工矿自动化

Coal mine intelligent information comprehensive carrier network

SUN Jiping, CHENG Jiamin

2022, 48(3): 1-4, 90. doi: 10.13272/j.issn.1671-251x.17905

<Abstract>(506) <HTML> (102) <PDF>(108)

Abstract:
At present, the information carrier network used in coal mine is mainly 100 Megabit, Gigabit and 10 Gigabit mining Ethernet ring network. The time delay and reliability of the network are uncontrollable. Therefore, it is difficult to meet the needs of few people or unmanned operation in underground coal mine and remote control on the ground. Quality of service (QoS) can guarantee the real-time performance and reliability of the highest priority application. However, the real-time performance and reliability of the highest priority application can not be guaranteed when multiple interface signals are imported at the same time and the data volume is large, or when the previous data packet is being sent. In order to solve the above problems, the technical requirements of coal mine intelligent information comprehensive carrier network are proposed. The requirements include wide transmission bandwidth, short transmission delay, high reliability, long transmission distance, strong anti-interference capability, intrinsically safe explosion-proof, strong adaptability to grid voltage fluctuation, strong anti-fault capability, good protection performance, multi-service comprehensive carrying, etc. Based on the above requirements, a coal mine intelligent information comprehensive bearing network based on flexible Ethernet (FlexE) is proposed. This network allocates different channels according to the requirements of different services on bandwidth, time delay and reliability. The businesses include time sensitive and time insensitive video, time sensitive and time insensitive audio, personnel positioning, vehicle positioning, equipment positioning, safety monitoring, power supply monitoring, transportation monitoring, drainage monitoring, coal working face monitoring and heading face monitoring. The network integrates coal mine monitoring, positioning, video and audio into one network. The coal mine intelligent information comprehensive carrier network based on FlexE not only meets the requirements of different services such as ground remote control, personnel positioning and safety monitoring for bandwidth, delay and reliability, but also realizes the coal mine intelligent information comprehensive carrier network, reducing the maintenance difficulty and workload.

Study on the weakening of coal wall with section resistance adjustment of fully mechanized support in hard thick coal seam with large mining height

JI Lei

2022, 48(3): 5-10. doi: 10.13272/j.issn.1671-251x.2022010006

<Abstract>(225) <HTML> (42) <PDF>(24)

Abstract:
The load acting on coal wall-support in different mining stages varies greatly. The low efficiency cutting of coal wall is the result of the mismatch between the support resistance and mining stage, and the incapability of the mine pressure to effectively break the coal. The support section resistance adjustment technology can meet the requirements of roof safety control in different mining stages (before periodic pressure, normal mining, after periodic pressure), adjust the support working resistance to change the load on the coal wall for fracturing and breaking coal, which can effectively solve the problem of thick and hard coal wall weakening. Based on the engineering background of 1102 fully mechanized working face in Yanghuopan Coal Mine, the technology of support section resistance adjustment in thick hard coal seam matching with mining stage is studied. The simulation results show the following points. ① The peak value and influence range of support pressure at each point of coal wall survey line decrease with the increase of initial support of hydraulic support in normal mining stage and pressure stage of working face. Under the same initial support, the peak value and the influence range of the support pressure on the coal wall in the pressure stage are larger than those in the normal mining stage. ② When the initial support of hydraulic support increases from 2000 kN to 8000 kN, the horizontal displacement of coal wall decreases by 17 mm in the pressure stage and 7.5 mm in the normal mining stage, indicating that reducing the initial support is conducive to weakening the hard coal wall. ③ In different mining stages, the damage degree of plastic zone of surrounding rock decreases with the increase of initial support of hydraulic support, indicating that the damage degree of coal wall decreases. ④ The support resistance is 6000-8000 kN in normal mining stage, 4000-6000 kN after periodic pressure, and more than 8 000 kN before periodic pressure, which can ensure the safety of roof and efficient cutting of thick and hard coal wall. The field application shows the following points. ① In 115 working cycles, the increased resistance state of the hydraulic support accounts for 64.8% of the statistical cycles (75.50% for the first resistance increasing type, 20.16% for the second resistance increasing type and 4.34% for the multiple resistance increasing type). The ratio of the expansion and contraction of the support movable column between 0-3% is 90%, indicating that the hydraulic support has a good capability to operate and control the roof in the field production. ② After adjusting the support resistance of the hydraulic support in sections, the average coal cutting time of the shearer is reduced to 1.8 h under the premise of effective roof control, which is reduced by 21.7% . The coal wall is weakened effectively, and the coal cutting efficiency is improved.

