工矿自动化

Overview of time synchronization technology for underground coal mine IoTs perception layer

YUAN Liang, CHEN Zhenping

2021, 47(11): 1-8. doi: 10.13272/j.issn.1671-251x.17845

<Abstract>(133) <HTML> (28) <PDF>(25)

Abstract:
Time synchronization is the basis and prerequisite for precise information perception in intelligent mines.Many characteristics of underground space in coal mines, such as narrow and long terrain and uneven surface of the roadway, can cause large cumulative effect of synchronization error and poor reliability of signal transmission, which brings great challenges to the research of time synchronization technology among wireless nodes.Two basic time synchronization methods, hierarchical time synchronization and distributed time synchronization method, are introduced in this paper.The special requirements of time synchronization methods for underground coal mine IoTs are analyzed.In addition to the convergence and synchronization precision, the energy efficiency, the topology robustness and the scalability of the synchronization algorithm need to be considered as well.The method should have less communication volume, longer synchronization period and certain topology robustness.Moreover, the method should be able to reduce the cumulative effect of synchronization error caused by large network diameter, and adapt to impact of network scale changes.The current research status of time synchronization of underground coal mine IoTs perception layer is analyzed, and it is concluded that the current research results mainly focus on network structure, synchronization precision and synchronization energy consumption.The research direction of time synchronization technology for underground coal mine IOTs perception layer is prospected, and it is pointed out that the focuses of future research is to design a time synchronization method with certain robustness to topology and time delay in the context of the particularity of underground communication environment and space environment in coal mine: ① It is suggested to improve the robustness of time synchronization method to topology from the perspective of topology dynamic maintenance.② It is advised to improve the convergence speed of consistent time synchronization method from the perspective of communication topology virtual construction.③ It is proposed to improve the robustness of time synchronization method to transmission delay from the perspective of timestamp processing and matrix completion.

Research on intelligent mining in Madiliang Coal Mine

XU Rijie, YANG Ke, WU Jinsong, KAN Lei

2021, 47(11): 9-15. doi: 10.13272/j.issn.1671-251x.2021080034

<Abstract>(141) <HTML> (26) <PDF>(28)

Abstract:
The existing research results of intelligent mining in coal mines have not been combined with the production practice to specify the application of key technologies of intelligent mining in coal mines.Taking the Madiliang Coal Mine as the engineering background, the key technologies and application effects of the construction achievements of intelligent mining in the coal mine named ten intelligent systems are described.The systems include intelligent dispatching remote centralized control system, equipment intelligent early warning and remote consultation system, intelligent coal mining system, intelligent heading system, intelligent belt transportation system, unattended integrated coal transportation and sale control system, intelligent traffic safety control system, Internet + remote office system, Internet of things + intelligent storage express service system and intelligent ventilation system.The key problems in intelligent mining in coal mines at this stage are pointed out in this paper, which include the urgent need to change the ideology and concept, large initial investment, unbalanced input-output ratio, poor adaptability of mining mode, unsound personnel training system and insufficient key technology innovation.In order to solve the above problems, it is proposed that the mutual collaboration between intelligent subsystems should be further enhanced, the research of intelligent robots should be promoted, the independent perception, analysis and decision-making capabilities of equipment should be improved, and the top-level architecture of intelligent coal mines and big data application centers should be built so as to realize intelligent coal mining, transportation and sales, improve mine production efficiency, ensure the safety of personnel, and achieve the goal of unmanned(fewer people)underground mining.

Digital coal seam-based precision mining system for fully mechanized working face

LI Xu, WU Xuefei, TIAN Ye, DONG Bo, DANG Enhui

2021, 47(11): 16-21. doi: 10.13272/j.issn.1671-251x.2021050066

<Abstract>(129) <HTML> (15) <PDF>(21)

