2020 Vol. 46, No. 7

  Previous Issue | Next Issue 
Display Method:
Cover Catalogue
Gas and coal dust explosion perception alarm and explosion source judgment method based on video image
SUN Jiping, FAN Weiqiang
2020, 46(7): 1-4.. doi: 10.13272/j.issn.1671-251x.17629
<Abstract>(84) <HTML> (18) <PDF>(16)
Abstract:
Video image characteristics of gas and coal dust explosion are analyzed: Explosive fireball is usually red with high brightness, high temperature and strong radiation of infrared and ultraviolet rays, and area of the fireballs expands rapidly; Area, brightness, color, shape and radiation intensity of flame front are constantly changing; Area, color and shape of smoke and dust are constantly changing; There are objects that move or deform rapidly. Based on visible light video image, near infrared video image, far infrared video image and ultraviolet video image, a method of gas and coal dust explosion perception alarm and explosion source judgment is proposed: According to brightness and change rate of highlight area, area and change rate of highlight area, image shape and its change, image color and its change, gas and coal dust explosion are identified; Explosion source is determined according to image changes and time sequence of the changes and camera damage at different positions. A gas and coal dust explosion perception alarm and explosion source judgment method is proposed based on multi-information fusion of visible light video image, near infrared video image, far infrared video image, ultraviolet video image, O2, CO2, CO, temperature, sound, vibration, air pressure, wind speed, wind direction, smoke, dust, etc. The method reduces impact of fire, roadway lamp, miner's lamp, car lamp, red clothing, electromechanical equipment heat, fault discharge of electrical equipment and cable, coal and gas outburst, rock burst, large area roof fall, flood, blasting operation, coal falling on working face, coal transfer and transportation on gas and coal dust explosion identification.
Review and prospect of coal mine informatization constructio
DING Enjie, LIAO Yubo, ZHANG Lei, LIU Zhongyu
2020, 46(7): 5-11. doi: 10.13272/j.issn.1671-251x.17624
<Abstract>(144) <HTML> (12) <PDF>(28)
Abstract:
Based on the definition of coal mine informatization, the characteristics, typical problems and their representative solutions in different stages of coal mine informatization construction are reviewed, which include single machine(system) automation, integrated automation, mine Internet of things, intelligent mine and perception mine. It is pointed out that: Single machine(system) automation mine, which only carries on simple control to a single device or system, belongs to the initial stage of coal mine informatization construction; Integrated automation mine, which realizes automatic control among multi systems and solves information island, belongs to the middle stage; Internet of things mine, intelligent mine and perception mine belong to the senior stage, in which Internet of things mine and intelligent mine separately realize connection and deep connection of person-person, person-object and object-object, and perception mine realizes cognition and knowledge integration of mine information and status. Relationships among coal mine informatization, digitization, virtualization and intelligence are combed. It is pointed out that: Coal mine informatization includes all contents of mine digitization, virtualization and intelligence; Physical mine, digital mine and virtual mine form an integral closed polygon through object integration, data integration and semantics integration, while smart mine is the core of the closed polygon. Main problems existed in current coal mine informatization construction are analyzed from aspects of perception layer, network layer, platform layer and application layer. Future development trends of coal mine informationzation technology are discussed, which are a large amount of autonomous devices, coal mine transparency and precise control, coordination of edge computing and cloud platform, and a large amount of intelligent APP.
