工矿自动化

Current situation and development trend of rock bolting construction equipment in coal roadway

KANG Hongpu, JIANG Pengfei, LIU Chang, WANG Ziyue, LUO Chao, GUO Jichang, CHEN Zhiliang, CAO Xiaoming

2023, 49(1): 1-18. doi: 10.13272/j.issn.1671-251x.18064

<Abstract>(1310) <HTML> (63) <PDF>(154)

Abstract:
The rock bolting construction equipment is an important part of the complete set of bolt support technology in coal roadway, which directly affects the speed and quality of rock bolting. After a long period of development, China's coal mines have developed various forms of rock bolting equipment, including single bolter, mobile bolter, roadheader bolter, bolter miner, bolter conveyor and straddle bolter. This paper systematically analyzes the development history, technical performance, technical parameters, applicable conditions and latest development of six kinds of rock bolting construction equipment. The single bolter is light, flexible and mature in technology, forming a series of products, which are widely used. The onboard bolter can be integrated on different platforms to form a variety of integrated construction equipment. The mobile bolter has formed a variety of models from two arms to nine arms. It can closely follow the heading equipment, work alternately with the heading equipment, and complete the rock bolting construction with multi-arm cooperation and multi-arm parallel operation. The onboard bolter is equipped on the cantilever roadheader, and various types of roadheader bolters are developed, realizing two functions of heading and bolt construction. The bolter miner has realized localization. The bolter miner with forward moveable bolting platform, shield type bolter miner and bolter miner with the integration of drilling and bolting are developed. The bolter conveyor from two arms to seven arms and the ten-arm straddle bolter are developed. The rock bolting, heading and transportation have been carried out in different zones. This paper introduces the technology and equipment of rock bolting with the integration of drilling and bolting. They include bolt with the integration of drilling and bolting, pump-injected anchoring agent, onboard bolter with the integration of drilling and bolting, drill box, rock bolt bin, anchoring agent pump-injection system and intelligent control system. The traditional six-step rock bolt construction process is simplified into one continuous process. It realizes the automatic operation of "one key rock bolting", significantly improving the speed and automation degree of rock bolting. The paper points out the development trend of rock bolting construction equipment in coal roadway. The trend includes following aspects: the digital intelligent bolt onboard bolter, onboard bolter positioning, pose self-adjustment and multi-onboard bolter collaborative control technology; the optimization of bolt (cable) structure and materials, upgrading of anchor grouting materials and improvement of construction equipment; the environmental dynamic sensing and stability discrimination of surrounding rock with heading; the fault diagnosis technology of rock bolting construction equipment and the online monitoring of roadway surrounding rock deformation and bolt load; establishing a big data platform to realize automation and intelligenitization of rock bolting.

Design of metasurface dual-gas sensor based on VO₂

LIU Hai, WAN Yinhui, CHEN Cong, GAO Peng, DAI Yaowei, ZHAO Jiaming, WANG Xinyan, LU Xiangyu, ZHAO Siyi

2023, 49(1): 19-27, 79. doi: 10.13272/j.issn.1671-251x.18041

<Abstract>(257) <HTML> (52) <PDF>(25)

Abstract:
The traditional mine gas sensor is vulnerable to the influence of temperature and ambient humidity and other factors, resulting in low stability. In order to solve the above problem, based on the principle of local surface plasmon resonance (LSPR) and the phase change characteristics of vanadium dioxide (VO₂), a kind of metasurface dual-gas sensor based on VO₂ is designed. The sensor structure is composed of three layers, and the surface is composed of multi-layer metal-dielectric-metal (MDM) structure. According to the phase change characteristics of VO₂, the metal plate is heated in the form of resistance heating by changing the applied bias voltage. The temperature of VO₂ is carefully controlled, and the different states of VO₂ are simulated by changing the conductivity of VO₂. When VO₂ is in a high-temperature metal state, the upper three layers form MDM structure. VO₂ shows metal properties and excites local surface plasmon resonance (LSPR) at 1721.3 nm to realize methane detection. The sensor's absorptance reaches 94.3%, and the methane sensitivity reaches 4.21 nm/%. When VO₂ is in a low-temperature insulation state, the lower three layers form MDM structure. LSPR is excited at 2694.6 nm to realize hydrogen detection. The sensor's absorptance reaches 95.9%, and the hydrogen sensitivity reaches 2.10 nm/%. When the environmental refractive index changes, the absorption peaks of VO₂ in both states are red-shifted and linear,which can be used to detect the change of the environmental refractive index. In order to verify the feasibility of the sensor, six different concentrations of methane, hydrogen and four different environmental refractive indexes are simulated and analyzed. The results show that the metasurface dual-gas sensor based on VO₂ can effectively detect methane and hydrogen with lower concentration. The sensitivity is greatly improved compared with the existing gas sensors. The error between the calculated and theoretical values of the resonant peak shift and the environmental refractive index change and the methane volume fraction change is very small. This indicates that the sensor has high accuracy. By analyzing the relationship between the environmental refractive index and the resonant wavelength, it is concluded that the sensor also has high detection sensitivity when the environmental refractive index changes.

