2017 Vol. 43, No. 5

  Previous Issue | Next Issue 
Display Method:
Cover Catalogue
A coal-rock image feature extraction and recognition method
SUN Jiping, YANG Kun
2017, 43(5): 1-5. doi: 10.13272/j.issn.1671-251x.2017.05.001
<Abstract>(84) <HTML> (38) <PDF>(33)
Abstract:
A coal-rock image feature extraction and recognition method based on binary cross-diagonal texture matrix was proposed. Binary cross-diagonal texture matrix of coal-rock image is extracted firstly. Then feature vector of coal-rock image is constructed by angular second moment energy, relevance, variance, inverse difference moment, entropy, sum entropy, difference entropy, sum average, contrast, inertia moment and information measurement of correlation, which are extracted from the binary cross-diagonal texture matrix. Finally, sparse representation is adopted to recognize coal-rock images. The experimental results show that the method can achieve better performance than image feature extraction and recognition method based on cross-diagonal texture matrix, whose average recognition rate can reach 94.38%, and improve real-time performance of coal-rock recognition with shorter feature extraction time of single image.
Research of precise pushing control scheme for hydraulic support and its applicatio
WANG Feng
2017, 43(5): 6-9. doi: 10.13272/j.issn.1671-251x.2017.05.002
<Abstract>(104) <HTML> (12) <PDF>(8)
Abstract:
For problems of poor control precision of hydraulic system of hydraulic support and inconsistent step distance of support pushing, a precise pushing control scheme for hydraulic support was put forward. Precise control of support moving and scraper conveyor pushing and automatic elimination of pin roll gap are realized by introducing pushing control logical valve and optimizing automatic support pushing control flow of electro-hydraulic control system. The experimental and field application results show that the scheme improves automatic pushing control accuracy of hydraulic support on fully mechanized coal mining face and guarantees consistent step distance of support pushing.
Design of predictive maintenance system of coal cleaning and processing equipments
REN Mingyue, LI Dong, MENG Guoying
2017, 43(5): 9-12. doi: 10.13272/j.issn.1671-251x.2017.05.003
<Abstract>(55) <HTML> (12) <PDF>(6)
Abstract:
Common faults and its causes of several main coal cleaning and processing equipments were analyzed. In view of problem that maintenance mode of current coal cleaning and processing equipment cannot accurately and effectively identify early fault and potential threat, a predictive maintenance system of coal cleaning and processing equipments was designed. The system is mainly composed of function module of basic information management, function module of real-time monitoring of equipment condition, function module of fault simulation, function module of predictive maintenance and decision, four modules are complement with each other and coordinates effect, which can evaluate running status of current equipment, and forecast development trend of fault, so as to realize the predictive maintenance and health diagnosis of the equipments.
Research on safety resource allocation of coal mine production logistics system
FENG Lijie, BAI Wenxiao, ZHAI Xueqi, WANG Jinfeng
2017, 43(5): 13-18. doi: 10.13272/j.issn.1671-251x.2017.05.004
<Abstract>(66) <HTML> (15) <PDF>(7)
Abstract:
For safety resource allocation of coal mine production logistics system, regression analysis method was used to fit an objective function of safety risk and cost on the basis of constructing safety resource index system of safety risk and cost. A multi-objective optimization model of safety resource allocation of coal mine production logistics system was constructed and adaptive evolutionary particle swarm algorithm was used to solve the optimization model. The example analysis result shows that the adaptive evolutionary particle swarm optimization algorithm can obtain different feasible solutions which satisfy multi-objective optimization requirements of safety resource allocation of coal mine production logistics system.
Status of coal mine safety monitoring system of Shenhua Group and its upgrading
ZHANG Qi
2017, 43(5): 18-21. doi: 10.13272/j.issn.1671-251x.2017.05.005
<Abstract>(58) <HTML> (10) <PDF>(8)
Abstract:
Some problems of coal mine safety monitoring system of Shenhua Group in application were pointed out, for example, operating maintenance was difficult, signal transmission distance could not meet application requirements of super long working face, there were data losing and false alarm, etc. According to Technical schemes of upgrading of coal mine safety monitoring system, technical status of coal mine safety monitoring system of Shenhua Group was analyzed as well as gap between the system and the schemes. Upgrading measures about coal mine safety monitoring system of Shenhua Group were proposed from aspects of construction principle, sensor, substation and software.
