the W1 and W2 sections were circular sliding.The calculated slope stability coefficients of the W1 and W2 sections were identical when goaf groups were not present and when goaf groups were present but the"three zones"effect was not considered,with values of 2.038 and 2.634,respectively.After considering the"three zones"effect,the stability coefficients decreased to 1.637 and 1.685,respectively,confirming that the"three zones"effect formed by goaf groups was a key factor affecting slope stability.

Abstract:In response to the problems of slow detection speed and low automation control level in traditional PLC-based mine air door monitoring technologies,a mine air door monitoring system based on PLC and an improved YOLOv11 model was proposed,which embedded the improved YOLOv11 model into the conventional PLC-based air door monitoring system to realize real-time and accurate recognition of underground personnel and vehicles and intelligent linkage control of air door opening and closing.Taking YOLOv11 as the base model,an EAW-YOLO model was proposed.The exponential moving average(EMA)attention mechanism was integrated into the C3k2 module to form a C3k2-EMA module to enhance the model's feature extraction capability.Then,ADown convolution was introduced to retain key information while performing channel dimensionality reduction.Finally,the WIoU loss function was introduced to enhance the regression convergence speed of the model by dynamically adjusting the weighting of different anchor boxes based on their importance.Experimental results showed that:① compared with YOLOv11,the EAW-YOLO model improved accuracy by 1.6％and mAP@0.5 by 1.9％,reduced the number of model parameters by 19.2％,and increased inference speed by 9.7％to reach 86.7 frames/s.② Compared with YOLOv11,Faster-CNN,EfficientDet,and RT-DETR,the EAW-YOLO model improved accuracy by 1.6％,0.6％,2.0％,and 0.2％,respectively,improved mAP@0.5 by 1.9％,0.7％,1.6％,and 1.1％,respectively,reduced the number of parameters by 0.5×106,135.0×106,1.8×106,and 40.7×106,respectively,increased inference speed by 7.7,51.2,9.8,and 35.1 frames/s,respectively,and reduced model size by 0.4,102.9,11.1,and 80.9 MiB,respectively.③ For different vehicles with large targets at close range,the EAW-YOLO model showed higher detection accuracy.For different vehicles with small targets at long distance,the detection accuracy of the EAW-YOLO model was slightly improved.For small personnel targets at long distance with blurred edge features,the EAW-YOLO model showed a larger improvement in detection accuracy and effectively identified correct personnel targets.In scenes with occlusion and strong backlighting,the EAW-YOLO11 model achieved higher detection accuracy.To verify the feasibility of the mine air door monitoring system based on PLC and the improved YOLOv11 model,laboratory validation was conducted,and the results showed that when the camera captured a vehicle model,the recognition signal was transmitted to the PLC in real time,thereby accurately controlling the opening and closing actions of the air door device.

Abstract:The coal-rock interface trajectory is multivariate time-series data,and complex correlations exist among different variables,which makes high-precision prediction challenging.To address this problem,this study proposed a coal-rock interface prediction model based on multichannel correlated complementary features,named SSIC-former,which integrated a Centralized Attention Mechanism(CAM),an Interactive Convolution Block(ICB),and a Sharpness-Aware Minimization(SAM)strategy.First,a sliding window method was used to construct continuous samples from the raw data.Then,an SSIC-former architecture for coal-rock identification was built to extract cross-channel correlation information and local features of the coal-rock interface,and reversible instance normalization was introduced to dynamically eliminate data nonstationarity.The CAM extracted correlated complementary features among multiple channels,while the ICB extracted local features at different scales and enabled dynamic cross-scale interaction,and their outputs were fused through residual connections to enhance feature representation.Finally,during the training stage,the SAM strategy was combined to prevent the model from falling into local optima,and the prediction results were output through a projection layer.Experimental results showed that:① An SSIC-former-based coal-rock interface prediction model achieved a mean absolute error of 6.37 mm,a mean absolute percentage error of 2.79％,a root mean square error of 8.08 mm,a mean square error of 0.07 mm2,and a coefficient of determination of 0.99,with an average inference time of 0.006 6 s per sample.Among Transformer-based models,it had the shortest inference time and met the low-latency requirements of real-time operation of shearers.(2)Compared with models based on LSTM,Crossformer,Nonstationary_Transformer,FPPformer,iTransformer,and PatchTST,the SSIC-former-based model outperformed the other models in the first five evaluation metrics mentioned above,indicating that the SSIC-former-based model had high prediction accuracy and strong generalization ability and provided more accurate results for coal-rock interface trajectory prediction.

