工矿自动化

Study on the perception and alarm method of coal mine rock burst and coal and gas outburst

SUN Jiping, CHENG Jijie

2022, 48(1): 1-6. doi: 10.13272/j.issn.1671-251x.17881

<Abstract>(244) <HTML> (128) <PDF>(53)

Abstract:
The paper puts forward a perception and alarm method of rock burst and coal and gas outburst based on temperature. The infrared thermal imager is used to monitor the temperature of objects, and the methane sensor is used to monitor the concentration of ambient methane. When the temperature of the objects is higher than the ambient temperature of the coal mine and the temperature of the exposed coal rock, and the number, volume and area of objects that are higher than the ambient temperature and the temperature of the exposed coal rock are large, it is determined that rock burst, coal and gas outburst, mine fire or gas and coal dust explosion accidents have occurred. The temperature of the high temperature object is further determine. If it is greater than the set threshold, it is determined that a mine fire or a gas and coal dust explosion accident has occurred. Otherwise, it is determined that a rock burst or a coal and gas outburst accident has occurred. The change of methane concentration is further analyzed. If the methane concentration rises rapidly, it is determined that a coal and gas outburst accident has occurred. Otherwise, it is determined that a rock burst accident has occurred. The paper puts forward a perception and alarm method of rock burst and coal and gas outburst based on velocity. The lidar, millimeter-wave radar, ultrasonic radar, binocular vision camera are used to monitor the moving speed of objects. The methane sensors are applied to monitor the concentration of ambient methane. When the moving speed of the object is not less than the set threshold, it is determined that rock burst, coal and gas outburst or gas and coal dust explosion accident have occurred. The number, volume and area of objects with abnormal velocity is further determined. If the number of objects with abnormal velocity is small, the volume and area are small, it is determined that a gas and coal dust explosion accident has occurred. If the number of objects with abnormal velocity is large, the volume and area are large, it is determined that a rock burst or a coal and gas outburst accident has occurred. The changes of methane concentration are further analyzed. If the methane concentration increases rapidly, it is determined that a coal and gas outburst accident has occurred. Otherwise, it is determined that a rock burst accident has occurred. A multi-information fusion method for perception, alarming and judging disaster source of rock burst and coal and gas outburst is proposed. The method monitors and integrates various information such as temperature, speed, acceleration, burial depth, sound, air pressure, wind speed, wind direction, dust, methane concentration, equipment status, micro-seismic, geosound, stress, infrared radiation, electromagnetic radiation and images so as to monitor the pressure and coal and gas outbursts. The source of the disaster is determined through the magnitude of parameter changes at different locations, the sequence relationship and sensor damage.

Error modeling and analysis of alternating measurement mode roadheader positioning system

LI Zhihai, LIU Zhixiang, XIE Miao, LI Yuqi, WANG Shuai

2022, 48(1): 7-15. doi: 10.13272/j.issn.1671-251x.2021060015

<Abstract>(1424) <HTML> (59) <PDF>(30)

Abstract:
The alternating measurement mode roadheader positioning technology will produce cumulative measurement error in the process of multiple alternating measurement, which will affect the positioning precision of roadheader. At present, the research mainly focuses on the causes of single measurement error, error distribution law and error reduction methods, but there is no research results on the error distribution law of multiple alternating measurement. By analyzing the working principle and positioning process of alternating measurement mode roadheader positioning system, the positioning error model of roadheader is established. The accuracy of the error model is verified by the graphic method, and the results show that the positioning errors obtained by the graphic method and the error model are basically the same, and and there are only 10⁻³ orders of magnitude errors between them. The impact of angle measurement error, distance measurement error, moving step length and distance between the roadheader and measuring platform on roadheader positioning error is studied by error model. The results show that the larger the angle measurement error, the larger the curvature of the positioning error curve, that is, the faster the error grows. And the Y_T axis positioning error grows faster than the X_T axis. The distance measurement error has a greater impact on the X_T axis positioning error, and the smaller the distance measurement error, the smaller the initial X_T axis positioning error. However, the error change speed is not affected. As the moving step length increases, the Y_T axis positioning error curvature increases, that is, the Y_T axis positioning error growing speed increases. The impacts of the distance between the roadheader and measuring platform and the moving step length on roadheader positioning error are basically equivalent. The orthogonal test method is used to analyze the impact degree of each factor on the positioning error of roadheader. The results show that the distance measurement error has the greatest impact on the positioning error of the X_T axis, followed by the angle measurement error. The moving step length and the distance between the roadheader and the measuring platform have the smallest impact and the two have the same degree of impact. The angle measurement error has the greatest impact on the positioning error of the Y_T axis, followed by the moving step length and the distance between the roadheader and the measuring platform, and the impacts of the two are the same. The impact of the distance measurement error is the smallest. The range analysis method is used to obtain the optimal parameter combination to reduce the positioning error.

