工矿自动化

Roadheader positioning method combining total station and strapdown inertial navigation system

ZHANG Xuhui, LIU Boxing, ZHANG Chao, YANG Wenjuan, ZHAO Jianxun

2020, 46(9): 1-7. doi: 10.13272/j.issn.1671-251x.17641

<Abstract>(48) <HTML> (6) <PDF>(13)

Abstract:
In order to solve the problems that roadheader positioning method based on total station could not locate because light path could be blocked due to excessive dust in coal mine underground and cumulative error of the method based on strapdown inertial navigation system(SINS) increased gradually with time, a roadheader positioning method combining total station and SINS was proposed. Firstly, total station is used to measure position parameters of roadheader, and SINS is used to measure and calculate position and posture parameters. Then, longitude and latitude of roadheader position measured by SINS are converted into coordinate values under Xi'an 80 coordinate system, so as to realize unification with total station measurement coordinate system. Finally, Kalman filtering method is used to fuse measured data of total station and SINS, so as to obtain position and attitude data of roadheader. The experimental results show that the method has high poisoning precision: in x direction, the maximum positioning error is 0.029 1 m, the minimum error is 0.010 0 m, and the average error is 0.019 93 m; in y direction, the maximum positioning error is 0.029 5 m, the minimum error is 0.011 0 m, and the average error is 0.018 26 m.

Current situation and development trend of heavy-duty operation robot for coal mine roadway repair

XUE Guanghui, HOU Chenxin, ZHANG Yunfei, WU Miao

2020, 46(9): 8-14. doi: 10.13272/j.issn.1671-251x.17658

<Abstract>(48) <HTML> (6) <PDF>(11)

Abstract:
Coal mine heavy-duty operation robot is an intelligent equipment to replace workers in high-risk positions, which faces challenges such as narrow working space and complex and changeable working environment. Current situations of heavy-duty industrial robots were summarized as well as development history of coal mine roadway repair equipment. It was pointed out that existing coal mine roadway repair equipment could only realize functions of remote control and automatic roll-cable with low intelligence level, and heavy-duty operation robot for coal mine roadway repair should be developed. The concept and functional localization of heavy-duty operation robot for coal mine roadway repair were put forward, and many key technical problems which needed to be solved were pointed out, such as accurate position and attitude perception in narrow and enclosed roadway space, walking path planning and control, operation trajectory planning and motion control, etc. Development directions of heavy-duty operation robot for coal mine roadway repair were expounded, which were improving its reliability, stability and intelligence level, and strengthening construction technique matching with other robots.

Digital twin driven remote automatic cutting control technology of roadheader

ZHANG Chao, ZHANG Xuhui, ZHANG Kaixin, XIE Nan, ZHOU Chuang

2020, 46(9): 15-20. doi: 10.13272/j.issn.1671-251x.17640

<Abstract>(74) <HTML> (9) <PDF>(18)

Abstract:
Existing remote cutting control methods of roadheader are mostly based on video monitoring and planar information, and roadway section forming quality depends on manual operation experience with low reliability. For the above problems, digital twin driven remote automatic cutting control technology of roadheader was researched, and implementation process of digital twin driven automatic cutting of roadheader was introduced from aspects of data sensing, data driving, data transmission and remote automatic cutting control. Position and attitude data of roadheader is obtained by use of vision measurement technology and tunneling environment data is gathered by gas and other sensors, which form data source of data twin driving. Vitual model of roadheader and virtual scene are established, and action programming and coupling between the virtual model and virtual scene are finished. Interaction between roadheader and the virtual model is realized by normal and inverse kinematics of roadheader. "S" shape cutting trajectory of roadway section is planned based on cubic polynomial method, and linear integral feedback sliding mode controller is designed to control cutting trajectory. MySQL database is taken as medium of data interaction, and remote data transmission is realized through underground industrial ethernet ring network and mine-used 5G technology. The experimental results show that the cutting head of roadheader can stably follow the planed trajectory, and position and attitude of cutting head of roadheader in virtual interface is accordant with the actual ones at the same moment.