Transparent mining mode and key technologies of fully mechanized working face

YUAN Changsuo, WANG Feng

2022, 48(3): 11-15, 31. doi: 10.13272/j.issn.1671-251x.2021110048

<Abstract>(326) <HTML> (162) <PDF>(66)

Abstract:
In order to solve the problem that the intelligent mining technology based on adaptive working face geological conditions can not meet the practical engineering application requirements, a transparent mining mode of fully mechanized working face is proposed, which includes three stages, namely model construction, positioning of space to be mined and cutting control decision and execution. The mode is based on the coal seam occurrence exploration, and the 3D digital model of working face is taken as the object. The height adjustment control strategy of the shearer is formulated by cutting the 3D digital model and extracting the track coordinates of the roof and floor of the coal seam to be mined. Finally, the shearer adjusts the height control according to the cutting track parameters to achieve the goal of autonomous coal cutting. This paper expounds the key technologies of transparent mining in fully mechanized working face, such as establishment of 3D digital model, establishment of 3D laser point cloud model, model cutting and cutting planning and shearer height adjustment control. In the 43102 fully mechanized working face of Yujialiang Coal Mine of CHN Energy Shendong Coal Group Co., Ltd., the transparent mining mode and key technologies engineering application are carried out. The initial 3D geological model of the working face is constructed, and the borehole survey is completed along the boundary line between the roof and floor of the coal seam so as to realize the detection of the occurrence of the coal seam in the working face. After the acquired data is imported into the initial 3D geological model, a 3D digital model of the working face is obtained. Geological mapping is carried out daily during the mining process of the working face, and the error correction of the 3D digital model is realized through the mapping data. The real-time 3D laser point cloud model of the stope is constructed, the 3D coordinate data set at the junction of coal wall and roof in the 3D laser point cloud model is extracted to form a cutting line. The cutting line is used to cut the 3D digital model to obtain the contour curve of roof and floor in the next coal cutting cycle. By analyzing the changes of coal seam occurrence, the cutting plan is formulated to guide the automatic height adjustment control of the drum in the subsequent coal cutting cycle of the shearer. The application results show that the error of the 3D digital model is less than ±0.2 m, and the shearer can automatically cut coal according to the coal seam occurrence conditions of the working face.

Key technology and development trend of intelligent mining in complex condition working face

ZHANG Shuai, REN Huaiwei, HAN An, GONG Shixin

2022, 48(3): 16-25. doi: 10.13272/j.issn.1671-251x.2021090041

<Abstract>(584) <HTML> (122) <PDF>(92)

Abstract:
In complex condition coal seam, there are a large number of geological condition parameter changes and a large range of parameter changes. The intelligent mining is the difficult problem which needs to be solved urgently at present. This paper analyzes the main geological conditions and problems of coal mines in different regions of China, and points out that compared with fully-mechanized coal mining, intelligent mining requires higher geological security. The more complex the geological conditions, the more precise the perception, the faster the analysis and decision-making, and the higher the data transmission rate of the control system. Taking the mining of 'three soft' coal seam in Huainan and Huaibei areas as an example, the problems faced in the intelligent mining process are discussed. The coal wall is frequently spalling, the scraper conveyor moves up and down, the adjacent supports are dislocated and the occlusion is not tight, the guard plates are not neat, the supports are tied to the bottom, and the advance roadway is deformed. It is pointed out that the conditions of surrounding rock (roof, floor and coal wall), coal seam strike/dip angle, rock pressure and stability of advance roadway are the five factors that affecting the normal continuous mining of the working face. In order to solve the problems caused by the above five factors, it is necessary to develop the key core technologies to solve the intelligent mining of complex working face from the aspects of surrounding rock parameter perception, trend analysis, fine control, dynamic system adaptation and self-adaptive decision-making. The application status, effect and problems to be solved in the future of the intelligent mining technology of complex conditions working face, such as the precise control and rapid follow-up technology of hydraulic support guard plate, roof partition cooperative support technology, working face equipment attitude monitoring technology, working face straightening technology, moving up and down control technology, stable pressure liquid supply control technology, simulation decision-making system platform and advance support technology, are described in detail. It is pointed out that for the coal seam with many complex conditions, the main directions of follow-up researches are the electromechanical and hydraulic integrated design of key components, distributed control mode, analysis and application of big data, cooperative rapid advancement control of equipment group, and the development of real-time simulation platform and intelligent decision-making system.

Application analysis of multi-access edge computing in intelligent mine network

LIU Haipeng, ZHOU Shuqiu

2022, 48(3): 26-31. doi: 10.13272/j.issn.1671-251x.2021100004

<Abstract>(264) <HTML> (43) <PDF>(46)

Abstract:
In order to solve the problems of various types, complex system and low resource sharing rate of software and hardware equipment, difficult network upgrading and transformation, and the incapability to meet the requirements of vertical services due to limited uplink and downlink transmission bandwidth and long total service delay, this paper proposes to introduce multi-access edge computing(MEC) technology into mine network to provide support for the realization of intelligent mine. For the intelligent mine service types of video monitoring, delay sensitive and connection, the application mode of MEC is discussed, and the characteristics of MEC supporting multiple protocols and equipment access are analyzed. It is pointed out that MEC is the only choice to provide integrated management and control based on the existing underground multiple protocols and equipment, and is the best solution to provide undifferentiated high-quality end-to-end service for users. The intelligent mine network computing tree model based on business requirements is established, and its evolution is divided into three stages, namely Pre-5G, 5G and Beyond-5G(6G). The main characteristics and symbolic technologies of each stage are analyzed, as well as the business characteristics such as load balance, business mobility, data security, scalability and integration characteristics. It is pointed out that each characteristic is the worst in the first stage and the best in the third stage. However, there is still a gap to achieve the goal of truly universal hardware devices and fully standardized interfaces. Combined with the computing tree model, the intelligent mine network MEC deployment model is proposed. It is pointed out that the model is based on a three-level flat structure with depth of 2, which can give full play to the edge computing capability of nodes at all levels, and dynamically select task unloading strategy while taking into account the load balance of nodes, so as to complete efficient task coordination. Moreover, the functions of nodes can be selected and flexibly deployed according to the actual situation on the ground or underground, which is suitable for all stages of intelligent mine construction.