Abstract:
The current automatic coal mining technology with memory cutting as the core technology cannot perceive the changes of geological conditions of the working face autonomously, and the shearer can hardly realize automatic height adjustment control according to the changes of coal seam thickness.And it is only a preliminary exploration for precision mining.In order to solve the above problems, a digital coal seam-based precision mining system for fully mechanized working face is developed.Firstly, the system establishes the initial 3D digital coal seam model by using coal mine geological data, working face cutting data and geological realistic data of the working face transportation and return air roadways and the cubic spline interpolation method.Secondly, through the fully mechanized mining equipment inertial navigation system, odometer, radar, angle sensor, the model dynamically senses the actual walking trajectory and cutting trajectory of the shearer, and dynamically corrects the established initial 3D digital coal seam model and generates the straightness detection curve of the scraper conveyor.Finally, according to the revised 3D digital coal seam model, the cutting trajectory curve of the shearer is dynamically planned and sent to the shearer control system to instruct the shearer to automatically adjust the height according to the change of coal seam thickness.Through the scraper conveyor straightness detection curve and hydraulic support travel information comprehensive analysis, the model calculates the displacement deviation of each hydraulic support for the next cut.And the displacement deviation of each hydraulic support for the next cut is sent to the hydraulic support control system of the fully mechanized working face to realize the hydraulic support automatic straightening.The test results show that the system realizes dynamic planning of cutting trajectory of the shearer, automatic tracking control of the height adjustment trajectory and automatic straightening of hydraulic support.The cutting trajectory of the shearer planning knife can be obtained through the CT slice of 3D digital coal seam model.The planned cutting trajectory error is less than 0.2 m.Without human intervention, the automatic cutting time is about 1 h for 250 m long working face, and the automatic cutting time for triangular coal is about 30 min.

Research on path planning algorithm of robot in coal mine based on membrane computing

HUANG Yourui, LI Jing, HAN Tao, XU Shanyong

2021, 47(11): 22-29. doi: 10.13272/j.issn.1671-251x.17847

<Abstract>(111) <HTML> (11) <PDF>(17)

Abstract:
The existing path planning algorithm of robot in coal mine uses fixed step size and serial mode to generate path, which has problems such as low success rate, poor real-time performance and low efficiency.Combining membrane computing(MC)with Informed RRT^* algorithm, this study proposes a path planning algorithm of robot in coal mine, namely MC-IRRT^* algorithm.The algorithm is divided into two stages, namely fast connectivity and path optimization.In the fast connectivity stage, the multi-step cellular membrane structure is constructed, and the step size is adjusted according to the size of the space area.The large step search is used in the area with larger feasible space to accelerate the search speed.The small step search is used in the narrow space to make the search space more refined and improve the success rate of the narrow space path search.In the path optimization stage, a multi-sampling cellular membrane structure is constructed, and multiple basic membranes are calculated in parallel, and the shortest feasible path is searched in parallel in multiple elliptical areas at the same time to save time and improve the efficiency of path optimization.The simple scene experimental results show that compared with Informed RRT^* algorithm, the search efficiency of MC-IRRT^* algorithm in the fast connectivity stage and the path optimization phase is increased by 76% and 40% respectively.The complex scene experimental results show that the path planning of RRT^* algorithm and Informed RRT^* algorithm fails, and both PQ-RRT^* algorithm and MC-IRRT^* algorithm can find feasible paths successfully.Compared with PQ-RRT^* algorithm, the rate of MC-IRRT^* algorithm is increased by 12.79%, and the planned path length is shortened by 8.18%.The MC-IRRT^* algorithm can not only pass through narrow feasible areas quickly, but also can choose to use smaller step at the turning point of the path so as to make the path smoother.

Research on uncalibrated visual servo control of mine intelligent inspection robot

LI Jing, HUANG Yourui, HAN Tao, LAN Shihao, CHEN Hongmao, GAN Fubao

2021, 47(11): 30-39. doi: 10.13272/j.issn.1671-251x.2021030077

<Abstract>(96) <HTML> (23) <PDF>(19)

Abstract:
In order to solve the problem of inaccurate estimation and poor robustness of image Jacobian matrix based on traditional Kalman filtering(KF)in the uncalibrated visual servo control of mine intelligent inspection robot, Kalman filtering algorithm with long and short-term memory(LSTM)(KFLSTM algorithm)is proposed.The KFLSTM algorithm uses the LSTM to compensate for the estimation error generated by the KF algorithm, uses the filter gain error, state estimation vector error and observation error for online training of the LSTM, and uses the trained LSTM model for optimal estimation of the Jacobian matrix to improve the real-time and robustness of visual servo control by improving the accuracy and stability of the Jacobian matrix estimation.The uncalibrated visual servo model based on the KFLSTM algorithm is established, and the most optimal Jacobian matrix is used as the input of the controller, which makes the controller output more accurate joint angular velocity so as to control the real-time operation of the manipulator.The KFLSTM algorithm is applied to the six-degree-of-freedom visual servo simulation experiment of the mine intelligent inspection robot.The results show that the image error convergence speed obtained by the KFLSTM algorithm is 100%-142% higher than that of the traditional KF algorithm, the image characteristic error is smaller, the positioning precision is 0.5 pixels, and the robot end effector moves smoothly.Moreover, the method has strong anti-noise interference capability, which can improve the precision and efficiency of the mine intelligent inspection robot effectively and enhance its stability and safety.