2020, 46(7): 12-15. doi: 10.13272/j.issn.1671-251x.17627
<Abstract>(68) <HTML> (12) <PDF>(16)
Abstract:
Non-line-of-sight propagation in object localization: a survey
HU Qingsong, ZHANG Henan, WANG Peng, YANG Wei, LI Shiyin
2020, 46(7): 16-27. doi: 10.13272/j.issn.1671-251x.17571
<Abstract>(121) <HTML> (26) <PDF>(29)
Abstract:
Due to the existence of obstacles, none-line-of-sight(NLOS) propagation is common in localization scenes like mines, which causes refraction, reflection, diffraction and scattering of localization signals, leads to the increase of ranging error, and further influences accuracy of object localization. The influence of NLOS propagation on localization methods is analyzed including TOA(Time of Arrival), TDOA(Time Difference of Arrival), AOA(Angle of Arrival), RSSI(Received Signal Strength Indication), etc. Then existing literatures are reviewed from four aspects: identification of NLOS propagation, suppression of NLOS propagation error, utilization of NLOS propagation and localization method design in NLOS scenes. For the identification of NLOS propagation, the residual test method, error statistics method, energy detection method, neural network algorithm and geometry relation method are focused on. For the suppression of NLOS propagation error, the filtering-based method, semi-parametric-based method, energy detection-based method and database-based method are mainly analyzed. For the utilization of NLOS propagation, the method of improving robustness of localization system and the one based on error learning and matching are summarized emphatically. For the localization method design in NLOS scenes, the literatures are reviewed from two situations: the LOS/NLOS mixed scenes and only NLOS scenes. The new research directions of NLOS propagation in object localization are discussed, which are improving localization accuracy by using multiple technologies together, improving localization accuracy in NLOS scenes through new technologies and realizing cooperative localization among different systems by introducing extra information of other information systems.
Probe on 5G architecture applied in coal mine underground
MENG Qingyong
2020, 46(7): 28-33. doi: 10.13272/j.issn.1671-251x.17620
<Abstract>(128) <HTML> (21) <PDF>(36)
Abstract:
Through comparing and analyzing network deployment of 5G non-standalone (NSA) and standalone (SA) as well as their advantages and disadvantages, and combining with current status of 4G "one network one base-station" generally applied in coal mine underground, a 4G-5G fusion network architecture of coal mine underground based on NSA is proposed which uses 4G network to realize voice and dispatch functions and 5G network to expand other intelligent applications, so as to minimize investment. 5G network transmission modes in coal mine underground are researched, and three front-haul transmission networking schemes of 5G hosted network are focused on as well as their applicable scenes: Fibre-optical direct-connection scheme is applicable for scenes including robot inspection in underground pump house, substation and other places, virtual reality(VR)/augmented reality(AR) training, unattended working face; Passive wavelength division multiplexing scheme is applicable for underground scenes with simple network deployment and high independent maintainability; Active optical transport network scheme is applicable for different scenes flexibly. Four application scenes of 5G network slice in coal mine underground are probed on, which are intelligent inspection robot, environment monitoring and security protection, VR/AR smart coal mine and driverless vehicle, and application modes of 5G networking architecture in different scenes are analyzed.
Law analysis and counter measures research of coal mine accidents in China from 2013 to 2018
NING Xiaoliang
2020, 46(7): 34-41. doi: 10.13272/j.issn.1671-251x.17610
<Abstract>(79) <HTML> (19) <PDF>(31)
Abstract:
Based on statistics of coal mine accident data during 2013-2018 in China, occurrence law and characteristics of coal mine accidents in China were studied from aspects of accident area, occurrence time, coal mine ownership and accident types, which provides basic support for analysis and early warning of regional coal mine safety situation from the macro level.The results show that:① The total number of coal mine accidents in the five southern provinces (cities) accounts for a relatively high proportion, Heilongjiang and Guizhou should be strictly prevented from consecutive major accidents, and the task of prevention and control of major accidents in coal provinces is still arduous.② The resumption of production from March to May after the Spring Festival and the increase in coal demand in the fourth quarter are the main reasons for the high incidence of accidents during these periods.③ Township coal mine accidents account for more than 50% of the total; state-owned local coal mines have better control of relatively serious accidents and major accidents, the numbers of accidents and deaths are below 10% of the total; state-owned key coal mine accidents account for more than 25% of the total, and the major accidents account for more than 35%, therefore, the state-owned key coal mines should be strictly controlled in major accidents.④ The number of roof accidents is the most,and gas accidents cause the most deaths;gas, roof and transportation are the key points to control the total amount of accidents, gas and flood are the key points to prevent and control major accidents. In view of the occurrence law and characteristics of coal mine accidents, the following counter measures and suggestions are proposed from four aspects of industrial policy, key prevention and control objects, technology and personnel, and supervision: further deepen the supply-side structural reform to fundamentally improve the overall safety level of coal industry; targeted control measures should be taken according to the key prevention and control objects identified from the aspects of accident area, occurrence time, coal mine ownership and accident type; increase the input of coal mine safety technology and equipment and strengthen the management and technical ability of coal mine workers; rationally allocate regulatory and supervisory resources and strengthen scientific oversight and supervision.