Study on optimization and evaluation of continuous mining scheme in coal seam group

LIU Xianwei, ZHANG Yandong, SHAN Chengfang, LI Yafeng, WANG Haiyang, MA Yingjian, GUO Yuming

2022, 48(3): 32-39, 54. doi: 10.13272/j.issn.1671-251x.2021110015

<Abstract>(222) <HTML> (89) <PDF>(11)

Abstract:
In order to optimize the continuous mining scheme of coal seam group in Yushuling Coal Mine, FLAC3D simulation is used to study the coal seam integrity and working face stress distribution law under two continuous mining schemes of downward mining and upward mining of coal seam group, and the economic benefits of the two schemes are compared. The results show that the coal seam suffers plastic damage to a certain extent during upward mining, but the damage scope of the coal seam plastic zone can be effectively reduced by arranging the transportation roadway and return air roadway of the lower No.7 and No.8 coal seams and the transportation roadway and return air roadway of the lower No.10 coal seam in an inboard way of 10 m. The undamaged areas of the lower No.7 and No.8 coal seams account for 87.5% and 60.4% respectively, and the integrity of the coal seam meets the requirements of safe mining. Compared with the downward mining, the average stress of the lower No.7 and No.8 coal seams during upward mining is reduced by 45.3% and 34.9% respectively, and the maximum supporting stress of the lower No.7 and No.8 coal seams is reduced by 66.7% and 36.4% respectively, and the economic benefit increase by 64.9%. Therefore, the upward mining is preferred as the continuous mining scheme of coal seam group in Yushuling Coal Mine. The optimization result of continuous mining scheme of coal seam group is theoretically verified by using analytic hierarchy process and fuzzy mathematics theory. By establishing the comprehensive evaluation index model of the coal seam group continuous mining scheme, constructing the judgment matrix of the criterion layer relative to the target layer and the index layer and carrying out the consistency test, the evaluation index weight vector is obtained. The membership degree matrix of each factor of the index layer relative to the downward mining and upward mining is constructed by using the linear function method and the binary comparison and ranking method, and the comprehensive membership degree index matrix is obtained. According to the evaluation index weight vector and the comprehensive membership index matrix, the comprehensive evaluation weights of the downward mining and upward mining schemes are obtained as 0.170 87 and 0.704 42 respectively, which verifies the feasibility of upward mining as the optimal scheme for the continuous mining of the coal seam group in this mine.

Research on outburst elimination technology of shield tunneling in middle roadway of outburst thin coal seam

ZHANG Nan, XU Jiuzhou, QIU Liming

2022, 48(3): 40-46. doi: 10.13272/j.issn.1671-251x.2021090023

<Abstract>(202) <HTML> (43) <PDF>(11)

Abstract:
In order to solve the problem of difficult prevention and control of coal and gas outburst in thin coal seam, the distribution characteristics of effective extraction area in thin coal seam are analyzed. Due to the limitation of the thickness of the thin coal seam, the expansion of the effective gas extraction area in the vertical direction is hindered, and it tends to extend in the horizontal direction, resulting in the effective extraction radius in the horizontal direction is much larger than the thickness of the coal seam. The effective extraction area is elliptically distributed. The gas seepage field mainly focuses on the direction and inclination of the coal seam. According to the characteristics, it is pointed out that the outburst elimination technology of shield tunneling in middle roadway based on the coal seam extraction mode can make the extraction area connected together. The technology is more suitable for gas extraction in thin coal seam. This paper analyzes the advantages and technical principles of applying the outburst elimination technology of shield tunneling in the middle roadway to block outburst elimination in thin coal seam. The gob-side entry retaining technology is adopted to make the return airway roadway of the previous working face as the air inlet roadway of the next working face. The gas extraction boreholes are constructed ahead of the air inlet roadway, and the extraction range covers and exceeds the predetermined middle roadway by more than 20 m. The gas extraction is used to eliminate the outburst danger of the middle roadway. tunneling the middle roadway. The gas extraction boreholes are constructed at the predetermined position in the middle roadway to the return airway roadway, and the extraction range covers and exceeds the predetermined return airway roadway by more than 20 m. The gas extraction is used to eliminate the outburst danger of the middle roadway. Finally, the return airway roadway is excavated to form the working face. Taking the thin coal seam of 9305 working face of a mine as the research object, the numerical simulation is carried out. The results show that when the extraction time is between 10 d and 30 d, the increase of the effective extraction radius is the largest. With the increase of the extraction time, the increase of the effective extraction range gradually decreases. When the borehole spacing is 3 m, the effective extraction radius between the two holes is almost tangent, and the extraction effect is the best. The extraction pressure can basically make most of the coal seam gas to be effectively diffused, resolved and passively extracted. The gas extraction in the middle roadway reduces the gas pressure between the return airway roadway and the progressive middle roadway area effectively. The field measurement results show that the optimal extraction borehole spacing for shield tunneling in the middle roadway of outburst coal seam in 9305 working face is 3 m, the borehole diameter is 94 mm, the effective extraction diameter is not more than 5 m, and the drilling depth is 107 m. The outburst elimination technology of shield tunneling in middle roadway reduces the gas volume fraction of the thin coal seam by about 70%, and the outburst elimination effect is remarkable.