Abstract:Bidirectional single-lane roadways are widely present in underground auxiliary transportation roadways of coal mines,where vehicles traveling in opposite directions must rely on passing bays for meeting and yielding,and multi-vehicle parallel operations are prone to lead to competition for spatiotemporal resources.In the absence of coordinated scheduling and conflict resolution,traffic congestion and delays in vehicle transportation tasks may occur and even lead to safety accidents.Existing studies have limitations in accurately modeling underground traffic conflicts and efficiently solving path optimization problems under complex constraints.To address these issues,a path optimization method for underground trackless rubber-tyred vehicles in coal mines based on an improved large neighborhood search algorithm was proposed.With the objective of minimizing travel distance cost,vehicle startup cost,and time window violation cost,traditional vehicle routing problem constraints including rated vehicle load,maximum travel distance,travel time,and demand point time windows were considered,and meeting rules based on passing bays as well as spatiotemporal conflict avoidance constraints were introduced to construct a path optimization model for underground trackless rubber-tyred vehicles.To obtain high-quality feasible solutions within an acceptable time,an Improved Adaptive Large Neighborhood Search(IALNS)algorithm was designed.This algorithm adopted a hierarchical mechanism with upper-level and lower-level paths to improve search efficiency,integrated multiple destroy and repair operators,introduced a simulated annealing criterion to balance the global exploration and local search capabilities,and applied a perturbation restart strategy based on an elite solution pool to avoid being trapped in local optima.Experimental results showed that the IALNS algorithm obtained optimal solutions consistent with those of the Gurobi solver while achieving higher efficiency and stability.Compared with genetic algorithms,particle swarm optimization algorithms,and adaptive large neighborhood search algorithms,the IALNS algorithm demonstrated improvements in solution quality,computational speed,and stability.Under different passing bay density conditions,the IALNS algorithm maintained stable solution performance.

Abstract:No-Reference Video Quality Assessment(NRVQA)is a key technique for evaluating the video quality of underground drilling sites in coal mines and enabling remote monitoring.Existing NRVQA methods are mostly designed for general ground scenes and are difficult to achieve satisfactory performance in underground drilling environments where composite image distortions are caused by coal dust and equipment vibration.To address this problem,an NRVQA method for underground drilling sites based on spatiotemporal domain dynamic aggregation was proposed.Video features of drilling site surveillance videos were extracted from two dimensions,namely spatial and motion.The spatial feature extraction branch was based on the Swin Transformer architecture and introduced a local perception enhancement module to strengthen the representation capability of texture and edge details under coal dust interference.The motion feature extraction branch embedded a DeformConv3D deformable convolution module into ResNet to accurately capture the dynamic characteristics of drilling rig motion trajectories and coal dust diffusion.A spatiotemporal dynamic aggregation module was designed to dynamically allocate the weights of spatial and motion features,enabling discriminative representation of different distortion types and degrees.The Coal-DB dataset was constructed and ablation experiments and comparative experiments were conducted.The results showed that the proposed method achieved Spearman rank correlation coefficient,Pearson linear correlation coefficient,Kendall rank correlation coefficient,and root mean square error values of 0.904 3,0.902 3,0.753 6,and 4.684 0,respectively,which were superior to the baseline model and mainstream video quality assessment methods such as VSFA and StableVQA.The predicted video quality scores of this method were closer to the subjective scores.