Prediction model of coal spontaneous combustion temperature based on data filling

ZHAI Xiaowei, LUO Jinlei, ZHANG Yuchen, SONG Bobo, HAO Le, ZHOU Yujie

2023, 49(1): 28-35, 98. doi: 10.13272/j.issn.1671-251x.2022090032

<Abstract>(241) <HTML> (85) <PDF>(34)

Abstract:
Most of the existing coal spontaneous combustion temperature prediction models are based on relatively complete index gas sample data. However, the index gas data are affected by instruments or human factors. There are often data missing phenomena, resulting in low accuracy and over-fitting of coal spontaneous combustion temperature prediction. In order to solve the above problems, the paper proposes to apply filling algorithms such as K-nearest neighbor algorithm (KNN), random forest algorithm (RF), decision tree algorithm (DT) and support vector regression algorithm based on particle swarm optimization (PSO-SVR) to fill in the missing values. The missing data and the filled data are trained by RF, SVR and extreme gradient boosting (XGBoost) algorithm respectively. The parameters are optimized by the PSO algorithm. The RF, XGBoost and SVR coal spontaneous combustion temperature prediction models based on data filling are constructed. CO, CO₂, CH₄, C₂H₆ and O₂ are selected as index gas in coal spontaneous combustion experiment, and six kinds of random data missing are designed. The overall missing rates are designed as 10%, 20% and 30%. The missing rates of CO and CO₂ are designed as 40%, 50% and 60%. The average absolute error percentage (MAPE) is used as the filling effect evaluation index. The MAPE, the judgment coefficient R² and the root mean square error (RMSE) are used as the model performance evaluation index. Four filling algorithms and three prediction models are compared. The results of the comparative analysis show the following points. The DT filling algorithm has better filling effect than the other three algorithms in six kinds of missing data cases. When there are more missing values of CO and CO₂, the MAPE between the filling value and the actual values of the RF algorithm is large. The XGBoost model works extremely well in the training set without adjusting the parameters, but it is very prone to overfitting. The prediction effect of SVR model is very poor and the model cannot meet the prediction requirements. In the case of six kinds of data missing, the MAPE of PSO-SVR, RF and PSO-RF coal spontaneous combustion temperature prediction models based on the DT filling algorithm are about 4%. The RF model based on the DT filling algorithm can predict the coal spontaneous combustion temperature without optimization and has good stability.

Study on dynamic response characteristics of resistivity in mining failure process of working face

LU Jingjin

2023, 49(1): 36-45, 108. doi: 10.13272/j.issn.1671-251x.18052

<Abstract>(197) <HTML> (57) <PDF>(15)

Abstract:
The mine resistivity method plays an important role in monitoring hidden danger of water hazards in coal working face. However, the abnormal response of mining failure process of coal working face will interfere with the identification of hidden danger of floor water hazards. In order to improve the interpretation precision of the mine resistivity method for monitoring hidden danger of floor water hazard in coal working face, simultaneously considering the influence of overburden failure and floor failure, a dynamic geoelectric model of the mining failure process in coal working face is established. The roof monitoring and floor monitoring are respectively carried out through three-dimensional numerical simulation and inversion imaging of mine resistivity method. The dynamic response characteristics of resistivity in the mining failure process are analyzed. The resistivity response characteristics of floor water hazard are identified and extracted. The analysis results show that the resistivity anomaly area formed in the process of mining failure moves forward with the advancing of the working face. There will be relatively low resistivity anomaly in the action range of the advance support pressure, and relatively high resistivity anomaly in the goaf area. The resistivity response at the fixed position of the working face will experience a process of first decreasing, then increasing, and then decreasing in the mining process. This process is basically consistent with the periodic stress change and failure process of the roof and floor in the mining process of the working face. The low resistance abnormal response intensity of floor water hazard is related to its position relative to the working face. When the distribution range of floor water hazard overlaps with that of goaf, the high resistance abnormal response of goaf will weaken the low resistance abnormal response of floor water hazard. When the distribution range of floor water hazard danger overlaps with the area affected by the advance support pressure, the low resistance abnormal response of the two will be superimposed together. The low resistance abnormal response can be enhanced to a certain extent. The influence of the mining damage process can be eliminated after the pure anomaly extraction of the hidden danger of floor water hazard. The pure abnormal response intensity of floor water hazards at different positions is basically the same, and their vertical influence scope is larger than that of mining damage.

Study on evaluation method of insulation performance of mine cable based on dielectric response method

LEI Zhipeng, LI Wei, HE Qinghui, MEN Rujia, WANG Ye, LIU Yang, LIN Lingyan

2023, 49(1): 46-55. doi: 10.13272/j.issn.1671-251x.18047

<Abstract>(1305) <HTML> (122) <PDF>(24)

Abstract:
The high voltage cable used in mine is affected by many factors, such as electricity, heat and machinery stress. These factors accelerate insulation aging and easily lead to cable leakage, short circuit or discharge. At present, the dielectric response method is introduced into analysis, evaluation and diagnosis of insulation performance and aging state of mine cables. In view of problems of insulation performance and aging state evaluation of mine cables, the commonly used ethylene propylene diene monomer (EPDM) insulated mobile flexible cable for mining is taken as the research object. The basic principles and typical characteristics of recovery voltage method, polarization/depolarization current method and frequency-domain dielectric spectroscopy method in dielectric response method are summarized. The advantages and disadvantages of the three methods are compared. The characteristics of cable insulation performance evaluation based on the dielectric response model are introduced. The characteristics include the aging factor extracted by the extended Debye model, relaxation characteristics extracted by the modified dielectric relaxation model and dielectric loss integral spectrum. The application of the dielectric response method in the evaluation of the insulation performance of mine cables is summarized from the following aspects. The aspects include the identification of trace corrosion degree of mine cables based on recovery voltage method and polarization/depolarization current method. The aspects include the evaluation of EPDM insulation multi-stress aging state based on polarization/depolarization current method and isothermal relaxation current, based on dielectric relaxation model and based on dielectric loss integral value. The existing online monitoring technology for the evaluation of the insulation performance of mine cables based on the dielectric response method cannot adapt to the working conditions of coal mines. The evaluation data is insufficient, and the relationship between the insulation deterioration degree and the characteristic quantity is unknown. In order to solve the above problems, this paper puts forward that the research should focus on two key technologies, namely, cable insulation state perception and the relationship between insulation degradation degree and characteristic quantity construction.