Research on deviation correction control of rapid tunneling robot based on vision measurement

ZHANG Xuhui, ZHOU Chuang, ZHANG Chao, XIE Nan, ZHANG Kaixin, LIU Boxing

2020, 46(9): 21-26. doi: 10.13272/j.issn.1671-251x.17639

<Abstract>(45) <HTML> (6) <PDF>(15)

Abstract:
Aiming at problems of insufficient positioning and control accuracy of tunneling robot in environment with high dust and low illumination of coal mine, a deviation correction control system of rapid tunneling robot based on vision measurement is designed. The explosion-proof camera installed on rapid tunneling robot is used to collect image of laser pointing instrument at the rear, and the collected image information is transmitted to explosion-proof computer through Ethernet. The explosion-proof computer is used to preprocess the image and then the pose of the rapid tunneling robot is calculated according to pose calculation model. The calculated pose information is compared with designed roadway axis information, and the pose deviation between the pose of the rapid tunneling robot and the roadway design axis is calculated. According to type and size of the pose deviation, different control strategies are adopted to calculate corrected control quantity and control instructions are output. The control command controls spool movement of solenoid proportional valve to control telescopic oil cylinder. According to the different expansion amount of the telescopic cylinder in each area, the pose of the rapid tunneling robot is adjusted to realize deviation correction control. The experimental results show that the average deviation of vision meosurement accuracy in X direction is 21.334 mm, that in Y direction is 34.154 mm, that of yaw angle is 0.493 ° and the error of deviation correction control in X direction is less than 30 mm, which meets requirements of actual working conditions.

Intelligent remote control technology for fully-mechanized roadheader of Tangkou Coal Mine

LIU Yansheng

2020, 46(9): 27-32. doi: 10.13272/j.issn.1671-251x.17537

<Abstract>(61) <HTML> (9) <PDF>(14)

Abstract:
At present, research and application of automation of fully-mechanized roadheader and intelligence of fully-mechanized process in China have achieved initial results, but there are still some problems in intelligent perception and remote control technologies. In terms of actual conditions of fully-mechanized heading face in Tangkou Coal Mine, automatic location, cutting, remote control technologies of fully-mechanized roadheader are used to develop an intelligent remote control system for fully-mechanized roadheader. Full-automatic explosive proof type total station is adopted to locate the roadheader combining with many sensors. Operation system, electrical control system and hydraulic pressure system of the roadheader are upgraded to realize location data analysis, automatic planning of cutting actions and other functions. Remote control of automatic location and one-key cutting of the roadheader are realized by use of long distance transmission protocol. The application show that after implementation of the intelligent remote control system for fully-mechanized roadheader, unmanned operation in range of 30-50 m away from fully-mechanized heading face in Tangkou Coal Mine is realized, which improvs safety production level, and only one operator is needed in a team to achieve goal of downsizing staffs and improving efficiency.

Research on self-renewing leakage detection technology of coal mine gas drainage pipe network system

XIONG Wei

2020, 46(9): 33-37. doi: 10.13272/j.issn.1671-251x.2020040016

<Abstract>(54) <HTML> (6) <PDF>(10)

Abstract:
Working environment in underground coal mine is harsh, and gas drainage pipelines are vulnerable to collision, coal falling and other injuries, resulting in gas leakage. When a large amount of air in tunnel enters pipe network system, the concentration of gas drainage in pipe network may be much lower than the concentration at the drilling hole. For the above problems, a self-renewing leakage detection technology of coal mine gas drainage pipe network system based on multi-Gaussian beam model was proposed. Multi-Gaussian beam model is adopted to strengthen the processing of the sound of the leakage points, main leakage types and noise sources of underground gas drainage pipe network system are analyzed, and leakage model and noise model are established.The collected sound samples are compared with pre-stored models to determine whether there is gas leakage, and the sound samples that occur more than 30% in the use environmen are automatically stored as gas leakage models to realize automatic model update and improve leakage detection accuracy. YJL40 leakage detector is developed based on self-renewing leakage detection technology, its main components include probe, metal hose, host and alarm. Self-renewing leakage detection technology and corresponding products are applied in high and low negative pressure drainage system in Gaojiazhuang Coal Mine for leakage detection of totals 7 585 m of pipelines, after the detected leakage points are effectively sealed, the gas volume fraction in drainage terminal is increased by 37.1% and 28% respectively, verifying the effectiveness of the self-renewing leakage detection technology.