Shearer drum load identification method based on audio recognition

ZHUANG Deyu

2022, 48(1): 16-20. doi: 10.13272/j.issn.1671-251x.2021070027

<Abstract>(216) <HTML> (66) <PDF>(39)

Abstract:
In order to solve the problems of the existing shearer drum load identification methods, such as difficult implementation of related algorithms, complex engineering implementation mode and high application difficulty, through analyzing the characteristics of the audio signal during shearer operation, a shearer drum load identification method based on audio recognition is proposed. In order to ensure that the audio signal in each analysis period has the same load condition under the same operation standard, the cutting current and the traction speed are introduced into the dynamic energy calculation as variables, and the dynamic energy normalization algorithm (DENA) is adopted to normalize the original audio signal of the shearer. The normalized signal is compared and analyzed with the signal in the standard operation condition library, and the difference between the two is judged by the maximum dissimilarity coefficient, so as to determine the characteristics of the drum load and realize the identification and judgment of the drum load. The test results show that DENA can effectively suppress the noise energy in the audio signal and improve the resolution of the key characteristic values in the audio signal. The boundary of the characteristic parameters of the audio signal is obvious when the shearer cuts coal and rock, and there is no cross aliasing phenomenon. Under ideal conditions, that is, when the maximum dissimilarity coefficient is less than 0.189, the total coal-rock interface recognition rate can reach 78.6%.

Borehole detection test of primary CO in coal seam

QIN Ruxiang, XU Shaowei, HOU Shuhong, TIAN Wenxiong, YANG Zhihua, FU Shigui

2022, 48(1): 21-25. doi: 10.13272/j.issn.1671-251x.2021070043

<Abstract>(120) <HTML> (71) <PDF>(25)

Abstract:
At present, many studies have come to the conclusion that the coal seam contains primary CO gas, but the possibility of CO being adsorbed by coal after CO generated in drilling construction is not considered. In order to explore whether there is primary CO in spontaneous combustion coal seam in Northwest China, the original coal seam in-situ drilling detection method is used to detect primary CO. Three test boreholes are arranged in a row along the roadway side in the solid coal area not affected by mining. After the boreholes are sealed, high-purity N₂ is used to replace the gas in the closed gas chamber, and the gas in the boreholes is extracted by a special air pump, so as to eliminate the impact of CO generated by coal oxidation on the test results during the construction of in-situ detection boreholes. On the basis of analyzing the source possibility of primary CO in coal seam and its emission theory, the variation characteristics of gas concentration in closed borehole with time are discussed. The results show that volume fraction of O₂ and CO in the sealed borehole decrease rapidly with the extension of sealing time, and the volume fraction of O₂ is stable below 2% after 12 days. After 12 days, the CO volume fraction is lower than 10⁻¹², and no CO gas is detected by gas chromatograp. The gas in the borehole is mainly N₂. It is concluded that there is no primary CO gas in the tested coal seam. The results of coal breaking test in N₂ environment and coal sample oxidation test at normal temperature and constant temperature show that CO gas detected at the initial stage of borehole sealing comes from coal breaking operation in drilling construction.

Research on deviation correction control of coal mine roadheader based on digital twin

XUE Xusheng, REN Zhongfu, MAO Qinghua, ZHANG Xuhui, MA Hongwei, WANG Yue

2022, 48(1): 26-32. doi: 10.13272/j.issn.1671-251x.2021100006

<Abstract>(1812) <HTML> (143) <PDF>(75)

Abstract:
In order to solve the problem of autonomous deviation control of roadheader in complex roadway environment, the paper analyzes the deviation reasons of roadheader, defines the functional requirements of deviation correction control of roadheader, proposes a deviation correction control system of coal mine roadheader based on digital twin, and introduces the system composition. Taking the roadheader central position control as an example, the system deviation correction control mechanism is analyzed, and a deviation correction control method of the roadheader based on binocular vision image information is proposed. Taking the roadway image detected by binocular vision as the basic data, by extracting the characteristics of the roadway image and analyzing the relationship between the roadway coordinate system and the roadheader coordinate system, the position and attitude parameters of the roadheader relative to the roadway space are calculated, and the deviation correction control of the roadheader is carried out according to the solution results. The digital model and the positioning and orientation parameter database of the roadheader and the roadway are constructed, and the virtual remote deviation correction control of the roadheader is realized through the virtual-real mapping relationship. The experimental results show that the deviation correction control system based on digital twin can compensate the yaw angle and offset distance of the roadheader under different working conditions effectively. The deviation correction process can be displayed on the monitoring interface in real time, and the simulation results of deviation correction path planning are consistent with the actual working conditions.

