工矿自动化

Analysis of wireless transmission tests in mines and preferred working frequency bands for mining 5G

SUN Jiping, PENG Ming, LIU Bin

2024, 50(10): 1-11, 20. doi: 10.13272/j.issn.1671-251x.18221

<Abstract>(114) <HTML> (21) <PDF>(25)

Abstract:
The development and deployment of mobile communication systems, personnel and vehicle positioning systems in mines require an analysis of wireless transmission characteristics, the selection of preferred working frequency bands, and the optimization of wireless communication base stations and positioning substations. In this study, wireless transmission tests were conducted in a large frequency range from 350 MHz to 6 GHz in mine environments such as curved tunnels, branch tunnels, main transportation tunnels, excavation tunnels, and fully mechanized mining faces. The test results were analyzed, revealing the characteristics of wireless transmission in mines: ① In curved tunnels, the lower the wireless transmission frequency, the smaller the attenuation, with the least attenuation in the 350 MHz to 900 MHz frequency band. ② In branch tunnels, the lower the frequency, the smaller the attenuation, with the least attenuation in the 350 MHz to 900 MHz frequency band. ③ In main transportation tunnels, the least wireless transmission attenuation was found in the 700 MHz to 900 MHz frequency band. ④ In excavation tunnels, the least attenuation was in the 700 MHz to 900 MHz frequency band. ⑤ In fully mechanized mining faces, the least attenuation was observed in the 433 MHz to 1 300 MHz frequency band. ⑥ With the same cross-sectional area of the tunnels, wireless transmission attenuation in curved tunnels was smaller than in branch tunnels, and the attenuation in branch tunnels emitted from branch sources was smaller than that emitted from main tunnels. Curves and branches in tunnels increased wireless transmission attenuation. Furthermore, this paper proposed the preferred working frequency bands and the best arrangement of antennas for wireless communication systems in underground coal mines, specifically in curved and branch tunnels: ① The working frequency bands for underground wireless communication systems should preferably be in the 700 MHz to 900 MHz range. ② To minimize the impact of curves and branches in tunnels on wireless transmission, wireless communication base stations, positioning substations, and their antennas should be set at the turning points of curved tunnels and at the branch points of branch tunnels. The research results have been applied to the People's Republic of China energy industry standards NB/T 11546-2024 General specification of 5G communication system for coal mines, NB/T 11523-2024 5G communication base station for coal mines, and NB/T 11547-2024 5G communication baseband controller for coal mines.

Global path planning algorithm for mining vehicles integrating simplified visibility graph and A^* algorithm

ZHANG Chuanwei, LU Siyan, QIN Peilin, ZHOU Rui, ZHAO Ruiqi, YANG Jiajia, ZHANG Tianle, ZHAO Cong

2024, 50(10): 12-20. doi: 10.13272/j.issn.1671-251x.2024070048

<Abstract>(130) <HTML> (19) <PDF>(16)

Abstract:
To address the low path planning efficiency of mining vehicles in narrow, winding underground tunnels with unknown obstacles, a global path planning algorithm, DVGA^*, was proposed, integrating simplified visibility graphs (SVG) and the A^* algorithm. Based on the construction of a point cloud map of the real environment, the algorithm connected the vehicle's visual tangent points from different viewpoints to dynamically generate the SVG. The visual tangent points were sequentially stored in the OPEN list as nodes, and nodes were selected for the CLOSED list based on the A^* algorithm's evaluation function to ensure the shortest path. This process continued until the endpoint appeared in the OPEN list, resulting in the optimal path points being stored while the remaining nodes in the OPEN list were deleted. Finally, a path smoothing algorithm was utilized to further reduce the number of path nodes, thereby enhancing path planning efficiency. Experimental results indicated that compared to the Complete Visibility Graph + A^* algorithm, SVG + A^* algorithm, and SVGCA^* algorithm, the DVGA^* algorithm had the shortest planning time for complex long-distance paths, with average path lengths reduced by 10.79%, 6.26%, and 2.86%, respectively, demonstrating stronger adaptability and higher planning success rates. Results from underground tests showed that in areas with variable tunnel widths and while avoiding static obstacles, the path planned by DVGA^* was smoother compared to that of the SVGCA^* algorithm. When avoiding dynamic obstacles, DVGA^* was able to promptly correct the path, ensuring timely and stable path planning. In complex and variable tunnel environments, the planning time and path length of DVGA^* were reduced by 11.51% and 1.54%, respectively, compared to SVGCA^*, indicating higher environmental adaptability and stability.