The essence, goal and technical method of intelligent coal mine data classification and coding

TAN Zhanglu, WANG Meijun

2023, 49(1): 56-62, 72. doi: 10.13272/j.issn.1671-251x.18032

<Abstract>(908) <HTML> (78) <PDF>(51)

Abstract:
Intelligent coal mine data classification and coding is a key part of intelligent coal mine data governance and fusion sharing standard system. However, there is no perfect methodology system. It is urgent to deeply study the technical objectives, technical principles and key technical processes of intelligent coal mine data classification and coding. Based on the analysis of the core problems to be solved in the process of data classification and coding in the advanced stage goal realization of the intelligent coal mine, the essence of intelligent coal mine data classification and coding is expounded. Intelligent coal mine data classification and coding is the recognition and construction of the intelligent coal mine information world, the optimization and mapping of the intelligent coal mine consciousness world, and the transformation and description of the intelligent coal mine physical world. This paper analyzes the goal requirements of intelligent coal mine data classification and coding from three aspects of overall strategic objectives, business strategic objectives and functional strategic objectives. Intelligent coal mine data classification and coding should promote the reshaping of the business mode of coal enterprises, change the value creation driving mode, focus on key value activities, and realize the scientific organization of intelligent coal mine data. The paper proposes that the intelligent coal mine data classification and coding should follow the basic principles of scientificity, standardization, integrity, uniqueness and effectiveness. The paper also proposes the basic idea of intelligent coal mine data classification and coding. Intelligent coal mine should adopt the data classification idea of "benchmark- expansion" two stages. In the first stage, the logical sequence of "business domain - data domain - object - attribute - data element" is adopted to determine the classification benchmark of intelligent coal mine data. In the second stage, the logical sequence of "intelligent application system - intelligent business system - system functions - data resources" is adopted for data classification, verification and supplement. The hierarchical coding method of line classification should be adopted for intelligent coal mine data coding. Based on the above basic ideas, it is pointed out that in general, intelligent coal mine data classification and coding needs to focus on five key steps: determining business domain, determining data domain, identifying object classes, extracting object class attributes and defining data elements.

Fusion denoising algorithm for vibration signal of mine hoist with low signal-to-noise ratio

WANG Houchao, NIU Qiang, CHEN Pengpeng, XIA Shixiong

2023, 49(1): 63-72. doi: 10.13272/j.issn.1671-251x.18019

<Abstract>(175) <HTML> (43) <PDF>(19)

Abstract:
Aiming at the nonlinear and low signal-to-noise ratio characteristics of mine hoist vibration signal in complex environments, a mine hoist vibration signal fusion denoising algorithm based on complete EEMD with adaptive noise (CEEMDAN) and adaptive wavelet threshold is proposed. Firstly, the CEEMDAN algorithm is used to decompose the noisy mine hoist vibration signal to obtain the intrinsic mode component (IMF) and the residual. The IMF component is judged for high and low frequency. The t-test method is used to test whether the mean value is significantly different from 0. The IMF component which tends to 0 is the high-frequency component, and the IMF component which is significantly different from 0 is the low-frequency component. Secondly, the appropriate wavelet basis function and decomposition level are selected. The high-frequency IMF component is denoised by using the adaptive wavelet threshold method. Finally, the processed high-frequency IMF components and the unprocessed low-frequency IMF components are reconstructed with the residuals to obtain the de-noised vibration signal from the fusion algorithm. The CEEMDAN denoising method, CEEMD-wavelet threshold combined denoising method, CEEMDAN-wavelet threshold combined denoising method and CEEMDAN-adaptive wavelet threshold fusion denoising method are used to denoise the simulated signal respectively. The results show the following points. ① The signal denoised by the CEEMDAN-adaptive wavelet threshold fusion denoising method is similar to the original signal in local waveform features and signal peak values. Some features of the signal waveform have been restored well. The feature information of the original signal has been well preserved in the process of denoising. ② The composite evaluation index H is used as the objective evaluation standard. The H value of the CEEMDAN-adaptive wavelet threshold fusion denoising method is the smallest. This shows that the denoising effect of the fusion denoising algorithm for the simulation signal is better than that of other denoising methods. The experiment is carried out on the running mine hoist in a mine in Heilongjiang Province. The results show the following points. ① The db4 wavelet basis function is used to decompose the noisy IMF component in four layers. The signal de-noised by CEEMDAN-adaptive wavelet threshold fusion de-noising method is smooth. Some waveform features of the signal have also been restored well. While removing the noise, the feature information of the original signal has been retained to the greatest extent. ② In the actual mine hoist vibration signal denoising process, the CEEMDAN-adaptive wavelet threshold fusion denoising method has the smallest H value and the best denoising effect.

