Abstract:Existing research on trajectory tracking control of inspection robots mainly suffers from the following problems:①insufficient synchronization control accuracy of dual motors under asymmetric load disturbances.② difficulty of a single control structure in balancing predictive optimization and dynamic disturbance rejection.③ poor adaptability and robustness of control algorithms under complex and variable road conditions(e.g.,varying slopes and surface states).To address these problems,a hierarchical double-closed-loop trajectory tracking control method based on Model Predictive Control(MPC)and Fuzzy Adaptive PID(FAPID)algorithms,namely MPC-FAPID,was proposed.Based on the kinematic model of a four-wheeled differential inspection robot,corresponding constraints were imposed on the control variables and control increments,and an MPC-based trajectory tracking controller was designed.To solve the problem of uncoordinated control caused by wheel speed disturbances in four-wheeled differential robots,the FAPID algorithm was introduced to reduce motor speed errors.The simulation results showed that the FAPID algorithm effectively reduced synchronization error,and its accuracy and robustness were superior to those of PID control and whale-optimized PID control.To overcome the limitation that a single-layer control structure could not balance predictive capability and anti-disturbance performance,a hierarchical double-closed-loop controller based on MPC-FAPID was designed:the outer loop MPC compensated for trajectory tracking errors and handled multiple constraints,while the inner loop FAPID suppressed load disturbance effects.Simulation results indicated that under straight-line motion on a gentle slope,the MPC-FAPID achieved an adjustment time of 0.87 s,which enabled faster convergence of robot pose to the reference trajectory compared with MPC-PID and MPC-whale-optimized PID.Under continuous turning conditions,compared with MPC-PID and MPC-whale-optimized PID,the MPC-FAPID better captured the variations in the reference trajectory,with maximum lateral,longitudinal,and heading angle errors of-0.051 m,0.000 47 m,and 0.040 8 rad,respectively.Experimental results showed that,compared with MPC-PID,MPC-FAPID reduced the maximum lateral error by 88.24％and the maximum longitudinal error by 87.76％in the multi-target point trajectory tracking test.

Abstract:Due to differences in geological occurrence and mining layout,the mechanism of rock burst requires targeted research based on specific mine and working face conditions.Taking the No.12240 working face of Gengcun Coal Mine,Henan Dayou Energy Co.,Ltd.as the research object,this study investigated the influence of the overlying hard roofs on rock bursts from the perspectives of microseismic energy events,dynamic-static load superposition in front of the working face,and online stress monitoring of hard roofs.The temporal and spatial patterns of hard roof instability were identified based on the distribution characteristics of microseismic energy events.A mechanical model of the front abutment pressure under full mining conditions was established,and a dynamic-static load coupling analysis method based on the energy superposition principle was proposed to calculate the total energy transmitted from the fractured hard rock strata to the working face.An online monitoring scheme for hard rock layer activity was also developed,and the dynamic stress evolution of the coal rock mass during mining was quantitatively revealed using cable-bolt monitoring data.The results show that the combined failure of the low-position hard layer,the first middle-position hard layer,and the second middle-position hard layer transmitted a total superimposed energy of 1.22 × 104 J to the working face,which significantly exceeds the critical rock-burst energy threshold of Gengcun Coal Mine.Cable-bolt monitoring data indicated a pronounced abnormal increase in stress within the 132-143 m range ahead of the cut-hole,which strongly correlated with the spatiotemporal evolution of microseismic energy events and was identified as the main trigger of rock bursts.Based on the dynamic stress-response characteristics of the cable bolts,the coal rock mass activity in front of the working face during advancement was divided into three typical stages:the slow-influence stage,the significant-influence stage,and the rapid-decline stage.

