2023 Vol. 49, No. 4

column
  Previous Issue | Next Issue 
Display Method:
Cover Catalogue
Academic Column of Editorial Board Member
Analysis and testing of wireless transmission attenuation in coal mine underground and research on the optimal operating frequency band
SUN Jiping, LIANG Weifeng, PENG Ming, ZHANG Gaomin, PAN Tao, ZHANG Hou, LI Xiaowei
2023, 49(4): 1-8. doi: 10.13272/j.issn.1671-251x.18093
<Abstract>(873) <HTML> (119) <PDF>(90)
Abstract:
The application of technologies such as 5G, UWB, ZigBee and WiFi6 in coal mine mobile communication, personnel and vehicle positioning, and wireless transmission has promoted coal mine safety production and intelligent construction. However, due to the limitations of electrical explosion-proof measures, the wireless transmission power underground in coal mines is not greater than 6 W, which restricts the wireless transmission distance in the mine, and increases the usage of base stations and system costs. It is not convenient for system use and maintenance. Under the condition that the wireless transmission power is limited by electrical explosion-proof measures, selecting a wireless operating frequency band with smaller transmission attenuation can effectively increase the wireless transmission distance, reduce the usage of base stations, and reduce system costs. In order to meet the needs of selecting and optimizing the working frequency band of wireless transmission in mines, wireless transmission tests in the 700 MHz to 6 GHz frequency band are conducted in the auxiliary transportation roadway and fully mechanized working face of the Sandaogou Coal Mine of the National Energy Group. The test results are analyzed and the optimal frequency band for wireless transmission in mines is proposed. ① The optimal operating frequency band for wireless transmission in auxiliary transportation roadways is 700 to 910 MHz. ② The optimal working frequency band for wireless transmission in fully mechanized working faces is 700 to 1 710 MHz. ③ The wireless transmission attenuation of the auxiliary transportation roadway is smaller than that of the fully mechanized working face. As the frequency increases, the difference in wireless transmission attenuation between the auxiliary transportation roadway and the fully mechanized working face decreases. ④ The optimal working frequency band for wireless transmission in mines is 700 to 1 710 MHz.
F5G industrial optical ring network communication technology and its application and prospect in coal mines
ZHAO Tingzhao, YUAN Shengfu, LI Chaofei, HOU Shangwu, HOU Zhentang, XIE Zhidong
2023, 49(4): 9-14. doi: 10.13272/j.issn.1671-251x.18026
<Abstract>(957) <HTML> (54) <PDF>(68)
Abstract:
The traditional wired communication network in coal mines has problems such as fixed bandwidth, low effective utilization, high time-delay, and inflexible system configuration. This cannot meet the development needs of intelligent business in coal mines. Mining 5G and WiFi6 wireless communication has the problem of large roadway attenuation and lower reliability than wired communication. According to the characteristics of F5G (the fifth generation fixed networks) industrial optical ring network communication technology, it is pointed out that F5G industrial optical ring network communication technology is the development trend of mine wired communication. Two key technologies of F5G industrial optical ring network are introduced. They are 10 Gibit/s PON (passive optical network) technology and digital quick optical distribution network (DQ ODN) technology. The advantages of F5G industrial optical ring network and traditional wired network in network delay, electrical safety, business safety, construction safety and maintenance safety are compared. Based on the demand characteristics and construction examples of F5G industrial optical ring network communication technology applied in coal mines, this paper analyzes the specific applications of F5G industrial optical ring network communication technology in scenarios such as underground industrial remote control, high-definition video transmission, industrial network migration, remote fault diagnosis, and wireless network signal transmission. It points out the shortcomings and prospects of F5G industrial optical ring network communication technology in coal mines. ① There are few types of mining equipment based on F5G industrial optical ring network communication technology. ② There is still room for improvement in the adaptation of scenarios and different business types. ③ The F5G industrial optical ring network communication technology is the same as the traditional Ethernet ring network communication interface in terms of system interface and protocol. The terminal equipment can be accessed and used without changing the adaptation. It is an effective solution for the industrial network in the future coal mine scenario. ④ Coal mines should build F5G pilot projects based on their own actual conditions to support the application and research of F5G industrial optical ring network communication technology with actual scenarios.