Research on pipe-following hole protection drilling technology in broken soft coal seam of the isolated island working face

CHEN Chao, CHEN Tianzhu, ZHANG Majun, WANG Changwei

2023, 49(1): 73-79. doi: 10.13272/j.issn.1671-251x.2022040084

<Abstract>(203) <HTML> (56) <PDF>(14)

Abstract:
It is easy to get stuck and collapse in the borehole of high stress and broken soft coal seam in the isolated island working face. This leads to great difficulty in borehole formation and poor gas extraction effect. In order to solve this problem, this paper puts forward a pipe-following borehole protection drilling technology. The 3206 isolated island working face of Wangpo Coal Mine is selected as the test site. It is analyzed that the working face needs to use high-torque and high-speed drilling rig to enhance the slag removal effect of the drilling tool and the capability to deal with accidents in the borehole. At the same time, it is necessary to consider the process of drilling wall protection in the high-stress section and the efficient slag removal process in the borehole. It is proposed to adopt the pipe-following borehole protection drilling technology in the high stress zone to achieve the effect of wall protection. The spiral drilling nitrogen-assisted slag removal process is adopted to enhance slag removal capacity and reduce the risk of coal spontaneous combustion during drilling. After the borehole passes through the high-stress area, the drilling depth of the borehole in the broken soft coal seam is further improved by optimizing the drilling tool assembly. The field test results show that the average hole depth is increased by 149% when using the second-stage hole protection drilling than when using rotary drilling directly. The average hole depth is increased by 114% when using the third-stage hole protection drilling. It shows that the pipe-following hole protection drilling is more suitable for the drilling construction of broken soft coal seam in 3206 island working face than the rotary drilling construction technology. The hole-forming rate of the plug-type screw drill pipe is higher than that of the screw thread-type screw drill pipe. The hole-forming depth of nitrogen assisted slag removal process for screw drilling is significantly greater than that of the dry screw slag removal process. ${\text{ϕ}} $100/63.5-28 mm plug-in sealed spiral drill pipe and nitrogen assisted slag removal process are most suitable for gas pre-extraction drilling construction in 3206 isolated island working face. The average hole depth is 100.6 m, and the hole formation rate is 80%. The gas extraction effect is better than other drilling tools and drilling slag removal technology.

Boom-type roadheader autonomous speed regulation cutting control system

ZHANG Xuhui, SHI Shuo, YANG Hongqiang, YANG Wenjuan, ZHANG Chao, WANG Tian

2023, 49(1): 80-89. doi: 10.13272/j.issn.1671-251x.2022110066

<Abstract>(1082) <HTML> (42) <PDF>(32)

Abstract:
The existing boom-type roadheader cutting control adopts a relatively simple control method and the cutting head completes the roadway section cutting at a constant speed. There's no comprehensive consideration of trajectory planning and autonomous speed control. Therefore, it is difficult to achieve high roadway engineering quality under complex geological conditions. In order to solve the above problems, a boom-type roadheader autonomous speed regulation cutting control system is proposed. Firstly, the three-dimensional model of the cutting head and coal seam are established and imported to ABAQUS software for finite element analysis. The relationship between the reaction force on the cutting head and the swing speed of the cutting arm is obtained. Then the relationship between the swing speed of the cutting arm and the acceleration of the cutting head is obtained. The acceleration is stratified by k-means clustering method. Secondly, the collision detection model of the cutting head is established by using the bounding volume hierarchy algorithm. The appropriate cutting trajectory of the rectangular roadway section is planned. The discrete cutting path planning points are generated through multiple discretizations. The inverse kinematics solution of the cutting arm is calculated to obtain the rotation radian, lifting radian and elongation of the cutting arm required for the cutting head to reach the discrete cutting path planning point. The global optimal speed model is used to solve the speed of the cutting head to move to the discrete cutting path planning point. Finally, the acceleration sensor is used to collect the vibration signal of the cutting arm. The target swing speed of the cutting arm is determined according to the acceleration layering result. Through fuzzy PID control, the swing speed of the cutting arm is adjusted to the target swing speed in time and accurately with the change of the cutting head acceleration. The experimental results show that the fuzzy PID control can achieve a relatively fast and non-overshoot swing speed adjustment of the cutting arm. Compared with the constant speed cutting control, the roadway section forming quality using the autonomous speed control cutting control is high. The width specification deviation is reduced by 37%, and the height specification deviation is reduced by 17%. The results meet the requirements of roadway forming quality specified in MT/T 5009-1994 Standard for quality inspection and assessment of coal mine roadway engineering.

Drill pipe counting method based on improved spatial-temporal graph convolution neural network

DU Jingyi, DANG Mengke, QIAO Lei, WEI Meiting, HAO Le

2023, 49(1): 90-98. doi: 10.13272/j.issn.1671-251x.2022030098

<Abstract>(245) <HTML> (156) <PDF>(35)

Abstract:
There are some problems in the existing drill pipe counting methods, such as repeated labor, large counting error, and failure to consider the timing information of actions. In order to solve the above problems, a drill pipe counting method based on an improved multi spatial-temporal graph convolution neural network (MST-GCN) model is proposed. Firstly, the video data of underground drilling is obtained through the mine monitoring camera. The Alphabose algorithm is used to extract the key points of the human body from the image sequence. The human skeleton on a single frame image and the skeleton sequence data on a continuous image sequence are obtained. The skeleton sequence representing human actions is built. Secondly, the MST-GCN model is designed based on the spatial-temporal graph convolution neural network (ST-GCN) model. The far space partition strategy is used to focus on the motion information of the key points that are far away from the skeleton. The squeeze and excitation network (SENet) is used to fuse the original space features and the far space features, so as to effectively identify the action categories on the skeleton sequence. Finally, support vector machine is used to identify the drilling pose on the drilling video to decide whether to save the skeleton sequence. If the sequence length is saved to 150 frames, the MST-GCN model is used to identify the action category. The identification interval of adjacent actions is set according to the actual drilling time, so as to record the number of actions and realize the drill pipe counting. The experimental results show that the recognition accuracy of the MST-GCN model is 91.1% on the self-built data set, which is 6.2%, 19.0% and 4.8% higher than that of ST-GCN, Alphapose-LSTM and NST-GCN, respectively. The loss value of the MST-GCN model converges below 0.2, and the learning capability is stronger. On the drilling videos under the same conditions, the average error values of the MST-GCN model, the artificial method and the improved ResNet method are 0.25, 0.75 and 21 respectively, which shows that the counting effect of the MST-GCN model is better. The average error of MST-GCN model is 9 and the miscount is low in the field application of drilling 1 300 pieces, which can meet the actual requirements.