Abstract:Existing studies on the dust transport pattern in fully mechanized excavation faces mostly focus on simplified conditions or short roadways,with insufficient simulation research on long-distance,full-scale working faces containing complex equipment.Dust control is often limited to optimizing a single dust removal technology,lacking an integrated control scheme that combines source suppression and ventilation-based dust control.To address these problems,a full-scale geometric model of an excavation face in the Gongwusu Coal Mine was established to numerically simulate dust pollution and diffusion in underground fully mechanized excavation faces.A comprehensive dust removal system composed of a high-efficiency foam atomization dust suppression device and a new self-dividing wall-attached air duct was developed.The synergistic effect of source capture and ventilation control was employed to enhance dust removal efficiency.Numerical simulation results showed that the dust distribution was related to the airflow direction.Because a large amount of airflow passed through the dust-producing area,the dust-laden airflow moved toward the roadheader area,causing high dust concentration near the roadheader.Over time,high-concentration dust nearly diffused throughout the entire working face,and the average dust concentration at the end of the roadway reached 105.9 mg/m3.In the breathing zone,high dust concentrations formed on both sides of the walkway,seriously polluting the breathing environment of underground workers.Field application results showed that the total dust and respirable dust removal efficiencies of the comprehensive dust removal system were 86.6％-89.7％and 86.6％-88.3％,respectively,significantly reducing the dust concentration in the roadway excavation site and improving the working environment of long-distance fully mechanized excavation faces.

Abstract:To address the problems of limited fault diagnosis accuracy of single-signal(current or vibration)methods and difficulty in identifying multiple coexisting faults under complex operating conditions of underground coal mine motors,a motor fault diagnosis method based on the combination of electrical and vibration signals was proposed,leveraging the electromechanical coupling characteristics and the complementarity of multi-sensor information.Fault information was captured from the motor current and vibration signals in the time domain,frequency domain,and time-frequency domain,respectively.The features were fused in the channel dimension to generate feature color images containing multi-domain information,thereby enriching the fault characterization.A Dual-Channel Residual Network(DCResNet)model embedded with an Improved Convolutional Block Attention Module(ICBAM),namely ICBAM-DCResNet,was constructed.Through multiple residual blocks and the attention mechanism of ICBAM,deep features of image samples were extracted.Finally,feature fusion and classification were performed to achieve fault diagnosis based on the combination of electrical and vibration signals.The comparative experimental results showed that multi-domain fusion achieved higher diagnosis accuracy than single-domain analysis,and the ICBAM-DCResNet model outperformed the Residual Network(ResNet)model,demonstrating stronger feature extraction capability for the signal samples.The experiment results on the public dataset demonstrated that the proposed motor fault diagnosis method based on the combination of electrical and vibration signals achieved an accuracy of 99.8％,with good identification performance for rotor and bearing faults and strong generalization ability.

Abstract:To address the limitations of current experimental and numerical studies on the propagation of gas-coal dust explosion shock waves,which are mostly confined to small-scale laboratory pipelines or local roadways,this study adopted a segmented relay simulation method,dividing the simulation process of gas-coal dust explosion shock wave propagation into two sections:the gas-coal dust explosion section and the shock wave propagation section.A geometric model was established according to the actual roadway size of a mine,and the propagation law of gas-coal dust explosion shock waves under different explosion conditions was simulated using Fluent software.The results showed that:① the explosion equivalent had a certain influence on the overpressure variation curve of the explosion shock wave and a significant influence on the peak overpressure.The peak overpressure increased markedly with increasing explosion equivalent.In the explosion section,the peak overpressure first increased and then decreased due to the energy accumulation effect,while in the shock wave propagation section,the peak overpressure decayed in the form of a power function,and the larger the explosion equivalent,the faster the overpressure attenuation.② When gas-coal dust explosions occurred at different locations,the propagation path length,roadway size,and roadway connection type had no significant effect on the overpressure variation curve.The overpressure curve along the propagation path exhibited a dynamic evolution from"multi-peak oscillations → single peak → multi-peak oscillations".However,these factors played an important role in overpressure attenuation:the longer the propagation path and the more the branch roadways,the more significant the attenuation,indicating that branch roadways had a good pressure relief effect.③ Under different explosion locations and explosion equivalent conditions,the attenuation law of overpressure along the propagation path was generally consistent.The overpressure attenuation rate gradually decreased with increasing propagation distance.A larger explosion equivalent resulted in a higher initial overpressure and a greater pressure gradient,leading to faster overpressure attenuation.The branch structure significantly promoted overpressure attenuation,with the most substantial attenuation occurring after the first open branch,while the attenuation magnitude of subsequent branches decreased successively.