Research on air leakage characteristics in goaf of working face under natural wind pressure

LIU Kunlun, CHANG Bo, MA Zujie, WANG Gang

2020, 46(9): 38-43. doi: 10.13272/j.issn.1671-251x.2020020027

<Abstract>(51) <HTML> (9) <PDF>(8)

Abstract:
Taking +450 m level B1+2 coal seam working face in the southern area of Wudong Coal Mine as an example, the law of natural wind pressure change is analyzed, combined with the field measured data of air volume changes in the air intake roadway, the actual impact of natural wind pressure on the working face is qualitatively explained. Air leakage amount and distribution are indirectly estimated by calculating projected area of wind speed, and the air leakage phenomenon in the goaf behind the working face caused by change of natural wind pressure is quantitatively studied combined with field measurement and curve fitting methods. Research result shows that the change of natural wind pressure in the southern area of Wudong Coal Mine has significant impact on branches in the ventilation system and the main ventilator operating points of the mine; the change of natural wind pressure is the main controlling factors that affects the change of air volume in the air intake roadway of B1+2 working face; In winter, due to the high natural wind pressure, the air volume in the air intake roadway becomes larger, the air amount leaking into the goaf is more than that in summer, the air flow velocity in the goaf is faster, and the flow field distribution range in the goaf is wider.

Research on behaviour law and control of mine pressure on fully mechanized top coal caving mining face with shallow burial depth

YANG Zhen, GUO Ruirui, YANG Yongliang

2020, 46(9): 44-50. doi: 10.13272/j.issn.1671-251x.2020060003

<Abstract>(57) <HTML> (8) <PDF>(9)

Abstract:
Current research on mine pressure law of working face mainly focus on mine pressure law and roof structure of large mining height working face with shallow burial depth, but there's few researches on behaviors law and control technology of strong mine pressure of fully mechanized top coal caving mining face with shallow burial depth. For the above problem, taking 42202 working face of a coal mine as research background, behaviors law of strong mine pressure of working face was researched using actual measurement method combining support monitoring and micro-seismic monitoring of working face: the first weighting interval of 42202 working face is 60 m, and periodic weighting interval is 18-26 m. When pressure is weighting, dynamic load coefficient of the support is as high as 1.58, depth of rib spalling is up to 1 100 mm, and shrinkage of the support is 50-80 mm. The strong mime pressure causes working face to crush support. When pressure is applied, the pressure in the middle part is large, while pressure on both sides are small, indicating that mine pressure appears more violently when working face pressure comes; Micro-seismic events are mainly concentrated in the advance position of the working face and auxiliary transportation roadway, and the change trend of daily cumulative energy and daily frequency is basically the same. The mechanism of strong mine pressure of fully mechanized top coal caving mining face with shallow burial depth was analyzed, it is pointed out that the main reason of the strong mine pressure on working face is joint instability effect between "voussoir beam" structure formed by upper key strata and "cantilever beam" structure formed by lower key strata. In view of the problem of strong mine pressure, weakening measure of roof caused by hydraulic fracturing was proposed. After adopting hydraulic fracturing measure, the maximum working resistance of support decreases from 59.1 MPa to 50.1 MPa, reducing by about 15%.The maximum stress of deep hole decreased by 15%, and the maximum stress of shallow hole decreased by 32%, indicating that hydraulic fracturing had a significant effect on roof weakening and roadway surrounding rock stress weakening.