Early warning technology of regional security situation of gas disasters
ZHANG Qinghua, NING Xiaoliang, SONG Zhiqiang, HE Shudong
2020, 46(7): 42-48. doi: 10.13272/j.issn.1671-251x.17632
<Abstract>(113) <HTML> (17) <PDF>(24)
Abstract:
In order to further improve the prevention and control capabilities of coal mine gas disasters in China and enhance efficiency of supervision, early warning technology of regional security situation of gas disasters was studied. According to coal mine supervision and management mode in China, early warning regions are divided into four regional levels: national region, provincial (city) level regions, coal supervision sub-bureau jurisdiction regions, and prefecture-level administrative regions. According to the needs of hierarchical control, the early warning is divided into four levels: blue, yellow, orange and red, and its risk level increases sequentially. The early warning index system of regional security situation of gas disasters has been established from five aspects: inherent natural attributes of regional coal mines, mine layout and mining conditions, temporal and spatial laws of accidents, acro technology and economic policies, and major hidden dangers in mines. The early warning model based on analytic hierarchy process has been constructed to realize the fusion analysis and decision-making of multiple indicators, and the regional early warning software system has been designed and developed to realize the dynamic data collection and storage, comprehensive analysis and real-time data early warning.
Geological anomaly intelligent identification method based on coal and gas outburst prediction characteristics
MA Guolong
2020, 46(7): 49-56. doi: 10.13272/j.issn.1671-251x.17619
<Abstract>(64) <HTML> (16) <PDF>(8)
Abstract:
In view of problems that existing geophysical prospecting and drilling methods of coal mine are not effective in advanced detecting of geological anomalies such as small geological structures and coal seam occurrence changes, as well as insufficient exploration and utilization of hidden information in outburst prevention and prediction data, the idea of geological anomaly intelligent identification according to association between outburst prediction characteristics and geological anomalies is put forward. From data distribution of a single coal and gas outburst prediction event and the data change of several consecutive coal and gas outburst prediction events, 10 indexes of outburst prediction characteristic are constructed, forming the coal and gas outburst prediction characteristic index system. Applying the method of association analysis, a method of geological anomaly intelligent identification based on coal and gas outburst prediction characteristics is proposed, and the key technologies are emphasized, such as binary attribute transformation of characteristic index, association rule analysis, effective rule extraction, identification criteria establishment and geological anomaly possibility levels classification. A geological anomaly intelligent identification system based on coal and gas outburst prediction characteristics is designed and devoloped using B/S structure, which achieves online collection of outburst prediction information, automatic analysis of outburst prediction characteristics, advanced dynamic identification of geological anomaly, and joint distribution of identification result via multi-channel of website and mobile terminal. The field test results show that the system can independently construct the geological anomaly identification criteria, and the total accuracy rate of geological anomaly identification reaches 87.63%, which provides an effective means for the coal mine to grasp the geological anomaly in advance, and realizes extended application of hidden value of the outburst prediction data.