Abstract:The disturbance response instability theory for rock burst derives the theoretical formulas and instability criteria for rock burst occurrence.However,the analytical solution for the critical stress of the roadway surrounding rock does not consider complex geological structures such as heterogeneous strata,as well as variable loading conditions.To address this issue,this study integrated the disturbance response instability theory for rock burst with StrataKing-3D,the parallel computing system for stratum movement.The impact of roadway support stress on the critical stress was investigated from two aspects:the simplified homogeneous model and the practical engineering model(taking a roadway in the Longjiabao coal mine as an example).Additionally,the safety factor of the roadway in the engineering model was calculated to evaluate the safety of the roadway surrounding rock.The results showed that for the homogeneous model,the numerically calculated value of the critical stress of the roadway surrounding rock was higher than the theoretically calculated value,which qualitatively agreed with the survey data from 20 rock burst mines across the country.For the practical engineering model,when the support stress was 0.4 MPa,the numerically calculated value of the critical stress of the roadway surrounding rock was 35.61 MPa,which was basically consistent with the current coal seam critical stress(36.9 MPa),validating the accuracy of the method combining theoretical and numerical calculations.When the support stress increased to 0.8 MPa,the critical stress reached 44.69 MPa,and the safety factor was 1.05,indicating that the roadway was basically safe.The research findings provide a new method for determining the roadway support stress.

Abstract:Precise positioning service is a fundamental support for intelligent coal mines.At present,most coal mines are equipped with Ultra-Wideband(UWB)-based precision positioning systems.Underground UWB positioning data jumps are a major factor affecting positioning reliability and accuracy.Existing solutions mainly suppress data jumps by adding auxiliary measurement methods,adjusting hardware,or applying continuous data filtering based on multiple measurements.These methods are difficult to implement,costly,and cannot identify data jumps when positioning tags move across different positioning areas.Taking the commonly used Double-Sided Two-Way Ranging(DS-TWR)method based on Time of Flight(TOF)in underground UWB positioning systems as the research object,this study proposed a ToF 4-WR communication positioning method.On the basis of the traditional 3-way ranging(3-WR)protocol,a measurement verification frame"Check"was added to address the issue that interference in the Response frame communication process of the traditional TOF 3-WR method could not be identified due to the lack of a reference.On this basis,a UWB signal jump identification method integrating multiple-interference verification mechanisms was proposed to identify data jumps in a single positioning process.For extreme cases involving continuous interference or drastic changes in the motion state of the positioning target,an anomaly detection mechanism based on multiple consecutive positioning results was introduced to further verify the reliability of positioning data.For the identified data jumps,the Kalman filter optimal estimation value was used to replace the identified data,achieving UWB positioning data jump suppression.Field tests conducted at Jinfeng Coal Mine showed that this method effectively identified underground UWB positioning jump signals,and the Kalman filter optimal estimation value accurately tracked the actual positioning trajectory,ensuring the accuracy and continuity of positioning data.