Mine infrared image enhancement algorithm based on dual domain and ILoG-CLAHE

FAN Weiqiang, LI Xiaoyu, WENG Zhi, LIU Bin, YANG Kun

2023, 49(1): 99-108. doi: 10.13272/j.issn.1671-251x.18033

<Abstract>(268) <HTML> (45) <PDF>(24)

Abstract:
The complex working environment of mine leads to the degradation of the infrared image. The existing infrared image enhancement algorithm is easy to lose the scene details or causes the target edge blur while improving the signal-to-noise ratio and contrast. In order to solve the above problems, a mine infrared image enhancement algorithm based on dual domain decomposition coupling improved Gaussian Laplacian (ILoG) factor and contrast limited adaptive histogram equalization (CLAHE) (ILoG-CLAHE) is proposed. Firstly, the dual domain decomposition model is used to decompose the mine infrared image into a detailed sub-images containing high-frequency information and a basic sub-images containing low-frequency information. Secondly, the CLAHE algorithm is used to improve the brightness, contrast and definition of the basic sub-images to highlight the general features of the monitoring scene. The constructed ILoG operator is used to suppress noise and sharpen edges of detail sub-images and eliminate gradient inversion. Thirdly, the reconstructed image with improved image quality is obtained through the basic sub-image and detail sub-image after reconstruction processing. Finally, a Gamma correction function of gray level redistribution is designed to adjust the brightness of the reconstructed image. The mine infrared-enhanced image is obtained. The performance of the algorithm is analyzed by subjective vision and objective indicators. The results show that the overall visual effect and objective index of the mine infrared image enhanced by the mine infrared image enhancement algorithm based on dual domain and ILoG-CLAHE have been greatly improved. The comprehensive enhancement performance and robustness are better. Compared with the original mine infrared image and the six comparison algorithms, the comprehensive evaluation index values of this algorithm are increased by 0.28, 0.11, 0.23, 0.38, 0.57, 0.04, and 0.10 respectively. The six algorithms include CLAHE algorithm, bilateral filtering(BF) decomposition and CLAHE enhancement of basic sub-images (BF-CLAHE) algorithm, BF decomposition and Gamma transform (BF-Gamma) algorithm, guided filtering and Gamma transform (GF-Gamma) algorithm, adaptive histogram equalization(AHE) coupled Laplacian transform (AHE-LP) algorithm, and un-sharp mask(UM) based layer fusion (LF-UM) algorithm. The brightness, clarity and contrast of images are greatly improved, and noise suppression and edge sharpening are realized. It shows that the algorithm is suitable for the enhancement of infrared images in the complex working environment of mine.

Coal and rock identification method based on Kalman optimal estimation of load data of rocker arm pin axle of shearer

SHI Guangliang, YU Rui, WANG Haiyan, GE Jinming, ZHANG Shengtao

2023, 49(1): 109-115, 122. doi: 10.13272/j.issn.1671-251x.2022060093

<Abstract>(149) <HTML> (54) <PDF>(11)

Abstract:
The shearer's coal and rock identification technology is the basis of intelligent control. The existing coal and rock identification method for the site environment and testing equipment requirements are higher. The actual fully mechanized working face is difficult to meet the necessary conditions. In order to solve the above problems, a coal and rock identification method based on the Kalman optimal estimation of the shearer rocker pin axle load data is proposed. On the basis of not increasing external auxiliary instruments and equipment, the rocker pin axle sensor is used to replace the existing pin axle to sense the coal and rock load, which can better adapt to the environment. By measuring the strain data of the rocker pin axle sensor located at the connection between the rocker arm and the connecting frame, the Kalman optimal estimation method is used to reduce the noise of the load data. The load intervals of the shearer under different working conditions such as cutting coal and rock are separated from each other. By judging the interval of the real-time load value, the coal and rock interface can be identified. The identification of coal and rock is verified on a fully mechanized experimental platform. The load of the rocker pin axle at the upper end of the coal wall side along the shearer traction direction is analyzed in three stages: no-load, cutting the coal wall and cutting the rock. The results show that before the load data is processed, there is overlap between the load intervals of cutting the coal wall and cutting the rock, and the coal and rock interface identification cannot be completed accurately. After the load data is processed by the Kalman optimal estimation algorithm, the load intervals under no-load, cutting the coal wall and cutting the rock conditions are separated from each other. In addition, the load interval length of each working condition is shortened by 65.6%-83.3%, and the mean square deviation is reduced by 66.5%-72.9%. The data fluctuation is smaller, which effectively improves data identification. In practical engineering applications, the expected load stress range in the coal seam cutting state can be set according to the method. Once this range is exceeded, it is judged that this is not a cutting the coal wall state and thus coal and rock identification is achieved.