Underground power supply system grounding fault section positioning method based on wide-area current transient component

OUYANG Min, DU San'en, LI Wenjun, HOU Gang, XUE Zhongxin, YANG Feiwen, GAO Bin, FAN Shengjun, WANG Feng, MAO Hao, HAN Peiqiang

2022, 48(3): 47-54. doi: 10.13272/j.issn.1671-251x.2021090028

<Abstract>(178) <HTML> (51) <PDF>(22)

Abstract:
At present, most of the research on underground power supply system grounding fault positioning in coal mine adopts the transient method, which needs to collect zero sequence voltage and zero sequence current of the line at the same time. Because it is difficult to collect zero sequence voltage accurately, it is easy to misjudge the normal operation section as the fault operation section when positioning the fault section, resulting in leapfrog tripping phenomenon. However, the current protection scheme for leapfrog tripping of underground power supply system is not suitable for neutral grounded system through arc suppression coil, and the cost is relatively high. In order to solve those problems, this paper presents an underground power supply system grounding fault section positioning method based on wide-area current transient component. When grounding fault occurs in underground power supply system of coal mine, the direction of zero-sequence current flowing through normal line and fault line is different. The closing opening difference operation (CODO) in mathematical morphology is used to extract the direction information of transient zero-sequence current of each line. The selection of structural element length in COCD plays a decisive role in the output of underground power supply system. The particle swarm optimization (PSO) algorithm is used to adaptively optimize the length of structural element, and the reliable extraction of polarity characteristics of grounding fault transient zero sequence current direction is realized. Based on the topology of multi-level power supply system, the polarity signals of the zero sequence current transient component output by the protection elements on each line are logically calculated. When the value is 1, the line is a normal operation line, and when the value is 0, the line is a fault line. Therefore, the precise positioning of the fault section is realized. Based on the neutral ungrounded system and the neutral grounded system through arc suppression coil, the positioning method is verified. The results show that the underground power supply system grounding fault section positioning method based on wide-area current transient component only needs to collect the zero-sequence current, and the method can achieve accurate positioning of the fault section in the operation mode of the neutral ungrounded and the neutral grounded through the arc suppression coil.

Path planning of coal gangue sorting robot based on G-RRT* algorithm

ZHU Ziqi, LI Chuangye, DAI Wei

2022, 48(3): 55-62. doi: 10.13272/j.issn.1671-251x.2021090015

<Abstract>(1249) <HTML> (66) <PDF>(42)

Abstract:
The coal gangue sorting environment is complex. In order to avoid the collision between robot and obstacles and improve sorting efficiency, it is necessary to carry out path planning for robot. The principle of coal gangue sorting system is analyzed. The path planning problem of coal gangue sorting robot is summed up as planning a collision-free path from a given starting point to a target point in the environment of obstacles, and the two constraints of high speed and avoiding collision with obstacles must be met at the same time. Combining the advantages of Cartesian space and joint space, a path planning scheme for coal gangue sorting robot with path planning in joint space and collision detection in Cartesian space is proposed. The scheme does not need to carry out kinematic inversion of the robot, and can avoid describing obstacles in joint space. In order to solve the problem of blindness in the improved rapidly-exploring random trees (RRT*) path planning algorithm, a variable probability target bias strategy is proposed and introduced into RRT* algorithm to obtain the G-RRT* algorithm. The target bias strategy with variable probability increases the target bias probability in the obstacle-free area so as to enhance the target orientation of the algorithm. In the obstacle area, the target bias probability value is reduced to ensure the obstacle avoidance capability of the algorithm. The G-RRT* algorithm combines the variable probability target bias strategy with RRT* algorithm. The G-RRT* algorithm not only retains the asymptotic optimal path length characteristic of RRT* algorithm, but also improves the target orientation of the algorithm, and can improve the path planning efficiency greatly. The experimental results show that compared with RRT-Connect algorithm and RRT algorithm with fixed probability target bias strategy, the G-RRT* algorithm can get the shortest average path length, and is more suitable for path planning of coal gangue sorting robot.