Abstract:Current studies on the evaluation of rock mass integrity in coal mine goafs mainly rely on the Rock Quality Designation(RQD)as the core parameter,lacking a multidimensional evaluation system that integrates parameters such as fracture development degree,spatial distribution characteristics,and RQD.Evaluating rock mass quality solely based on RQD cannot comprehensively represent the spatial distribution characteristics of fractures,leading to limitations in the reliability and universality of the evaluation results.To address this problem,a fuzzy comprehensive evaluation model of rock mass integrity based on combined weighting was proposed.The model extracted five key parameters,including fracture density,total length,maximum width,fracture rate,and RQD,from borehole television images using an improved YOLOv8 network model to establish a multidimensional evaluation indicator system for rock mass.The Analytic Hierarchy Process(AHP)and Entropy Weight Method(EWM)were used to determine the subjective and objective weights,respectively,and reasonable weight distribution was achieved through combined weighting.Membership functions were established for each indicator corresponding to the fracture development degrees,and fuzzy matrix operations were applied to achieve the classification of rock mass integrity level.A validation analysis was conducted using data from the 349-350 m depth interval of a coal mine goaf in Shandong Province.The results showed that the Fuzzy Comprehensive Evaluation model for rock mass integrity based on combined weighting was consistent with expert judgment results across 96.3％of the borehole depth intervals,outperforming the AHP method(94.9％)and EWM method(94.4％).This approach effectively improved the accuracy and reliability of the rock mass integrity evaluation.

Abstract:The complex underground environment in coal mines,including factors such as light source fluctuation,noise,and environmental interference,can affect the Tunable Diode Laser Absorption Spectroscopy(TDLAS)system.This results in a decreased signal-to-noise ratio of the first-harmonic spectrum signal,which severely compromises the accuracy and stability of gas detection.To address these problems,a first-harmonic denoising algorithm for the TDLAS system based on an improved wavelet threshold was proposed.First,the optimal wavelet basis and decomposition level were determined using an enumeration algorithm to identify the optimal parameters suitable for the first-harmonic spectrum signal.Then,a continuously differentiable threshold function was developed to address the issues of abrupt changes in hard thresholds and detail loss in soft thresholds.Finally,an adaptive threshold based on the local variance of the first-harmonic spectrum signal was designed,enabling the threshold to dynamically adjust according to local signal characteristics,thereby achieving precise separation of noise and effective signals.Simulation results showed that compared with the traditional wavelet threshold algorithm,the improved wavelet threshold denoising algorithm increased the signal-to-noise ratio by 19.03 dB,reduced the mean square error by 98.75％,and improved the waveform similarity coefficient by 0.083 3,demonstrating superior denoising performance.Methane detection results indicated that the noise energy in the frequency band of the denoised signal was significantly reduced,and the useful signal was concentrated in the target frequency band,showing that the improved wavelet threshold denoising algorithm could effectively suppress the noise in the first-harmonic signal.

Abstract:At present,Optical Frequency Domain Reflectometry(OFDR)technology has made certain progress in multi-seam stress monitoring,but few studies have applied OFDR to investigate the dynamic evolution of overburden fractures under repeated mining of closely spaced double coal seams.Taking the 360608 working face of Xinji No.l Mine,China Coal Xinji Energy Co.,Ltd.as the engineering background,horizontal and vertical optical fiber networks were deployed in combination with OFDR technology to analyze the differences in optical fiber responses to overburden deformation between the mined and unmined areas of No.8 coal seam during mining of No.6-1 coal seam,thereby revealing the mechanism by which the mined and unmined areas of the upper seam influenced the overburden failure characteristics during lower seam mining.The results showed that:① after No.8 coal seam was fully mined,the overburden fractures exhibited an"irregular trapezoidal"shape,with caving angles of 48° on the crosscut side and 36° on the stop line side,and a fracture development height of 32.5 cm.② In the unmined area of No.8 coal seam,the overburden evolved into a typical"voussoir beam"structure during No.6-1 coal seam mining,with a fracture development height of 53 cm and a smooth variation in optical fiber strain(peak ≤55.5 με).③ In the mined area of No.8 coal seam,repeated mining weakened the overburden structure,increasing the fracture development height to 76.25 cm(23.25 cm higher than in the unmined area)and causing severe fluctuations in optical fiber strain(peak up to 9 987 με).The key stratum breakage induced"stepped"fracture penetration,and both the fracture development height and strain amplitude on the coal-wall side were significantly greater than those on the crosscut side.④ Field monitoring showed that the fracture development height of the unmined No.8 coal seam was about 53 m,consistent with the similarity simulation results.The study confirmed that the goaf of the upper coal seam enhanced the fracture development height of the lower coal seam by 43.9％and increased the strain magnitude by 3-5 times through stress transfer and structural weakening,providing a theoretical basis for safe multi-seam mining and disaster prevention.