Research on intelligent hazard early warning architecture and key technologies for coal mine
DING Zhen, LI Haodang, ZHANG Qinghua
2023, 49(4): 15-22. doi: 10.13272/j.issn.1671-251x.2022090016
<Abstract>(1341) <HTML> (69) <PDF>(176)
Abstract:
The monitoring alarming or early warning of five major hazards in coal mines are initially achieved in China. The hazards include gas, fire, water damage, roof and dust. However, the level of intelligence is relatively low, and it does not have the capability to self-analyzing and making decisions. Under the framework of the concept of intelligent mines, the connotation of intelligent hazard early warning for coal mine is elaborated. The four features of intelligent hazard early warning are proposed: accurate perception data, intelligent early warning models, collaborative early warning and hazard prevention, and efficient emergency decision-making. The overall architecture of intelligent hazard early warning for coal mine is designed. It consists of four layers: perception control layer, transmission layer, storage analysis layer, and application layer. It can achieve intelligent early warning and control of various hazards. It adopts the data processing principles of unified standards, unified collection, unified storage, unified analysis, and unified presentation. It can achieve multi-source heterogeneous data sharing and deep mining utilization for intelligent hazard early warning, so as to solve problems such as isolated data island and data chimney. Based on the overall architecture of intelligent hazard early warning for coal mine, an intelligent hazard early warning business process has been designed to provide reference for intelligent hazard early warning design. The key technologies of intelligent hazard early warning of coal mine are summarized. The key technologies include precise monitoring and early warning of gas, fire, water damage, roof and dust, and intelligent hazard fusion early warning technology. The difficulties and development directions of each key technology are analyzed. Taking intelligent hazard early warning platform of Qinglongsi Coal Mine as an example, the application effects of intelligent hazard early warning technology in monitoring, hazard early warning, emergency rescue and hierarchical control are demonstrated. It is proposed to conduct in-depth research on precise hazard perception technology and equipment, multi field coupling hazard mechanism, and self-learning and adaptive technology of warning models to achieve intelligent hazard early warning in advanced stages.
Overview
Research summary on coal industry internet technology
YANG Jun, ZHANG Chao, YANG Huifan, GUO Yinan
2023, 49(4): 23-32. doi: 10.13272/j.issn.1671-251x.18081
<Abstract>(846) <HTML> (62) <PDF>(93)
Abstract:
The coal industry internet is an important engine to accelerate the high-quality development of the coal field. It can effectively drive the equipment intelligence and industry digitization in the energy field. The architecture of the coal industry internet is given. The research status and development direction of the coal industry internet technology are analyzed from five aspects: perception layer, transmission layer, empowerment platform, industrial APP, and information security. The perception layer has made progress in achieving ultra-low power consumption, precise perception, high reliability, and automatic energy capture. However, there are still problems such as single perception method and susceptibility to environmental factors. It cannot fully meet the needs of ubiquitous perception in mines. The intelligence level of the perception layer can be further improved through the development of new sensors, low-power and energy collection technologies, anti-electromagnetic interference technologies, and intelligent perception technologies. The existing Ethernet, 4G, WiFi and other technologies in the transmission layer cannot meet the high reliability, high bandwidth, and low latency transmission requirements of intelligent mines. 5G technology can meet the ubiquitous sensing requirements of the entire mine. However, there are still problems in underground applications such as limited maximum RF power and the incapability to reliably respond to underground emergency scenarios. Therefore, currently, 5G cannot fully replace traditional underground communication networks. The empowerment platform is the center and core of the coal industry internet to promote intelligence. It points out that big data is the key element of the empowerment platform. The mechanism model and diagnostic decision-making model of the coal industry are the soul of the empowerment platform. Digital twin technology can empower the production, decision-making, management and other links of the coal industry. Industrial APP can provide services for various links in the coal industry chain, and help the coal industry overcome challenges such as high risks, difficulty in process inheritance and innovation, and difficulty in industrial chain collaboration. However, the development and application of industrial APP in the coal industry are still immature. Information security is the guarantee for the intelligent construction of coal mines, and measures need to be taken from physical information security, network information security, system information security, data information security, and application information security to improve the level of security protection.
Research on key technologies of coal mine intelligent excavation
LI Fei, ZHANG Lin, SHANG Yuqi, KONG Dezhong, WANG Yuliang, CHEN Long, ZHANG Zhiwei
2023, 49(4): 33-41. doi: 10.13272/j.issn.1671-251x.2022100062
<Abstract>(2271) <HTML> (96) <PDF>(160)
Abstract:
This paper introduces the research results of the main coal mine roadway excavation technologies in recent years. The technologies include cantilever roadheader comprehensive excavation technology, continuous shearer tunneling technology, and integrated excavation technology. The applicability and promotion value of these three main roadway excavation technologies in China is analyzed. The following points are pointed out. ① The comprehensive excavation technology of the cantilever roadheader can only "excavate before anchoring". The excavation and support processes cannot be carried out simultaneously, which limits the excavation efficiency. ② The continuous shearer tunneling technology can only be carried out in near horizontal coal seam conditions. It has certain requirements for the stability of the roof. The applicability is weak. ③ The integrated excavation technology is only suitable for rapid excavation of single roadways with large cross-sections. The integrated excavation and anchoring machine used is large and expensive. The machine has certain requirements for the stability of the bottom plate of the excavated roadways. Compared to the continuous mining machine excavation technology, the integrated excavation technology has a good application prospect in China. Expanding the excavation function of the original roadheader to the function of excavation and support can promote the research and application of integrated excavation and anchoring technology. The study analyzes the research achievements of intelligent cutting, remote intelligent monitoring, and intelligent collaborative control in the robotized intelligent excavation technology of coal mine roadways in recent years. The following points are concluded. ① Intelligent cutting technology mainly focuses on the research of adaptive recognition of coal and rock. ② Remote intelligent monitoring technology has evolved from remote real-time monitoring to remote visual monitoring. The development of virtual simulation technology visualizes the situation of underground excavation roadways on the ground. And it feeds back control signals to the excavation working face to remotely synchronize and control the excavation working face roadheader unit. This becomes an important symbol of the current intelligent remote monitoring of roadway excavation. ③ There is currently limited research on intelligent collaborative control technology. This study explores the development directions of intelligent coal mine roadway excavation. The directions include strengthening the integration and collaboration of excavation equipment, modular combination of equipment, 5G mining wireless network equipment, remote intelligent monitoring system for excavation, and research on difficult and slow excavation roadway excavation engineering.