IMU-LiDAR integrated SLAM technology for unmanned driving in mines

HU Qingsong, LI Jingwen, ZHANG Yuansheng, LI Shiyin, SUN Yanjing

2024, 50(10): 21-28. doi: 10.13272/j.issn.1671-251x.18209

<Abstract>(106) <HTML> (22) <PDF>(32)

Abstract:
Simultaneous localization and mapping (SLAM) is a critical technology for unmanned driving. Existing SLAM methods have the drawbacks of significant cumulative errors and drift in coal mine roadway environment. In this study, a roadway environment feature-assisted SLAM algorithm integrating inertial measurement unit (IMU) and LiDAR was proposed. IMU observation data was used to predict the motion state of point cloud and motion compensation was applied to reduce point cloud distortion caused by equipment movement. Pose transformation information from LiDAR odometry was obtained through point cloud registration, forming a LiDAR odometry constraint. Point clouds from roadway sidewalls and floor were extracted and fitted to planes, establishing environmental constraints. Using IMU pre-integration constraints, LiDAR odometry constraints, and environmental constraints, the algorithm applied factor graph optimization to achieve tight coupling between LiDAR and IMU, enabling high-precision 3D reconstruction of roadway scenes and accurate localization of autonomous vehicles. Simulation experiments showed that the absolute trajectory root mean square error (RMSE) of the roadway environment feature-assisted IMU-LiDAR integrated SLAM algorithm was 0.1162 m, and the relative trajectory RMSE was 0.0409 m, improving positioning accuracy compared to commonly used algorithms such as LeGO-LOAM and LIO-SAM. Based on the test results in a real environment, the algorithm provides excellent mapping performance with no drift or trailing, demonstrating strong environmental adaptability and robustness.

Research on pedestrian detection technology for mining unmanned vehicles

ZHOU Libing, YU Zhengqian, WEI Jianjian, JIANG Xueli, YE Baisong, ZHAO Yexin, YANG Siliang

2024, 50(10): 29-37. doi: 10.13272/j.issn.1671-251x.2024050058

<Abstract>(93) <HTML> (15) <PDF>(21)

Abstract:
The working environment of mining unmanned vehicles features complex lighting conditions, leading to frequent occurrences of missed detections in pedestrian detection, which undermines the reliability and safety of these vehicles. To address the challenges posed by intricate tunnel lighting conditions, a low-light image enhancement algorithm was proposed. This algorithm decomposed low-light images from the RGB color space into the HSV color space, applied a Logarithm function to enhance the V component, and employed a bilateral filter to reduce noise. Morphological operations were applied to the S component for closing, followed by Gaussian filtering to further eliminate noise. The enhanced image was then transformed back into the RGB color space and subjected to a semi-implicit ROF denoising model for additional noise reduction, resulting in an enhanced image. To tackle issues of missed detections and low accuracy in pedestrian detection, an improved YOLOv3-based pedestrian detection algorithm for mining unmanned vehicles was introduced. This approach replaced the Residual connections in YOLOv3 with densely connected modules to enhance feature map utilization. Additionally, a Slim-neck structure optimized the feature fusion architecture of YOLOv3, facilitating efficient information fusion between feature maps and further improving the detection accuracy for small-target pedestrians, while its unique lightweight convolutional structure enhanced detection speed. Finally, a lightweight convolutional block attention module (CBAM) was integrated to improve attention to object categories and locations, thereby enhancing pedestrian detection accuracy. Experimental results demonstrated that the proposed low-light image enhancement algorithm effectively improved image visibility, making pedestrian textures clearer and achieving better noise suppression. The average precision of the pedestrian detection algorithm for mining unmanned vehicles based on enhanced images reached 95.68%, representing improvements of 2.53%, 6.42%, and 11.77% over YOLOv5, YOLOv3, and a coal mine key position personnel unsafe behavior recognition method based on improved YOLOv7 and ByteTrack, respectively, with a runtime of 29.31 ms. YOLOv3 and a coal mine key position personnel unsafe behavior recognition method based on improved YOLOv7 and ByteTrack experienced missed detections and false positives based on enhanced images, while the proposed pedestrian detection algorithm effectively mitigated these issues.

Research status and development trends of SLAM technology in autonomous mining field

CUI Shaoyun, BAO Jiusheng, HU Deping, YUAN Xiaoming, ZHANG Kekun, YIN Yan, WANG Maosen, ZHU Chenzhong

2024, 50(10): 38-52. doi: 10.13272/j.issn.1671-251x.2024070010

<Abstract>(168) <HTML> (35) <PDF>(15)