Abstract:Existing image super-resolution reconstruction methods have difficulty coping with multi-source coupled degradations such as coal dust scattering and non-uniform blur in underground coal mine environments,and they are limited by local receptive fields,making it difficult to capture global structures,while excessive model complexity prevents lightweight deployment on underground edge devices.To address these issues,a blind super-resolution reconstruction method for underground coal mine images based on degradation kernel diffusion was proposed.In the degradation modeling stage,degradation kernel diffusion modeling was introduced,and the reverse sampling process of a diffusion probabilistic model was used to explicitly simulate the degradation kernel distribution in complex underground coal mine scenes,thereby correcting reconstruction artifacts caused by degradation estimation bias at the early stage.In the image reconstruction stage,a hybrid Transformer-CNN encoder and a dynamic invertible decoder were designed,in which a parallel dual-branch structure was used to complementarily extract local textures and global dependencies,and a dynamic proportional fusion mechanism was employed to achieve adaptive interaction between degradation features and image content,reducing the number of model parameters while ensuring lossless transmission of deep features.By combining L1 loss,Structural Similarity(SSIM)loss,and perceptual loss,a multi-metric joint loss function was constructed to enhance perceptual image quality while ensuring pixel-level accuracy.Experiments were conducted on the CMUID underground coal mine image dataset and public benchmark datasets.The results showed that,in terms of objective evaluation metrics,the proposed method achieved overall superior performance in peak signal-to-noise ratio and SSIM compared with competing methods while maintaining a lower parameter count.In terms of subjective visual quality,the proposed method effectively suppressed low-light noise,sharpened edge structures,and clearly restored texture details of conveyor belts and coal blocks in underground coal mine scenes.

Abstract:Mining wireless short-range communication technology has the characteristics of low latency,high reliability,and flexible networking,and is a key means to address problems encountered in the intelligent mine construction,such as large data transmission delay,complex information interaction processes,and limited equipment control accuracy.At present,research on mining wireless short-range communication mainly focuses on ZigBee,WiFi,and 5G.ZigBee is difficult to meet the requirements of routine applications,WiFi suffers from co-channel interference and large transmission delay,and 5G involves uncontrollable data transmission risks and high costs.To address these problems,this study proposed a mining wireless short-range communication solution with sidelink communication operating in licensed dedicated frequency bands as the core.Two types of architectures were constructed,including an independent networking architecture for mining sidelink communication and a hybrid networking architecture integrating mining sidelink communication and 5G for mining,forming a new full-scenario mining communication mode of"wide-area coverage plus local enhancement".To meet the requirements of time synchronization,resource efficiency improvement,and reliability assurance in the application of sidelink communication in coal mines,key technologies such as GNSS-free time synchronization,dynamic configuration of resource pools based on subframes and subchannels,physical-layer wireless signal transmission,and distributed resource allocation for terminals were investigated,which effectively improved the adaptability and reliability of the system in complex coal mine environments.Application scenarios of mining sidelink communication technology in intelligent equipment control,underground autonomous driving,and emergency command during disasters were also studied,which verified its practical value in promoting the integration of mining operations and communication systems.A test system simulating a GNSS-free underground coal mine environment was built in the laboratory,and the test results showed that the average system latency was less than 23 ms,which effectively met the requirements of critical mining scenarios for wireless short-range communication technology and provided a reliable wireless short-range communication solution for intelligent mine construction.

Abstract:To investigate the coupling mechanism between permeability evolution of coal around boreholes and the radial stress distribution and failure characteristics in hard low-permeability coal seams,and to reveal the radial gas seepage characteristics of coal around boreholes,the radial stress distribution characteristics and fracture development degree of coal around boreholes were analyzed.Axial stress was applied using a constant-speed constant-pressure pump until coal sample failure occurred,simulating the entire process from elastic deformation to failure.By combining steady-state and transient methods,experimental studies on the radial gas seepage characteristics of coal around boreholes in hard low-permeability coal seams were conducted,and the permeability evolution characteristics during the whole deformation and failure process of coal samples were obtained.The results showed that:① coal around boreholes radially formed a crushed zone,a plastic zone,and an elastic zone in sequence.In the crushed zone,the coal structure became unstable and a large number of interconnected fractures were generated.In the plastic zone,new fractures were generated,but fracture apertures were restricted under high stress.In the elastic zone,primary fractures underwent elastic closure.② The permeability of coal around boreholes along the radial direction of the borehole decreased rapidly and then increased slowly,showing an overall distinct V-shaped variation trend.③ When the confining pressure increased from 3 MPa to 4 MPa,the permeability of coal samples decreased significantly,and the permeability under a confining pressure of 4 MPa was only 4.57％of that under 3 MPa.④ Within each stress zone along the borehole radial direction,the crushed zone exhibited the highest permeability,the plastic zone showed a stress peak and the lowest permeability,and the stress concentration phenomenon in the elastic zone gradually disappeared while permeability gradually recovered to the original permeability of the coal seam.