Research and prospect of UWB radar wave transmission attenuation based on borehole rescue
WEN Hu, LIU Shengkai, ZHENG Xuezhao, CAI Guobin, HUANG Yuan, ZHANG Hui
2023, 49(4): 42-49. doi: 10.13272/j.issn.1671-251x.18053
<Abstract>(240) <HTML> (52) <PDF>(30)
Abstract:
Obtaining the position of underground trapped personnel quickly and precisely is a key issue for life information detection in the early stage of borehole rescue. In the process of vertical drilling and rescue, due to the collapse of the roadway in the detection area or the displacement of the final hole position, it is impossible to obtain the position of the trapped personnel quickly and accurately. It delays the golden time of rescue and affects the safety of personnel. Through conducting a UWB radar wave transmission attenuation study, a rescue plan can be quickly formulated for on-site rescue commanders. This paper analyzes the current situation and demand of UWB radar wave application in mine borehold rescue. Combined with the background of mine borehold rescue, it is pointed out the attenuation law of UWB radar wave transmission. The study analyzes the influence of the characteristic parameters of the medium on the attenuation of radar wave transmission from the perspective of anisotropy of the medium. The influence of dielectric parameters on radar wave transmission attenuation is analyzed from four aspects: dielectric constant, conductivity, magnetic permeability and spatiotemporal variation. The influence of radar characteristic parameters on radar wave transmission attenuation is analyzed from two aspects: radar frequency and polarization. Based on the above analysis, it is pointed out that there are few studies on the simultaneous penetration of UWB radar waves through anisotropic media such as coal and rock masses and the mechanism of media propagation and attenuation. There are few theories and experiments on UWB radar wave transmission attenuation in complex and changeable underground or simulating disaster environments. And there are few summaries of relevant laws. The mapping relationship database between key parameters and influencing factors of UWB radar waves is not yet complete. The key technologies to be studied in the future are given as follows. It is suggested to conduct research on anisotropic media such as coal and rock masses at both macro and micro levels. It is suggested to establish an experimental simulation system for radar wave transmission attenuation under catastrophic environmental conditions. It is suggested to add research on UWB radar signal propagation characteristics and channel modeling numerical simulation in unstructured environments after disasters.
Analysis and Research
A scale-adaptive target tracking method for coal mine underground based on cloud-edge collaboration
MU Qi, HAN Jiajia, ZHANG Han, LI Zhanli
2023, 49(4): 50-61. doi: 10.13272/j.issn.1671-251x.2022100093
<Abstract>(215) <HTML> (60) <PDF>(26)
Abstract:
The moving targets in coal mine underground monitoring videos often have significant scale changes and deformations. This results in low accuracy of target tracking algorithms based on computer vision. Moreover, the massive amount of video data makes it difficult for centralized cloud-based data processing methods to meet the real-time requirements of target tracking. In order to solve the above problems, a scale-adaptive target tracking method for coal mine underground based on cloud-edge collaboration is proposed. A scale-adaptive target tracking algorithm based on depth estimation is designed. The scale-adaptive target tracking is achieved by constructing a depth-scale estimation model, which uses target depth values to estimate scale values. The problem of low tracking accuracy caused by target scale change and deformation is solved. An intelligent monitoring system architecture based on cloud-edge collaboration is designed. The sub-modules of the scale-adaptive target tracking algorithm, which are divided into fine granularity, are deployed at the edge and cloud of the system according to the required computing resources. The algorithm's operational efficiency is improved through distributed parallel processing at the edge and cloud, solving the problem of poor real-time performance in the centralized data processing. The scale-adaptive target tracking method based on cloud-edge collaboration is applied in coal mine underground video sequences. The tracking performance and real-time performance are verified experimentally. The results show that compared with three classic target tracking algorithms, namely kernel correlation filter (KCF), discriminant scale space tracking (DSST) algorithm, and scale adaptive multiple feature (SAMF) algorithm, the scale-adaptive target tracking algorithm based on depth estimation has higher tracking precision and success rate when there are significant scale changes and deformations in coal mine underground targets. Compared with traditional cloud computing processing methods, the deployment method of scale-adaptive target tracking algorithm based on cloud-edge collaboration reduces the total delay of the algorithm by 32.55%. It effectively improves the real-time performance of target tracking of intelligent monitoring system in coal mine underground.