Coal-rock recognition method based on distance metric learning
WU Yunxia, SHEN Shaofei
2017, 43(5): 22-26. doi: 10.13272/j.issn.1671-251x.2017.05.006
<Abstract>(109) <HTML> (34) <PDF>(21)
Abstract:
A coal-rock recognition method based on distance metric learning was proposed. In the method, features of coal-rock images are extracted firstly from training sets of coal-rock images. Then a fit distance metric is gotten, which can make distance between any two features of coal samples or the ones of rock samples smaller and distance between features of coal samples and rock samples bigger, so as to improve classification and recognition effect. Finally, classifier is used to recognize coal-rock. The experimental results show when extracted coal-rock features are LBP, HOG or GLCM features, the method has higher coal-rock recognition rate than coal-rock recognition methods based on Euclidean distance, LDA or ITML.
Extraction method of texture feature of images of coal and gangue
MI Qiang, XU Yan, LIU Bin, XU Yunjie
2017, 43(5): 26-30. doi: 10.13272/j.issn.1671-251x.2017.05.007
<Abstract>(54) <HTML> (13) <PDF>(9)
Abstract:
In view of problems of less extraction feature parameters and low recognition precision existed in image processing methods of coal and gangue, an extraction method of texture feature of images of coal and gangue fused with local binary pattern and gray level co-occurrence matrix was proposed. Firstly, the preprocessed images of coal and gangue were transformed into local binary pattern images, then the local binary pattern images were used to generate gray level co-occurrence matrix, the mean value and normalization of those texture features including angular second moment, correlation, contrast and entropy were processed. Finally, support vector machine was used for samples training and recognition results were obtained. The experimental results show that the method can effectively extract the texture feature of images of coal and gangue, and the recognition rates of coal and gangue are respectively 94% and 96%.
Energy balancing routing method for coal mine wireless multimedia sensor network
WANG Hui, YANG Wei, LIU Junbo
2017, 43(5): 31-36. doi: 10.13272/j.issn.1671-251x.2017.05.008
<Abstract>(99) <HTML> (13) <PDF>(5)
Abstract:
According to multimedia information collection requirements and characteristics of confined band space in coal mine tunnel and limited energy of sensor nodes, a wireless multimedia sensor network (WMSN) system model of coal mine was built, and an energy balancing routing method for coal mine WMSN was proposed, which included a position and residual energy based hierarchy clustering in virtual grids (PREHCVG) algorithm and an energy and distance based ant colony routing (EDACR) algorithm. In the method, PREHCVG algorithm divides nodes into different virtual grid for cluster management based on communication radius of the nodes in the network, and selects cluster head nodes according to residual energy and location information of the nodes. EDACR algorithm selects routing nodes from cluster head nodes and alternative cluster head nodes according to residual energy and distance information of the nodes. The simulation results show that the energy balancing routing method for coal mine WMSN can effectively balance energy consumption of WMSN nodes, reduce the number of energy-exhausted nodes and prolong life cycle of WMSN compared to traditional LEACH algorithm.
Detection method of joints twitching of powerful conveyor belt
LUO Minghua
2017, 43(5): 37-40. doi: 10.13272/j.issn.1671-251x.2017.05.009
<Abstract>(58) <HTML> (13) <PDF>(4)
Abstract:
In view of problem of inaccurate calculation of joints twitching caused by belt jitter, deviation and speed changes of powerful conveyor belt, a detection method of joints twitching based on joint image registration was proposed. The joint image of the secondary acquisition is registered, and the Y-difference method is used to locate the joints in the registration image. Distances of all the joint points are calculated and compared with the reference image to obtain the joint twitching distance. The change trends of all joints can be obtained according to the twitching distance. Experimental results show that the method has high accuracy and can meet practical application requirements.
Attitude angle measuring system of hydraulic support
ZHANG Kun, LIAN Zisheng
2017, 43(5): 40-45. doi: 10.13272/j.issn.1671-251x.2017.05.010
<Abstract>(51) <HTML> (12) <PDF>(5)
Abstract:
In view of problem that measuring result is inaccurate while using single angle sensor to realize attitude angle measurement of hydraulic support on fully mechanized coal mining face, an attitude angle measuring system of hydraulic support based on tilt sensor and gyroscope was proposed. The system uses SVT626T type tilt sensor and ML7100 type three-axis gyroscope to measure inclination angle and axial deflection angle, and data of the two kinds of sensor are fused by Kalman filter taking pitch angle as an example. The Matlab simulation and experimental results show that the system can effectively solve the problems of the measurement error caused by acceleration of the top beam and the drift and error accumulation of the gyroscope caused by long time measurement, and improves the attitude measuring accuracy.
