Online First have been peer-reviewed and accepted, which are not yet assigned to volumes /issues, but are citable by Digital Object Identifier (DOI).
Research on denoising of partial discharge signal of mining high voltage cable based on improved variational modal decomposition
Aiming at the problems of large amount of white noise and periodic narrow-band interference in partial discharge (PD) signal of mining high voltage XLPE cable, A denoising method based on improved Variational Modal Decomposition (VMD) is proposed for partial discharge signals of mining high-voltage cable. Firstly, the K in VMD algorithm is optimized by Spearman correlation coefficient, and then the noisy signal is decomposed into a series of intrinsic mode functions (IMF); IMF is divided into noised-dominated IMF and the PD-dominated IMF by kurtosis criterion; The noised-dominated IMF is denoised by improved wavelet threshold, and the rough penalty method is used to smooth the PD-dominated IMF; The processed IMF is reconstructed and the denoised signal is finally obtained. The simulation and measured signal results show that this method can effectively remove the noise in PD signal. Compared with the complete ensemble empirical mode decomposition (CEEMD) algorithm, the signal-to-noise ratio is improved by 46.29% and the mean square error is reduced by 32.61%.
Simulation of spark discharge characteristics of CL composite circuit
Based on the current research on the discharge characteristics of CL composite circuit is not particularly comprehensive, so the discharge principle of CL composite circuit is studied, and two different states are obtained, respectively for oscillation and non-oscillation two states. Non oscillatory state because of the previous studies, therefore, the main study of oscillation state, analyzes the principles of the Ann circuit, deduces CL compound circuit sparks current, power, and the mathematical model of spark energy, using MATLAB to the power supply voltage, filter capacitance and inductance parameters of the simulation, get the 3 d and 2 d figure, The influence of power supply voltage, filter capacitance and inductance on discharge characteristics of CL composite circuit is analyzed. The results show that the spark current, power and energy all increase with the increase of filter capacitance. With the increase of inductance, the greater the hindrance to current, the spark power and spark energy will decrease. As the supply voltage increases, spark current, power and energy all increase.
Study on the method of personnel accurate detection in shearer operating space
Shearer is one of the key equipment in fully mechanized working face, and its intelligence is the necessary condition to realize less-human and unmanned mining. Unfortunately, although shearer has functions including three-dimensional positioning, memory cutting, remote monitoring and etc., the detection and pre-warning function for errant personnel who straying into the shearer operating space has not yet been realized. The lack of this function may lead to serious safety accidents once underground personnel straying into the shearer operating space. Hence, it is necessary to research the key technologies of personnel detection in shearer operating space to realize the safety production when shearer operating and achieve safe and efficient production of coal mine. In view of the characteristics of low illumination and complex operating environment of fully mechanized working face, an accurate personnel detection system in shearer operating space based on infrared thermal imaging technology is proposed. By analyzing the characteristics of infrared image noise in fully mechanized working face, a multi-level guided filtering model based on Gaussian mask is proposed; Based on Lucas-Kanade optical flow and fuzzy segmentation theory, the motion information extraction for moving foreground target in dynamic background and the segmentation for infrared scene information are realized, respectively; Combined with the moving-target motion information and infrared-scene segmentation results, a weight voting method based on morphology theory is constructed to realize the accurate detection of personnel in shearer operating space. Finally, the underground industrial test was carried out in the 21208 fully mechanized working face of Gengcun Coal Mine of Henan Dayou Energy Co., Ltd. the test results show that the tracking deviation of the proposed personnel detection system in the shearer operating space in the actual fully mechanized working face is as low as 0.1065 pixel width, and the coincidence ratio is 96.10%. As accurate personnel detection in shearer operating space is the premise of effective personnel safety protection, the establishment of the personnel accurate detection system provides technical support for the safety production of intelligent fully mechanized working face.