Research on gas disaster risk early warning data collection technology for regional coal mines
LI Mingjian, ZHAO Xusheng, TAN Guowen, SONG Zhiqiang, LIAO Cheng
2020, 46(7): 57-63. doi: 10.13272/j.issn.1671-251x.17611
<Abstract>(112) <HTML> (12) <PDF>(12)
Abstract:
Taking gas disaster risk macro early warning of all coal mines within the jurisdiction of all levels of coal mine safety supervision departments and mining group companies, it is pointed out that the basic data of regional coal mine gas disaster risk prediction has the characteristics of multi-source, heterogeneous, massive, multi-dimensional, etc., and there are some problems in data collection, such as incomplete information collection and single data collection mode, solidified dimensions, etc.; the basic data of regional coal mine gas disater risk prediction is divided into four types： natural environment risk data of regional mine, production system risk data of regional mine, gas prevention risk data of regional mine, and macro-security environmental risk data; collection technologies of coal mine safety monitoring and gas disaster early warning data with structured characteristics, supervision and law enforcement inspection data with semi-structured characteristics, and coal mine audio and video monitoring data with unstructured characteristics are introduced, and the research of coal mine safety monitoring and gas disaster warning data collection technology based on .NET Core cross-platform Web API, and macro-security environmental risk data collection technology based on topic crawler are introduced in detail; data collection system of gas disaster risk early warning for regional coal mines suitable for Internet environment is designed, and field test show that the system can comprehensively, reliably and timely collect basic data of regional coal mine gas disaster risk early warning.
Construction and application of multivariate data visualization system for coal and gas outburst predictio
PU Yang, SONG Zhiqiang, NING Xiaoliang
2020, 46(7): 64-69. doi: 10.13272/j.issn.1671-251x.2020020054
<Abstract>(111) <HTML> (13) <PDF>(9)
Abstract:
In view of problems of low visualization degree,low outburst prediction accuracy and low real-time performance in existing coal and outburst prediction methods,a multivariate data visualization system for coal and gas outburst prediction is constructed taking Xinyuan Coal Mine as a test mine.The system obtains basic data involved in outburst prediction through the ways of geophysical exploration, drilling, etc. and WTC gas outburst parameter meter, safety monitoring system, and special data acquisition instrument, and transmits the outburst prediction data through underground industrial ring network and ground office network; two-level prediction method of regional overall control and local online identification covering the spatio-temporal evolution relationship of outburst danger is adopted,so that the messy original data becomes orderly through deep mining of multivariate data of coal and gas outburst,laying the foundation for data visualization; the data of regional prediction subsystem and local prediction subsystem is effectively fused through integrated visualization platform of outburst prediction based on WebGIS to realize intuitive display of prediction results and multivariate data, so that the outburst prediction process can be controlled and the results can be checked. The application results show that the system changes the single and discontinuous status of outburst prediction index of Xinyuan Coal Mine, and significantly improves the accuracy and real-time performance of coal and gas outburst prediction.
Manual adjustment noise data processing method for coal mine gas sensor
HU Feng, YE Fuhao, WANG Guoyin, DAI Ji
2020, 46(7): 70-75. doi: 10.13272/j.issn.1671-251x.17605
<Abstract>(129) <HTML> (16) <PDF>(9)
Abstract:
Traditional noise data processing methods have certain requirements for input data, and have a long running time. However, there are some problems of manual adjustment noise data of coal mine gas sensor such as less quantity, poor quality, inconsistent time and easy to be affected by environment, it is difficult to filter the noise data by traditional noise processing methods. For the above problems, a manual adjustment noise data processing method for coal mine gas sensor is proposed. The data average value is used to fill the missing value of concentration data of coal mine gas sensor; the feature set and sample set of concentration data of coal mine gas sensor are constructed by using multi time granularity; five curve fitting functions, namely Gaussian function, mixed Gaussian function, binomial function, trinomial function and piecewise binomial function, are used to fit manual adjustment noise data, and parameters of the fitting function are determined based on the least square method, and the optimal fitting function is obtained according to fitting effect; through analysis of manual adjustment noise data, it is concluded that the noise data is related to the slope, peak and difference of gas concentration before and after adjustment, according to these basic characteristics, the manual adjustment noise data is identified and deleted. The experimental results verify effectiveness of the method.