PDR algorithm for precise positioning of underground personnel based on LSTM personalized step size estimation

GUO Qianqian, CUI Lizhen, YANG Yong, HE Jiaxing, SHI Mingquan

2022, 48(1): 33-39. doi: 10.13272/j.issn.1671-251x.2021070052

<Abstract>(266) <HTML> (157) <PDF>(44)

Abstract:
The traditional pedestrian dead reckoning (PDR) algorithm has low positioning precision due to the accumulated errors of step size and heading, which can not meet the requirements of precise positioning of underground personnel. In order to solve the problem, a PDR algorithm for precise positioning of underground personnel based on long short-term memory (LSTM) personalized step size estimation is proposed. Firstly, the acceleration and gyroscope inertia information in the movement of underground personnel is collected, and the movement distance of each step is calculated to construct step size data. The LSTM model of personalized step size estimation of the underground personnel is obtained through off-line training. Secondly, in the online prediction stage, the underground personnel movement data such as acceleration, gyroscope and geomagnetism are collected in real-time through the mine intrinsically safe smart phone. The underground personnel movement step and step size of each step are obtained by using the step detection algorithm and personalized step size estimation model respectively. The heading angle is obtained by using the Kalman filtering and heading estimation algorithm. Finally, the current position of underground personnel is predicted according to step size estimation and heading angle. In Inner Mongolia Ordos Gaotouyao Coal Mine, the underground personnel movement data is collected for testing, and the results show as follows. The PDR algorithm for precise positioning of underground personnel based on LSTM personalized step size estimation has a step detection precision of 96.5% and a step size prediction precision of 90%. The algorithm has a relative positioning error of 2.33% in the real underground environment, which improves the personnel positioning precision in coal mine.

Coal flow detection method for conveyor belt based on TOF depth image restoration

WANG Xinyue, QIAO Tiezhu, PANG Yusong, YAN Gaowei

2022, 48(1): 40-44. doi: 10.13272/j.issn.1671-251x.2021080018

<Abstract>(310) <HTML> (105) <PDF>(34)

Abstract:
In the traditional belt conveyor coal flow detection device, the nuclear belt scale has certain safety and environmental protection hidden dangers, and the detection precision of electronic belt scale is easily affected by the factors such as belt tension and stiffness. Moreover, non-contact detection methods based on technologies such as ultrasound, linear laser stripes and binocular vision have problems such as poor real-time performance and large measurement errors. A coal flow detection method for conveyor belt based on time-of-flight(TOF) depth image restoration is proposed. The TOF camera is used to obtain the coal conveying image of the conveyor belt. The TOF image is equalized, and the frame difference method and the boundary following algorithm are used to remove the background noise and obtain the coal region of interest. In order to solve the problem of inaccurate edge information caused by flying pixel noise and multi-path error noise at the edge of TOF depth image, the intensity image-guided depth image restoration algorithm is proposed. The Canny edge detection algorithm is used to find similar edges between the depth image and the intensity image. Based on the effective edge information of the intensity image, the unreliable data of the edge of the depth image is corrected. Furthermore, the high-precision depth images are obtained based on Navier-Stokes equation and median filter. The coal area is divided at the pixel level, the coal volume calculation model is established to obtain coal flow of conveyor belt by combining the conveyor belt speed. The experimental results show that the detection error is less than 3.78%, the standard deviation is less than 0.491 and the average processing time is 83 ms, which meets the actual production requirements.