Abstract:
Autonomous driving is identified as one of the key technologies for mining intelligence, with simultaneous localization and mapping (SLAM) technology serving as a key link to realize autonomous driving. To advance the development of SLAM technology in autonomous mining, this paper discusses the principles of SLAM technology, mature ground SLAM solutions, the current research status of mining SLAM, and future development trends. Based on the sensors employed in SLAM technology, the study analyzes the technical principles and corresponding frameworks from three aspects: vision, laser, and multi-sensor fusion. It is noted that visual and laser SLAM technologies, which utilize single cameras or LiDAR, are susceptible to environmental interference and cannot adapt to complex environments. Multi-sensor fusion SLAM emerges as the most effective solution. The research examines the status of mining SLAM technology, analyzing the applicability and research value of visual, laser, and multi-sensor fusion SLAM technologies in underground coal mines and open-pit mines. It concludes that multi-sensor fusion SLAM represents the optimal research approach for underground coal mines, while the research value of SLAM technology in open-pit mines is limited. Based on the challenges identified in underground SLAM technology, such as accumulated errors over time and activity range, adverse effects from various scenes, and the inadequacy of various sensors to meet the hardware requirements for high-precision SLAM algorithms, it is proposed that future developments in SLAM technology for autonomous mining should focus on multi-sensor fusion, solid-state solutions, and intelligent development.

Research on the targetless automatic calibration method for mining LiDAR and camera

YANG Jiajia, ZHANG Chuanwei, ZHOU Libing, QIN Peilin, ZHAO Ruiqi

2024, 50(10): 53-61, 89. doi: 10.13272/j.issn.1671-251x.2024070056

<Abstract>(127) <HTML> (29) <PDF>(19)

Abstract:
The realization of autonomous driving for mining vehicles relies on accurate environmental perception, and the combination of LiDAR and cameras can provide richer and more accurate environmental information. To ensure effective fusion of LiDAR and cameras, external parameter calibration is necessary. Currently, most mining intrinsically safe onboard LiDARs are 16-line LiDARs, which generate relatively sparse point clouds. To address this issue, this paper proposed a targetless automatic calibration method for mining LiDAR and camera. Multi-frame point cloud fusion was utilized to obtain fused frame point clouds, increasing point cloud density and enriching point cloud information. Then, effective targets such as vehicles and traffic signs in the scene were extracted using panoramic segmentation. By establishing a corresponding relationship between the centroids of 2D and 3D effective targets, a coarse calibration was completed. In the fine calibration process, the effective target point clouds were projected onto the segmentation mask after inverse distance transformation using the coarse-calibrated external parameters, constructing an objective function based on the matching degree of effective target panoramic information. The optimal external parameters were obtained by maximizing the objective function using a particle swarm algorithm. The effectiveness of the method was validated from three aspects: quantitative, qualitative, and ablation experiments. ① In the quantitative experiments, the translation error was 0.055 m, and the rotation error was 0.394°. Compared with the method based on semantic segmentation technology, the translation error was reduced by 43.88%, and the rotation error was reduced by 48.63%. ② The qualitative results showed that the projection effects in the garage and mining area scenes were highly consistent with the true values of the external parameters, demonstrating the stability of the method. ③ Ablation experiments indicated that multi-frame point cloud fusion and the weight coefficients of the objective function significantly improved calibration accuracy. When using fused frame point clouds as input compared to single-frame point clouds, the translation error was reduced by 50.89%, and the rotation error was reduced by 53.76%. Considering the weight coefficients, the translation error was reduced by 36.05%, and the rotation error was reduced by 37.87%.

Method for identifying passable areas in mines based on spatiotemporal continuous compensation

DAI Bo, WANG Yafei, LI Ruoyao, LI Zexing, ZHANG Yichen, ZHANG Ruitao

2024, 50(10): 62-67, 79. doi: 10.13272/j.issn.1671-251x.2024050067

<Abstract>(73) <HTML> (24) <PDF>(6)

Abstract:
Identifying passable areas is a crucial aspect of autonomous driving technology in mining. Open-pit mining road scenes are characterized by unclear road boundaries and varying surface flatness. When using traditional concentric circle ground segmentation models for fitting mining road planes, misclassification issues often arise, such as disconnection between passable areas and vehicles, and inconsistencies in passable area recognition results across frames. This paper proposed a method for identifying passable areas in mining roads based on spatiotemporal continuous compensation. First, the mining road was modeled using a concentric circle model, and principal component analysis was applied for multi-plane fitting to obtain the initial segmentation results of passable areas. Next, based on spatial connectivity, regional connectivity filtering and point connectivity filtering were performed on the initial passable areas using the region-growing algorithm and density-based spatial clustering of applications with noise algorithm, respectively, to obtain passable areas that meet spatial connectivity criteria. Finally, to eliminate unstable regions with inconsistent passability across different point cloud frames, a grid map was constructed based on a normal distribution transformation algorithm, and temporal stability weights were used to assess grid stability, ultimately filtering out unstable regions through regional grid projection. Test results in mining indicated that the proposed method for identifying passable areas achieved an accuracy of 93.44%, representing a 2.27% improvement over existing mainstream algorithms; the recall rate was 99.14%, reflecting an 8.26% enhancement compared to current mainstream algorithms. The proposed method not only exhibits good spatial connectivity in disconnected areas but also demonstrates strong temporal stability in rugged regions.