Research status and development trend of mine detection unmanned aerial vehicle
ZHANG Duo, WU Peili, ZHENG Xuezhao, GUO Jun
2020, 46(7): 76-81. doi: 10.13272/j.issn.1671-251x.17538
<Abstract>(102) <HTML> (10) <PDF>(20)
Abstract:
By analyzing research status of power system, positioning system, environmental monitoring system and communication system of mine detection unmanned aerial vehicle (UAV) at home and abroad, the problems of mine detection UAV were pointed out, such as insufficient cruising power, poor positioning accuracy, weak information perception ability and poor information data transmission performance. For the above problems, the development trends of mine detection UAV were prospected: ① Application of new energy or new power supply technology, the whole power management system is optimized in a more efficient and reasonable way to detect power consumption of electric equipment in real time, improve power efficiency and enhance endurance time of detection UAV, and meet explosion-proof performance. ② Development of UAV cluster system based on collaborative navigation search, the hybrid UAV cluster control structure overcomes the shortcomings of poor communication reliability and low search efficiency in distributed structure and solves the problems of weak robustness and autonomy in centralized structure; the system can improve the positioning accuracy and shorten the rescue time through mathematical optimization algorithm for information derivation and multi-UAV collaborative information fusion. ③ Design of UAV monitoring platform based on multi-sensor fusion technology, the multi-sensor information coordination and mutual fusion based on BP neural network algorithm can improve the UAV's perception ability to underground environment. ④ Application of multi-UAV chain wireless Mesh networking mode, when multi-UAVs search in underground environment, the information collected by each UAV is local area information， all UAVs conduct information fusion and resource complementarity to update the environmental information status in real time through the chain wireless Mesh networking mode, so as to improve reliability of detection and rescue efficiency.
Mine tagless target location method based on combined space and frequency diversity
TENG Yue, SUN Yanjing, DING Enjie, HUO Yu, YANG Yue, ZHANG Xiaoguang
2020, 46(7): 82-88. doi: 10.13272/j.issn.1671-251x.17551
<Abstract>(91) <HTML> (28) <PDF>(9)
Abstract:
Due to complicated underground environment, traditional active location technologies make it inconvenient for workers to carry tags or lose tags during operation, which are limited in application of underground target location, while existing passive location technologies such as geometric method, fingerprinting method and so on has low location precision due to dense multipath interference in underground, which cannot be used in underground directly. For the above problems, a mine tagless target location method based on combined space and frequency diversity is proposed. The method, which is based on non-uniform sampling principle in Fourier domain, reconstructs target reflectivity function through inverse Fourier transform of echo signals of the target in wavenumber domain, so as to realize target location. Passive broadband harmonic tags are used to generate the required harmonic signals for eliminating fundamental frequency interference introduced by transmitting antenna. The combination of space and frequency diversity is achieved by using space diversity of the tags and frequency diversity of the harmonic signals and fusing multi-channel information, which solves the problem of low location precision caused by insufficient sampling information. A differential reception algorithm is used to eliminate phase errors caused by downlink multipath interference, which can improve mine tagless target location precision. The simulated experiment results show that the method can effectively expand coverage of wavenumber domain and restrain multipath interference, so as to realize accurate target location. Under the condition of low signal-to-noise ratio, the location precision can reach decimeter level.