Research on coal and rock recognition model based on improved 1DCNN

YIN Yuxi, ZHOU Changfei, XU Zhipeng, SHI Chunxiang, HU Wenyuan

2023, 49(1): 116-122. doi: 10.13272/j.issn.1671-251x.2022080051

<Abstract>(876) <HTML> (69) <PDF>(47)

Abstract:
With the acceleration of intelligent construction of coal mines, efficient recognition of coal and rock has become a technical problem to be solved urgently in intelligent coal mining. The existing coal and rock recognition methods under complex coal mine geological conditions have problems of low precision, poor universality and are difficult to apply in engineering. In order to solve the above problems, a coal and rock recognition model based on improved 1-dimensional convolutional neural network (1DCNN) is proposed. Based on the 1DCNN, a plurality of continuous convolution layers are used for extracting one-dimensional vibration signal features. The global average pool (GAP) layer is used for replacing the full connection layer. The model training parameters are reduced, and computing resources are saved. At the same time, a cosine annealing attenuation method with a linear hot start is adopted for optimizing the learning rate. Therefore, the model training is prevented from falling into a local minimum region, and the training quality is improved. In order to intuitively describe the feature extraction process and classification capability of the improved 1DCNN model for coal and rock cutting vibration data, the t-distributed stochastic neighbor embedding (t-SNE) manifold learning algorithm is used to visually analyze the feature learning process of the model. The results show that the improved 1DCNN model can realize the recognition of coal and rock cutting states well through feature learning layer by layer. Based on the measured vibration data obtained in the process of coal and rock cutting of the MG 650/1590-WD shearer in a mine in Shaanxi province, the model is trained and the result shows that the accuracy of the improved 1DCNN model is 99.91% on the training set and 99.32% on the test set. The model can be directly used to classify the original vibration signals of the shearer in coal and rock cutting, and can effectively identify the cutting state of coal and rock. Compared with traditional machine learning, ensemble learning and the unmodified 1DCNN model, the improved 1DCNN model has obvious advantages. The average recognition accuracy rate reaches 99.56%. The calculation cost is greatly saved, and the model recognition speed is improved.

Acoustic emission and fragment fractal characteristics of rock burst tendency coal samples under different strain rate loads

LYU Pengfei, LU Kangbin, CAO Shubin, CONG Risheng

2023, 49(1): 123-130, 139. doi: 10.13272/j.issn.1671-251x.2022050022

<Abstract>(206) <HTML> (50) <PDF>(17)

Abstract:
At present, the correlation analysis between the acoustic emission characteristics of the rock failure process and the fractal characteristics of sample fragments has been carried out. Some achievements have been obtained. But the quantitative description of the failure degree of coal samples with rock burst tendency under the condition of unidirectional loading with different strain rates and the quantitative relationship between the failure degree and the loading strain rate are few. In order to solve this problem, based on the MTS-C64. 106 electro-hydraulic servo system, the raw coal samples are subjected to uniaxial static load with different strain rates. In the test, the PCI-2 acoustic emission card is used to monitor the fracture process of the samples under load in real-time. The fractal theory is used to analyze the fracture fragments of the samples. The relationship between the fracture degree of the samples and the load strain rate is quantitatively evaluated. The results show the following points. ① On the basis of static load, the peak strength of sample failure increases with the increase of strain rate dynamic load. ② With the increase of the loading strain rate, the total number of AE decreases, and the number of high-energy AE events increases. The AE ringing count and energy amplitude undergo a consistent transition process of "slow increase-rapid increase-sudden increase." ③ The loading energy input rate of the sample is basically consistent with the increasing trend of acoustic emission ringing count and internal impact number. It will also experience the change of "slow increase-rapid increase-sudden increase." ④ The constant for the positive correlation between acoustic emission and vibration strength decreases with increasing loading strain rate. The constant which is negatively related to the ratio of the number of high and low energy vibrations, increases with increasing loading strain rate. The failure mode of the raw coal sample will experience a "shear failure - splitting failure - bursting failure" transformation. ⑤ When the loading strain rate is low, the upper part of the sample is destroyed. When the strain rate increases, the sample is gradually destroyed from the middle to the lower part. The failure process of the raw coal sample under the action of dynamic strain rate is mainly the brittle propagation behavior of cracks. ⑥ The fractal dimension of the impact fragment mass of the sample has a quadratic function relationship with the loading strain rate. There is an extreme value of the loading strain rate that maximizes the damage to the sample, with the test showing a strain rate extreme value of 2.8×10⁻³ s⁻¹.

Coal mine gas and coal dust explosion sound recognition method based on wavelet packet energy

YU Xingchen, WANG Yunquan

2023, 49(1): 131-139. doi: 10.13272/j.issn.1671-251x.18070

<Abstract>(749) <HTML> (56) <PDF>(25)

Abstract:
At present, it is difficult to meet the emergency rescue needs of gas and coal dust explosion accidents due to the rate of missing and false alarms in coal mine gas and coal dust explosion monitoring. In order to solve the above problems, a coal mine gas and coal dust explosion sound recognition method based on wavelet packet energy is proposed. This method installs mine-used pickups in the key monitoring areas of the coal mine to collect the working sound and environmental sound of the coal mine equipment in real-time. The wavelet packet energy ratio of sound is extracted through wavelet packet decomposition, and the feature vector characterizing the sound signal is formed. The feature vector is input into the BP neural network to obtain the sound recognition model of coal mine gas and coal dust explosion. The wavelet packet energy ratio of the sound signal to be measured is extracted and input into the model as the feature vector to recognize the type of sound signal to be measured. According to the requirements of feature vectors and output results, a BP neural network with 8, 8 and 1 nodes in the input layer, hidden layer and output layer is established to train the recognition model. By analyzing the results of wavelet packet decomposition of underground acoustic signals in coal mines, it is confirmed that the Haar wavelet function is used and the number of wavelet packet decomposition layers is chosen to be 3. The experimental results show that the energy proportion of gas and coal dust explosion sound decomposed by wavelet packet is obviously different from other sounds. The wavelet packet energy proportion distribution of the same sound signal with different time is stable. Therefore, the wavelet packet energy proportion can effectively represent the features of the sound signal and has strong robustness. BP neural network training speed is fast, and only a small number of training iterations can achieve the expected error. The recognition accuracy is up to 95% in the presence of many disturbing sound signals in the coal mine. BP neural network has the best recognition effect compared with the extreme learning machine model and support vector machine model.