Research on lateral-longitudinal coordinated control of unmanned dump trucks in open-pit mine

PAN Guoyu, BAO Jiusheng, HU Deping, ZOU Xueyao, YIN Yan, WANG Maosen, ZHU Chenzhong, ZHANG Lei, YANG Rui

2024, 50(10): 68-79. doi: 10.13272/j.issn.1671-251x.2024070017

<Abstract>(66) <HTML> (19) <PDF>(11)

Abstract:
Open-pit mine unmanned dump trucks face harsh transportation conditions, such as low-grade roads with numerous ramps and curves, as well as heavy and highly variable loads. Most existing vehicle motion control strategies are designed for conventional road environments, making them unsuitable for direct application to mine dump trucks. To address these issues, a lateral-longitudinal coordinated control system based on preview error and layered feedback was proposed for unmanned open-pit mine dump trucks. The lateral control was based on a linear quadratic regulator (LQR) and employed a feedforward controller to reduce steady-state errors, while a fuzzy controller was used to adaptively adjust the preview distance, thereby improving path tracking accuracy. The longitudinal control established a layered feedback longitudinal speed controller, which used model predictive control and fuzzy proportional-integral-differential (PID) feedback control. In addition, an inverse model for vehicle driving and braking was established to minimize the impact of load and road gradient changes on longitudinal speed tracking. Simulation results indicated that: ① The error between the actual speed and the desired speed was within 2%, demonstrating that the speed tracking performance of the dump truck could meet requirements under both empty downhill and fully loaded uphill conditions. ② Due to the lateral-longitudinal coordinated control’s ability to adjust vehicle speed in real time based on varying road curvature, the coordinated controller achieved higher path tracking accuracy compared to single lateral control in both operating conditions, while also enhancing vehicle maneuverability and stability. Laboratory test results showed that: ① The peak lateral error during empty downhill runs was 0.0199 m, and the peak direction error was 0.1840 rad. Both errors increased at curves, but their fluctuations were minimal, ensuring that the test vehicle effectively tracked the desired path. ② During loaded uphill runs, the peak lateral error was 0.0168 m, and the peak direction error was 0.0714 rad. The error trends were opposite to those observed in empty downhill tests, but the errors remained within acceptable limits, resulting in good path tracking performance. ③ Both peak errors were lower compared to those in empty downhill tests, which validated the effect of varying speeds on lateral control accuracy.

Relative dynamics modeling and force-position hybrid control of dual-arm cutting robot

LIU Peng, ZHOU Haochen, MA Hongwei, CAO Xiangang, ZHANG Xuhui, DUAN Xuechao, MAO Qinghua, TIAN Haibo, XUE Xusheng, WANG Chuanwei

2024, 50(10): 80-89. doi: 10.13272/j.issn.1671-251x.2024070104

<Abstract>(41) <HTML> (11) <PDF>(2)

Abstract:
The dual-arm cutting robot addresses the low efficiency of traditional single-arm roadheaders when cutting large cross-sections. However, its dynamic interaction with coal-rock affects control performance. In current studies, both arms of the dual-arm cutting robot interact with the same object, forming a closed kinematic chain, which fails to meet the control requirements for independent arm movement and the output force of each cutting head. To solve this issue, a force-position hybrid control system based on the robot’s relative dynamics model was designed. The kinematic and dynamics models of the dual-arm cutting robot were established, with the relative dynamics model derived using the robot’s relative Jacobian matrix and principles of virtual displacement and virtual work. This model used a single variable to describe the motion states of both arms, integrating their independent dynamics models into a unified one. Based on this relative dynamics model, a force-position hybrid control system was developed for the robot’s dual arms, with system stability and feasibility verified via the Lyapunov function. Simulation results indicated that the dual-arm cutting process had a larger workspace compared to single-arm cutting, allowing for efficient large cross-section cutting. The force-position hybrid control system enabled synchronized tracking of expected relative position and force, with the absolute error in tracking the target cutter position kept within 0.3132 m and a root mean square error of 0.1447 m.