Attitude control of mine inspection unmanned helicopter based on cellular membrane computing

XU Jiachang, HUANG Yourui, LI Hongjin, LIU Yu, HAN Tao

2021, 47(11): 40-44. doi: 10.13272/j.issn.1671-251x.17846

<Abstract>(61) <HTML> (14) <PDF>(11)

Abstract:
The effective attitude control of mine inspection unmanned helicopter is an important manifestation of the pros and cons of inspection capabilities.The existing unmanned helicopter attitude control changes along with the application scene, and the perturbation changes with it, resulting in the unmanned helicopter attitude fluctuation amplitude and error become larger.In order to solve the above problems, the cellular membrane computing is used to realize the attitude control of mine inspection unmanned helicopter.According an underground unmanned helicopter dynamics model, the unmanned helicopter attitude dynamics model is constructed.The cellular membrane system suitable for the underground unmanned helicopter attitude model is constructed, and the unmanned helicopter attitude membrane controller(MC)is designed.Through flight experiments over the ground and in simulated roadway, the effect of MC on the attitude control of unmanned helicopters is verified.And compared with traditional sliding mode controller(TSC)and linear feedback controller(LFC), the results are listed as follows.In the experimental environment over the ground, the attitude angle of the unmanned helicopter under MC is controlled at-0.8-0.8 rad, and the attitude fluctuation amplitude is less than that of the TSC and the LFC.In the simulated roadway environment, the attitude angle of the unmanned helicopter under MC is controlled at-1.8-2.0 rad, and the fluctuation amplitude becomes smaller.The attitude angle errors of unmanned helicopter under MC are smaller than those of TSC and LFC.

Research on trajectory planning algorithm of manipulator arm of coal mine rescue robot

HAN Tao, LI Jing, HUANG Yourui, XU Shanyong, XU Jiachang

2021, 47(11): 45-52. doi: 10.13272/j.issn.1671-251x.17844

<Abstract>(106) <HTML> (12) <PDF>(15)

Abstract:
In order to solve the problems of unreasonable trajectory planning of rescue robot manipulator arm and slow convergence speed of the planning method in the complex environment of coal mines, a trajectory planning algorithm of manipulator arm of coal mine rescue robot based on grey wolf optimization with cuckoo search(CS-GWO)is proposed.With the quintic polynomial interpolation as the basic trajectory planning method, the trajectory planning is carried out in the manipulator arm joint space, and the obtained trajectory is optimized by the CS-GWO algorithm to realize the time-energy optimal trajectory planning of the manipulator arm.The CS-GWO algorithm integrates the two perturbation process of the cuckoo search(CS)algorithm into the position update method of the grey wolf optimization(GWO)algorithm.Combined with the Lévy flight mode of the CS algorithm and the characteristics of the random update of the nest position, the algorithm enables the wolves to randomly jump out of the local search area in the process of approaching the prey, expands the search range, avoids the algorithm from falling into the local optimal solution, and enhances the GWO algorithm's global search capability.Matlab simulation results show that the CS-GWO algorithm can improve the convergence speed of the CS algorithm and the global search capability of the GWO algorithm effectively, with better stability and better overall performance.The use of the manipulator arm trajectory planning algorithm can obtain a time-energy optimal trajectory.The curves of angular displacement, angular velocity, and angular acceleration of each joint are smooth and continuous, which solves the optimal trajectory planning problem of manipulator arm of rescue robot in the complex environment of coal mines effectively.

Research on the predictive fault diagnosis of mine ventilator based on digital twin and probabilistic neural network

JING Haixiang, HUANG Yourui, XU Shanyong, TANG Chaoli

2021, 47(11): 53-60. doi: 10.13272/j.issn.1671-251x.17852

<Abstract>(186) <HTML> (36) <PDF>(19)

Abstract:
In order to solve the problems of poor predictability and low accuracy in the current fault diagnosis methods of mine ventilator, a predictive fault diagnosis method of mine ventilator based on digital twin and probabilistic neural network(PNN)is proposed.Unity3D, 3dsMax and SciFEA are used to build the digital twin model of ventilator to simulate the structural characteristics, physical properties and operation rules of the real ventilator, and the method uses PREspective to communicate with the PLC of the ventilator in real time to map the operation status of the ventilator to the digital twin model in real time.Based on the digital twin model of the ventilator, combined with expert knowledge, machine learning and historical data, the study constructs a predictive fault diagnosis model of the ventilator.The model continuously learns and updates the model parameters by analyzing the relationship between the real-time data and the operation status of the ventilator.The improved whale optimization algorithm(IWOA)is used to obtain the optimal value of the smoothing factor through the biological behaviors of surrounding prey, preying and searching prey, and assigns the optimal value to the PNN.The optimized PNN is applied to perform predictive fault diagnosis of the ventilator, and the result of the predictive fault model of the ventilator is compared with the actual situation to judge whether the results match the actual situation.If the diagnosis is wrong, the predictive fault diagnosis model needs to be corrected until the fault judgment is accurate.The experimental results show that compared with the PNN fault diagnosis accuracy optimized by the genetic algorithm(GA), particle swarm optimization algorithm(PSO)and whale optimization algorithm(WOA), the fault diagnosis accuracy of PNN optimized by IWOA reaches 97.5%, indicating that the predictive fault diagnosis method of mine ventilator based on digital twin and PNN can meet the requirements of real-time and accuracy of ventilator fault diagnosis.