Study on the optimal control of supply air volume in switchover process of mine main ventilators

CAI Jiahao, WANG Qianjin, FU Xiaorong, MA Xiaoping

2023, 49(1): 140-145, 161. doi: 10.13272/j.issn.1671-251x.2022050059

<Abstract>(327) <HTML> (72) <PDF>(22)

Abstract:
The supply air volume fluctuates in a large range or even interrupts during the switching process of mine main ventilators, which is easy to cause the gas concentration to exceed the limit. The commonly used model-based main ventilator switchover control method is difficult to handle the constraints well. The intelligent algorithm relies on expert knowledge and experience, which is subjective and arbitrary. In order to solve the above problems, taking the switchover process of main ventilators in the No.2 Mine of China Pingmei Energy and Chemical Group Co., Ltd. as the research background, the optimal control of supply air volume in the switchover process of main ventilators is studied. Based on the hydrodynamics equation and the concept of graph theory, the dynamic model of the main ventilator switchover process is established. The Taylor expansion is used to linearize it to reduce the computational complexity. The switchover process of mine main ventilator is strongly nonlinear, and the system state is constrained. It is a discrete multi-input and multi-output system. The model predictive control (MPC) algorithm is used to study the air volume control problem. The MPC system of the main ventilator switchover process is designed, which converts the air volume optimization into a quadratic programming problem. The primal-dual neural network is used to solve the optimization problem online to realize the real-time optimal control of the supply air volume during the main ventilator switchover process. The test results show that the MPC system can effectively switch the main ventilator, and the air volume of four air doors can well track the reference value during the switchover process. The operation time of each sampling time is 0.027 s, which meets the real-time requirements of the switchover process. The maximum fluctuation of supply air volume is only 0.9%, which is significantly better than the traditional PID control effect.

Optimization of multi-hole hydraulic cutting combined extraction parameters under superposition effect

NI Xing

2023, 49(1): 146-152. doi: 10.13272/j.issn.1671-251x.2022060110

<Abstract>(153) <HTML> (54) <PDF>(20)

Abstract:
In the process of hydraulic cutting in low permeability and high gas coal seams, there are problems such as unclear cutting disturbance range and unclear optimal hole spacing for cutting drilling. In order to solve the above problems, the 1908 working face of Gaoshan Coal Mine in Yuneng, Guizhou Province is taken as the research background. On the basis of establishing the fluid-solid coupling model of gas extraction in coal body with hydraulic cutting, with the help of COMSOL numerical simulation software, the effective extraction radius of hydraulic cutting borehole and the change of gas pressure around the borehole in the 1908 working face of Gaoshan Coal Mine are studied. Based on the simulation results, the effective extraction range and gas pressure change between holes are analyzed under the influence of the extraction superposition effect between holes when the hydraulic cutting drilling holes are arranged in multiple holes. Finally, the optimal hole spacing and extraction time are obtained. The results show the following points. ① The single hole extraction effect of hydraulic cutting drilling is significantly improved with the cutting depth. However, the effective extraction radius of the borehole increases slowly. In order to obtain the best cutting depth, the effective extraction radius of each borehole is fitted in a trinomial way. With the increase of hydraulic cutting depth, the range of effective extraction radius slows down after rapid increase and finally tends to be stable. The optimal cutting depth of Gaoshan Coal Mine is 1.5 m, and the effective extraction radius is 3.1 m. ② Under the same extraction time, the gas pressure in the coal body decreases with the shortening of the distance between two holes. It shows that the smaller the hole spacing is, the more serious the disturbance caused by hydraulic cutting between holes is, and the more significant the influence of the extraction superposition effect is. ③ On the premise of ensuring that the outburst elimination meets the standard, it is best to choose a hole spacing of 7 m for arranging hydraulic cutting drilling. ④ Originally, in the "square" hole arrangement, the maximum gas pressure at the point where the blind area may occur at the hole center is only 0.67 MPa, which is less than the critical value. The effective coverage area of the "square" hole arrangement is larger than that of the "triangle" hole arrangement, and the repeated area of drainage is reduced. This reduces the amount of drilling and improves the efficiency of gas control. ⑤ Through field test, it is concluded that in the 60 d extraction period, the hydraulic cutting drilling arrangement with a hole spacing of 7 m and a "square" hole arrangement can effectively improve the concentration and purity of gas extraction. It can also extend the period of high efficiency extraction. It can eliminate the blank zone of gas extraction in the coal body between boreholes to eliminate the outburst of the coal body in the area between boreholes.