Study on the prediction of gangue content rate in fully mechanized caving face based on DeepLab v3+

WANG Zhifeng, WANG Jiachen, LI Lianghui, AN Bochao

2024, 50(10): 90-96. doi: 10.13272/j.issn.1671-251x.2024070001

<Abstract>(40) <HTML> (20) <PDF>(6)

Abstract:
To tackle the challenge of accurately determining the volumetric gangue content rate under actual stacking conditions of coal-gangue in fully mechanized caving faces, a prediction method based on the DeepLab v3+ model was proposed. A dataset consisting of images depicting coal-gangue accumulation was constructed, and a semi-automatic data labeling method, along with Contrast Limited Adaptive Histogram Equalization (CLAHE), was employed for image preprocessing. The DeepLab v3+ model was utilized for the semantic segmentation of coal-gangue images, which facilitated the calculation of the projected area gangue content rate. A numerical model was established using the PFC^3D numerical simulation software based on the reconstructed three-dimensional coal-gangue block, simulating the top coal drop and the coal transport process via scraper conveyor. The volume of each gangue or coal particle was extracted using the FISH programming language, enabling the calculation of the volumetric gangue content rate of the coal-gangue accumulation. By analyzing the quantitative relationship between the projected area gangue content rate and the volumetric gangue content rate under varying top coal thickness conditions, a predictive model for the volumetric gangue content rate of coal flow was developed. Experimental results indicated that the accuracy, mean pixel accuracy, and mean intersection-over-union (IoU) of the DeepLab v3+ model were 97.68%, 97.72%, and 95.33%, respectively, all surpassing those of classical semantic segmentation models such as FCN8s and PSPNet. This enabled precise and rapid identification of the projected area gangue content rate of coal-gangue accumulations. The coefficient of determination (R²) for the volumetric gangue content rate prediction model was 0.9828, demonstrating robust predictive performance.

Rapid prediction algorithm for flow field in fully mechanized excavation face based on POD and machine learning

JIN Bing, ZHANG Lang, LI Wei, ZHENG Yi, LIU Yanqing, ZHANG Yibin

2024, 50(10): 97-104, 119. doi: 10.13272/j.issn.1671-251x.2024080090

<Abstract>(48) <HTML> (8) <PDF>(3)

Abstract:
To effectively utilize dust suppression measures in fully mechanized excavation faces, this study proposed a rapid prediction algorithm for the flow field based on proper orthogonal decomposition (POD) and machine learning. First, computational fluid dynamics (CFD) technology was used to simulate the air flow field and dust concentration field under various conditions, generating high-dimensional flow field data. Then, the POD method was applied to reduce the dimensionality of this data, extracting core modes that captured the main characteristics of the flow field and producing basis function modes and mode coefficients. Machine learning techniques were subsequently used to predict the mode coefficients that accounted for over 90% of the total energy under different conditions, enabling predictions of mode coefficients for unknown conditions. Finally, by reconstructing the flow or dust concentration field data using the predicted mode coefficients and basis function modes, rapid and accurate predictions for the flow field in excavation faces were achieved. The results showed that the numerical simulation model for the excavation face had a relative error within 3%, accurately reflecting the actual air flow and dust distribution. Selecting the first five modes for the flow field and the first seven modes for the dust concentration field balanced the accuracy and efficiency of POD reconstruction. The support vector machine (SVM) model outperformed the Random Forest and Neural Network models in predicting mode coefficients. For 60 different conditions, the relative errors between the POD and SVM-predicted flow velocity and dust concentration, and the CFD results, were 0.36 m/s and 86.24 mg/m³, respectively. The average prediction time for the flow and dust concentration fields was 73 seconds, achieving high-precision, rapid predictions for airflow and dust concentration in mine excavation faces.

Study on the strain response characteristics of coal and rock borehole walls under high-pressure gas fracturing

KONG Zixing, MA Yankun, YANG Fade, WANG Xiaoqi, GONG Liqiang, JIANG Mingfeng

2024, 50(10): 105-111. doi: 10.13272/j.issn.1671-251x.2024090009

<Abstract>(39) <HTML> (12) <PDF>(4)

Abstract:
There has been a lack of precise methods for monitoring and evaluating the entire process of gas fracturing. However, strain monitoring can effectively record the real-time initiation and propagation of cracks. By studying the strain response of borehole walls during high-pressure gas impact, the relationship between crack formation and strain response during the fracturing process can be clarified, enabling the identification of the optimal fracturing angle. A true triaxial experimental system for high-pressure gas fracturing of coal and rock was used, and experiments were conducted at five different impact angles (0, 30, 45, 60, 90°) to investigate crack morphology, pressure curves, and strain response characteristics of the borehole walls. The experimental results revealed that: ① As the impact angle increased, the crack morphology of coal and rock exhibited a pattern that was initially complex but later became simpler. ② The gas pressure during the fracturing process passed through four stages: an increase, a sharp drop, accumulation, and steady release. ③ The strain data for the borehole walls were predominantly tensile, and the strain curve displayed two distinct peaks: the first peak occurred 0.1 seconds after the pressure curve reached its peak, coinciding with the formation of the main crack; the second peak was generally associated with the propagation and expansion of the main crack. ④ When the impact angle was 45°, a more complex crack network tended to form within the specimen, resulting in the most effective fracturing.