Conveyor belt damage detection method based on improved YOLOv4

ZHOU Yujie, XU Shanyong, HUANG Yourui, TANG Chaoli

2021, 47(11): 61-65. doi: 10.13272/j.issn.1671-251x.17843

<Abstract>(176) <HTML> (26) <PDF>(24)

Abstract:
In order to solve the problems of low detection precision, slow detection speed and lack of damage detection for small areas in existing conveyor belt damage detection methods, a conveyor belt damage detection method based on improved YOLOv4 is proposed.Based on YOLOv4, this method improves the PANet path fusion network part, increases the fusion with the shallow characteristic layer, increases the fusion of the original 3 scales of the characteristic layer to 4 scales, improves the characteristic extraction capability of the model for conveyor belt damage, and improves detection precision.The number of convolutions after fusion of each characteristic layer in the PANet part is reduced from 5 to 3 so as to reduce the amount of calculation and improve the detection speed.The conveyor belt damage images are labeled and input into the improved YOLOv4 model for training and testing.The experimental results show that the conveyor belt damage detection method based on improved YOLOv4 has a fast loss convergence speed and has a good model training effect.Based on improved YOLOv4 conveyor belt damage detection method, the average precision of the conveyor belt tear, surface wear and surface defect detection has reached 96.86%, and the detection speed has reached 20.66 frames/s.Compared with YOLOv4, YOLOv3 and Faster-RCNN, the average precision has increased by 1.4%, 6.35% and 2.16% respectively, and the detection speed has increased by 2.39, 2.34 and 15.25 frames/s respectively.Compared with YOLOv4, the conveyor belt damage detection method based on improved YOLOv4 has higher detection precision and better detection effect for small areas damages.

Support state perception and data processing technology of hydraulic support

PANG Yihui

2021, 47(11): 66-73. doi: 10.13272/j.issn.1671-251x.2021040061

<Abstract>(124) <HTML> (12) <PDF>(17)

Abstract:
The support state perception and data processing of hydraulic support are the key factors to realize adaptive support of hydraulic support and advance prediction and early warning of roof disasters.However, the existing technology mainly performs statistical analysis of hydraulic support initial support force and end-of-loop resistance.There are problems such as insufficient perception information, in-depth data mining and inaccurate prediction and early warning.The relationship between mining stress, roof fracture and hydraulic support load change is analyzed, and the 'five-stage' viewpoint of the destabilization process of roof rock fracture and the 'double-factor' control method of determining the reasonable working resistance of hydraulic support are explained.The characteristic parameters of the support state of the hydraulic support are given, and a technology architecture for the comprehensive perception of the support state of the hydraulic support based on the coupling relationship between the hydraulic support and the surrounding rock is proposed.Moreover, it is pointed out that the non-contact sensor will be the key to solve the problem of inadequate sensing of the support state of the group hydraulic support.In view of the characteristics of low dimension, small number of samples, and correlation of multiple characteristic parameters of support state perception data of hydraulic support, the analysis and prediction method of hydraulic support support state perception data based on template curve library is proposed.Based on the mapping relationship between mining stress and hydraulic support support state, the technology architecture of roof disaster intelligent prediction platform is proposed, which can realize the advance prediction and early warning of abnormal hydraulic support support condition and roof disaster.

