WO2022057397A1 - 一种矿山智能化无人开采大数据分析决策方法和系统 - Google Patents
一种矿山智能化无人开采大数据分析决策方法和系统 Download PDFInfo
- Publication number
- WO2022057397A1 WO2022057397A1 PCT/CN2021/104829 CN2021104829W WO2022057397A1 WO 2022057397 A1 WO2022057397 A1 WO 2022057397A1 CN 2021104829 W CN2021104829 W CN 2021104829W WO 2022057397 A1 WO2022057397 A1 WO 2022057397A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- data
- model
- mining
- transparent
- coal
- Prior art date
Links
- 238000005065 mining Methods 0.000 title claims abstract description 133
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000004458 analytical method Methods 0.000 title abstract description 9
- 239000003245 coal Substances 0.000 claims abstract description 117
- 238000005520 cutting process Methods 0.000 claims abstract description 107
- 230000008569 process Effects 0.000 claims abstract description 19
- 238000004519 manufacturing process Methods 0.000 claims abstract description 8
- 238000005516 engineering process Methods 0.000 claims description 66
- 238000012937 correction Methods 0.000 claims description 38
- 238000007405 data analysis Methods 0.000 claims description 27
- 238000005553 drilling Methods 0.000 claims description 23
- 238000005259 measurement Methods 0.000 claims description 18
- 238000012544 monitoring process Methods 0.000 claims description 15
- 238000009826 distribution Methods 0.000 claims description 13
- 238000000547 structure data Methods 0.000 claims description 12
- 230000035515 penetration Effects 0.000 claims description 8
- 238000004220 aggregation Methods 0.000 claims description 5
- 230000002776 aggregation Effects 0.000 claims description 5
- 238000006073 displacement reaction Methods 0.000 claims description 4
- 238000010801 machine learning Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 108010001267 Protein Subunits Proteins 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 208000008918 voyeurism Diseases 0.000 description 2
- 206010010356 Congenital anomaly Diseases 0.000 description 1
- 241000219122 Cucurbita Species 0.000 description 1
- 235000009852 Cucurbita pepo Nutrition 0.000 description 1
- 102000002067 Protein Subunits Human genes 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000013209 evaluation strategy Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000005211 surface analysis Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/05—Geographic models
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21C—MINING OR QUARRYING
- E21C35/00—Details of, or accessories for, machines for slitting or completely freeing the mineral from the seam, not provided for in groups E21C25/00 - E21C33/00, E21C37/00 or E21C39/00
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21F—SAFETY DEVICES, TRANSPORT, FILLING-UP, RESCUE, VENTILATION, OR DRAINING IN OR OF MINES OR TUNNELS
- E21F17/00—Methods or devices for use in mines or tunnels, not covered elsewhere
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T19/00—Manipulating 3D models or images for computer graphics
- G06T19/20—Editing of 3D images, e.g. changing shapes or colours, aligning objects or positioning parts
Definitions
- the present application relates to the technical field of intelligent mining, and in particular, to a method and system for big data analysis and decision-making of intelligent unmanned mining in mines.
- the purpose of this application is to provide a big data analysis and decision-making method and system for intelligent unmanned mining of mines, specifically intelligent unmanned mining of transparent working faces of mines, so as to solve or alleviate the problems existing in the above-mentioned prior art.
- the present application provides a big data analysis and decision-making method for intelligent mining of transparent working face, including: step S101, constructing a transparent geological model and planning cutting template of the coal mining face; The model is cut to obtain the interface curve of the cut-out roof and the interface of the cut-out bottom plate of the transparent geological model, and based on inertial navigation technology and radar positioning technology, according to the working condition monitoring data of the fully mechanized mining equipment, the cutting model is corrected in real time; Step S103, the fully mechanized mining machine automatically cuts the coal mining face in real time according to the revised planning cutting template.
- This application provides a transparent working face intelligent mining big data analysis and decision-making system, including:
- the model building unit is configured to build a transparent geological model of the coal mining face and a planning cutting template; the model building unit includes: a geological model building subunit and a planning cutting template building subunit, and the model correction unit includes: a first correction subunit , the second correction subunit and the third correction subunit.
- This application collects and analyzes geological data through technologies such as roadway fine measurement, borehole detection, slot wave seismic exploration, etc., establishes a transparent geological model with multiple steps in the transparent working face, and constructs a big data analysis of intelligent mining of the transparent working face.
- the overall design framework for decision-making using the unification and correlation of multiple communication protocol data of different equipment in the coal mining face, based on the mining process, fully mechanized mining automation control technology, inertial navigation technology and radar ranging technology, through the mining process.
- the coal seam and the newly generated geological data in the production process are constantly revised and updated to the transparent geological model, and the precise control decision-making information of the fully mechanized mining equipment is obtained. Intelligent and precise mining.
- Fig. 1 is a schematic flow chart of the big data analysis and decision-making method for intelligent mining of transparent working face
- Figure 2 is a schematic flow chart of constructing a transparent geological model of a coal mining face
- Fig. 3 is a schematic flow chart of the top/bottom interface curve of the coal mining face
- Fig. 4 is a schematic flow chart of planning cutting template correction
- Figure 5 is a schematic diagram of the structure of the big data analysis and decision-making system for intelligent mining of transparent working faces.
- CT computed tomography
- Fig. 1 is the schematic flow chart of the intelligent mining big data analysis and decision-making method provided by the application; as shown in Fig. 1, the transparent working face intelligent mining big data analysis and decision-making method includes:
- Step S101 constructing a transparent geological model and a planning cutting model of the coal mining face
- the cascade model of the coal mining face is constructed, and the transparent geological model with multiple steps of the coal mining face is obtained;
- the geological data includes at least: geological structure data, coal thickness floor data, coal seam undulation state data, coal seam hidden structure data, coal thickness distribution data, and drilling hole penetration coal seam roof and floor position data.