Fractal characteristics of mine fracture structures and their impact on rockburst

LAN Tianwei, WANG Shunxiang, ZHANG Mancang, LI Zhu, WU Guoqiang, FANG Ping, LU Kaixiang, LIU Yonghao, TANG Xiaofu

2024, 50(10): 112-119. doi: 10.13272/j.issn.1671-251x.2024060092

<Abstract>(31) <HTML> (8) <PDF>(4)

Abstract:
Fracture structures in mines are critical geological factors in triggering rockbursts. This study investigated the impact of fracture structures on rockburst, focusing on the Junde mining area. Using geological dynamic zoning, the fracture structures in the mining area were classified into grade Ⅰ-Ⅴ fracture blocks based on length. The box-counting method in fractal theory was employed to calculate the fractal dimension of grade Ⅴ fracture blocks. The study analyzed the overall and partitioned fractal characteristics of the fractures and explored the coupling relationship between the fractal dimension of fracture structures, structural stress distribution, and rockburst. The results showed: ① The overall fractal dimension of the fractures was highly consistent with the fractal dimension of the NW-trending fractures, indicating that NW-trending fractures had a more significant influence on rockburst in the Junde mining area than NE-trending fractures. ② The fractal dimensions varied among fractures of different orientations, demonstrating clear spatial distribution differences and a positive correlation between fractal dimension and fracture complexity. This implied that a greater fractal dimension corresponded to a more complex spatial distribution of fracture structures, thereby increasing the likelihood of rockbursts. ③ Higher structural complexity was associated with higher stress concentration, and rockbursts in coal seams primarily occurred in high-stress regions, showing a high level of consistency between structural complexity and stress concentration. This study provides a new perspective for predicting and mitigating rockburst risks by quantitatively analyzing fracture structures through fractal dimensions.

Image clarification algorithm for underground dust and mist based on enhanced grid network

GU Yanan, LI Qing, LIU Chenchen, ZHANG Fukai

2024, 50(10): 120-127, 159. doi: 10.13272/j.issn.1671-251x.2024070036

<Abstract>(68) <HTML> (26) <PDF>(8)

Abstract:
To address the issues of dark images, detail loss, and over-enhancement in existing underground dust and mist image clarification algorithms, an image clarification algorithm based on enhanced grid networks was proposed. This algorithm consisted of three parts: a preprocessing module, a backbone module, and an output module. The preprocessing module generated a set of feature maps using the feature extraction module IRDB, which served as the input for the backbone module. The IRDB integrated the advantages of the Inception architecture and the Residual Dense Block (RDB), increasing the depth and width of the network under limited resources, thereby enhancing the network's representational ability, generalization capability, and handling of dust and mist at different scales. The backbone module employed a grid network to further extract features at various scales of the image and implemented transformations of feature maps at different scales through upsampling and downsampling. To better capture detailed information in the images, a channel attention mechanism was introduced within the grid network. Experimental results indicated that with 5 IRDB modules, the network model achieved the best Peak Signal to Noise Ratio (PSNR), Structural Similarity Index (SSIM), and Naturalness Image Quality Evaluator (NIQE) metrics. Visually, the images processed using the proposed algorithm exhibited richer detail information, more natural colors, and improved clarity and contrast. The PSNR, SSIM, and NIQE values for the images processed by the proposed algorithm on the underground dataset were 23.69, 0.8401, and 8.95, respectively, with a moderate image processing speed, and the overall performance surpassed similar algorithms such as DCP and AOD-Net.

Study on vibration characteristics of drill rod system in a coal mine drilling robot under interlaced soft and hard inclined coal seams

KANG Mingxia, WANG Zhongbin, LIU Xinhua, WEI Dong, ZHAO Lala

2024, 50(10): 128-134, 146. doi: 10.13272/j.issn.1671-251x.2023120052

<Abstract>(41) <HTML> (13) <PDF>(4)

Abstract:
Research on the vibration characteristics of the drill rod system in a coal mine drilling robot is essential for the prediction and control of drilling trajectories. Considering the complex interaction mechanisms between the drill rod system and coal seams during horizontal drilling, an experimental platform and vibration monitoring system for the coal mine drilling robot were established. Horizontal drilling experiments were conducted under various layering conditions of soft and hard coal seams and different seam inclination angles. The empirical mode decomposition method was used to decompose, filter, and reconstruct the collected data to eliminate noise interference and study the vibration characteristics of the drill rod system under interlaced soft and hard inclined coal seams. The results showed that as the inclination angle of the coal seam increased, the longitudinal, transverse, and torsional vibration amplitudes of the drill rod system increased when the robot was drilling through hard→medium-hard→soft or soft→medium-hard→hard coal seams. At the same inclination angle, the vibration amplitudes in the longitudinal, transverse, and torsional directions were higher when drilling through soft→medium-hard→hard coal seams than through hard→medium-hard→soft seams. When the inclination angle was small, the interlaced soft and hard coal seams had a greater impact on the drill rod system's vibration characteristics, whereas at larger angles, the seam inclination angle had a more significant effect than the layering. Moreover, larger sand and gravel particles had a certain impact on the vibration of the drill rod system.