Research on intelligent visual obstacle avoidance of underground mobile robot

PENG Jiguo, ZHANG Bo, SUN Lingfei, DENG Pan

2020, 46(9): 51-56. doi: 10.13272/j.issn.1671-251x.2020030023

<Abstract>(51) <HTML> (7) <PDF>(10)

Abstract:
In view of problems that existing obstacle avoidance methods of underground mobile robot cannot accurately detect obstacle position information when facing complex obstacles and is inability to perform accurate obstacle avoidance control for the underground nonlinear obstacles, an intelligent visual obstacle avoidance method of underground mobile robot based on fuzzy control was proposed. First, binocular stereo vision module is used as obstacle detection sensor to perceive underground environment information, detect distribution of obstacles in real time, and construct occupation grid map. Then， the octree structure model is used to construct three-dimensional point cloud, and the tree structure is used to describe point cloud data structurally, which is mapped to the occupation grid map to obtain regional distribution of obstacles. Finally, a fuzzy control strategy is used to process distribution of obstacles detected in real time in the occupation grid map, and distribution of obstacles in the occupation grid map at the current moment and the running speed of the mobile robot are used as input variables of the fuzzy controller. The fuzzy control algorithm is used to calculate steering angle and acceleration of the mobile robot at the next moment, so as to realize intelligent obstacle avoidance control of the underground mobile robot. According to actual space occupied by the mobile robot, an external bounding box is designed to further stabilize control algorithm, and the obstacle avoidance strategy is combined to perform intelligent obstacle avoidance to avoid collision between mobile robot and obstacle. The experimental results show that the method can accurately describe distribution of underground obstacles, and enable the mobile robot to avoid obstacles accurately and autonomously according to the designed fuzzy control rules, so as to realize adaptive movement.

Research on dual-arm parallel coal gangue sorting robot and its trajectory planning

ZHAO Minghui

2020, 46(9): 57-63. doi: 10.13272/j.issn.1671-251x.2020040059

<Abstract>(73) <HTML> (6) <PDF>(8)

Abstract:
At present, the automatic sorting system of gangue mostly adopts series mechanical arm, which can only sort out the gangue with small particle size.The separation speed is slow and the separation effect is not ideal. In view of this problem, a kind of dual-arm parallel coal gangue sorting robot was designed. The robot adopts the sorting mode of pushing rather than grasping, which can sort the gangue with the particle size of 300-600 mm, and greatly reduce the torque demand of the manipulator and improve the sorting speed. In order to avoid rigid impact caused by frequent start-up and stop and prolong the service life of the motor, parabola interpolation function, cubic polynomial interpolation function and quintic polynomial interpolation function are respectively used for trajectory planning in joint space. Simulation and comparative analysis results show that the angular acceleration curve transition is smooth when using quintic polynomial interpolation function for trajectory planning, the angle and angular velocity constraints of the starting and ending points of the robot trajectory are satisfied, and the angular acceleration constraint is also satisfied, so that the motion trajectory of the sorting robot is more stable. The experimental results show that for the coal gangue with particle size of 300-600 mm,the recognition rate and sorting rate of dual-arm parallel coal gangue sorting robot are 91.14% and 86.29% respectively, with high sorting accuracy and stability; it only takes 1.2 s to complete a single complete sorting operation, which greatly shortens the sorting cycle compared with manual sorting; through joint space trajectory planning, the rigid impact of the motor in the sorting process is reduced, which can ensure the system stable work for a long time.