Study on Mechanism of rock burst behavior induced by coal pillar in multi-coal seam mining with hard- thick roof strata
In this paper, order to comprehensively study the mechanism of rock burst induced by coal pillar under the condition of hard-thick roof strata, using numerical simulation and on-site data monitoring, the characteristics of overlying rock movement in the process of fully mechanized top coal caving mining under the condition of hard-thick roof strata was studied, the mechanism of rock burst behavior in the working face was analyzed, and the potential risk of rock burst in the subsequent mining process was analyzed. The results show as follows: Influenced by the coal pillar, hard-thick roof strata and the ahead supporter pressure, the stress of surrounding rock and supporter pressure in the middle and lower part of the working face and near the coal pillar in the section are obviously greater than that of the upper roadway area, which is easy to produce the ruck burst induced by coal pillar and hard-thick roof strata; when the workface is close to the boundary of "knife-shape-like" gob, the boundary stress of the I010405 gob can be transferred down to I010203 workface and stacked with lateral and advanced supporter stress. Finally, the three supporter stress formed, which would cause rock burst hazard of I010203 workface to increase. At this stage, more efforts should be made to prevent the impact of the I010203 workface to pass through the dangerous area smoothly. The rock burst of the field monitoring is consistent with the theoretical analysis results. The research results can provide reference for the prevention and control of rock burst in similar conditions.
Development and Research on the Active Disturbance Control for the Underground Crawler Detection Robot
Aiming at the current disaster detection and rescue problems in underground mines, this paper proposed a six-swing arm crawler detection robot for complex ground environments. Firstly, the overall structure of the robot's structure was designed, especially for the mobile chassis, and the working condition parameters of the robot's typical operations were analyzed subsequently. Secondly, aiming at the problem of efficient motion control of the robot on complex ground, the driving scheme of the robot control system was designed creatively. Thirdly, the permanent magnet synchronous motor (PMSM) driven by the crawler on both sides has been mathematically modeled and the field oriented control (FOC) was researched in the robot motion drive system. Moreover, aiming at the shortcomings of traditional direct torque control system such as weak anti-interference performance and large flux pulsation, the speed loop control based on active-disturbance rejection control (ADRC) and the current loop control algorithm based on Proportional integral control (PI) controller were designed to improve the ability of motor disturbance suppression, fast speed and the sports performance. Finally, it was verified by a comparative test with the algorithm of the double PI loop. The test results shown that the motion response of the PMSM system of the robot by using the ADRC algorithm is more fast, without overshoot, and has stronger anti-interference ability, which can effectively improve both of the ability of the climbing obstacles, and the stable operational stability for the robot.
Running State Prediction of Belt Conveyor Based on Audio Feature Fusion Res-CNN-LSTM Network
Abstract: In order to solve the problems of inconvenient installation, poor stability, and lack of prediction of the operating status of the belt conveyor using contact sensors and machine vision to monitor the operating status of the mining belt conveyor, Res-CNN-LSTM based on audio feature fusion is proposed. Network-based belt conveyor operation state prediction method. Firstly, the audio signal is filtered and denoised, and then the one-dimensional Mel cepstrum coefficient MFCC0 of the signal is extracted by the Mel cepstrum method (MFCC) as the input of the network model; considering that the deepening of the network model will lead to over-fitting and performance degradation,The residual block is introduced to optimize the network model. Experiments are carried out on the laboratory belt conveyor platform. During the experiment, the network model parameters are continuously optimized. The results show that the audio signal can obtain more information about the operation status of the belt conveyor; compared with other models, the designed network model predicts the accuracy is the highest, and the training time is short; at the same time, it is verified that the model has high robustness under different working conditions.