An enhancement method for low light images in coal mines
KONG Erwei, ZHANG Yabang, LI Jiayue, WANG Manli
2023, 49(4): 62-69, 85. doi: 10.13272/j.issn.1671-251x.2022110054
<Abstract>(469) <HTML> (205) <PDF>(87)
Abstract:
Underground lighting in coal mines is limited. There is a large amount of dust and mist, resulting in low contrast, uneven lighting, weak detail information, and a large amount of noise in the collected images. The image enhancement methods based on traditional models have poor robustness, often causing excessive image enhancement and color distortion. Most image enhancement methods based on deep learning do not consider the noise amplification caused by enhancement. In order to solve the above problems, an enhancement method for low light images in coal mines is proposed. The image enhancement network is constructed by using convolutional neural networks. The network includes feature extraction modules, enhancement modules, and fusion modules. The feature extraction module convolves the input image to varying degrees, extracts multi-level image features, and obtains multiple feature layers. The enhancement module enhances the extracted feature layers through sub-networks to enhance different levels of detail features. The fusion module fuses the enhanced feature layers and outputs enhanced images. Then, through the constraints of the structure loss function, content loss function and area loss function, the image quality is improved. The image color distortion and noise amplification are effectively suppressed to obtain the final enhanced image. The experimental results show that this method can effectively improve the brightness and contrast of low light images in coal mines. The method has strong noise suppression capability, enabling the image to better restore the original details while avoiding overexposure or color distortion.
A method for enhancing low light images in coal mines based on Retinex model containing noise
LI Zhenglong, WANG Hongwei, CAO Wenyan, ZHANG Fujing, WANG Yuheng
2023, 49(4): 70-77. doi: 10.13272/j.issn.1671-251x.2022080047
<Abstract>(342) <HTML> (129) <PDF>(18)
Abstract:
The low light images can lead to many computer vision tasks not achieving the expected results. This can affect subsequent image analysis and intelligent decision-making. The existing low light image enhancement methods for underground coal mines do not consider the real noise of the image. In order to solve this problem, a method for enhancing low light images in coal mines based on Retinex model containing noise is proposed. The Retienx model containing noise is established. The noise estimation module (NEM) is used to estimate real noise. The original image and estimated noise are used as inputs to the illumination component estimation module (IEM) and reflection estimation module (REM) to generate and couple the illumination and reflection components. At the same time, gamma correction and other adjustments are made to the illumination components. And division operations are performed on the coupled image and adjusted illumination components to obtain the final enhanced image. NEM uses a three-layer CNN to perform Bayer sampling on noisy images. It reconstructs them to generate a three channel feature map which is the same size as the original image. Both IEM and REM use ResNet-34 as the image feature extraction network. The multi-scale asymmetric convolution and attention module (MACAM) is introduced to enhance the network's capability to filter details and important features. The qualitative and quantitative evaluation results indicate that this method can balance the relationship between light sources and dark environments, reduce real-world noise's impact, and perform well in image naturalness, realism, contrast, structure, and other aspects. The image enhancement effect is superior to models such as Retinex-Net, Zero-DCE, DRBN, DSLR, TBEFN, RUAS, etc. The effectiveness of NEM and MACAM is verified through ablation experiments.
Intelligent decision-making method for coal caving based on fuzzy deep Q-network
YANG Yi, WANG Shengwen, CUI Kefei, FEI Shumin
2023, 49(4): 78-85. doi: 10.13272/j.issn.1671-251x.2022090068
<Abstract>(168) <HTML> (67) <PDF>(14)
Abstract:
During the coal caving process in the fully mechanized caving face, due to the impact of coal dust and dust water mist on the workers' line of sight, there are problems of over-caving and under-caving in manually controlled coal caving. In order to solve this problem, the tail beam of the hydraulic support is regarded as an intelligent agent, and the coal caving process is abstracted as a Markov optimal decision. A deep Q-network (DQN) is used to make decisions on the action of the coal drawing port. However, there is an overestimation problem in the DQN algorithm. A fuzzy deep Q-network (FDQN) algorithm is proposed and applied to intelligent decision-making of coal caving. The fuzzy control system is constructed by using the fuzzy features of the coal seam status in the coal caving process. The coal quantity and the coal gangue ratio in the coal seam state are taken as the inputs of the fuzzy control system. The output action of the fuzzy control system is replaced with the action of the DQN algorithm using the max operation to select the output Q value of the target network. It improves the online learning rate of the agent and increases the reward value of coal caving action. The coal caving model for the fully mechanized caving face is constructed. The three-dimensional numerical simulation of the coal caving process based on DQN, double depth Q-network (DDQN), and FDQN algorithms is conducted respectively. The results show that the FDQN algorithm has the fastest convergence speed, which is 31.6% faster than the DQN algorithm. It increases the online learning rate of the intelligent agent. The coal caving effect based on the FDQN algorithm is the best from three aspects: the straightness of the coal gangue boundary, the remaining coal above the tail beam, and the amount of gangue in the released body. The extraction rate based on the FDQN algorithm is the highest and the gangue content is the lowest. Compared with the DQN algorithm and DDQN algorithm, the extraction rate of the FDQN algorithm has increased by 2.8% and 0.7% respectively, and the gangue content has decreased by 2.1% and 13.2% respectively. The FDQN-based intelligent decision-making method for coal caving can adjust the action of the hydraulic support tail beam based on the coal seam occurrence status. It effectively solves the problems of over-caving and under-caving during the coal caving process.