Underground target positioning based on differential error suppression optimization method

SONG Yunzhong, WANG Renhui

2020, 46(9): 64-68. doi: 10.13272/j.issn.1671-251x.2019050056

<Abstract>(45) <HTML> (5) <PDF>(6)

Abstract:
In view of problem that positioning accuracy of positioning methods based on time ranging, namely arrival time, one-way ranging, two-way ranging and symmetrical double-sided two-way ranging (SDS-TWR) is disturbed by timing error factors such as clock asynchronization between nodes, timer frequency offset and equipment delay, an underground target positioning method based on differential error suppression optimization method was proposed. Combining with SDS-TWR positioning method, the method uses characteristics of target node as both transmitting node and receiving node to solve relationship between transmission time and length simultaneously. Irrelevant variables such as timer frequency offset and equipment delay are eliminated through matrix form and coordinates of unknown target node are only related to the measured time, so as to effectively eliminate influence of timing error on the positioning result of the target node, and achieve purpose of precise positioning. The simulation results show that compared with the one-way ranging and two-way ranging methods, the differential error suppression optimization method can effectively suppress influence of equipment delay and timer frequency offset on the positioning method based on time ranging, and can accurately locate the unknown node with high positioning accuracy, the range of ranging error is only ［-0.036 9 m, 0.037 7 m］, which is 0.012% of one-way ranging error and 0.061% of two-way ranging error.

Research on speed control algorithm of coal mine local ventilator

DU Gang, MA Xiaoping, ZHANG Ping

2020, 46(9): 69-73. doi: 10.13272/j.issn.1671-251x.2020030025

<Abstract>(29) <HTML> (7) <PDF>(8)

Abstract:
At present, coal mine local ventilator system mainly adopts conventional PID control algorithm to carry out frequency-conversion speed-regulation，but the conventional PID control parameter adjustment mainly relies on artificial experience, adjustment time is long, real time is poor, and easy to occur over-regulating and oscillating output of the control quantity. To solve the above problems, a particle swarm optimization (PSO) optimized PID control algorithm was proposed and applied to the speed control of coal mine local ventilator. PSO algorithm is added to the speed control system of coal mine local ventilator based on the conventional PID control algorithm to realize PID control parameter optimization. The conventional PID control part directly runs in accordance with the optimal parameter setting obtained by Z-N tuning method; PSO optimized PID control part randomly generated a set of three-dimensional particles through the algorithm program of S function, and calls the function assignin to assign three-dimensional particles values to Kp，Ki，Kd parameters of speed control system simulation model, taking control system error indicator ITAE as fitness function for iterative optimization, unity of PSO optimization and PID parameter setting optimization is realized.The simulation results show that compared with the conventional PID control, after PSO algorithm optimization, the output performance of local ventilator speed control are improved significantly, especially the overshoot and the regulation time index, and the overshoot is only 20% of the conventional PID control algorithm.

Super-resolution reconstruction method of mine image based on online multi-dictionary learning

WANG Haitao, YU Wenjie, ZHANG Guanglei

2020, 46(9): 74-78. doi: 10.13272/j.issn.1671-251x.17655

<Abstract>(75) <HTML> (12) <PDF>(14)

Abstract:
Aiming at problem that dictionary learning method was poorly effective in reconstruction of mine image with noise and complex environment, a super-resolution reconstruction method of mine image based on online multi-dictionary learning was proposed. The method uses K-means clustering algorithm to divide image training set into multiple kinds of images, and trains multiple sets of high-resolution dictionaries and low-resolution dictionaries for different kinds of images, so as to improve feature representation ability of the dictionaries for complex environmental images. According to non-local self-similarity of image, non-local constraint is introduced to further constrain solution space of sparse coefficient, and online dictionary learning is used to optimize the dictionaries in the multi-dictionary learning stage, so as to improve accuracy of sparse coefficient solution and anti-noise interference ability of image reconstruction process. The experimental results show that the method can effectively improve quality of reconstructed image, suppress image blocking effect and edge jagged effect caused by noise, enhance image details, and achieve better visual effect.