Study on the fast fluid supply and return scheme of hydraulic support column in fully mechanized working face

ZHOU Rulin, QIAO Zishi, MENG Lingyu

2021, 47(11): 74-80. doi: 10.13272/j.issn.1671-251x.2021080006

<Abstract>(101) <HTML> (5) <PDF>(15)

Abstract:
The hydraulic support automatic follow-up control should have the performance of high support, fast support moving, large moving distance, etc.Among these performance, under the premise of ensuring stope safety, shortening the time of working face empty roof is an extremely critical issue.However, the current hydraulic support automatic follow-up control has problems such as long action time, lower efficiency than manual operation, control parameters set by experience and other problems, resulting in the slow moving speed of the fully mechanized working face, and poor matching of hydraulic system pressure and flow.In order to reduce the action time of the hydraulic support and improve the moving speed of the fully mechanized working face, the flow-pressure mathematical model of the hydraulic support valve-controlled cylinder unit in hydraulic cylinder extension action transient process is established.The analysis shows that the instantaneous pressure of the hydraulic cylinder extension is mainly related to the supply and return hydraulic pressure, and has a quadratic relationship with time.Based on the above conclusions, three schemes for column fast fluid supply and return named direct supply by column liquid supply valve, two-level control + column fast liquid supply valve, and direct supply by electro-hydraulic controlled reversing valve are presented.The working principles of the three schemes are introduced in detail.The simulation models of hydraulic support based on the three schemes are established in AMESim software, and the stability and rapidity of the three schemes are compared by analyzing the transient pressure and action time of the rod cavity and rodless cavity of hydraulic cylinder when the hydraulic support executes the cycle of column lowering-support moving-column lifting under different schemes.The results show that the pressure curves of the rod cavity and rodless cavity of hydraulic cylinder are basically the same when the hydraulic support executes the cycle of column lowering-support moving-column lifting under the three schemes.It is considered that the stability of the three schemes is basically the same.The total time for the hydraulic support to perform the cycle of column lowering-support moving-column lifting under the direct supply by electro-hydraulic controlled reversing valve is the shortest, which is 9.35 s and is 22.1% shorter than the traditional scheme.Therefore, it is concluded that the direct supply scheme by electro-hydraulic controlled reversing valve is the best scheme.

Research on the protection range of pressure-relief in the mining of upper protective layer

QIN Ruxiang, YANG Ke, CHENG Jian

2021, 47(11): 81-87. doi: 10.13272/j.issn.1671-251x.2021050028

<Abstract>(163) <HTML> (9) <PDF>(10)

Abstract:
At present, the research on the protective layer pressure relief range mainly focuses on the analysis of the evolution characteristics of coal seam stress, deformation and plastic failure and the pressure relief range of the lower protective layer mining.There are few investigations on the protective layer protection effect, and more error of experimental results caused by less points taken in the actual measurement process.In order to solve the above problems, taking the 18125 working face of Pan'er Coal Mine of Huainan Mining Group as the research object, the stress distribution of the protected layer, the expansion and deformation rate of the coal seam roof and floor and the change characteristics of coal seam gas pressure after the mining of the protective layer are studied by numerical simulation calculation and field investigation and analysis methods.The results are listed as follows.① The vertical stress in the direction of the protected layer is symmetrically distributed along the central axis, and the tendency pressure relief zone is elliptical.② After the mining of the upper protective layer working face, the crustal stress relief zone is formed on its floor, the stress of the floor coal rock layer is reduced, and the coal rock layer in the pressure relief zone moves upwards and deforms.Due to the different spacing between the protective layer and the protected layer, there is a gap between the movement of the protected layer and the amount of deformation.The closer to the mining layer, the greater the expansion and deformation of the protected layer, and the more obvious the pressure relief effect of the protected layer.30-60 m behind the working face of the protective layer is the best area for pressure relief and gas extraction of the protected layer.③ According to the relative relationship between the gas pressure observation borehole and the position of the initial cutting hole of the working face of the protective layer and the gas pressure observation results, the maximum effective pressure relief angle of the mining direction of the protective layer is about 69.8°.④ Through numerical simulation and combining with field investigation and analysis, according to the stress distribution of the protected layer, the expansion and deformation rate of the roof and floor of the coal seam and the change characteristics of the coal seam gas pressure, it is concluded that the pressure relief angle of the protected layer is about 60°, and the pressure relief angles of both the upper and lower tendency are 75°.

Analysis and prevention of impact damage in deep goaf roadway under dynamic and static load

TANG Jiebing, JU Wenjun, CHEN Fabing

2021, 47(11): 88-94. doi: 10.13272/j.issn.1671-251x.2021030071

<Abstract>(96) <HTML> (3) <PDF>(8)