[Achievements of Scientific Research]
Research and application of intelligent early warning system for coal mine fires
LIU Dongyang, ZHANG Lang, YAO Haifei, XU Changfu, ZHAO Youxin, ZHANG Yibin, DUAN Sigong
2024, 50(1): 1-8, 16.   doi: 10.13272/j.issn.1671-251x.2023070092
Abstract: Currently, the coal mine fire monitoring system has achieved separate monitoring of some indicators such as the iconic gases, temperature, smoke, and flame of coal spontaneous combustion in mines.But the system has not effectively, comprehensively, and uniformly monitored the factors related to coal mine fires. In order to solve this problem, potential risk factors of coal mine fires are analyzed from two aspects: internal and external factors. A method of monitoring fire situation in different sources and areas is proposed. In terms of internal fires, monitoring is mainly carried out on goaf areas, enclosed goaf areas, and artificial natural fire observation points that are prone to fires. In terms of external fires, monitoring is mainly carried out on the mechanical and electrical chambers and their distribution points, belt conveyor systems, cables, and other aspects. A monitoring index system for coal mine fire sources and areas has been established. The system regularly collects or updates fire feature parameter data through manual or online monitoring. According to the data collection method and impact degree, fire monitoring indicators are divided into dynamic indicators, static indicators, and related indicators. The overall architecture and business process of a fire intelligent warning system is designed. The system uses a warning method based on multi index joint logical reasoning to achieve internal fire warning, and uses a multi parameter fusion warning method based on D-S evidence theory to achieve external fire warning. The on-site test results show that the fire intelligent warning system has achieved effective monitoring and warning of mine fires, with a visual display function of a coal mine fire risk warning "one picture". The system has a fire intelligent simulation demonstration function and a dynamic planning function for disaster avoidance routes.
<HTML> <PDF>(15565KB)
[Achievements of Scientific Research]
Automatic height adjustment technology of shearer based on cutting roof and floor height prediction model
LI Zhongzhong, LIU Qing
2024, 50(1): 9-16.   doi: 10.13272/j.issn.1671-251x.2023060044
Abstract: The traditional coal seam cutting path planning predicts the height of the drum through geometric control, planning calculation, and other methods. But there are problems with large data errors in planning and prediction and inability to adapt to changes in geological conditions. In order to solve the above problems, a shearer automatic height adjustment technology based on a cutting roof and floor height prediction model is proposed. Firstly, the factors affecting the height of the cutting roof and floor are analyzed. It is pointed out that the main factors affecting the height of the cutting roof and floor include the fluctuation data of the coal seam, historical cutting data, elevation data of the scraper conveyor, and manual operation records. The above four types of data are fused and processed to establish a cutting roof and floor height prediction algorithm model based on long short term memory (LSTM) model and gray Markov model. The height of the cutting roof and floor is predicted through an algorithmic model. Secondly, based on the height data of the cutting roof and floor, combined with the position and posture and spatial coordinates of the shearer, a geometric model for calculating the height of the drum is established. At the same time, correction is made according to factors such as the sliding amount of the scraper conveyor and whether the addition and subtraction process is carried out. Finally, the height sequence of the roof and floor is converted into a drum height sequence. The cutting roof and floor height is converted into the target height of the shearer drum, which is executed by the shearer to the target height, achieving automatic adjustment of the drum height. The industrial test results show the following points. ① Under the control of automatic height adjustment technology, 90% of the predicted height deviation values of the roof and floor drums are within 10 cm of the actual height. The predicted height of the drums is significantly consistent with the actual height. ② Compared with traditional manual control methods, the number of manual intervention height adjustment times for cutting coal in the middle has decreased from 49 to 21. It indicates that the height prediction model for cutting the roof and floor and the geometric model for calculating the height of the drum are accurate and reasonable, and the automatic height adjustment technology for the shearer drum is feasible.