Research on precise positioning of shield roadheader robot system in coal mine

MA Hongwei, YANG Jinke, MAO Qinghua, WANG Qiang

2022, 48(3): 63-70. doi: 10.13272/j.issn.1671-251x.2021070082

<Abstract>(2178) <HTML> (74) <PDF>(49)

Abstract:
At present, most of the positioning methods of underground tunneling equipment in coal mines adopt single auxiliary measurement methods such as machine vision, odometer and total station to combine with inertial navigation measurement to suppress the cumulative position error caused by inertial navigation solution over time. However, the single auxiliary measurement method is easy to be affected by the underground environment, and there are certain errors in position measurement, which leads to the reduction of the precision of the combined measurement method with inertial navigation. In order to solve the above problems, taking shield roadheader robot system in coal mine as the research object, a combined positioning method of strapdown inertial navigation+digital total station+displacement sensor is proposed. Firstly, the position and attitude angle parameters of the roadheader robot are calculated by using strapdown inertial navigation. Secondly, the position information of the roadheader robot measured by the digital total station and calculated by the displacement sensor are used to feedback and correct the position information calculated by the strapdown inertial navigation, so as to reduce the cumulative position error generated by the inertial navigation over time. Finally, the position and attitude angle information calculated by the strapdown inertial navigation, the position information obtained by the total station measurement and the position information estimated by the displacement sensor are fused by the multi-information fusion algorithm based on the federated filter, so as to obtain the accurate position and attitude information of the roadheader robot. The simulation and industrial experiment results show that the combined positioning method can well suppress the accumulative position solution errors of pure inertial navigation and realize the precise positioning of the shield roadheader robot in coal mines. The position errors in the x-axis and y-axis directions are controlled at ±0.03 m and ±0.02 m respectively, which meets the requirements of the underground driving face.

Research on trajectory planning of drill rig manipulator based on improved particle swarm optimization

SHEN Shuce, SHI Yannan, SONG Jianfeng, REN Ze, WANG Yiying, WANG Hanqiu

2022, 48(3): 71-77, 85. doi: 10.13272/j.issn.1671-251x.2021090049

<Abstract>(170) <HTML> (100) <PDF>(16)

Abstract:
The manipulator is an important device of anti-outburst and anti-impact drill rig, which is related to whether the drill rig can drill normally and truly realize unmanned operation. In order to ensure the rapid, accurate and stable operation of the drill rig manipulator, the trajectory planning optimization is particularly important. There are some problems in the existing trajectory planning of drill rig manipulator, such as higher order, prematurity of optimization algorithm and so on. In order to solve the above problems, a time optimal trajectory planning method of drill rig manipulator based on improved particle swarm optimization ( PSO) algorithm is proposed. Firstly, the 3D model of the drill rig manipulator is constructed by using the standard Denavit-Hartenberg ( D-H), and the workspace of the manipulator is obtained by Monte Carlo method, and four path points are selected as interpolation points from the workspace. Secondly, in order to make the manipulator reach the specified position quickly and smoothly, the trajectory of the manipulator is constructed by using 3-5-3 piecewise polynomial interpolation in the joint space. Finally, by the improved PSO algorithm, the constructed trajectory is optimized in the shortest time, and the optimal trajectory planning of the drill rig manipulator is obtained. The Matlab simulation results show that the time optimal trajectory planning method of the drill rig manipulator based on improved PSO algorithm can not only ensure the smooth operation of each joint of the drill rig manipulator, but also reduce the running time from 3.168 5 s to 2.385 4 s, reduce the overall running time by about 25% compared with that before optimization, and improve the efficiency of the manipulator.

Multi-sensor fusion positioning of detection robot for tailings pond flood discharge tunnel

ZHOU Yibo, ZHOU Weiyi, GUO Zhenwu, WANG Binrui

2022, 48(3): 78-85. doi: 10.13272/j.issn.1671-251x.2021090063

<Abstract>(140) <HTML> (33) <PDF>(17)

Abstract:
The environment in the flood discharge tunnel of tailings pond is complex, and the existing positioning algorithm of detection robot has the problem of positioning failure in weak texture indoor scene, which is difficult to be applied to the precise positioning and accumulative error elimination of detection robot in this kind of environment. In order to solve the above problems, a multi-sensor fusion positioning algorithm of detection robot for tailings flood discharge tunnel is proposed. Based on the odometry method and graph theory, the algorithm simplifies the long-distance positioning in the flood discharge tunnel environment to multi-segment short-distance positioning by using the ArUco code. Firstly, the odometer is calibrated by UMBmark algorithm, which effectively eliminates two types of system errors of wheel diameter and axle diameter. Secondly, the extended Kalman filter (EKF) algorithm is used to fuse the information of the odometer and the inertial measurement unit (IMU), and the odometry method is used to realize the calculation of the position and attitude information of the detection robot during the movement process. Finally, the ArUco code is used as a road sign and fixed inside the tunnel. The detection robot carries the calibrated camera to identify and process the ArUco code information. The robot uses the measurement values of each sensor to form constraints, and combines constraints with the graph optimization method to achieve position and attitude optimization. And according to the information carried by the ArUco code, the accumulative error is eliminated so as to realize the long-distance high-precision positioning of the detection robot in the narrow and long space and weak texture scene. The multi-sensor fusion positioning algorithm is operated and closed in the actual scene of the tailings pond flood discharge tunnel, and 10 groups of repeated positioning experiments traveling 40 m are carried out respectively. The results show that the multi-sensor fusion positioning algorithm has high stability and precision, can correct the accumulative error effectively and realize the precise positioning of the detection robot in the flood discharge tunnel environment. The average positioning error of traveling 20 m is 19.77 cm, the average positioning error of traveling 40 m is 21.23 cm, and the average corrected error of traveling 20 m is 4.2 mm.