Abstract:
The existing research on rock bursts in goaf roadway mainly focuses on the static load caused disaster.However, there is few research on the dynamic load superimposed disaster mechanisms based on static load.In terms of the dynamic load stress wave response of the surrounding rock of the roadway, the damage mode of the roadway is not related with the stress wave disturbance and its mechanical effects.In order to solve this problem, taking 3-1103 working face in Ordos mining area, Inner Mongolia as the research object, the study analyzes the impact damage characteristics of the goaf roadway and the dynamic and static load sources of the rock burst.The goaf roadway is under the 'F' type overburden rock structure on the side of the goaf, and the source of static load is the superimposed stress field of the lateral concentrated support stress and the advanced mining concentrated support stress of the working face.The source of dynamic load is the initial pressure of the basic roof, periodic pressure and the near-field mine earthquake formed by the square area break and the far-field mine seismic release energy.The combined effect of dynamic and static load under the impact roof rock layer can easily induce impact disaster in roadways with different stress fields under high ground stress and stress concentration.The FLAC3D numerical simulation method is used to analyze the stress state of the impact roadway under the dynamic and static load sources of the goaf roadway and the impact of the stress wave of the mine earthquake, and to verify and analyze the field impact damage characteristics in comparison.The numerical simulation results have a strong consistency with the field damage characteristics.During the goaf compaction process, the maximum vertical concentrated stress is transferred from the coal pillar to the side of the roadway side, and the bolt axial force shows an asymmetrical distribution state.During the dynamic load process, the principle stress difference of the roadway surrounding rock is repeatedly loaded and unloaded, the peak particle velocity(PPV)value of the stress wave on the front wave side is larger than that on the back wave side.The shallow stress wave of surrounding rock is reflected and superimposed, the PPV value is consistent with the maximum displacement of the shallow part of the surrounding rock after dynamic load.The surrounding rock of the goaf roadway forms the difference in stress field between the side of the roadway and the coal pillar side as well as the difference in dynamic load stress field in the process of dynamic and static load.According to the damage characteristics of goaf roadway under dynamic and static load and the results of its numerical simulation and validation analysis, the separate source prevention and control measures of static load decompression and load reduction, dynamic load earthquake reduction and energy dissipation are formulated.The measures are roof hydraulic fracturing, roof and floor blasting decompression, decompression of large-diameter boreholes of roadway and reinforcement of roadway surrounding rock.These measures are used to prevent the accumulation of elastic energy of thick and hard roof, weaken the amplitude of stress wave, and improve the surrounding rock stress environment.After taking pressure relief measures, the measured microseismic energy is released in the form of small energy level and multiple frequency.The total microseismic energy is reduced by 49.2% compared with that before pressure relief, the proportion of microseismic small energy events below 10³ J increases from 75% before pressure relief to 89%, the static load of the field roadway surrounding rock is reduced, and there was no sudden change of stress when dynamic and static load are superimposed, which has proved the effectiveness of impact prevention and control measures.

Intelligent fully mechanized mining support technology and equipment for thin-medium-thick coal seam

GAO Xicai, MA Tengfei, WANG Qi, LIU Shuai, ZHANG Xichen, FAN Kai, TANG Jianqiang, HU Bin

2021, 47(11): 95-100. doi: 10.13272/j.issn.1671-251x.2021080037

<Abstract>(196) <HTML> (41) <PDF>(11)

Abstract:
In the context of the complex geological conditions such as large thickness variation of thin-medium-thick coal seam, development of strike fault and broken roof in Southwest China, intelligent fully mechanized mining support technology and equipment for thin-medium-thick coal seam are proposed.Through the implementation of grouting reinforcement and roof-lifting transformation for broken roof in the hanging wall and the footwall of fault layer, as well as the adoption of the coupled support technology of bolt-mesh-anchor combined support+advance reinforcement+blasting roof cutting+pillar hanging net gangue retaining+delayed shotcrete reinforcement+finishing wall in gob-side entry retaining, the stability of the roadway is greatly improved.A lateral self-advancing advanced support group consisting of eight advanced supports and two end supports is designed to realize the coordination and cooperation of the roof support at the end of the working face and the rapid advancement of the advanced supports.The intelligent fully mechanized mining equipment for thin-medium-thick coal seam and its optimal layout scheme are proposed.When the mining height at both ends of the working face is less than the height of the roadway, a cushion frame is used to support the head and tail of the shearer.The length of the scraper conveyor head and tail beyond the coal wall is controlled at 800 mm to ensure that the undercover amount reaches 97 mm so as to clear the floating coal in time.The scraper conveyor head is equipped with a trailer parallel to the floor, and the scraper conveyor head and tail are directly pushed as a whole through the transition support auxiliary pushing device, which effectively solves the problem of mutual interference between the rocker arm of the shearer and the scraper conveyor.The study proposes an active preventive intelligent coal cutting technology in the fault zone, which is composed of end cutting triangular coal following section process and middle oblique cutting following section process.The technology uses half cutting depth and fractional cutting methods to improve the safe coal cutting speed of the shearer under the fault zone condition.