A compressive sensing measurement matrix for image signal

LI Wenzong, HUA Gang

2022, 48(1): 45-52. doi: 10.13272/j.issn.1671-251x.2021070048

<Abstract>(120) <HTML> (37) <PDF>(21)

Abstract:
The amount of monitoring image information in unmanned working area of mine is large, and the hardware performance requirements are high in the image transmission and storage stage, which causes the problems of increased energy consumption and sudden decrease of the service life of sensor nodes. At present, when reconstructing mine monitoring image signal, the precision of compressive sensing measurement matrices such as Gause and Bernoulli is low. In order to solve the above problems, a new block Pascal compressive sensing measurement matrix (BPCSM) is designed. The BPCSM matrix uses the idea of non-uniform sampling and blocking in time domain, arranges multiple identical small-size Pascal matrices in a diagonal manner, and combines with the joint orthogonal matching tracking algorithm so as to realize the compression sampling and reconstruction of underground monitoring image signals. And the characteristics of orderly arrangement of row elements of Pascal matrices are used to strengthen the sampling of low frequency band of image signals so as to improve the reconstruction precision. The experimental results show that the reconstruction precision of BPCSM matrix for mine monitoring image signals is much higher than that of the commonly used measurement matrices such as Gause and Bernoulli. When the sampling rate is 0.3, the peak signal-to-noise ratio (PSNR) of the miner image reconstructed based on BPCSM matrix is about 26 dB, and the miner's facial contour is clear. When the sampling rate is 0.5, the PSNR of the miner image reconstructed based on BPCSM matrix has reached 30 dB, which can recover almost all the details of the miner image, indicating the better reconstruction performance of the BPCSM matrix. By selecting the appropriate Pascal matrix size, the reconstruction performance of the image signal can be further improved to meet the application requirements of the mine environment.

Digital recognition method of methane sensor based on improved CNN-SVM

TANG Shoufeng, SHI Jingcan, ZHOU Nan, ZHAO Renci, TONG Guangming, HUANG Jie

2022, 48(1): 53-57. doi: 10.13272/j.issn.1671-251x.2021070033

<Abstract>(128) <HTML> (48) <PDF>(21)

Abstract:
The methane sensor material has light reflection, and there are attachments on the display panel, which causes the poor quality of the sensor numerical image collected by the automatic verification system of methane sensor, and the difficulty of character recognition. However, the existing instrument character recognition methods based on machine learning have low recognition rate and slow algorithm running speed. In order to solve the above problems, a digital recognition method of methane sensor based on improved convolutional neural network (CNN) and support vector machine (SVM) is proposed. The numerical image of methane sensor is preprocessed by four steps, including image enhancement, numerical region image extraction, image segmentation and decimal point positioning. And the processed digital images are taken as a custom data set. In order to solve the problem of long running time of the CNN-SVM model, PCA algorithm is used to reduce the dimension of the image characteristics extracted from the CNN fully connected layer, and the most important data characteristics are used to replace the original data as the samples of the SVM classifier for classification and recognition. The verification results on the custom dataset show that the improved CNN-SVM model has higher accuracy and shorter running time than the traditional CNN model and CNN-SVM model. The verification results on the classical MNIST dataset show that considering the precision and real-time requirements, the improved CNN-SVM model has better comprehensive performance than CRNN, SSD, YOLOv3 and Faster R-CNN. A micro high-definition USB camera is used to collect the numerical images of methane sensor. The trained improved CNN-SVM model is transplanted to raspberry pi for image processing and recognition. The results show that the recognition success rate of methane sensor digital recognition method based on improved CNN-SVM is 99%, which is consistent with the simulation analysis results.

Noise reduction method for wire rope damage signal under strong noise background

WU Dong, ZHANG Baojin, LIU Weixin, LI Guang, GONG Tao, YANG Jianhua

2022, 48(1): 58-63. doi: 10.13272/j.issn.1671-251x.2021070012

<Abstract>(193) <HTML> (60) <PDF>(15)

Abstract:
The wire rope damage signal is a kind of non-stationary and non-periodic impact signal, and the noise reduction processing and characteristic extraction of its characteristic signal become difficult problems to be solved urgently. If the wavelet base or decomposition layer number of wavelet transform method is not suitable, which will introduce other noise interference while reducing signal noise, and affect the effect of signal processing and characteristic extraction. Compared with the wavelet transform, the moving average method only needs to select a certain shift window width to achieve effective noise reduction, but the shift window width needs to be selected artificially, and the blindness is large. In order to solve the above problems, a noise reduction method of wire rope damage signal under strong noise background is proposed. Different types of broken wire data are collected by magnetic flux leakage (MFL) sensor of wire rope, and strong Gaussian white noise is added to the signal to simulate the strong noise background. The adaptive moving average method is used to reduce the noise of the wire rope damage signal, and the quantum particle swarm optimization (QPSO) algorithm is used to optimize the window width of the moving average method. The signal-to-noise ratio (SNR) of the damage signal is used as the fitness function, and the SNR of damage characteristic signal is maximized by the QPSO algorithm, so as to achieve the optimal signal noise reduction effect. The experimental results show that compared with wavelet transform, the adaptive moving average method has more obvious noise reduction effect, higher signal-to-noise ratio and smoother signal for wire rope stationary and fluctuating signals under strong noise background. The measured results show that the noise reduction effect of the adaptive moving average method is also better than that of the wavelet transform for the wire rope damage signals with relatively weak noise on site, which verifies that the adaptive moving average method has good universality.