Design and simulation analysis of a dual-source magnetic loop structure for mining steel wire rope

ZHOU Ping, WANG Shihao, ZHOU Gongbo, ZHAO Tianchi, LI Xuanhan, YAN Xiaodong

2024, 50(10): 135-146. doi: 10.13272/j.issn.1671-251x.2024070079

<Abstract>(84) <HTML> (17) <PDF>(5)

Abstract:
Currently, the electromagnetic detection methods for mining steel wire ropes have limitations: the main flux detection method has low accuracy in detecting local damage, while magnetic leakage-based detection methods have limited quantitative accuracy in local damage assessment. A dual-source magnetic detection method was proposed to simultaneously detect both the main flux and magnetic leakage in mining steel wire ropes, leveraging the complementary strengths of these two methods in local damage detection. Two excitation loop designs were proposed: a double-source ring-shaped tubular excitation loop and an independent separation excitation loop. Finite element simulation was used to verify the feasibility of the two schemes, and the independent separation loop was chosen as the basic structure of the magnetic circuit. The effects of various armature parameters, such as size and magnet properties, on the magnetization performance were studied, as well as the influence of the magnetic bridge structure parameters on the magnetic field distribution. The results indicated that:① The magnetization amplitude was positively correlated with the number of loops and negatively correlated with the armature length, while the height had almost no effect on the magnetization performance; ② The magnetization amplitude was positively correlated with the material grade, length, and thickness, and negatively correlated with the lift-off distance; ③ The magnetization amplitude was positively correlated with thickness, negatively correlated with air gap size, while lift-off distance had little effect on the magnetization performance; ④ The air gap of the magnetic bridge significantly influenced the magnetic flux density distribution within the bridge circuit.

Dynamic route planning for emergency escape in coal mines using a Dijkstra-ACO hybrid algorithm

LU Guoju, SHI Wenfang

2024, 50(10): 147-151, 178. doi: 10.13272/j.issn.1671-251x.2024020050

<Abstract>(76) <HTML> (20) <PDF>(5)

Abstract:
Emergency escape route planning in coal mines must adapt promptly to the changing underground environment. Traditional methods, relying on static networks with fixed weights, lack the flexibility needed for real-time adjustments in response to dynamic underground conditions. To address this limitation, a dynamic route planning approach for coal mine emergency escape was proposed using a Dijkstra-ACO (ant colony optimization) hybrid algorithm. By analyzing the impacts of tunnel slope and water level on escape routes, an optimal route dynamic planning model for emergency escape in coal mines was developed. This model allowed for real-time adjustment of escape routes based on environmental changes in tunnel slope and water level, thereby improving escape efficiency and safety. The Dijkstra-ACO hybrid algorithm was employed to obtain the optimal route model, where the Dijkstra algorithm was used for rapid identification of an initial route, while the ACO algorithm refined the result to find the shortest and safest escape route, ensuring adaptability to environmental changes. A simulated coal mine environment was constructed, modeling various tunnel types and parameters, including slope, water level, to test the dynamic route planning approach. Results showed that in three test areas of varying sizes, i.e., 50 m×100 m, 100 m×200 m, and 150 m×250 m, the routes generated by the Dijkstra-ACO hybrid algorithm were over 19% shorter compared to those from the A^* algorithm and modified ACO algorithm, with an obstacle avoidance improvement of over 5%.

Structural optimization and intelligent parameter control of ventilation and dust removal systems for comprehensive excavation workface

LIU Dandan, SHEN Qixiang, WANG Weilian, GUO Shengjun, WANG Chunmei, HE Ping

2024, 50(10): 152-159. doi: 10.13272/j.issn.1671-251x.2024080076

<Abstract>(58) <HTML> (14) <PDF>(8)