Autonomous positioning method for inspection robots in fully mechanized working face
HUANG Xiping, YANG Fei
2023, 49(4): 86-91. doi: 10.13272/j.issn.1671-251x.2022060005
<Abstract>(293) <HTML> (95) <PDF>(31)
Abstract:
At present, the track type robot is widely used in the inspection robot of the fully mechanized working face. When the robot passes through the track connection, it will produce jitter. It causes an increase in the positioning error of the inertial navigation/odometer combination. In order to solve this problem, based on the integrated navigation algorithm of inertial navigation/odometer, a piecewise filtering method based on jitter detection is adopted to achieve autonomous positioning of the inspection robot. Based on the gyroscope data of the inspection robot passing through the track connector, a sliding window method is used to dynamically analyze the pitch angular velocity of the robot. The local maximum rising edge and local maximum falling edge are determined by calculating the derivative sum. When the maximum rising edge and maximum falling edge alternately appear, it is considered that the track connector has been recognized. The jitter detection is achieved, thus dividing the robot's motion state into stable operation state and jitter state. When the robot is in a stable operation state, both the gyroscope and odometer data are relatively stable. At this time, the inertial navigation/odometer combination navigation method is used for filtering and solving. The gyroscope error is corrected based on the characteristic that the gyroscope data should be stable near zero. When the robot is in a jitter state, the odometer may generate errors due to wheel slip and bouncing in the air. At this time, a pure inertial navigation algorithm is used to eliminate the impact of odometer errors on the integrated navigation positioning. The experimental results show that the jitter detection algorithm can accurately determine the track connections. The segmented filtering method based on jitter detection can effectively improve the positioning precision of the inspection robot. The average positioning error is less than 5 mm, meeting the precise positioning requirements of the fully mechanized working face.
Intelligent recognition of coal and rock based on wavelet packet multi-scale fuzzy entropy and weighted KL divergence
LI Yiming
2023, 49(4): 92-98. doi: 10.13272/j.issn.1671-251x.2022100023
<Abstract>(215) <HTML> (64) <PDF>(14)
Abstract:
Intelligent recognition of collapsed coal and rock is a prerequisite for intelligent coal caving. Real-time and precise recognition of collapsed coal and rock can avoid the problem of "under caving" or "over caving" of top coal caused by manual coal caving. Most existing coal and rock recognition methods obtain collapsed coal and rock feature vectors through data dimensionality reduction processing, and construct recognition models for coal and rock recognition. However, data dimensionality reduction, model establishment, and training all require a long time. To some extent, these factors affect the efficiency of continuous fully mechanized caving mining. In order to solve the above problems, an intelligent coal and rock recognition method based on wavelet packet multi-scale fuzzy entropy and weighted KL divergence is proposed. Wavelet packet decomposition is performed on the vibration signals of the tail beam after the hydraulic support is impacted by collapsed coal and rock under different working conditions (top coal collapse, rock collapse, and large top coal collapse) to obtain a series of frequency bands. The sequences of each frequency band are coarse-grained. The method calculates the fuzzy entropy under multiple scales of coarse-grained sequences in each frequency band, that is, wavelet packet multi-scale fuzzy entropy. The method uses it as a feature vector. The method uses the ratio of the energy of each frequency band after wavelet packet decomposition to the total energy of the vibration signal as the weight of the weighted KL divergence. The weighted KL divergence of the unknown samples to be tested and the sample feature vectors under different working conditions are compared. The real-time and precise recognition of collapsed coal and rock is achieved. The experimental results show that the method based on wavelet packet multi-scale fuzzy entropy and weighted KL divergence can effectively recognize the category of collapsed coal and rock. The method based on multi-scale fuzzy entropy and KL divergence and the method based on wavelet packet fuzzy entropy and KL divergence have poor recognition performance. When wavelet packet multi-scale fuzzy entropy is used as the feature vector, the recognition accuracy of the BP neural network reaches 95%. It further verifies that wavelet packet multi-scale fuzzy entropy can be used as the feature vector to characterize collapsed coal and rock. The entire coal and rock identification process takes 1.063 9 seconds, which basically meets the real-time requirements of intelligent recognition of collapsed coal and rock. At the same time, it greatly reduces the impact on the efficiency of continuous fully mechanized caving mining. Its comprehensive performance is superior to similar coal and rock recognition methods.