Underground pedestrian detection model based on Dense-YOLO network

ZHANG Mingzhen

2022, 48(3): 86-90. doi: 10.13272/j.issn.1671-251x.17861

<Abstract>(218) <HTML> (131) <PDF>(47)

Abstract:
The pedestrian detection is a key technology to realize unmanned mining vehicles. The visibility of images captured in low light environment in coal mine is poor, which greatly affects the effect of pedestrian detection. The existing pedestrian detection methods ignore the influence of underground low light environment on target detection precision, and the detection effect is not ideal. In order to solve this problem, an underground pedestrian detection model based on Dense-YOLO network is proposed. The low light images are decomposed into light image and reflection image, and the light image is enhanced by Gamma transformation, weighted logarithmic transformation and contrast-limited adaptive histogram equalization (CLAHE). The enhanced images are weighted and fused by brightness weight and color weight. The bilateral filtering algorithm is used to process the reflection image to enhance the texture of the image. The enhanced light image and the reflection image processed by bilateral filtering are multiplied point by point to reconstruct the RGB image, and the ROF denoising model is used to denoise the fused image globally to obtain the final enhanced image. The dense module with residual block is added to YOLOv3 to build underground pedestrian detection model based on Dense-YOLO network. The addition of residual block is beneficial to avoid gradient disappearance and gradient explosion in the network training process. The experimental results show that the image visibility and pedestrian detection can be improved effectively by enhancing the low light image. The missed detection rate of Dense-YOLO network for enhanced images is 4.55%, which is 14.91% lower than that of RetinaNet network. The underground pedestrian detection model based on Dense-YOLO network effectively reduces the missed detection rate of pedestrian detection.

Research on fault diagnosis method of ventilation network based on machine learning

ZHANG Lang, ZHANG Yinghui, ZHANG Yibin, LI Zuo

2022, 48(3): 91-98. doi: 10.13272/j.issn.1671-251x.2021120093

<Abstract>(329) <HTML> (81) <PDF>(37)

Abstract:
The machine learning algorithm predicts unknown data by learning known data. Most of the existing fault diagnosis methods of ventilation system focus on a machine learning algorithm, which can not guarantee the selected algorithm to be optimal. In order to solve this problem, eight machine learning algorithms are compared, and three algorithms, support vector machine ( SVM), random forest and neural network, are selected to study the fault diagnosis of ventilation network. According to the actual layout of the mine ventilation system, a ventilation network pipeline model is constructed according to the criteria of geometric similarity, motion similarity and dynamic similarity. A ventilation network consisting of pipeline network branches and pipeline network nodes is obtained, and air volume data is obtained through experiments, and the data is preprocessed by a standardized method. Through cross-validation and grid search, the parameters of ventilation network fault diagnosis model based on SVM, random forest and neural network are optimized. The results of experiment and field test show that the accuracy of ventilation network fault diagnosis model based on SVM, random forest and neural network are 0.89, 0.88 and 0.95 respectively on the test set of experimental platform, and 0.86, 0.90 and 0.96 respectively on the test set of coal mine field. The neural network model has the best fault diagnosis effect. 120 sets of fresh air volume data collected in coal mine field are input into neural network model for prediction, and the fault diagnosis accuracy rate reaches 0.98, which verifies the feasibility and accuracy of the ventilation network fault diagnosis model based on neural network.

Risk prediction of coal and gas outburst

LI Yan, NAN Xinyuan, LIN Wanke

2022, 48(3): 99-106. doi: 10.13272/j.issn.1671-251x.2021070072

<Abstract>(264) <HTML> (112) <PDF>(24)

Abstract:
In order to solve the problems of low accuracy and slow response speed of existing support vector machine (SVM)-based coal and gas outburst prediction methods, a risk prediction method of coal and gas outburst based on improved grey wolf optimizer (IGWO) optimized SVM is proposed. The influence degree of each influencing factor on coal and gas outburst is analyzed by using the grey relational entropy weight method, and gas pressure, gas content, initial gas diffusion speed and mining depth are extracted as main control factors of coal and gas outburst according to the correlation degree order, and the main control factors are divided into a training set and a test set, and normalized. In order to improve the defects of the traditional grey wolf optimizer (GWO) population easily falling into local optimum and slow optimization speed, the out-of-bounds processing mechanism and the random difference mutation strategy embedded in Levy flight are introduced to improve the grey wolf optimizer (ie IGWO), so as to improve the convergence precision and speed of GWO effectively. The core parameters and penalty parameters of SVM are optimized by IGWO, and the main control factors of coal and gas outburst are input into IGWO-SVM for classification. And the classification results are compared with the actual test set so as to realize the risk prediction of coal and gas outburst. The simulation results show that compared with the prediction methods based on whale optimization algorithm-SVM ( WOA-SVM), grey wolf optimizer-SVM ( GWO-SVM) and particle swarm optimization-SVM ( PSO-SVM), the prediction method based on IGWO-SVM has higher prediction precision, and can meet the precision and reliability requirements of coal and gas outburst prediction while improving the operation efficiency of SVM. The accuracy rate reaches 96.67% and the prediction speed is 5.58 s.