Research on distributed storage of 3D stack grid model of coal mine geology based on HDF5

GUO Jun

2023, 49(1): 153-161. doi: 10.13272/j.issn.1671-251x.18056

<Abstract>(181) <HTML> (61) <PDF>(17)

Abstract:
The realization of multi-resolution expression and multi-parameter fusion of coal mine geological environment by using true 3D gridded geological model is one of the key contents of coal mine geological big data research. The core issues are the organization, storage and management of 3D geological model data. Aiming at the data scale, distributed storage and query performance of 3D geological grid model in coal mines, a distributed storage scheme of 3D stack grid model based on HDF5 is proposed. In terms of grid data organization, the 3D geological model data is compressed and organized in blocks by using the stack grid model. The problem of large-scale geological grid model data organization is solved by data segmentation. The data segmentation also concentrates the data with similar space in the adjacent hard disk sector or storage device. It is conducive to improving the efficiency of data scheduling. In terms of data storage, HDF5 is used as the persistence layer of storage to store all original data. The memory database Redis is used to store hot data, HDF5 metadata and other related information. In terms of Web services, H5Serv is used to send and receive HDF5 data. In terms of HDF5 distribution, network file system (NFS) is used to realize the sharing of HDF5 data between different node servers. Rsync and Inotify are used to realize real-time synchronization of HDF5 data in different node servers. Nginx is used to realize load balancing of reverse proxy and data service nodes during access. The Docker container technology is used to uniformly deploy the data node service and Nginx service. The JupyterLab interactive analysis platform is used to realize the scheduling and management of real-time data resources. The experimental results show that the data organization of the geological model based on the stack grid and the distributed storage based on HDF5 can realize the effective storage management and spatial query of 3D geological grid model of the coal mine. Compared with the voxel model and octree model, the data volume of the stack grid model is small. It is convenient to realize the spatial quick query of the geological interface. The spatial query performance is better than the relational database MySQL and the non-relational database MongoDB. The stack grid model is more suitable for the grid expression and data organization of the coal measures sedimentary stratigraphic structure. The file storage based on HDF5 is significantly more space-saving than MySQL and MongoDB database storage. The main reason is that the DataSet of HDF5 can directly store data blocks without additional storage information. The data organization and storage scheme based on stack grid model and HDF5 can provide references for the effective storage management of 3D geological grid model in coal mines.

Research on the intelligent management system of the trackless rubber-tyred vehicles in the coal mine

YANG Kun

2023, 49(1): 162-170. doi: 10.13272/j.issn.1671-251x.18002

<Abstract>(1040) <HTML> (110) <PDF>(97)

Abstract:
In the coal mine, underground working places are scattered, transportation routes are complex, and there are many bends and intersections in the roadway. Based on the above characteristics and the needs of intelligent construction of coal mines, the intelligent management system of trackless rubber-tyred vehicles in coal mines is studied from the aspects of demand analysis, system architecture and key technologies. Through demand analysis, it is concluded that the intelligent management system of mine trackless rubber-tyred vehicles should have the functions of precise positioning of mine vehicles, real-time collection of mine vehicle working conditions information, mine vehicle mobile communication, mine vehicle intelligent navigation, real-time monitoring and control of mine vehicle status and mine vehicle anti-collision warning. The key technologies of the system are introduced in detail. The application of UWB positioning technology in mine trackless rubber-tyred vehicle positioning is analyzed. It is suggested that the mobile communication technology of mine vehicles should adopt WiFi and 4G/5G technology. The characteristics of common path-planning technology are discussed. It is concluded that the mine trackless rubber-tyred vehicle navigation technology should adopt the path planning algorithm based on graph search with high maturity. The mine trackless rubber-tyred vehicle navigation and track playback technology should be combined with GIS technology. The traffic light control technology of mine vehicles is studied. The intersection model and single-vehicle passing lane model are proposed. The vehicle anti-collision warning technology is studied. According to the position of pedestrians and vehicles and the relative direction and distance between them and the UWB base station, the anti-collision early warning principle under the two modes of the same base station and the cross-base station is analyzed. The experimental results show that the mine vehicle communication based on UWB, mine vehicle path planning and vehicle track playback based on A^* algorithm, traffic light control, anti-collision early warning and other functions can meet the application requirements.

Optimization design and application of circularly polarized antenna in mine UWB positioning system

JU Chen

2023, 49(1): 171-176. doi: 10.13272/j.issn.1671-251x.18071

<Abstract>(218) <HTML> (158) <PDF>(30)

Abstract:
The antenna is an important part of the mine UWB positioning system. In order to suppress the multipath reflection signal received by the mine UWB positioning system and improve the positioning precision of the mine UWB positioning system, the traditional circularly polarized antenna structure is optimized. This study designs a new type of right-handed circularly polarized microstrip antenna. Firstly, the rectangular slot is changed to the cross slot. The current trajectory is changed to make the difference between the two orthogonal linearly polarized electric fields closer to 90°. The axial ratio is reduced to make the circularly polarized purity of the antenna higher. Secondly, the cross slot is smoothly expanded into a diamond slot to improve the cross-polarization level and suppress the orthogonal rotation. Therefore, the antenna can achieve higher right-handed circularly polarized purity. The HFSS software is used to simulate the new right-handed circularly polarized microstrip antenna. The simulation results show that the cross-polarization level in the main radiation direction is more than 10.4 dBi, which can achieve good right-handed circularly polarized effect. The measured results of the operating frequency band and echo of the new right-handed circularly polarized microstrip antenna sample are basically consistent with the simulation results. The results indicate that the new antenna structure is easy to be processed and the influence of the process deviation within the normal tolerance on the antenna performance is relatively small. The new right-handed circularly polarized microstrip antenna sample is used for the field test of the UWB positioning system based on the arrival phase difference in the tunnel environment. The test results show that the stability of the arrival phase difference of the signal is significantly improved. The multipath effect is significantly suppressed, which can effectively improve the positioning precision of the UWB positioning system. The new right-handed circularly polarized microstrip antenna has the advantages of small size, light weight and easy fabrication.

2023 Vol. 49, No. 1

Submission System

Latest AcceptedMore>