Ontology construction and safety rule reasoning of main types of work in coal mine

WU Panxin, LIU Peng, SHU Ya, YU Qiankun, DING Enjie

2022, 48(1): 64-70. doi: 10.13272/j.issn.1671-251x.2021080053

<Abstract>(109) <HTML> (48) <PDF>(14)

Abstract:
At present, the ontology of coal mine field focuses on the prediction of accidents, and there is no ontology research for the operation safety of coal mine operating personnel. In order to detect the dangerous operation of operating personnel in time to provide safety warning for operating personnel, a method of ontology construction and safety rule reasoning for main types of work in coal mine is proposed. According to the actual production situation of coal mine, the information of operating personnel, apparatus, operating methods, location, environment, accidents and state in coal mine production is formally represented. The main types of work ontology of coal mine covering coal mining system, roadway heading system, electromechanical transportation, geological survey, ventilation gas, comprehensive dust prevention, coal preparation plant and other production systems is constructed by ontology language. According to the safety production regulations in the professional literature of coal mine field, the safety rules are formulated based on Jena custom rule grammar, and the reasoning of operation safety of operating personnel in the main types of work ontology of coal mine is realized based on the safety rules. The experimental results show that it is effective and feasible to judge the safety state of operating personnel based on the ontology of main types of work and safety rules, which provides an auxiliary guarantee method for coal mine safety production.

Prediction model of water inrush in coal mine based on IWOA-SVM

QIU Xingguo, LI Jing

2022, 48(1): 71-77. doi: 10.13272/j.issn.1671-251x.2021050043

<Abstract>(153) <HTML> (86) <PDF>(18)

Abstract:
The traditional prediction algorithm of water inrush in coal mine is easy to fall into local optimum, the prediction results accuracy is low and the speed is slow. In order to solve the above problems, a prediction model of water inrush in coal mine based on improved whale optimization algorithm (IWOA) and support vector machine (SVM) is proposed. IWOA improves the whale optimization algorithm (WOA) from three aspects, whale population initialization, nonlinear adjustment factor and random differential evolution (DE). Tent mapping is used to initialize the whale population to improve the possibility of the whale population finding the optimal prey. The non-linear change strategy of the adjustment factor is applied to improve the global search capability of the algorithm in the early stage of the iteration and the local search capability in the later stage of the iteration so as to speed up the convergence speed. The mutation, crossover and selection operations of DE algorithm are introduced to enhance the global search capability of WOA. The parameters of SVM model are optimized by IWOA. The six factors affecting water inrush in coal mine, including water pressure, thickness of aquiclude, dip angle of coal seam, fault drop, distance between fault and working face and mining height are taken as the input characteristic vectors of the model. The two water inrush results of water inrush and safety are taken as the output vectors. The objective function is established to minimize the error between the water inrush prediction results and the actual results, and the coal mine water inrush prediction model based on IWOA−SVM is obtained. The experimental results show that IWOA has the highest prediction accuracy, minimum standard error, fast convergence and good robustness compared with particle swarm optimization, DE algorithm and WOA. The accuracy of water inrush prediction of IWOA−SVM is 100%. Compared with the traditional water inrush coefficient method, SVM and WOA−SVM, IWOA−SVM shows higher accuracy and stability.