Abstract:
This study addressed the challenges of vortex formation and dead air zones in traditional long-pressure short suction ventilation and dust removal systems. By leveraging the Coanda effect, the system's structure was optimized through the nesting of the exhaust and pressure ducts. This design enhanced airflow in the negative pressure duct, promoting adherence to the tunnel walls, reducing dust dispersion, and significantly lowering energy consumption. Simulations utilizing flow field analysis and discrete phase model (DPM) revealed an optimal pressure-extraction ratio of 2∶3. Under this ratio, results indicated that the optimized system reduced dust concentrations at the driver's position and downwind side by 5.56% and 55.41%, respectively, compared to traditional systems. With the structure and pressure-extraction ratio established, further improvements in dust removal efficiency were achievable through parameter regulation. Key parameters included the distance between the duct and the dust-producing surface, the distance from the duct's central axis to the ground, and the distance between the pressure and extraction ducts. Convolutional neural network (CNN) was employed for intelligent parameter control, enabling the identification of optimal parameters for varying initial dust concentrations. Experiments conducted on 45 parameter regulation schemes using a scaled-down experimental platform demonstrated that the CNN model outperformed BP neural networks in accuracy and stability for dust concentration predictions. When initial dust concentrations at the driver's position and downwind side ranged from 300 to 900 mg/m³, the optimized system achieved an average dust concentration reduction of 51.49% to 83.88%, thereby validating the effectiveness of parameter control.

Effects of air curtain dust control parameters on dust pollution in fully mechanized mining faces

LI Changjie, XIN Chuangye, WANG Hao

2024, 50(10): 160-167. doi: 10.13272/j.issn.1671-251x.2024080054

<Abstract>(65) <HTML> (25) <PDF>(6)

Abstract:
The effectiveness of air curtain dust control is influenced by various factors, including suction ventilation and radial airflow distribution. Existing research is largely limited to the effects of single factors on air curtain dust control. To understand the impact of dust control parameters on dust pollution in fully mechanized mining faces, numerical simulations were conducted to investigate the evolution of airflow and dust dispersion under different conditions of radial airflow distribution and negative pressure dust control. The results indicated that: ① Radial airflow distribution primarily affected the entrainment effect of the axial jet field, while negative pressure dust control flow mainly influenced the negative pressure effect of suction at the working face. When the ratio of radial airflow distribution to total air supply was not less than 0.8 and the ratio of total air supply to negative pressure dust control flow was less than 1.0, the air curtain transitioned to axial movement in the jet region, forming an axial dust control flow field with a thickness of not less than 1.4 m. ② As radial airflow distribution and negative pressure dust control flow increased, the airflow quantity and speed distribution on the suction side of the tunnel became more uniform, leading to reduced dust dispersion distance and lower dust mass concentration at the operator's position. Based on these findings, the optimized parameters for air curtain dust control in fully mechanized mining faces were determined: radial airflow distribution at 288 m³/min (with a ratio of radial airflow distribution to total air supply of 0.9) and negative pressure dust control flow at 426 m³/min (with a ratio of total air supply to negative pressure dust control flow of 0.75). Field measurements showed that after applying the optimized air curtain dust control parameters, the dust reduction rate at the operator's position reached 93.5%, significantly improving the working environment.

Migration and distribution patterns of cutting dust in a continuous mining face under ventilation disturbance

HUANG Chao, TANG Mingyun, WANG Lele, CAI Jianguo, YUAN Yanan

2024, 50(10): 168-178. doi: 10.13272/j.issn.1671-251x.2024080046

<Abstract>(81) <HTML> (18) <PDF>(5)

Abstract:
To understand the migration and distribution patterns of cutting dust in the continuous mining face under ventilation disturbance, the 15218 continuous mining face of the Hongliulin Coal Mine in Shaanxi was taken as the research object. A physical model of the continuous mining face was constructed using SolidWorks. Based on the Euler-Lagrange method, CFD software was employed to numerically simulate the airflow field, dust concentration distribution, and dust particle size distribution. The results showed that: ① Most of the dust-laden airflow in the continuous mining face migrated toward the return air side. Dust primarily accumulated in the triangular area beneath the cutting drum of the continuous miner and in the region from the tail of the continuous miner to the middle of the tunnel. ② Dust accumulation was less in the vortex zone, with some dust accumulating in the shuttle car. In the wake zone, dust formed a concave, strip-like cloud. ③ As the dust-laden airflow moved toward the tunnel exit, coarse dust settled the most, followed by fine dust, while ultrafine dust settled the least. The quantities of ultrafine dust, fine dust, and coarse dust initially increased and then decreased with the increase in tunnel height. The quantities of ultrafine dust, fine dust, and coarse dust decreased as the distance from the mining face and the return air side tunnel wall increased. ④ The dust concentration and area at the breathing zone height decreased as wind speed increased. The proportions of ultrafine dust, fine dust, and coarse dust were approximately 15%, 54%, and 31%, respectively, and were generally unaffected by changes in wind speed. ⑤ A wind speed of 1.6 m/s facilitated dust removal in the breathing zone plane but also lifted more dust into the breathing zone, making it necessary to appropriately increase the wind speed for global dust removal while implementing targeted measures for localized dust control.

Current Issue
2024 Vol. 50, No. 10

Submission System

Latest AcceptedMore>

Current Issue 2024 Vol. 50, No. 10

Submission System

Latest AcceptedMore>

Current Issue
2024 Vol. 50, No. 10