Miner action recognition model based on DRCA-GCN
LI Shanhua, XIAO Tao, LI Xiaoli, YANG Fazhan, YAO Yong, ZHAO Peipei
2023, 49(4): 99-105, 112. doi: 10.13272/j.issn.1671-251x.2022120023
<Abstract>(189) <HTML> (44) <PDF>(24)
Abstract:
The underground "three violations" behavior brings serious safety hazards to coal mine production. It is of great significance to perceive and prevent unsafe actions of underground personnel in advance. The poor video quality in coal mine monitoring leads to limited accuracy of image based action recognition methods. In order to solve the above problem, a dense residual and combined attention-graph convolutional network (DRCA-GCN) is constructed. A miner action recognition model based on DRCA-GCN is proposed. Firstly, the human pose recognition model OpenPose is used to extract human key points. The missing key points are compensated to reduce the impact of missing key points caused by poor video quality. Secondly, DRCA-GCN is used to identify the miner actions. DRCA-GCN introduces a combined attention mechanism and a dense residual network on the basis of the spatio-temporal inception graph convolutional network (STIGCN). By using the combined attention mechanism, the capability of each network layer in the model to extract important time series, spatial key points and channel features is enhanced. By using the dense residual network to compensate for the extracted action features, the feature transmission between different networks is strengthened. It further enhances the model's recognition capability for miner action features. The experimental results indicate the following points. ① On the public dataset NTU-RGB+D120, when using Cross-Subject(X-Sub) and Cross-Setup(X-Set) as evaluation protocols, the recognition precision of DRCA-GCN is 83.0% and 85.1%, respectively. It is 1.1% higher than the precision of STIGCN, and higher than other mainstream action recognition models. The effectiveness of the combined attention mechanism and dense residual network is verified through ablation experiments. ② After compensating for missing key points, on the self built mine personnel action (MPA) dataset, the average recognition accuracy of DRCA-GCN for squatting, standing, crossing, lying down and sitting movements increases from 94.2% to 96.7%. The recognition accuracy of DRCA-GCN for each type of action is above 94.2%. Compared with STIGCN, the average recognition accuracy has been improved by 6.5%. It is not likely to misrecognize similar actions.
Coal gangue target detection of belt conveyor based on YOLOv5s-SDE
ZHANG Lei, WANG Haosheng, LEI Weiqiang, WANG Bin, LIN Jiangong
2023, 49(4): 106-112. doi: 10.13272/j.issn.1671-251x.2022080043
<Abstract>(959) <HTML> (110) <PDF>(60)
Abstract:
Traditional coal gangue image detection methods require manual extraction of image features. The methods have low accuracy and practicality. The existing coal gangue target detection methods based on improved YOLO have improved in speed and precision, but they still cannot meet the real-time intelligent coal gangue sorting needs of belt conveyors in coal preparation plants. In order to solve the above problems, an improvement is made to the YOLOv5s model, and a YOLOv5s-SDE model was constructed. A method for coal gangue target detection of belt conveyors based on YOLOv5s-SDE is proposed. The YOLOv5s-SDE model enhances useful features, suppresses useless features, and improves the detection effect of small target coal gangue by adding squeeze-and-excitation (SE) module to the backbone network. The model replaces ordinary convolutions with depthwise separable convolutions to reduce parameter and computational complexity. The loss function of the bounding box regression CIoU is replaced by the EIoU. This improves the convergence speed and detection precision of the model. The results of the ablation experiment show that the YOLOv5s-SDE model has a detection accuracy of 87.9% for coal gangue images, a mean average precision (mAP) of 92.5%, and a detection speed of 59.9 frames/s. It can effectively detect coal and gangue, meeting real-time detection requirements. Compared with the YOLOv5s model, the accuracy of the YOLOv5s-SDE model decreases by 2.3%, the mAP increases by 1.3%, the number of parameters decreases by 22.2%, the calculation amount decreases by 24.1%, and the detection speed increases by 6.4%. The comparative experimental results of similar improved models show that the detection precision of YOLOv5s-STA model and YOLOv5s-Ghost model is significantly lower. The detection performance of the YOLOv5s-SDE model, YOLOv5s model and YOLOv5s-CBAM model is generally similar. But in the case of motion blur and low lightning, the overall detection performance of the YOLOv5s-SDE model is better.
An improved tiny YOLO v3 rapid recognition model for coal-gangue
ZHENG Daoneng
2023, 49(4): 113-119. doi: 10.13272/j.issn.1671-251x.18079
<Abstract>(203) <HTML> (106) <PDF>(44)
Abstract:
The traditional coal gangue sorting methods have low efficiency, significant safety hazards, and limited application scope. The existing machine vision-based coal gangue image recognition methods are difficult to balance model recognition speed and accuracy. And the methods do not comprehensively consider the impact of different input image sizes, low important channel weights, and large convolution parameters on model precision. In order to solve the above problems, an improved tiny YOLO v3 coal gangue rapid recognition model is proposed based on the tiny YOLO v3 model. Firstly, a spatial pyramid pooling (SPP) network with multiple convolutional kernels combined pooling is introduced in the tiny YOLO v3 model to ensure that the input feature maps can be processed to a fixed size before being output. Secondly, a squeeze-and-excitation (SE) module with adjustable RGB channel weights is introduced to enhance the connections between the channels in the previous layer feature maps. It emphasizes the differences between the feature values of the interested channels and the features of different targets. It ensures the capture of key information and network sensitivity. Finally, the dilated convolution containing zero weight points is introduced to replace part of the convolution layer in the tiny YOLO v3 model. Under the premise of not adding model parameters, multi-scale context information can be captured to expand the receptive field and improve the calculation speed of the model. This model is compared with the tiny YOLO v3 model, Faster RCNN model, and YOLO v5 series models respectively. The results show the following points. ① Compared with tiny YOLO v3, the improved tiny YOLO v3 coal gangue rapid recognition model has significantly improved recognition accuracy and speed. ② Compared with Faster RCNN, the improved tiny YOLO v3 coal gangue rapid recognition model has reduced training time by 65.72%, increased recognition precision by 11.83%, increased recognition recall by 0.5%, and increased model mean average precision (mAP) by 3.02%. ③ Compared with the YOLO series model, the improved tiny YOLO v3 coal gangue rapid recognition model has a significant increase in recognition speed while maintaining the advantage of recognition precision. The results of the ablation experiment show that the improved tiny YOLO v3 coal gangue rapid recognition model has a recognition accuracy of 99.4%. It is 4.9% higher than the tiny YOLO v3 model added with the SPP network. The time to test each image is 12.5 ms, which is 1 ms less than the tiny YOLO v3 model added to the SPP network.