Line laser assisted visual monitoring for opening of water plug-in gate valve in coal preparation plant

TIAN Jun, LI Ming, JIANG Jin, ZHU Meiqiang, LEI Meng

2020, 46(9): 79-82. doi: 10.13272/j.issn.1671-251x.17626

<Abstract>(30) <HTML> (7) <PDF>(9)

Abstract:
Aiming at problem that opening of water plug-in gate valve in coal preparation plant needs manual adjustment and cannot achieve centralized control, a line laser assisted visual monitoring method for opening of water plug-in gate valve in coal preparation plant was proposed. Line laser is used as an auxiliary detection means to increase target detection characteristics and avoid influence of light changes on target detection, and video monitoring system is used to collect plug-in gate valve image. Template matching method is used to locate target in the image, adaptive threshold method is used to detect line laser projected on the gate, and then adjacent disconnected areas of the line laser on the gate are connected through morphological operations such as corrosion, expansion and so on. Meanwhile, Gaussian filtering method is adopted to remove image noise, so position and length of the line laser in the image are obtained to detect opening of plug-in gate valve. PLC centralized control system realizes closed-loop control of opening of plug-in gate valve by comparing the detected opening value and the set one. The experimental results show that the method can accurately locate plug-in gate valve under different background brightness conditions, and improve detection accuracy of opening of plug-in gate valve.

A mine-used adaptive power supply with super wide input voltage range

LIN Yin, MENG Xiaohong, LIU Yahui

2020, 46(9): 83-87. doi: 10.13272/j.issn.1671-251x.2019110045

<Abstract>(61) <HTML> (10) <PDF>(11)

Abstract:
For problems of existing mine-used power supply such as inconvenient access, large volume, poor anti-fluctuation ability, complex circuit and high cost, a mine-used adaptive power supply with super wide input voltage range was designed. The power supply adopts input-series flyback converter, which can reduce voltage stress of power switching tube and convert super wide input voltage into stable DC voltage. The test results show that when input voltage is AC85-900 V, the maximum error of power supply output voltage is only 1.1%, ripple voltage is not more than 139 mV, and efficiency is 87.4%. In test of insulation withstand voltage, leakage current is not more than 1.53 mA and insulation resistance is not less than 50 MΩ, which meet explosion-proof requirements of GB 3836.4-2010 Explosive atmospheres Part 4: Equipment protection by intrinsic safety "i".

Cross-coupling control method for motor of mine cable winding car

WU Guoping, YAN Xiaoheng

2020, 46(9): 88-93. doi: 10.13272/j.issn.1671-251x.2020020045

<Abstract>(63) <HTML> (9) <PDF>(6)

Abstract:
In order to improve working accuracy of motor unit of mine cable winding car, aiming at problems of load disturbance and speed adjustment in the operation control of cable motor and reel motor, a cross-coupling control method for motor of mine cable winding car was proposed. Fruit fly optimization algorithm (FOA) is used to optimize PI parameters of motor cross-coupling control model, and ITAE function is used as evaluation index to measure parameter optimization performance. The simulation analysis results show that compared with genetic algorithm (GA), using FOA for PI parameter optimization has higher convergence speed and lower error; the cross-coupling control model using FOA for PI parameter optimization can complete motor speed adjustment within 20 ms, which has high adjustment speed, high convergence accuracy and good stability; the motor can quickly follow response after interference is applied, which verifies that the cross-coupling control method for motor of mine cable winding car has good anti-interference and follow ability.

Mine flood perception based on gray level co-occurrence matrix and regression analysis

CAO Yuchao

2020, 46(9): 94-97. doi: 10.13272/j.issn.1671-251x.17678

<Abstract>(51) <HTML> (6) <PDF>(6)

Abstract:
Aiming at problems of low recognition rate and poor stability and timeliness when image recognition was used in mine flood perception, a mine flood perception method based on gray level co-occurrence matrix and regression analysis was proposed. Gray co-occurrence matrix of sample image is calculated, and contrast, dissimilarity, homogeneity, entropy, correlation and energy of the gray co-occurrence matrix are extracted as eigenvalues to form eigenvectors. The classifier is determined based on the sum of the minimum distance from the eigenvector of the sample image to nonlinear regression equation, and flood is identified by the classifier. The experimental results show that recognition rate of the method on data set composed of anthracite, sandstone and surging water is 96.33% for image with resolution of 256×256, and average time-consuming of single image is 16.288 5 ms.