Numerical study of pulverized coal ignition under different oxygen conditions based on solid-gas coupling

YAO Huawei, HE Xiaodong, WANG Zhe

2022, 48(3): 107-111, 117. doi: 10.13272/j.issn.1671-251x.2021090068

<Abstract>(237) <HTML> (45) <PDF>(16)

Abstract:
The plane hot plate test is the most commonly used method to evaluate the self-heating and ignition hazards of pulverized coal, especially for the accumulation of pulverized coal on the hot surface. In order to solve the problem of lacking of numerical study on the ignition characteristics of pulverized coal coupled with air based on hot plate experiment, a multi-physical field numerical model of coal spontaneous combustion with solid gas coupling is established on the basis of literature [9]. The simulation results show that the thickness of bituminous pulverized coal is 5 mm, 12.5 mm, 20 mm and 30 mm, and the diameter is 100 mm. When the thermal runaway of pulverized coal occurs, the bituminous pulverized coal slowly heats up to 170 ℃ before 30 min, and a high temperature region appears in the center of the coal layer, and the thermal runaway occurs suddenly at 37 min. When the thermal runaway of bituminous pulverized coal does not occur, the temperature of coal sample becomes stable after 30 min, and the temperature is lower than 150 ℃, without obvious high temperature point. The simulation results are in good agreement with the experimental results in literature 9. Under the condition of thicker bituminous pulverized coal, the minimum ignition temperature of the numerical model is compared with the results of literature 9, and the difference between the two is small, which verifies the reliability of the numerical model. Based on the numerical model, the spontaneous combustion characteristics of bituminous pulverized coal under different oxygen mass fractions are analyzed. ① As the thickness of bituminous pulverized coal increases, the minimum ignition temperature tends to decrease. ② In the thermal runaway stage, the high temperature area is located at the upper part of the pulverized coal center. ③ The temperature rise of pulverized coal in the early stage is caused by the heat transfer of hot plate. With the increase of pulverized coal temperature, the dominant factor of coal oxidation reaction changes from heat to oxygen. ④ The peak value of pulverized coal temperature increases linearly with the oxygen mass fraction, and the ignition delay time decreases exponentially with the oxygen mass fraction.

Information model of coal mine safety production monitoring system based on OPC UA

RONG Xue, HUANG Yourui, CHU Yiran, XU Shanyong

2022, 48(3): 112-117. doi: 10.13272/j.issn.1671-251x.17898

<Abstract>(190) <HTML> (41) <PDF>(30)

Abstract:
There are many kinds of subsystems in the coal mine safety production monitoring system, and the types of equipments in the subsystems are multifarious, which leads to the low semantic completeness of data and the fragmentation of information interaction data caused by the heterogeneous information of equipment. At present, although the research of coal mine informatization construction has basically realized the network integration of each subsystem, the massive data obtained can not be effectively shared, and the integration analysis can not be carried out. In order to solve the above problems, this paper proposes an information model of coal mine safety production monitoring system based on OPC UA. According to the relevant information of coal mine safety production monitoring system and the general modeling rules of OPC UA information model, the mapping relationship between actual equipment of coal mine safety production monitoring system and information model is analyzed, and the overall structure of information model of coal mine safety production monitoring system is proposed. It is pointed out that when new functions need to be extended in coal mine safety production monitoring system, they can be extended in function set. When new equipment needs to be added to the subsystem, new components can be added to the equipment set to ensure the extensibility of the information model. Taking the information model of gas extraction monitoring system as an example, the information model of methane sensor is established by using UaModeler tool. After the information model is graphically designed, the XML description file is generated and imported into the address space of OPC UA server. Through the third-party client UaExpert connecting server to test the information model of the OPC UA, the results show that the information model can realize the mapping in the address space of the OPC UA according to the mapping rules, and access the server's address space through the OPC UA client. The attributes of any object in each coal mine safety production monitoring subsystems can be obtained, which verifies the feasibility of using the OPC UA information model to realize the information interconnection.