A dynamic coal quantity detection system for conveyor belt based on ultrasonic array
HAO Hongtao, WANG Kai, DING Wenjie
2023, 49(4): 120-127. doi: 10.13272/j.issn.1671-251x.2022080048
<Abstract>(252) <HTML> (65) <PDF>(23)
Abstract:
Dynamic coal quantity detection for conveyor belt is the foundation and key to achieving energy consumption optimization measures for multi-stage belt conveyors such as coal flow starting and automatic speed regulation. The existing coal quantity detection methods based on ultrasonic have low precision. Multiple ultrasonic sensors are susceptible to interference. In order to solve the above problems, a dynamic coal quantity detection system for conveyor belts based on ultrasonic array is designed. Using the principle of ultrasonic ranging, the coal material height corresponding to the detection points of each ultrasonic sensor array element is detected in real-time through an ultrasonic array. The cross-section slicing method is used to calculate the total volume of coal material passing through the conveyor belt per unit time. The real-time coal flow and total coal quantity of the conveyor belt are calculated based on the coal material stacking density. In order to reduce the crosstalk of the same frequency acoustic wave and the error caused by the attenuation of ultrasonic waves in harsh underground environments, 10 ultrasonic sensor arrays with different center frequencies are selected and arranged in a 2×5 linear array form. The collected coal height data is compensated through multiple rows of ultrasonic sensors to improve the accuracy of coal height data detection. The analysis results of real-time performance indicate that the ultrasonic array detection speed theoretically meets the coal quantity detection requirements of a belt conveyor with a belt speed of 5 m/s. The experimental results show that the average relative errors of regular material volume detection are 4.99% and 5.16% at belt speeds of 0.125 m/s and 0.170 m/s, respectively. Under simulated actual operating conditions, the average relative error of coal quantity detection is 5.56%. In the low belt speed state, the system has a measurement accuracy of over 94% for regular materials and coal. It basically achieves real-time and accurate detection of the dynamic coal quantity of the conveyor belt, meeting the coal quantity detection requirements of the belt conveyor.
Application of a quick drill pipe connection method in high-power electro-hydraulic drilling rigs
XING Wang, LI Fen, WANG Ningfang, LI Dongsheng, LI Wangnian
2023, 49(4): 128-133. doi: 10.13272/j.issn.1671-251x.2022080093
<Abstract>(167) <HTML> (72) <PDF>(10)
Abstract:
In order to solve the problem of long time consumption and low efficiency in the pickup and placement and unscrewing of the drill pipe screw (drill pipe connection) on high-power electro-hydraulic drilling rigs, a quick drill pipe connection method is proposed. To achieve quick drilling and drill pipe connection, a method of closed loop linkage of the manipulator and power head synchronization on the buckle is adopted. After receiving the command for drilling and drill pipe connection, the mechanical arm, mechanical beam, and power head act simultaneously. When the drill pipe interferes (collides) with the power head and main holder during the curve trajectory movement, the mechanical beam stops acting. And the power head continues to retreat away from the main holder. When the interference is removed, after the mechanical beam continues to move until it is in place, the manipulator large arm and small arm are linked to quickly place the drill pipe into the middle loading and unloading area from top to bottom. When the forward rotation pressure reaches the preset value of 10 MPa, the screw engagement of the drill pipe ends. Aiming at the continuous cyclic action of lifting and connecting the drill pipe, the differential displacement synchronization method is adopted. By calculating the difference between the radial retraction of the mechanical grip and the axial displacement of the beam, the problems such as excessive time and interference of the manipulator in grasping and releasing the drill pipe during the loosening process of the power head and drill pipe threads are effectively solved. When the mechanical grip radially rises by 300 mm, the greater the difference in axial displacement from the mechanical beam, the safer it will be. After the power head releases the front buckle, the manipulator resets and control ends. The results of industrial tests show that compared with conventional methods, the average time saved by this quick drill pipe connection method for drilling down and drill pipe connection and lifting and drill pipe connection is 179 s and 41 s respectively, and the success rates of overall drilling down and drill pipe connection and lifting and drill pipe connection have increased by 22.3% and 19.1% respectively.