Design of on-line detection system of mine emulsion concentratio

XI Bo, WANG Shi'ao, GUO Jianwei

2020, 46(9): 98-103. doi: 10.13272/j.issn.1671-251x.2020040023

<Abstract>(42) <HTML> (8) <PDF>(8)

Abstract:
In view of problems that existing emulsion concentration detection methods are greatly affected by temperature and cannot be measured in real time and tracked and sampled throughout the entire process, on the basis of traditional density method, an on-line detection system of mine emulsion concentration was designed. The system monitors real-time status information of emulsion through tension sensor, temperature sensor and liquid level sensor embedded in storage tank and sends it to DSP control terminal. The DSP control terminal solves the current emulsion concentration based on principle of density method and uploads it to the host computer to achieve real-time on-line detection function. Temperature compensation technology is used to reduce measurement error at different temperatures, FIR digital filtering technology is used to filter the vibration interference caused by the sensor bracket and box, and gradient descent algorithm is used to correct the tension sensor parameters to improve measurement accuracy. Experimental results show that the system can realize real-time and on-line detection of mine emulsion concentration, and the maximum error between the detection value and the standard value is 1.5%, which meets the requirements of coal mine production.

Prediction method of coal spontaneous combustion based on relevance vector machine

LIU Bao, MU Kun, YE Fei, WANG Fan, WANG Jingting

2020, 46(9): 104-108. doi: 10.13272/j.issn.1671-251x.17578

<Abstract>(60) <HTML> (8) <PDF>(10)

Abstract:
In terms of coal spontaneous combustion degree prediction, the radial basis function (RBF) neural network method is complex in structure and easy to fall into local optimum, the kernel function based on support vector machine (SVM) is sensitive to parameters due to Mercer condition, the traditional machine learning method has a large error. For the above problems, a coal spontaneous combustion prediction method based on relevance vector machine (RVM) is proposed. Taking Tingnan Coal Mine which is prone to spontaneous combustion as an example, the temperature rising process of coal sample spontaneous combustion is simulated, and the data of gas concentration and coal spontaneous combustion temperature are collected to establish training samples and test samples. The RVM model is constructed from the training samples, and the optimal parameters of the model are obtained. The test samples are substituted into the trained RVM model to predict coal spontaneous combustion temperature. Compared with coal spontaneous combustion prediction methods based on RBF neural network and SVM, the results show that the coal spontaneous combustion prediction methods based on RBF neural network and SVM have small training error but large test error, which indicates that the two methods have over fitting phenomenon and poor generalization ability. The training error and test error of the coal spontaneous combustion prediction method based on RVM are close and prediction accuracy is the highest.

Optimal control of mine multi-level relay drainage system

HAN Xiuqi

2020, 46(9): 109-112. doi: 10.13272/j.issn.1671-251x.2019120057

<Abstract>(66) <HTML> (6) <PDF>(8)

Abstract:
The electricity consumption of mine multi-level relay drainage system is very large, in order to improve economy of drainage system operation, it is necessary to optimize drainage system control, but current optimal control methods of mine multi-level relay drainage system have some problems such as easy overflow of sump and frequent start and stop of water pump. For the above problems, an optimal control strategy of mine multi-level relay drainage system was proposed. The optimal control model of mine multi-level relay drainage system was established which took water level of each level sump must be between the lowest and highest level and displacement of each level sump should not be less than inflow as constraint conditions, and the lowest sum of electricity costs of each level within one drainage period as objective function. By introducing margin into flow constraint condition, frequent start and stop of water pump is avoided. Gray model is used to predict water inflow, so as to obtain accurate water level of sump and avoid overflow accident. The application results show that the optimal control strategy can reduce electricity cost of drainage system under premise of ensuring safety of drainage.

2020 Vol. 46, No. 9

Submission System

Latest AcceptedMore>