<HTML> <PDF>(2086KB)
[Achievements of Scientific Research]
A coal mine data acquisition, fusion and sharing system based on object model
SHANG Weidong, WANG Haili, ZHANG Xiaoxia, WANG Hao, XU Hualong
2024, 50(1): 17-24, 34.   doi: 10.13272/j.issn.1671-251x.2023070047
Abstract: In current coal mine data acquisition, fusion, and sharing, there are problems of lack of standardization and semantic inconsistency in device attributes, inability to cross operating systems in data acquisition protocols, poor real-time data access, and low data sharing efficiency. In order to solve the above problems, a coal mine data acquisition, fusion, and sharing system based on object model is designed. On the basis of the coding standard for coal mine data based on tag numbers, a device object model is designed to overcome the problems of lack of standardization of device attributes and semantic inconsistency in device attributes. By using industrial protocol acquisition, Restful API Q&A acquisition, and file data acquisition methods for data access, it can support domestic operating systems and provide convenient message monitoring tools to accurately determine the cause of communication abnormalities. The model implements data fusion through device object model mapping, introduces data governance mechanisms to ensure data accuracy and consistency, and stores data in the form of object models to save storage space and improve storage efficiency. The model stores all device object data in one table. The object-oriented data sharing interface can be simplified into real-time data sharing interface and historical data sharing interface, reducing redundant interfaces and thus reducing data access times. The application results show that the system reduces the difficulty of semantic parsing during data usage after standardizing device data. The system improves the performance of data computation, storage, and access, providing guarantees for big data analysis.
<HTML> <PDF>(1853KB)
[Achievements of Scientific Research]
Underground personnel positioning system based on 5G+UWB and inertial navigation technology
LI Mingfeng, LI Yan, LIU Yong, WU Xuesong, XU Jisheng, CHANG Jianming, WANG Tao, PAN Hongguang
2024, 50(1): 25-34.   doi: 10.13272/j.issn.1671-251x.2023100066
Abstract: In practical applications of coal mine personnel positioning systems, there are problems of insufficient equipment computing power and storage resources. The problems result in preventing the use of complex ranging and positioning algorithms, inadequate real-time transmission and response performance of positioning data, and significant human and material resource losses in system deployment. In order to solve the above problems, a new underground personnel positioning system based on 5G+UWB and inertial navigation technology is proposed. The system deploys UWB positioning base stations with low energy consumption and strong anti-interference capability at the end. The positioning base station is connected to the 5G base station in a cascaded manner. The positioning base station collects UWB and inertial navigation data, and uses the 5G network to transmit it back to the computing platform. The positioning information is solved and stored on the computing platform. The inertial navigation based personnel position estimation is used as the predicted value. The UWB based trilateral positioning algorithm is used to obtain personnel position estimation as the observed value. The Kalman filter is used to fuse the predicted and observed values to reduce positioning errors. The testing system is built at the main experimental base of the coal mine, simulating the real underground environment of the coal mine, and conducting comparative experiments. The results show the following points. ①In the x-axis direction and the y-axis direction, the coincidence degree between the position information obtained by the Kalman filter algorithm of the fusion inertial navigation and the real position information is the highest, indicating that the position information obtained by the Kalman filter algorithm of the fusion inertial navigation is closest to the real position, and the average error is 22.192 cm. ② The position information of the underground personnel positioning system combined with 5G + UWB and inertial navigation technology has the highest coincidence degree with the real position information, and the error is [15 cm, 20 cm], with a maximum average error of 26 cm on the x-axis and 24 cm on the y-axis, exceeding the precision of most current underground personnel positioning systems.