Experimental study on gas adsorption and desorption characteristics of coal sample under variable temperature and pressure
XIA Hui, CAI Feng, YUAN Yuan, XU Chao
2020, 46(7): 89-93. doi: 10.13272/j.issn.1671-251x.2019100005
<Abstract>(86) <HTML> (10) <PDF>(10)
Abstract:
In order to study influence of temperature and pressure on gas adsorption and desorption characteristics of coal sample, adsorption capacity, isosteric heat of adsorption, Langmuir adsorption constant, initial effective diffusion coefficient and diffusion kinetic parameter under different temperatures(20,25,30,35,40,45,50 ℃) and pressure(0-5 MPa) were analyzed by use of gas adsorption and desorption experimental device. The results show that adsorption capacity decreases with the increase of temperature and increases with the increase of pressure. When adsorption capacity is constant, the higher the temperature is, the greater the gas adsorption pressure is, and isosteric heat of adsorption increases with the increase of adsorption capacity. Langmuir adsorption constant a decreases firstly, and then rises and decreases again with the increase of temperature, and reaches peak value at 45 ℃, while Langmuir adsorption constant b decreases with the increase of temperature. Initial effective diffusion coefficient and diffusion kinetic parameter increase with the increase of temperature, and increase amplitude is most obvious at 35-40 ℃.
PENG Zhiyan,ZHA Wenhua.Research on optimization of staggered distance on simultaneous mining faces in ultra-close coal seams［J］.Industry and Mine Automation，2020,46（7）：94-99.
PENG Zhiyan, ZHA Wenhua
2020, 46(7): 94-99. doi: 10.13272/j.issn.1671-251x.2019110021
<Abstract>(53) <HTML> (11) <PDF>(7)
Abstract:
In view of problem that using existing ultra-close coal seam combined mining research methods to obtain mining staggered distance has bigger errors, taking No.9 and No.10 coal seams of a coal mine as engineering background, the mining pressure law of simultaneous mining face in ultra-close coal seams was analyzed under three kinds of mining staggered distances of 30, 36, 44 m. The evolution characteristics of working resistance changes and support pressure of the working face supports under the three mining staggered distance were studied. The results show that the working resistance of the support on 100402 fully mechanized working face decreases first and then increases with increase of mining staggered distance. The utilization rate of the working resistance of the support in the inclined direction of the 100402 fully mechanized working face has the most stable variation range under the 36 m mining staggered distance. The advance support pressure peak value of 090402 conventional mining face decreases first and then increases with the increase of mining staggered distance, which is consistent with the change law of working resistance of support. When the mining staggered distance is 36 m, the two roadways of the upper and lower working faces are affected by the advanced support pressure, the front roof bolt pressure changes steadily, the roof separation is small, and the amount of separation layer is basically stable within 0.6 mm, indicating that the 36 m mining staggered distance is reasonable, and the bolt pressure and roof separation in the advance section of the two roadways on the working face increase slightly, so the roadway support needs to be strengthened.
An optimized identification method of coal-bearing stratum lithology
ZHANG Ning, ZHANG Youzhen, YAO Ke
2020, 46(7): 100-106. doi: 10.13272/j.issn.1671-251x.2020010037
<Abstract>(60) <HTML> (13) <PDF>(9)
Abstract:
In view of difficulties in obtaining stratum information parameters and low accuracy of lithology identification in existing lithology identification method of coal-bearing stratum in coal mine underground, an optimized identification method of coal-bearing stratum lithology based on principal component analysis (PCA) algorithm and kernel fuzzy C-means clustering (KFCM) algorithm was proposed. A high-dimensional drilling parameters set was constructed by using drilling test rig to obtain six kinds of drilling sensitive parameters, such as penetration rate, rotary torque, drilling pressure, rotational speed, rotary pressure and mud pump flow rate, which was taken as identification data sources, including training samples and test samples. Combining feature extraction advantage of PCA algorithm and good clustering effect of KFCM algorithm, a lithology identification model based on PCA-KFCM algorithm was established. The PCA algorithm was used to extract features of the training samples and reduce the dimension of the data to obtain eigenvalues and eigenvectors of the training samples. KFCM algorithm was used to conduct fuzzy core clustering on principal component data sets of training samples, and the test rock samples were divided into several types. The criterion was established by the Mahalanobis distance method, and the formation lithology of the test samples was identified by the minimum Mahalanobis distance. The test results show that the optimized identification method of coal-bearing stratum lithology based on PCA-KFCM algorithm can effectively identify formation lithology, and the identification accuracy is improved by 23.2% compared with the conventional KFCM algorithm.