Abstract:To address the problems of strong nonlinear coupling and significant spatial heterogeneity in multivariate time series data from coal mines,a risk early warning model for underground coal mine personnel integrating multi-source time series data was proposed.A multimodal data synchronization method based on a co-directional dual-pointer sliding window was adopted.Combined with Kalman filtering,a delay compensation mechanism was introduced to improve interpolation accuracy,thereby achieving high-precision time alignment of signals with different sampling frequencies.A ten-dimensional feature vector was constructed,and the SHAP method was utilized for global and local importance analysis to eliminate redundant features,achieving efficient dimensionality reduction.This significantly improved the interpretability and robustness of model decision-making while maintaining prediction performance.The Mixture of Attention Heads(MOA)mechanism was incorporated to capture the nonlinear dependencies and potential coupling features of multi-source signals.The MOA-Transformer model was constructed,where the Transformer encoder structure was used for feature-engineering-based risk level classification.The MOA was then employed to construct feature representations for classification.Field test results showed that the proposed model outperformed models such as recurrent neural networks and convolutional neural networks in terms of accuracy,precision,recall,and F1-score.It could achieve high detection rates and low false alarm rates under conditions of few abnormal events,providing a feasible technical approach for risk identification and graded early warning for underground coal mine personnel.

Abstract:To address the issues of low detection accuracy,excessive model complexity,and high deployment and maintenance difficulty in existing scraper conveyor chain detection methods based on deep learning under low illumination conditions in coal mines,a lightweight chain detection algorithm based on improved YOLOv11n-YOLO-Chain—was proposed.First,an image edge information enhancement module was constructed to optimize the C3k2 module of YOLOv11n,effectively extracting edge features from chain images.Then,a weighted Bidirectional Feature Pyramid Network(BiFPN)was used to replace the neck network of YOLOv11n,thereby effectively reducing the number of model parameters and lowering model complexity.Finally,a lightweight detection head was introduced to capture subtle features of chain scale variations in complex underground scenarios,further reducing redundant parameters and model complexity,improving the detection performance of the lightweight model,and providing support for subsequent chain fault detection.Experimental results on a single-scenario scraper chain image dataset from a coal mine in Shanxi showed that,compared with the original YOLOv11n model,YOLO-Chain improved the mAP@0.5:0.95 accuracy by 3.7％,while reducing the number of parameters and computational load by 35％and 10％,respectively,and decreasing the model size by 31％.Compared with current mainstream models such as the YOLO series,SSD,Faster RCNN,and RT-DETR-R18,YOLO-Chain also demonstrated advantages in multiple indicators.Experimental results on a multi-scenario chain image dataset collected from multiple coal mines under complex working conditions such as low illumination,smoke interference,dust occlusion,and partial obstruction showed that the F1-score and mAP@0.5 of YOLO-Chain increased by 0.2％and 0.5％,respectively,compared with YOLOv11n,with arithmetic speed increased by 8,demonstrating good applicability and generalization ability.

Abstract:Currently,partial discharge(PD)signals of high-voltage mining cables are easily buried in noise and difficult to extract.Variational Mode Decomposition(VMD)is an effective method for PD denoising,but the number of decomposition layers and penalty factor of the VMD algorithm are difficult to determine.To address this problem,a denoising method for PD signals of high-voltage mining cables based on Adaptive Spiral Flying Sparrow Search Algorithm(ASFSSA)-VMD-KSVD was proposed.ASFSSA was used to optimize VMD,and a chaotic mapping strategy was utilized to make the population distribution more uniform and avoid falling into local optima.A series of intrinsic mode functions(IMF)were obtained through VMD,and the Composite Multiscale Fuzzy Dispersion Entropy(CMFDE)was then used to screen the properties of IMF components,dividing them into signal-dominated components and noise-dominated components.For screened noise-dominated components,training samples were constructed for KSVD dictionary learning,and noise was further suppressed through sparse coding and dictionary updating.The processed coefficients were reconstructed,and the signal blocks were superimposed to obtain the denoised signal.The denoising performance was evaluated using Signal-to-Noise Ratio(SNR),Root Mean Square Error(RMSE),and Normalized Cross-Correlation(NCC).The experimental results showed that under different SNR conditions,the SNR after denoising using the ASFSSA algorithm was much higher than that of the GWO and IWOA algorithms,demonstrating a significant advantage in noise suppression.The RMSE after denoising using the ASFSSA algorithm was much smaller than that of the Grey Wolf Optimization(GWO)and Improved Whale Optimization Algorithm(IWOA)algorithms,indicating the smallest difference between the true and predicted values during denoising.The NCC after denoising using the ASFSSA algorithm was very close to 1,showing excellent waveform similarity.