The technology of gob-side entry retaining supported by flexible formwork wall with roof cutting and pressure relief for composite roof in deep mine

SHEN Binxue, ZHOU Hongfan, ZHU Lei, WU Yuyi, QIU Fengqi, WANG Guopu, GUO Lin, HUANG Jianbin

2021, 47(11): 101-106. doi: 10.13272/j.issn.1671-251x.2021040072

<Abstract>(96) <HTML> (5) <PDF>(11)

Abstract:
In Lianghuai area of China, due to the influence of the large buried depth of the mine and the complicated roof conditions, when gob-side entry is retained, the roof deformation of the gob-side entry retaining is large, the coal side is easily extruded and the floor heave is serious.In order to solve this problem, taking the 360804 fully mechanized working face of Xinji No.1 Mine as the research object, the technology of gob-side entry retaining supported by flexible formwork wall with roof cutting and pressure relief is proposed.The bilateral cumulative energy blasting technology is used in the advance working face to carry out pre-splitting of the roof of the gob-side entry retaining to reduce the roof stress of the gob-side entry retaining effectively.With the continuous mining of the working face, when the working face coal wall is lagged a certain distance, the flexible formwork wall made of concrete is used to support the roadway side in order to achieve strong support for the roof of the gob-side entry retaining.The field application results show that there are two obvious fractures at different heights of blasting hole, which indicates that the blasting roof cutting effect is good.The maximum separation of the shallow part of the roadway roof is 7 mm, the maximum separation of the deep part is 19 mm, and the roadway roof support is relatively intact.The roadway roof and floor deformation is 430 mm, the two sides deformation is 487 mm, the roadway surrounding rock deformation is within the allowable range, and the roadway retaining effect is good.

Research on coal and gangue detection algorithm based on improved YOLOv5s model

SHEN Ke, JI Liang, ZHANG Yuanhao, ZOU Sheng

2021, 47(11): 107-111. doi: 10.13272/j.issn.1671-251x.17838

<Abstract>(198) <HTML> (16) <PDF>(51)

Abstract:
In order to solve the problems of slow detection speed and low detection precision of the existing deep learning-based coal and gangue target detection methods, an improved YOLOv5s model is proposed and applied to coal and gangue target detection.The YOLOv5s model is improved by embedding self-calibrated convolutions(SCConv)in the Backbone area of YOLOv5s model as the characteristic extraction network, which can better fuse multi-scale characteristic information.Because the size of coal and gangue is too small compared with the whole image, the Neck area of YOLOv5s model is appropriately simplified, and the 19×19 characteristic map branches suitable for detecting larger size objects are deleted, thus reducing model complexity and improving the real-time detection performance.The anchor box obtained by clustering with K-means algorithm is linearly scaled to improve the model detection precision.The experiment of coal and gangue target detection based on improved YOLOv5s model shows that compared with YOLOv5s model, the improved YOLOv5s model can detect the corresponding coal and gangue accurately.The size of improved YOLOv5s model is reduced by 1.57 MB, the frame rate is increased by 2.1 frames/s, and the average precision is improved by 1.7%, indicating that the improved YOLOv5s model has improved both detection precision and detection speed.

Test of roof interception directional drilling for close distance coal seam group gas control in Qidong Coal Mine

ZHANG Chaoju, FANG Jun, YANG Yali, WANG Xian, YANG Xiaoji

2021, 47(11): 112-118. doi: 10.13272/j.issn.1671-251x.2021020016

<Abstract>(66) <HTML> (4) <PDF>(6)

Abstract:
In the existing methods of close distance coal seam group gas control, there are problems such as large engineering quantities, high cost and long cycle.In order to solve the above problems, taking the 94 mining area of Qidong Coal Mine as the research object, a gas control method by using roof interception directional drilling is proposed.Firstly, the roof interception directional drilling with multiple upward branch holes is constructed in the roof of the mining coal seam.Secondly, the upward branch holes are used to extract the gas from the upper adjacent coal seam in advance.Finally, the main hole is used to extract the pressure relief gas from the upper adjacent seam and the gas from the working face of the mining coal seam and the goaf during the coal seam mining.This method improves the gas extraction effect of the close coal seam group from two aspects of pre-extraction and mining pressure relief extraction, and solves the problems of gas occurrence parameter measurement and directional drilling and hole protection in complex fractured formation.In order to solve the problems of the design and construction of roof interception directional drilling, the method adopts directional drilling for coal seam exploration and pressure maintaining sealed coring technology, composite directional drilling and composite slag removal technology, and steel screen pipe completion technology to realize efficient hole formation of roof interception directional drilling for close coal seam group and long-distance accurate gas measurement.Field tests are carried out in the 94 mining area of Qidong Coal Mine.One roof interception directional drilling is completed, the main hole depth is 608 m, the construction branch holes are 6, the gas content is tested by sealed coring technology twice, and the lower protective screen pipe is 485 m.The gas extraction test is carried out for 207 days.The initial gas extraction net amount is 0.35 m³/min.After 30 days of extraction, gas extraction net amount gradually drops to below 0.1 m³/min.After 65 days of extraction, the overall gas extraction net amount remains stable.The test results show that the roof interception directional drilling can pre-extract the adjacent coal seam gas effectively, reduce the coal seam gas content in advance, and reduce the pressure relief gas emission from the source during the later mining of the working face.