Research on unloading drill-rod action identification in coal mine water exploratio
DANG Weichao, YAO Yuan, BAI Shangwang, GAO Gaimei, WU Zhefeng
2020, 46(7): 107-112. doi: 10.13272/j.issn.1671-251x.2019070074
<Abstract>(67) <HTML> (12) <PDF>(14)
Abstract:
In view of low efficiency and error prone problems in the way that supervisors of underground water exploration operation realize monitoring of unloading drill-rod operation by watching video, 3D convolutional neural network (3DCNN) model is proposed to identify unloading drill-rod action in water exploration operation. In 3DCNN model, 3D convolution layer is used to automatically extract action features, 3D pooling layer is used to reduce dimension of motion features, softmax classification is used to identify unloading dirll-rod action, and batch normalization layer is used to improve convergence speed and identification accuracy of the model. When the 3DCNN model is used to identify unloading drill-rod action, firstly, the data set is preprocessed, and several frames of images are extracted from each video as representatives of an action, and the resolution is reduced; secondly, the training set is used to train the 3DCNN model, and the trained weight file is saved; finally, the trained 3DCNN model is used to test the test set, and the classification results are obtained. The experimental results show that when the number of sampling frames is 10, the resolution is 32×32, and the learning rate is 0.000 1, the highest recognition accuracy of the model can reach 98.86%.
A coal-gangue optimization identification method
ZHAO Minghui
2020, 46(7): 113-116. doi: 10.13272/j.issn.1671-251x.2020040058
<Abstract>(106) <HTML> (12) <PDF>(12)
Abstract:
Aiming at problem that target detection of coal-gangue image is not accurate due to wear of conveyor belt, which affects identification accuracy of coal-gangue, a coal-gangue optimization identification method is proposed. After pre-processing of collected images such as cutting, denoising and grayscale, the trained cornernet-squeeze deep learning model is used to judge whether there is coal or gangue to be detected in the images. If there is, position of coal or gangue in the images is located, which can effectively reduce background interference of conveyor belt during detection. The location area is analyzed by gray histogram, then according to third moment characteristic parameter of image gray histogram, coal-gangue is classified to determine whether it is coal or gangue to improve identification accuracy. The experimental results show that the method has high identification accuracy and good real-time performance with identification accuracy of 91.3% and identification time of 41 ms for single image.
A constant power cutting method of continuous shearer based on fuzzy control
YUAN Gang
2020, 46(7): 117-122. doi: 10.13272/j.issn.1671-251x.2020010007
<Abstract>(57) <HTML> (11) <PDF>(12)
Abstract:
Due to complicated working conditions in underground coal mine, the load of cutting motor of continuous shearer changes randomly, which often leads to shutdown of the cutting motor due to overload. However, the current constant power cutting method of continuous shearer can only optimize current of cutting motor in a small range, and cannot realize self-adaptive adjustment and effectively solve overload phenomenon of the motor. For the above problems, a constant power cutting method of continuous shearer based on fuzzy control was proposed, which could realize self-adaptive regulation of walking motor speed through establishment of fuzzy controller of cutting motor current and walking motor speed. The fuzzy controller takes the difference between actual current and rated current of the cutting motor and the difference change rate as input variables, the speed regulation proportion value of the walking motor as the output variables. When the cutting motor current is not normal, fuzzy control method was used to adjust walking motor speed to make the cutting motor current in rated range, so as to realize constant power cutting.The verification results show that compared with the linear curve method, the maximum current of the cutting motor is only exceeds 9% of the rated current after using fuzzy control, current overload times of the cutting motor are significantly reduced, and constant power cutting of the continuous shearer is well realized.

苏ICP备 05016349号-2

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