Abstract:To address the problem of large differences in foreign object sizes,complex backgrounds,and poor detection performance of small and slender targets in coal mine conveyor belts,a foreign object detection method based on an improved YOLOv11n model was proposed.The core improvements of the YOLOv11n model included three aspects:first,a Scale Sequence Feature Fusion(SSFF)module was introduced into the neck network to enhance the effective capture and fusion of information at different scales through sequential scale interaction;second,a parallel C3K2PPA module was constructed,introducing a Parallelized Patch-Aware Attention(PPA)module in the spatial dimension to highlight key region representations and improve recall;third,a Band-Aware Contrast Fusion(BACF)module was designed at the lateral fusion layer of the same scale.By combining belt-directional priors and high-pass edge indicators,and replacing simple concatenation with pixel-wise gating,the module suppressed periodic background noise along the belt direction and enhanced cross-branch differences without increasing the number of channels,thereby improving the model's discriminative capability and robustness under complex working conditions.The experimental results showed that the precision and recall of the improved YOLOv11n model reached 0.914 and 0.892,respectively,with mAP@0.5 and mAP@0.5:0.95 values of 93.1％and 62.2％,showing significant improvement over the original YOLOv11n and outperforming mainstream lightweight models such as YOLOv5s,YOLOv8n,and YOLOv10n in accuracy and robustness.The inference speed of the model reached 96 frames per second,indicating high real-time performance and efficient execution in coal mine conveyor belt foreign object detection tasks.Heatmap analysis showed that the improved YOLOv11n model effectively enhanced the target-area focusing capability,reduced redundant bounding boxes,and improved the detection accuracy of small targets.

Abstract:At present,the commonly used extraction-type dust-removal system in mine tunneling roadways causes local air volume loss during operation,and the air-curtain generator suffers from air-distribution problems that affect the air supply at the tunneling face.To address the problems of dust control and airflow regulation at rock roadway tunneling faces,a linkage air-curtain dust-isolation device was developed based on the extraction-type dust-removal system,which enabled the purified airflow from the dust-removal system to directly form a dust-blocking air curtain.A crescent-shaped guide vane was installed at the bend of the air duct in the air-curtain dust-isolation device.Numerical simulations verified that this design reduced fluid velocity loss by 17.11％,thereby decreasing the local air volume loss caused by the operation of the dust-removal system.A resistance-calculation formula for the linkage air-curtain dust-isolation device of the extraction-type dust-removal system was derived to provide a basis for selecting dust-removal fans.A roadway geometric model,a fluid-motion mathematical model,and a discrete-phase model of dust particles were established to numerically simulate the flow field and dust-migration patterns in the tunneling roadway.The results showed that when the air-curtain dust-isolation device was positioned 6 m from the tunneling face,with a pressure-extraction ratio of 1:1.1 and a gradually widened slit-shaped jet outlet,the dust concentration decreased from 4× 10-5 kg/m3 to 5 × 10-6 kg/m3 after passing through the air curtain,achieving a dust-reduction rate of 87.5％.The jet airflow was uniform and sufficient without mutual interference,confining high-concentration dust within a smaller space and preventing its diffusion.