Optimization design of magnetic flux circuit for mine wire rope damage detection

TIAN Jie, TIAN Zhuang, GUO Hongfei, LIU Ningzhe, MA Jianwu

2022, 48(3): 118-122. doi: 10.13272/j.issn.1671-251x.2021120013

<Abstract>(279) <HTML> (108) <PDF>(24)

Abstract:
The magnetic flux leakage(MFL) detection method is the most widely used method for detecting the mine wire rope damage, and there is no research on the influence of magnetic noise signal in magnetic flux circuit on the MFL detection signal of wire rope damage. Based on the principle of MFL detection for wire rope damage, the equivalent magnetic circuit model of MFL detection is constructed, and the magnetic field distribution of the magnetic flux circuit is simulated by Ansoft Maxwell finite element software. The results show that there are many magnetic noise circuits in the magnetic flux circuit besides the main magnetic flux and the MFL of wire rope damage, which are easy to interfere with the MFL detection signal of wire rope. The MFL of armature magnetic conduction path and the coupling MFL between permanent magnets on both sides and air medium have the greatest influence. Based on the simulation results, the magnetic flux circuit is optimized. The contact part between the armature and the permanent magnet is changed from a right-angle structure to a rounded structure to reduce the MFL at this part, increase the main magnetic flux in the armature magnetic conduction path, and then enhance the MFL detection signal of wire rope damage. The annular magnetic bridge circuit shielding device is designed with high magnetic conductivity material and installed in the damage MFL detection area so as to guide the direction of the coupling MFL between the permanent magnets on both sides and the air medium, and reduce the influence of the coupling MFL on the detection of wire rope damage MFL. The experimental results show that after the optimization of the magnetic flux circuit, the characteristics of the wire rope damage detection signal are more obvious than those before the optimization, and the collected signal increases from 6.14 mV to 18.59 mV. It is verified that the optimization scheme can improve the transmission efficiency of the magnetic flux circuit, have the aggregation and enhancement effect on the damage MFL, and reduce the superposition effect of the permanent magnet-air coupling MFL and the wire rope damage MFL, which is conducive to improving the accuracy of wire rope damage detection.

Underground location service system design

DU Zhigang, CHU Nan, LUO Ke

2022, 48(3): 123-128, 134. doi: 10.13272/j.issn.1671-251x.2021040070

<Abstract>(179) <HTML> (31) <PDF>(27)

Abstract:
The location service aims to provide accurate real-time position information of target objects, which is based on positioning. However, the current underground positioning system has some problems, such as low positioning precision, poor real-time performance, insufficient capacity, limited database carrying capacity, only supporting one-dimensional positioning and so on. In order to avoid the influence of underground positioning system on location service, an underground location service system is designed. The system adopts a Docker-based micro-service architecture, which overcomes the problems of development iteration and performance bottleneck of the traditional monolithic architecture and looses the coupling between businesses. The system adopts the simultaneous ranging method of multi-label and multi-anchor nodes, which improves the ranging efficiency and the capacity of the positioning system while ensuring the ranging accuracy. The system uses multi-source data fusion positioning algorithm to improve the discrimination accuracy of the direction of the sign card relative to the anchor base station. The system adopts the positioning algorithm based on Kalman filter and weighted LM method and the low-complexity characteristic extraction method to optimize the positioning results, reduce noise interference, remove redundant data and improve positioning precision. The system introduces the time series database for mixed data storage, and stores time series data such as historical track in InfluxDB to improve system data access performance. The system adopts the publish-subscribe mode for asynchronous message transmission, which increases the reusability and sharing of public information. The system adopts Bearer verification for the location service interface to protect system data security and underground sensitive data. The practical application results show that the system can provide high-precision real-time position information of various underground targets, and provide important data support for the working face limit monitoring system, human-machine approach protection device, auxiliary transportation system and automatic driving system.

Mine underground space modeling method based on semantic multi-scale

LI Wenjing, ZHANG Xinxin, LIN Zhiyong, QIU Li, QIU Liqiang

2022, 48(3): 129-134. doi: 10.13272/j.issn.1671-251x.2021110012

<Abstract>(166) <HTML> (39) <PDF>(15)

Abstract:
In order to solve the problems of semantic-based underground mine entity modeling method, such as the lack of detail level division, the small degree of freedom of model configuration, and the lack of multi-scale fine expression, parametric modeling and semantic multi-scale ideas are applied to the construction of mine multi-level of detail (LOD) model, and a mine underground space modeling method based on semantic multi-scale is proposed. It is determined that the modeling object is the entity element in mine underground space. The modeling objects are divided into roadway model and in-roadway model according to the position of the entity element. The roadway model comprises a roadway main body model and other artificial structure models, and the in-roadway model comprises a mine facility model and an equipment model. The different semantic classes are defined according to the semantic information of the entity elements. The semantic classes are divided into families, and then the families are decomposed into component elements according to their functions. Each semantic class is described by quantifiable indicators such as semantic attributes, geometric attributes, appearance attributes and characteristic attributes. The mine LOD model is designed, which includes six levels of discrete LOD models, namely roadway network model, roadway rough model, roadway fine model, main facility model in roadway, main equipment model in roadway, and other equipment models in roadway. Combining the discrete LOD model with various attributes can clearly show the level of detail and the primary and secondary relationships of the mine LOD model. The mine underground space modeling method based on semantic multi-scale can provide entity element models with different detail richness, reduce the computational complexity of scene rendering and improve the efficiency and flexibility of model construction.

2022 Vol. 48, No. 3

Submission System

Latest AcceptedMore>