Affection analysis of geometric layout on position and attitude detection accuracy of roadheader
FU Shichen, LI Yiming, CHENG Long, ZONG Kai, ZHANG Minjun, TAO Yunfei, WU Miao
2017, 43(5): 46-49. doi: 10.13272/j.issn.1671-251x.2017.05.011
<Abstract>(22) <HTML> (7) <PDF>(5)
Abstract:
In order to realize unmanned and high accurate detection of position and attitude of boom-type roadheader on fully mechanized excavation face, a position and attitude detection system of roadheader based on ultra wide band ranging technology was proposed, calculation methods of positioning coordinate and attitude angle of roadheader were deduced based on the system, and affection of distance and angle between base stations on positioning accuracy and affection of distance between positioning points of roadheader on attitude angle detection accuracy were analyzed by Matlab simulation. The simulation results show that positioning accuracy of the system decreases with increase of distance between base station and positioning point of roadheader; positioning accuracy of the system increases with increase of distance between base stations; under the case of angle between base stations in yoz plane is 60°, positioning accuracy of the system is higher than the one when the angle is 0° or 90° respectively; distance between base station and positioning point of roadheader has no significant affection on attitude angle detection accuracy; and attitude angle detection accuracy increases with decrease of distance between positioning points of roadheader.
A new fault diagnosis method of rolling bearing of shearer
GONG Maofa, GUO Yixuan, YAN Peng, WU Na, ZHANG Chao
2017, 43(5): 50-53. doi: 10.13272/j.issn.1671-251x.2017.05.012
<Abstract>(27) <HTML> (8) <PDF>(5)
Abstract:
In view of unstable problem existed in fault diagnosis result for rolling bearing of shearer based on K-means clustering algorithm, a new fault diagnosis method of rolling bearing of shearer based on TDKM-RBF neural network was proposed. The method adopts Tree Distribution algorithm to determine initial clustering center of the K-means clustering algorithm, so as to eliminate volatility of K-means clustering results. The method uses K-means algorithm to determine the parameters of the RBF neural network, then the trained neural network was used for fault diagnosis. The simulation results show that the method has quick clustering process,higher steability, and obviously improves accuracy of fault diagnosis for rolling bearing of shearer.
Fault diagnosis of mine-used transformer based on optimized fuzzy Petri net
LI Shiguang, XUE Han, LI Zhen, GAO Zhengzhong, LI Ying
2017, 43(5): 54-57. doi: 10.13272/j.issn.1671-251x.2017.05.013
<Abstract>(36) <HTML> (12) <PDF>(4)
Abstract:
For oil-immer transformer used in places with coal dust and no explosion hazard,an improved fault diagnosis model of mine-used transformer based on fuzzy Petri net was proposed. Fuzzy generation rule was used to establish fault diagnosis model according to relationship between fault symptom and the fault. Self-learning and adaptive ability of Elman network algorithm are used to optimize initial parameters of the model, and the settings of initial parameters of the fuzzy Petri net are more reasonable. Matlab simulation results show that fault diagnosis accuracy of the optimized model and unoptimized model is 87.88% and 75.76% respectively, which verifies effectiveness of the optimized model.
Analysis of stress and fatigue of eccentric shaft of unilateral driven swing scree
ZOU Mengqi, LIU Chusheng, WU Jida
2017, 43(5): 58-61. doi: 10.13272/j.issn.1671-251x.2017.05.014
<Abstract>(36) <HTML> (10) <PDF>(12)
Abstract:
The three-dimensional structure model of unilateral driven swing screen was established by PROE software, and the load history on the eccentric shaft was obtained by dynamic simulation analysis. The stress distribution curve and stress cloud of the eccentric shaft were analyzed by using analytical method and finite element method. The analysis results show that the dangerous part of the eccentric shaft appears at the support of the intermediate bearing, and the maximum stress is about 35 MPa. The fatigue life (0.98 a) of the eccentric shaft was calculated by using the local stress-strain method, which can effectively prevent accident occurrence. These results provide a reliable basis for design and improvement of eccentric shafts.
A multi points ultrasonic detection method for material flow of belt conveyor
ZHANG Li
2017, 43(5): 62-65. doi: 10.13272/j.issn.1671-251x.2017.05.015
<Abstract>(45) <HTML> (16) <PDF>(6)
Abstract:
For large detection error of single point ultrasonic ranging technology used in material flow detection of belt conveyor when coal distributed unevenly or was big, a material flow detection method of belt conveyor based on multi points ultrasonic counter ranging technology. The method can calculate approximate sectional area of material by locating multi points on surfaces of material and belt, so as to get material flow according to running speed of belt conveyor. The test result shows that the method has smaller detection error than the single point ultrasonic ranging technology under the condition of big coal with uneven distribution.