Abstract:The existing straightness evaluation methods for fully mechanized mining faces adopt planar straightness,describing straightness through information from a single piece of equipment such as a hydraulic support or a scraper conveyor,without considering external factors or the relative relationships among equipment.As a result,they cannot accurately and comprehensively reflect the actual straightness of a fully mechanized mining face under real working conditions.To address these issues,an overall three-dimensional spatial straightness evaluation method for fully mechanized mining faces was proposed.In three-dimensional space,based on a three-level coordinate system,the straightness of a single piece of fully mechanized equipment was evaluated using the degree of deviation between the trajectory of both the scraper conveyor and hydraulic support group and their own straightness baseline.On this basis,the evaluation of overall three-dimensional spatial straightness of the fully mechanized mining face was conducted by integrating the curved coal seam surface,equipment deviation,and advancement errors of the floating connection mechanism.Compared with two-dimensional planar straightness,the proposed method based on three-dimensional spatial straightness reduced errors and effectively eliminated the distortion effect caused by planar projection.The use of overall equipment straightness effectively solved the problem that the straightness of a single piece of equipment could not represent the overall straightness of the fully mechanized mining face.By considering the coupling relationship between the coal seam and the equipment and the lateral movement of the scraper conveyor,the straightness calculation and evaluation became closer to the actual working conditions,significantly improving the accuracy of straightness evaluation.The experimental results showed that the straightness evaluation results obtained by the proposed method were close to those obtained using the standard deviation method,verifying its accuracy.In addition,through multi-aspect deviation evaluation,the factors that may affect straightness at a specific moment could be dynamically analyzed and adjusted in real time.

Abstract:The reservation of small coal pillars in roadway excavation along goaf under deep mining conditions of thick coal seams is an effective way to reduce resource loss caused by wide coal pillar protection.However,the high stress concentration and mining-induced disturbance caused by the reduction of pillar width remain significant.It is therefore necessary to comprehensively consider the strength characteristics of coal pillars,the changes in the bearing stage,and the influence of pressure relief by roof cutting on the development of the plastic zone to determine a reasonable width for small coal pillars.Taking the roadway excavation along goaf with reserved small coal pillars in a certain coal mine as the engineering background,the width of the internal plastic zone of the coal pillar was calculated based on an ideal elastic-plastic constitutive model considering the residual strength of coal,and the variation of the plastic zone in coal pillars with different widths before and after pressure relief by roof cutting was analyzed.The results showed that the expansion of the plastic zone in small coal pillars was the most significant during the working face mining stage.The width of the plastic zone first increased and then decreased with the increase of coal pillar width.Pressure relief by roof cutting significantly reduced the width of the plastic zone,with a maximum reduction of 43.2％compared with that without pressure relief by roof cutting.Under the condition of pressure relief by roof cutting,the plastic zone in a 5 m-wide small coal pillar accounted for only 46.7％after mining,leaving more than half of the elastic zone for bearing,and the reasonable width of the small coal pillar was determined to be 5 m.On this basis,a numerical simulation of the 5 m-wide small coal pillar under pressure relief by roof cutting was carried out.The results showed that compared with the condition without roof cutting,the peak vertical stress inside the coal pillar decreased by more than 36％,the maximum deformation of the roof and floor decreased by 8.4％and 9.8％,and the maximum deformation of the pillar rib and solid coal rib decreased by 48.8％and 46.7％,respectively.Industrial test results showed that under pressure relief by roof cutting,the convergence of the roof-floor and ribs of the roadway with a 5 m-wide coal pillar decreased by more than 52％and 63％,respectively,compared with that without roof cutting,ensuring the safe and efficient mining of the working face.