CHEN Fang, ZHANG Jinman, XU Liangji, LI Jiewei, XU Ruirui, ZHANG Kun

2022, 48(1): 78-84. doi: 10.13272/j.issn.1671-251x.2021030080

<Abstract>(103) <HTML> (105) <PDF>(13)

Abstract:
The in-depth research on the breaking and deformation law of overburden rock under the geological and mining conditions of thick loose aquifer are lacking at present. Taking 11111 working face of Pansidong Coal Mine in Huainan mining area as the engineering background, the similar material model is constructed, and the digital photogrammetry extraction displacement method is used to record the overburden rock breaking process and overburden rock deformation during the model roadway heading. The causes of water loss and settlement of aquifer are analyzed. The overburden rocks form two main longitudinal diversion fissure zones under the action of W-type shear stress arch. The further development of the diversion fissure zone causes water loss and consolidation of the aquifer, and the aquifer is further compacted under the action of gravity of the thick loose layer. With the intensification of the overburden rock breaking movement, О type shear stress arch is formed under the joint extrusion of bending zone and overburden rock, which compresses the thin space and leads to the large amount of surface subsidence. The damage of overburden rock under water loss condition is analyzed. After the roadway heading work of the working face is completed and the overburden rock reaches a steady state, the front caving angle is 57°, the rear caving angle is 62°, and the height of the diversion fissure zone is 63 m. Under the action of stress concentration, the overburden rock above the open-cut hole and the stop-mining line is broken to produce longitudinal fissure, and the overburden rock in the area of the collapse zone above the open-cut hole and the stop-mining line produces lateral separation fissure. The longitudinal fissures and lateral separation fissures intensify the hydraulic connection between overburden rock and the aquifer. The dynamic movement law of overburden rock under water loss state is given. With the advance of mining face, the overburden settlement of each observation line increases gradually, and the overburden settlement of the observation line close to the working face is the largest. The trend of the subsidence curves of the observation lines in the overburden rock above the working face is basically similar, and the jump of the subsidence curves is consistent. The trend of the subsidence curves of the observation lines above the aquifer is basically consistent, and the jump of the subsidence curves is synchronous. The jump of the subsidence curves of observation lines in the overburden rock above the working face and the one of the observation line above the aquifer are asynchronous, indicating that the aquifer plays an important role in the movement and deformation of the overburden rock.

Roof pressure prediction method of coal working face based on spatiotemporal correlation analysis

LUO Xiangyu, LIU Junbao, LUO Yingxiao, XIE Panshi, WU Yongping

2022, 48(1): 85-90. doi: 10.13272/j.issn.1671-251x.2021100012

<Abstract>(125) <HTML> (85) <PDF>(21)

Abstract:
The roof pressure is usually measured by the hydraulic support working resistance, and the effect of the roof pressure prediction method based on depth learning is greatly affected by the training sample set. The construction of the training sample set depends on the selection of the time window and the identification of the closely related hydraulic support group. However, the existing methods rely on manual experience to determine the time window, and ignore the correlation between different hydraulic supports, which seriously hinders the improvement of the roof pressure prediction precision. In order to solve the above problems, a roof pressure prediction method of coal working face based on spatiotemporal correlation analysis is proposed. Firstly, the optimal time window is selected by calculating the grey correlation degree of working resistance series of the same hydraulic support in the time dimension. Secondly, the optimal auxiliary matrix is obtained by calculating the grey correlation degree of working resistance sequences of different hydraulic support in spatial dimension, and the closely related hydraulic support group is identified. Finally, based on the optimal time window and the optimal auxiliary matrix, the label and corresponding characteristics of each training sample are determined, and the training sample set is constructed to train the long short time memory (LSTM) model to predict the roof pressure. The experimental results show that the proposed method can reduce the prediction error of roof pressure effectively compared with the method which relies on manual experience to construct training sample sets to complete LSTM model training.

Prediction of strata behaviors law based on GRU and XGBoost

CHAI Jing, LIU Yilong, WANG Anyi, QU Shijia, OUYANG Yibo

2022, 48(1): 91-97. doi: 10.13272/j.issn.1671-251x.2021070062

<Abstract>(112) <HTML> (36) <PDF>(18)

Abstract:
In the process of using optical fiber frequency shift value monitored by optical fiber sensor to characterize the strata behaviors law, the data collected by the sensor is missing, and the strata behaviors law can not be accurately predicted. In order to solve this problem, taking Qianqiu Coal Mine as the engineering background, under the premise of partial data loss of the lower half of the optical fiber, two prediction models, GRU (Gated Recurrent Unit) and LSTM (Long Short-Term Memory), are introduced to compare and predict the missing optical fiber frequency shift value. The convergence speed of the GRU model is better than that of the LSTM model, which shows that the missing value processing method based on the GRU model is better. The original and complete optical fiber frequency shift value is converted into the average optical fiber frequency shift change which can characterize the strata behaviors position, and the XGBoost (eXtreme Gradient Boosting) model and the BP neural network model are introduced for comparative prediction. The XGBoost model can predict all the 'peak' positions in the test set accurately. However, the BP neural network model can only predict two 'peak' positions, which shows that the prediction effect of the XGBoost model is better than that of the BP neural network model. The predicted optical fiber frequency shift missing value is replaced to the missing position to form 'complete' optical fiber frequency shift value data. The data is converted into the average optical fiber frequency shift change and then the XGBoost model is used for prediction. The results show that both the LSTM model and the GRU model can predict the data of the lower half of the optical fiber accurately, and the GRU model has higher accuracy than the LSTM model. The XGBoost model can predict the periodic pressure in the test set accurately. After the missing data predicted by the GRU model is integrated into the missing position, the XGBoost model can still predict the strata behaviors effectively.