Research and application of hydraulic slotting gas extraction technology in coal seams containing gangue
LI Xiaoshen, LIU Ruipeng
2023, 49(4): 134-140. doi: 10.13272/j.issn.1671-251x.2022100095
<Abstract>(173) <HTML> (72) <PDF>(8)
Abstract:
In order to study the application of hydraulic slotting enhanced gas extraction technology in coal seams containing gangue, theoretical analysis shows the following points. Compared with ordinary drilling, hydraulic slotting borehole can enhance gas extraction by increasing coal seam permeability, coal body exposure area, and gas flow channels. A coal seam gas flow control equation has been established considering changes in porosity and permeability. Taking the 21218 working face of Dongpang Mine as the engineering background, a numerical model for hydraulic slotting gas extraction in coal seams containing gangue is established by using COMSOL numerical simulation software. By solving the control equation of coal seam gas flow, the gas pressure distribution law of hydraulic slotting gas extraction borehole under different slotting heights and drilling spacing conditions is studied. The construction parameters for hydraulic slotting gas extraction borehole with a slotting of 0.3 m in the upper coal seam, a slotting of 0.1 m in the lower coal seam, and a borehole spacing of 7.5 m are determined. Based on the above parameters, 28 groups of 7 hydraulic slotting borehole are constructed on-site at the 21218 working face of Dongpang Mine to extract gas from coal seams containing gangue. The results show that compared with ordinary borehole, the construction quantity of hydraulic slotting borehole per 100 meters of roadway decreases by 28.51%. The net amount of gas extraction increases from 115300 m3 to 214300 m3 with an increase of 85.86%. The average gas volume fraction of the excavation working face during the roadway excavation period decreases from 0.06% to 0.01%. The gas extraction effect is good and the gas extraction efficiency is effectively improved.
Non-repeated support advanced support intelligent control system
HAN Zhe, XU Yuanqiang, ZHANG Desheng, ZHAO Quanwen, DU Ming, LI Hui, ZHOU Jie, ZHANG Shuai, LIU Jie, GAO Jianxun, WEN Cunbao, ZHOU Xiang, ZHAO Kai
2023, 49(4): 141-146, 152. doi: 10.13272/j.issn.1671-251x.2022090004
<Abstract>(185) <HTML> (169) <PDF>(21)
Abstract:
The non-repeated support advanced support equipment in environments with small space, large vibration, and severe electromagnetic interference has problems of low sensing technology level, imprecise motion control, and complex operation process. In order to solve the above problems, a non-repeated support advanced support intelligent control system is proposed. According to the controlled requirements of the non-repeated support advanced support technology, it has the capability to detect surrounding environmental information such as posture, obstacles, and positions. It has control methods of adaptive, self- adjusting, and self -decision-making. It has fast, stable, and precise execution components. It is pointed out that this intelligent control system proposes three key technologies: intelligent perception, logical control and execution. Based on the control functions and task flow of the intelligent control system for non-repeated support advanced support, the overall architecture of the system is proposed. The multi-sensor fusion technology based on attitude, obstacle recognition, pressure, position, and velocity information is proposed to control and execute multi working condition motion control strategies. The integrated prototype of "turn-transport-support" for advanced support in transportation roadways is developed. And ground tests are conducted. The test results show that the intelligent control system for non-repeated support advanced support can achieve visual recognition of the center point and obstacles of the support, automatic walking and stroke judgment of the support handling trolley, automatic offset and rotation of the support, and automatic grasping and lifting functions of the support. The visual recognition sensor can achieve support frame number coding recognition, support posture, and support area decision-making functions. The automated operation process of "walk-grasp-lower-turn-walk-turn-lift-loose-lower" is implemented. It can meet the application requirements.
Measurement of UWB signal path loss and center frequency selection in underground coal mines
LYU Ruijie
2023, 49(4): 147-152. doi: 10.13272/j.issn.1671-251x.18085
<Abstract>(164) <HTML> (65) <PDF>(20)
Abstract:
The deployment of UWB, 5G and WiFi6 systems underground in coal mines has problems such as multiple base stations, multiple transmission cables, multiple power supply equipment, high system costs, and heavy maintenance workload. Integrating UWB, 5G and WiFi6 antennas into the same integrated base station or sub station can effectively solve the above problems. However, the distance between UWB, 5G and WiFi6 antennas in the integrated base station is close, resulting in high mutual interference. Choosing different operating frequency bands is an effective method to solve the high mutual interference between UWB, 5G and WiFi6 antennas in integrated base stations. To be compatible with ground equipment, the selection range of mining WiFi6 and 5G operating frequency bands is relatively small, while the selection range of UWB operating frequency bands is relatively large. At present, the positioning system for mine personnel and vehicles mainly uses the UWB mainstream chip DW1000, with a center frequency of 3.5, 4.0, 4.5 and 6.5 GHz. The UWB with a center frequency of 3.5 GHz is similar to the 5G operating frequency band of 3.5 GHz. It is not suitable for selection. The three frequency bands of UWB with center frequencies of 4.0, 4.5 and 6.5 GHz are not similar to the 5G and WiFi 6 frequency bands. The frequency band with smaller attenuation can be selected as the center frequency of the mining UWB. The underground testing results of coal mines show that the path loss of the 4.0 GHz signal is the smallest, and the transmission distance is the farthest under the same other conditions. This not only solves the problem of interference between UWB, 5G and WiFi6, but also reduces the number of base stations and system costs. It is easy to use and maintain. Therefore, the UWB center frequency should preferably be 4.0 GHz.

苏ICP备 05016349号-2

Supported by: Beijing Renhe Information Technology Co. Ltd.  Visits：