Abstract:The floor heave failure of small coal pillar roadways involves multiple disciplines,with numerous coupled influencing factors,and the current understanding of its failure mechanism remains incomplete.Existing studies have limitations in explaining floor heave phenomena under complex geological conditions and mining processes.To address these issues,theoretical analysis and numerical simulation were used to investigate the failure mechanism of floor heave in small coal pillar roadways.It was found that the actual stress borne by the roadway exceeded the ultimate strength of the floor strata,causing shear and tensile fractures.Under the horizontal thrust of the overlying basic roof fracture structure and the deformation of the coal pillar,the floor experienced complex stress.Large shear stress occurred at the contact surfaces between the floor and both sides of the coal pillar base,and together with the weak floor strata,jointly contributed to the occurrence of floor heave.Based on the failure mechanism,a targeted technology of"flexible formwork wall gob-side entry retaining+blasting pressure relief+floor lifting+bottom corner anchor cable+concrete paving and solidification"was proposed.The flexible formwork wall gob-side entry retaining helped share the load of the overlying strata borne by the small coal pillar and transferred the stress originally concentrated on the roadway floor to the flexible formwork wall and surrounding rock.Blasting pressure relief at the floor corner dispersed stress and reduced stress concentration.Floor lifting removed debris and restored the roadway section,providing space for support.The bottom corner anchor cables were embedded into stable strata to resist floor heave.The concrete paving and solidification formed a bearing layer,improving the shear and compressive strength of the floor.Field application results showed that the amount of floor heave decreased by 92.04％after adopting this technology,and almost no deformation occurred on the surface of the flexible formwork wall.

Abstract:The underground Received Signal Strength Indicator(RSSI)signal exhibits non-stationary characteristics such as sharp spikes,high-frequency jitter,and trend drift under the influence of multipath propagation,occlusion,and electromagnetic interference,resulting in large positioning errors.Existing positioning methods lack collaborative suppression of multi-source interference,and their feature extraction and multi-scale feature fusion are insufficient.To address these problems,an underground RSSI positioning method based on multi-stage denoising and a dual-branch temporal network was proposed.Multi-stage denoising suppressed spike interference,high-frequency jitter,and trend drift through outlier elimination and interpolation repair,adaptive Kalman filtering,and wavelet-domain adaptive gating,respectively,thereby producing a more stable RSSI sequence with preserved details.The dual-branch temporal network introduced the first-order difference as an auxiliary disturbance prior,extracted features in parallel through a trend branch and a disturbance branch,and adaptively fused them via a channel attention mechanism.A Bidirectional Long Short-Term Memory(Bi-LSTM)network was then used to capture contextual temporal dependencies,ensuring trajectory smoothness and continuity in complex dynamic environments.Test results showed that the RSSI signal became more stable after multi-stage denoising while preserving local dynamic features without excessive smoothing.The dual-branch temporal network achieved high accuracy,F1-score,precision,and recall with fast convergence;in tests under different scenarios,both accuracy and F1-score exceeded 85％,demonstrating good generalization.In continuous positioning tasks under dynamic environments,the average positioning error of the proposed method was only 0.12 m.

Abstract:At present,the average number of cameras in coal mines exceeds 500,making continuous manual monitoring impossible and large screens insufficient for comprehensive display.Reviewing videos afterward cannot promptly identify potential safety hazards,making it difficult to prevent accidents.Therefore,Artificial Intelligence(AI)-based video monitoring in coal mines has become an inevitable choice under the principle of"no operation without video".Conventional AI models have problems such as poor generalization and difficulty in recognizing abnormal events.Large AI models can solve these problems and should possess functions including data collection and indexing,large-model pre-training,fine-tuning and deployment,and model iteration,while supporting multimodal data including images,videos,text,and audio.General-purpose large AI models are trained using large-scale data from the mining industry to form large AI models for mining.Large AI models for mining have advantages such as powerful functions,good generalization,strong versatility,and high reliability.Large AI models for mining should have a scenario generation function that allows users to use a small amount of labeled data to automatically generate scenario models through workflows,meeting the application needs of mine production,safety,geological surveying,transportation and sales,coal preparation,operations,and management.Based on the safety production requirements of coal mines,the functional,interface,data,software and hardware platform,and deployment requirements of large AI models for mining are proposed to standardize their planning,design,engineering construction,operation and management,and maintenance,and to promote the application of AI in coal mines.