Design of voice miner's lamp based on WiFi

WANG Fei

2022, 48(1): 98-102. doi: 10.13272/j.issn.1671-251x.2021010077

<Abstract>(182) <HTML> (64) <PDF>(26)

Abstract:
In order to solve the problem that most of the existing miner's lamps only have the functions of lighting, positioning, environment perception and so on, and do not have the voice intercom function, a voice miner's lamp with voice intercom function based on WiFi is designed. The voice miner's lamp takes industrial Ethernet ring network and WiFi network as transmission platform, and adopts VoIP voice communication technology so as to realize voice playback, audio acquisition, and intercom function with the dispatching center. The audio codec chip is used to realize the conversion of voice analog signal and digital signal, and UDP protocol is applied to transmit the signal to the dispatching center so as to complete the two-way transmission of voice data and realize the integration of voice intercom and miner’s lamp lighting. This paper introduces the key technologies of voice intercom function in details. Audio data encoding format and cache management, reliable voice data transmission mechanism are used to ensure the accuracy of voice playback. The low-power sleep technology of WiFi module and microcontroller STM32L151 are used to reduce the average current of the voice miner's lamp and extend the working time. The test results show that the voice miner's lamp can meet the demand of voice intercom between the dispatching center and the underground workers, the communication distance between the voice miner's lamp and the WiFi base station can reach 400 m, the intercom transmission delay between the voice miner's lamp and the dispatching center is less than 1 s, and the multicast transmission delay between the voice miner's lamps is less than 3 s. The average current of the voice miner's lamp is less than 70 mA during intercom, and the average current is less than 5 mA during idle time.

Research on positioning and re-measurement mechanism of underground precise personnel positioning system

TANG Lijun, WU Wei, LIU Shisen

2022, 48(1): 103-108. doi: 10.13272/j.issn.1671-251x.2021090077

<Abstract>(201) <HTML> (80) <PDF>(33)

Abstract:
During the underground transmission of wireless signal, the measurement between card reader and marker card fails due to signal strength attenuation and interference. When the measurement fails, the marker card can only wait until the fixed measurement time slot in the next super-frame to measure the distance with the card reader again. As the marker card and the card reader re-measurement interval time is long, it is not conducive to control the real-time dynamic distribution of underground personnel in time. In order to solve this problem, a positioning and re-measurement mechanism of underground precise personnel positioning system is proposed. When the marker card measurement fails, the positioning and re-measurement mechanism uses the idle time slot to re-measure the marker card. When multiple marker cards compete for idle time slots for re-measurement, the hierarchical analysis method is used to determine the re-measurement priority of marker cards using idle time slots according to the accumulated re-measurement times, signal strength and movement speed of the marker cards. And the positioning card reader gives priority to the marker cards which fail in measurement according to the re-measurement priority level. The test results show that when the number of marker cards is less than 70, the positioning re-measurement mechanism can improve average the measurement success rate, reduce average the re-measurement delay, improve the time average slot utilization rate, and enable to monitor the uninterrupted marker card movement track in real time.