Research on lightweight coal and gangue target detection method

DU Jingyi, SHI Zhimang, HAO Le, CHEN Rui

2021, 47(11): 119-125. doi: 10.13272/j.issn.1671-251x.2021040029

<Abstract>(118) <HTML> (8) <PDF>(26)

Abstract:
In order to solve the problems of low precision, poor real-time performance and easy missing detection of small targets in the current deep learning-based coal and gangue target detection methods, the SSD model is improved by using lightweight network, self-attention mechanism and anchor frame optimization method to construct Ghost-SSD model, and then a lightweight coal and gangue target detection method is proposed.The Ghost-SSD model is based on the SSD model, and the GhostNet lightweight characteristic extraction network is used to replace the main network layer VGG16 so as to improve the detection speed of coal and gangue targets.In order to solve the problem that the shallow characteristic map contains more background noise and insufficient semantic information, the self-attention module is introduced to enhance the characteristics of the shallow characteristic map and increase the focus on the foreground region.Moreover, the dilated convolution is applied to increase the receptive field of the shallow characteristic maps and enrich the semantic information of the shallow characteristic maps.The K-means algorithm is used to cluster the anchor frames, optimize the size of the anchor frame, and further improve the precision of coal and gangue target detection.The experimental results show that when the Ghost-SSD model is applied in coal and gangue target detection, the mean average precision is 3.6% higher than that of the SSD model, the detection speed is increased by 75 frames/s, and the detection precision and speed are better than that of the Faster-RCNN and Yolov3 models.Moreover, the model has a good detection effect on small coal and gangue targets.

Research on bearing residual life prediction method of coal mine machinery equipment

SUN Yongxin

2021, 47(11): 126-130. doi: 10.13272/j.issn.1671-251x.17834

<Abstract>(80) <HTML> (5) <PDF>(15)

Abstract:
The bearing residual life prediction of coal mine machinery equipment is of great significance for equipment maintenance.The existing bearing residual life prediction methods are either difficult to establish an accurate mathematical model of bearing failure, or the prediction precision is constrained by the sample completeness and accuracy.And the degradation characteristic quantity usually adopts time domain and frequency domain indicators, which are greatly affected by the harsh working environment of coal mine machinery equipment, resulting in low prediction precision.In order to solve this problem, a bearing residual life prediction method of coal mine machinery equipment based on empirical mode decomposition(EMD)and grey model(GM)is proposed.EMD is used to filter the vibration acceleration signal of coal mine machinery equipment bearings.The root mean square of the filtered signal is extracted as the degraded characteristic quantity representing the bearing health state so as to form the degraded characteristic quantity sequence.The GM is trained with the degraded characteristic quantity sequence, then the GM bearing residual life prediction model is established to predict the change trend of the degraded characteristic quantity, and the time interval when the degraded characteristic quantity reaches the set threshold is used as the residual life prediction value.The test bench and engineering application results show that the method can effectively predict the bearing residual life of coal mine machinery equipment with high prediction precision, and the prediction results can guide field equipment maintenance.

Research on the influence of coal mine dust concentration on UWB ranging precision

DING Zhen, ZHANG Yuchen

2021, 47(11): 131-134. doi: 10.13272/j.issn.1671-251x.17859

<Abstract>(121) <HTML> (12) <PDF>(21)

Abstract:
The environment of the fully mechanized working face in coal mines is harsh and the dust concentration is high.When ultra wide band(UWB)is used for positioning, it is easy to be interfered by dust.UWB ranging will have certain errors, so the positioning precision cannot meet the requirements of intelligent coal mines.To order to solve this problem, the principle of UWB ranging is analyzed, and it is pointed out that the main factors affecting the precision of UWB ranging are multipath effect and non-line-of-sight propagation.The generation of multipath effect and non-line-of-sight propagation is closely related to dust concentration, and the influence of dust concentration on the precision of UWB ranging in coal mines is explored through experiments.The experimental results show that the UWB ranging error increases as the dust concentration increases, and the growth rate of UWB ranging error accelerates.

2021 Vol. 47, No. 11

Submission System

Latest AcceptedMore>