<HTML> <PDF>(7306KB)
[Achievements of Scientific Research]
Hydraulic fracturing and punching integration enhanced permeability gas extraction technology
WANG Baogui
2024, 50(1): 35-41.   doi: 10.13272/j.issn.1671-251x.2023050014
Abstract: The existing hydraulic fracturing, hydraulic punching, hydraulic slotting, hydraulic cutting and other underground hydraulic permeability enhancement technologies in coal mines have complex processes, single adaptability conditions, and high labor intensity. However, drilling and punching integration, drilling and expansion integration, hydraulic punching/fracturing integration and other technologies are not ideal for enhancing the permeability of hard coal. There are problems such as cumbersome processes and inability to operate continuously. In order to solve the above problems, a hydraulic fracturing and punching integration enhanced permeability gas extraction technology is proposed. During the drilling process, high-pressure water jet is used to perform hydraulic enhanced permeability operations on coal seams at fixed points (directional, segmented). It can achieve integrated drilling, hydraulic punching of soft coal, and hydraulic injection fracturing of hard coal. The study reveals the principle of hydraulic fracturing and punching integration permeability enhancement. The hydraulic punching is used to flush out part of the coal body in soft coal seams, achieving pressure relief and permeability enhancement of soft coal seams. The fixed-point hydraulic jet fracturing is performed on hard coal seams, achieving fracture formation and permeability enhancement in hard coal seams. The drilling tool of hydraulic fracturing and punching integration is developed to meet the requirements of high pump pressure and large displacement. The drilling tool has strong rock breaking and chip removal capabilities. The process is simple and controllable. The drilling tool control methods for high-pressure water jet punching and hydraulic jet fracturing are provided. The stamping process during drilling and stamping process during drill withdrawal are discussed. The on site engineering tests are conducted using fracturing and punching integration drilling tools in the 16101 bottom drainage roadway of a coal mine. The results show that hydraulic punching operation in the soft coal section shortens the time by 60% to 80% compared to traditional hydraulic punching. The coal output from a single hole increases by about 2 times, and the average gas extraction purity per 100 meters per hole increases by 1 time. The hydraulic jet fracturing operation is carried out in the hard coal section. The average gas extraction purity per 100 meters per hole increases by 2 times compared to traditional hydraulic punching.
<HTML> <PDF>(1985KB)
Research progress on coal rock recognition technology based on electromagnetic waves
LIU Yuan, SI Lei, WANG Zhongbin, WEI Dong, GU Jinheng
2024, 50(1): 42-48, 65.   doi: 10.13272/j.issn.1671-251x.2023070095
Abstract: Applying electromagnetic waves to coal rock recognition can effectively improve the resolution capability of coal rock interfaces. Based on the coal rock interface model, the principle of using electromagnetic wave technology for coal rock recognition is explained. The paper introduces six methods for coal rock recognition, including γ–ray method, radar detection method, Terahertz signal method, electron resonance method, X-ray method, and infrared thermal imaging method. The principles of each method are analyzed, and the advantages and disadvantages of each method are compared as well as their applicability in coal mines underground. The research status of each method is analyzed in combination with practical industrial applications. The γ–ray method has significant advantages in detection distance, but it has radiation problems. It is basically eliminated. The radar detection method has the advantage of accurate recognition, but due to its severe signal attenuation and short detection distance, it is currently generally used for thickness measurement in thin coal seams. The Terahertz signal method has a short detection distance and can only be applied when the composition of the underground environment is stable. The electronic resonance method has severe signal attenuation, short detection distance, and high difficulty. It is currently basically abandoned in mines. The X-ray method has strong penetration and clear imaging, but it poses great harm. In the infrared thermal imaging method, the active infrared excitation method requires a lot of time to excite coal and rock, and there are significant safety hazards in high gas mine environments. Although the cutting flash temperature method takes a short time, it is difficult to achieve effective coal rock recognition for situations with multiple cutting teeth and complex layout. It is pointed out that the accuracy of electromagnetic wave coal rock recognition is determined by the echo information of electromagnetic waves, and further in-depth exploration should be carried out.