Research on technology of continuous conveyor used with matching tunnel boring machine in long-distance inclined shafts
JIN Ya, ZHU Liping, HUANG Yangzhu
2017, 43(5): 65-68. doi: 10.13272/j.issn.1671-251x.2017.05.016
<Abstract>(30) <HTML> (6) <PDF>(5)
Abstract:
In view of problems of traditional construction method for long-distance inclined shafts development which uses drilling and blasting method or freezing method combined with rail or trackless vehicles for slag-out, that it needs many equipments, has high requirement for scheduling and transportation management and low slag-out efficiency, superiority of the construction method using tunnel boring machine for excavation with continuous conveyor for slag out was analyzed. Structure of continuous conveyor was introduced. The key technologies need to improve were pointed out, including large capacity belt storage technology, intelligent conveyor belt tensioning technology, fast belt take-up or retracting technology, safe extension installation technology, control and protection technology, etc. The practical application of Bulianta Coal Mine shows that excavation speed of the construction method using tunnel boring machine for excavation with continuous conveyor for slag-out is 4-5 times of that of traditional construction mode, which can meet the requirements of rapid construction of long distance inclined coal mine.
Design of ZigBee wireless sensor network system for mine gas monitoring
XU Ruihua, WANG Kaimin
2017, 43(5): 68-71. doi: 10.13272/j.issn.1671-251x.2017.05.017
<Abstract>(38) <HTML> (11) <PDF>(6)
Abstract:
In view of problems of high cost, poor mobility and limited coverage of mine gas monitoring adopted by wired sensor network, a ZigBee wireless sensor network system for mine gas monitoring was designed. Sampling nodes are used to collect underground gas concentration real-timely, the collected data is transmitted to sink nodes with ZigBee protocol.After the data is gathered by the sink nodes, it is transmitted to embedded gateway. At last, the data processed by the embedded gateway is transmitted to mine monitoring center, so as to realize real-time display of mine gas concentration. The experimental results show that the system has high reliability, good real-time performance and wide coverage area.
Design of an intelligent accurate personnel positioning system for mine
WU Wei, TANG Lijun, JIANG Decai
2017, 43(5): 72-75. doi: 10.13272/j.issn.1671-251x.2017.05.018
<Abstract>(58) <HTML> (13) <PDF>(10)
Abstract:
In view of problems of difficult deployment and high cost caused by a lot of wired communication cable and low intelligence of request for help in emergency existed in current accurate personnel positioning system of coal mine underground, an intelligent accurate personnel positioning system for mine was designed. In the system, personnel label position is acquired exactly by use of time of arrival ranging method based on ultra wide band positioning technology, personnel label information collected by card reader is uploaded to substation through data concentrator by use of LoRa wireless communication technology, and information of request for help is sent to manager automatically through emergency processing plan when persons lose ability of triggering help button manually. The test results show that the system can achieve reliable wireless data transmission with bit error rate of less than 5% within 2 km, whose positioning accuracy is 1 m, and automatic alarm rate is above 93.5% when persons lose ability of triggering help button manually.
Design of automatic control system of forced drainage of coal mine
GONG Xuedong, CHEN Wei, ZHU Yakun
2017, 43(5): 75-78. doi: 10.13272/j.issn.1671-251x.2017.05.019
<Abstract>(53) <HTML> (11) <PDF>(11)
Abstract:
Automatic control system of forced drainage was designed which was applicable to coal mine and can achieve monitoring and control of submersible pumps in a ground control room. The system takes programmable control technology as core, uses a variety of mine intrinsically safe sensors to real-timely monitor parameters such as water level, outlet pressure and submersible pump temperature, and realizes automatic control of forced drainage system through operation of diving electro hydraulic gate valve.The field industrial test results show that the system is running well and the PLC controls stably.
Application of improved FastICA algorithm in compound fault diagnosis of vibrating scree
XU Yuanbo, CAI Zongyan
2017, 43(5): 79-82. doi: 10.13272/j.issn.1671-251x.2017.05.020
<Abstract>(46) <HTML> (10) <PDF>(4)
Abstract:
In view of problem that common fault characteristic extraction methods could not extract compound fault characteristic completely and effectively, an improved fast independent component analysis(FastICA) algorithm was proposed. The improved FastICA algorithm adaptively selects different nonlinear function to take progressive analysis, so data characteristic extracted by the improved FastICA algorithm is more accurate than that extracted by FastICA algorithm. The improved FastICA algorithm was applied to compound fault diagnosis of vibrating screen. The simulation and actual test results show that the improved FastICA algorithm can extract different fault characteristics effectively with higher separation accuracy.

苏ICP备 05016349号-2

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