Construction and application of mine electromechanical equipment accident knowledge graph

LI Zhe, ZHOU Bin, LI Wenhui, LI Xiaoyun, ZHOU You, FENG Zhanke, ZHAO Han

2022, 48(1): 109-112. doi: 10.13272/j.issn.1671-251x.2021100009

<Abstract>(330) <HTML> (148) <PDF>(71)

Abstract:
It is difficult to judge the root cause of equipment accident from the appearance of coal mine electromechanical equipment accident and part of monitoring data, and there is a lack of effective methods to improve the efficiency of equipment accident treatment by using historical data and experience knowledge. In order to solve the above problems, the mine electromechanical equipment accident knowledge graph is constructed. Firstly, the data relationships of the four-group ontology model are designed, and the ontology and the relationship types between the ontologies are determined. Secondly, according to the designed data relationships, a combination method of machine learning and rule templates is used to extract entities, relationships and attributes from databases and texts. Finally, based on the Python language, through the py2neo library, the entities, relationships and attributes are created and stored in the Neo4j graph database with Cypher statements, so as to realize the construction and update of the knowledge graph. The application of mine electromechanical equipment accident knowledge graph in mine electromechanical equipment accident diagnosis, risk management and intelligent question and answer can enable users to effectively use related knowledge of mine electromechanical equipment accident, help equipment maintenance personnel to quickly find the accident chain, locate the cause of the accident and put forward maintenance schemes, so as to achieve the purpose of reducing the accident rate and the accident handling time.

Research on denoising method of remote sensing image in mining area

CHE Shouquan, LI Tao, BAO Congwang, JIANG Wei

2022, 48(1): 113-118. doi: 10.13272/j.issn.1671-251x.2021090086

<Abstract>(149) <HTML> (67) <PDF>(17)

Abstract:
Denoising is an important preprocessing step for the effective application of remote sensing images in mining area. The existing remote sensing image denoising methods based on statistics, domain transformation and learning generally have the problems of excessive smoothing of details and insufficient texture preservation. Based on the good edge-preserving property of guided filtering, an iterative guided filtering method is proposed. The method enhances the edge characteristics extraction effect of remote sensing images by guided mapping of residual information, and iteratively performing guided filtering and hyper-parameter shrinkage. The iterative guided filtering is combined with traditional wavelet soft threshold, non-local mean (NLM) filtering, block matching 3D(BM3D) filtering and other denoising methods, which improves the peak signal-to-noise ratio of the traditional method effectively. Among them, NLM filtering and BM3D filtering have the most obvious effects on improving the denoising performance. The iterative guided filtering and BM3D filtering are fused, and the denoised images are initially obtained through BM3D filtering to obtain residual data. The iterative guided filtering is used to process the residual data. While improving the image denoising effect, the image detail characteristics are well preserved. The iterative guided filtering and BM3D filtering fusion method are used for coal gangue yard identification and landslide area edge recognition in remote sensing images of mining areas, and good results have been achieved.

Blasting pressure relief technology for preventing rock burst in deep heading roadway

MA Wentao, MA Xiaohui, LYU Dazhao, WANG Bing, ZHU Gangliang

2022, 48(1): 119-124. doi: 10.13272/j.issn.1671-251x.2021030088

<Abstract>(277) <HTML> (74) <PDF>(34)

Abstract:
In order to solve the problems of low pressure relief intensity, untimely pressure relief and high labor intensity in the prevention and control of rock burst by using large diameter borehole pressure relief in deep heading roadway, taking the 401103 withdrawal roadway of Mengcun Coal Mine in Binchang mining area of Shaanxi Province as the engineering background, the main control factors of rock burst are analyzed. It is considered that the strong rock burst tendency, large buried depth and fault structure of coal and rock layers are the main reasons of rock burst. Coal and rock layers have strong rock burst tendency, which makes the coal rock system capable of generating rock burst. The large buried depth of the working face leads to a high level of concentrated static load, which reduces the threshold for rock burst. The high concentrated static load in the main bearing area superimposes the concentrated dynamic load released by fault energy accumulation, which can easily induce shock start and lead to the appearance of rock burst. The use of blasting pressure relief to prevent rock burst is manifested in structural reconstruction, stress release and energy consumption. The implementation of blasting cracking in the peak area of the supporting pressure of the surrounding rock of the heading roadway can form a pressure relief protection zone in the surrounding rock of the roadway, thereby reducing the tendency of coal rock burst, weakening high concentrated stress, increasing rock burst energy consumption and reducing the risk of rock burst. For the 401103 withdrawal roadway, the blasting pressure relief scheme of roof, heading face and side are proposed. And the effect of pressure relief and anti-rock burst is tested by seismic wave CT detection and micro-seismic monitoring. The results show that after adopting the blasting pressure relief scheme, the area of the high stress area is reduced by 50%, and the stress concentration is significantly reduced. The average energy of microseismic events is significantly reduced, the energy is all less than 10⁴ J. And there is no sharp change in the energy of microseismic events and the pressure relief effect is good.

2022 Vol. 48, No. 1

Submission System

Latest AcceptedMore>