<HTML> <PDF>(3224KB)
[Analysis and Research]
A multi-target road detection model in a low-light environment in an open-pit mining area based on hyperbolic embedding
GU Qinghua, SU Cunling, WANG Qian, CHEN Lu, XIONG Naixue
2024, 50(1): 49-56, 114.   doi: 10.13272/j.issn.1671-251x.2023060021
Abstract: The environment of open-pit mines is distinctive, and the conditions of the roads in them are complex and constantly changing. Insufficient lighting in the area being mined can make it challenging to identify and position multiple targets on the roads. This, in turn, affects the results of detection and poses serious risks to the safe operation of uncrewed mining trucks.Currently available models to identify obstacles on roads cannot accommodate the impact of poor lighting, and thus, yield inaccurate results. They also have significant shortcomings in identifying small obstacles in the mining area. In this study, we develop a multi-target model of detection for the dark/light environment of an open-pit mine using hyperbolic embedding to address the above-mentioned issues. We introduce the Retinex-Net convolutional neural network to the image preprocessing stage of the detection model to enhance dark images and improve their clarity. To address the issue of an excessively large number of features in the dataset without a clear preference for focus, we incorporate the global attention mechanism into the improved process of feature extraction. This enabled the collection of critical feature-related information in three dimensions. Finally, we incorporate a fully connected hyperbolic layer into the prediction stage of the model to minimize feature loss and prevent overfitting. The results of experiments to verify the proposed model showed that ① it could reliably classify and accurately identify large-scale targets in the low-light environment of the open-pit mining area, and was able to highly accurately identify mining trucks and small vehicles over long distances. It could also accurately identify and locate scaled targets, including pedestrians, such that this satisfies meeting the safety-related requirements of uncrewed mining trucks operating in diverse environments.② The model achieved an accuracy of detection of 98.6% while maintaining a speed of 51.52 frames/s, where this was 20.31%, 18.51%, 10.53%, 8.39%, and 13.24% higher than the accuracies of the SSD, YOLOv4, YOLOv5, YOLOx, and YOLOv7, respectively. Its accuracy of detection of pedestrians, mining trucks, and excavators on mining roads exceeded 97%.
<HTML> <PDF>(19941KB)
[Analysis and Research]
A coal foreign object detection method based on cross modal attention fusion
CAO Xiangang, LI Hu, WANG Peng, WU Xudong, XIANG Jingfang, DING Wentao
2024, 50(1): 57-65.   doi: 10.13272/j.issn.1671-251x.2023110035
Abstract: The RGB image of coal foreign objects lacks target space and edge information, the color and texture between the object to be detected and the background are similar, the contrast is low, and there are overlapping and occlusion phenomena among the objects to be detected, resulting in insufficient feature extraction of coal foreign objects, and the existing foreign object detection methods are difficult to achieve ideal results. In order to solve the above problems, a coal foreign object detection method based on cross modal attention fusion is proposed. By introducing Depth images to construct a dual feature pyramid network (DFPN) for RGB images and Depth images, a shallow feature extraction strategy is adopted to extract low-level features of Depth images. Basic features such as deep edges and deep textures are used to assist deep features of RGB images, effectively obtaining complementary information between the two features. It thereby enriches the spatial and edge information of foreign object features and improves detection precision. A cross modal attention fusion module (CAFM) based on coordinate attention and improved spatial attention is constructed to synergistically optimize and fuse RGB features and Depth features. It enhances the network's attention to the visible parts of occluded foreign objects in the feature map, and improves the precision of occluded foreign object detection. Finally, regional convolutional neural network (R-CNN) is used to output the classification, regression, and segmentation results of coal foreign objects. The experimental results show that in terms of detection precision, the average segmentation precision AP of the proposed method is 3.9% higher than the better Mask transformer in the two-stage model. In terms of detection efficiency, the proposed method has a single frame detection time of 110.5 ms, which can meet the real-time requirements of foreign object detection. The coal foreign object detection method based on cross modal attention fusion can assist color, shape, and texture features with spatial features. It accurately recognizes the differences between coal foreign objects and between coal foreign objects and conveyor belts, effectively improves the detection precision of complex feature foreign objects. It reduces false alarms and missed detections, and achieves precise detection and pixel level segmentation of coal foreign objects under complex features.
<HTML> <PDF>(7740KB)

Industry NewsMore>