- geological structure data, coal thickness floor data, coal seam undulation state data can be obtained through fine measurement of roadway; coal seam hidden structure data can be obtained through channel wave seismic exploration; coal thickness distribution data, coal seam roof and floor penetration data can be obtained through downhole drilling location data.
- the constructed transparent geological model can be smoother, more consistent with the actual situation of the bottom layer, and the model accuracy is higher.
- the analysis of the undulating shape of the coal seam mainly draws the contour map of the roof and floor and the contour map of coal thickness. Constraints; on the other hand, by simulating the contour lines of the roof and floor of the panel area, the constraint information of the roof and floor is added, and the undulating shape of the coal seam is basically determined.
- the development of faults is judged by means of geophysical exploration methods such as channel wave seismic exploration and pit penetration, combined with the contour lines of the roof and floor of the coal seam.
- the shape of the scour zone is usually a lens shape or a gourd string. According to the shape of the scour zone, a trend surface analysis is performed to predict the scope of the scour zone. Combined with lithology (mud content) and other information to judge the two wings of the scour zone. Coal seam bifurcation, according to the realistic situation, define the coal seam bifurcation and judge the nature of the coal seam bifurcation.
- Fig. 2 is a schematic flow chart of constructing a transparent geological model of a coal mining face provided by the application; as shown in Fig. 2, in step S101, constructing a transparent geological model of a coal mining face includes:
- Step S111 constructing a first-level transparent geological model of the coal mining face according to the data of the air inlet and return airway, the ground drilling data, and the realistic data of the incision;
- the data of the air inlet and return airway and the realistic data of the cut holes are included in the coal seam undulation state data and the coal thickness distribution data obtained by the fine measurement of the roadway; the surface drilling data is included in the data of the roof and floor positions of the drilling holes passing through the coal seam obtained by the downhole drilling.
- Step S121 based on the first-level transparent geological model, according to the data of the air inlet and return airway, ground drilling data, realistic data of incisions, drilling measurement data, and channel wave seismic exploration data, construct a second-level transparent geological model of the coal mining face ;
- the borehole measurement data at least include: coal thickness distribution data, the position data of the roof and floor of the borehole passing through the coal seam;
- the channel wave seismic exploration data at least include: coal seam hidden structure data;
- the first-level transparent geological model is dynamically updated through borehole observation data and channel wave seismic exploration data to improve the model accuracy, so that the model accuracy of the second-level transparent geological model is 150 mm. within.
- the borehole measurement data is included in the position data of the roof and floor of the borehole passing through the coal seam obtained through downhole drilling.
- Statistical collation of drill hole penetration points provides constraints for analyzing the spatial distribution of coal seams and thickness distribution of coal seams and constructing 3D geological models.
- Step S131 based on the secondary transparent geological model, according to the data of the air inlet and return airway, ground drilling data, realistic data of incision, drilling measurement data, updated realistic data, and channel wave seismic exploration data, construct three coal mining working faces.
- a high-level transparent geological model in which the updated realistic data is the realistic data of the coal seam exposed by the incision during the mining process and the newly generated geological data during the production process.
- the secondary transparent geological model is constructed and dynamically updated to improve the accuracy of the model.
- the updated realistic data specifically includes the cut-out realistic data as well as the newly generated borehole measurement data, Caobo seismic exploration data and other geological data in the production process.
- the planning cutting template is generated. That is, according to the cutting plan, the coal seam digital model (transparent geological model) of the working face to be mined is cut, and the cutting path of the shearer is obtained according to the cutting plane of the coal seam digital model. Specifically, based on the "CT" slicing technology, the transparent geological model is gridded, and the coal seam floor at the stop point of the air inlet road is selected as the reference zero point, and the relative coordinates are transferred. Angle, mining height, mining inclination, mining speed, mining direction to establish the planning cutting template of coal mining face.
- the planning and cutting template includes at least: the planning and cutting model of the shearer, the planning and control model of the hydraulic support and the planning model of the scraper conveyor;
- the planning and cutting model of the shearer includes: the basic state information of the shearer and the The related equipment relationship of the shearer; among them, the basic status information of the shearer includes: the shearer running state, the shearer attitude sensor, the actual displacement of the shearer encoder, the accuracy of the mining height and undercover value, and the video information of the shearer;
- the related equipment relationship of the shearer includes: the relationship between the shearer and the transparent geological model "CT" slice, hydraulic support, and scraper conveyor.
- the hydraulic support planning control model includes: support information and the related equipment relationship of the support; wherein, the support information includes: support state of the support, support attitude sensor, support stroke sensor and support video information;
- the associated equipment relationship of the support includes: hydraulic support and scraper The relationship between plate conveyor and shearer.
- the scraper conveyor planning model includes: the basic state information of the conveyor and the related equipment relationship of the conveyor; wherein, the basic state information of the conveyor includes: straightness measurement data, the pitch angle of the conveyor, the load of the conveyor, the motor operation data of the conveyor and the video information of the conveyor;
- the related equipment relationship includes: the relationship between the conveyor and the hydraulic support, the relationship between the conveyor and the shearer; the relationship between the conveyor and the hydraulic support includes: the conveyor, the position of the hydraulic support, and the range of the conveyor relative to the support.
- Step S102 based on the "CT" slicing technology, the transparent geological model is sectioned to obtain the incision roof interface curve and the incision floor interface curve of the transparent geological model, and based on inertial navigation technology and radar positioning technology, according to the fully mechanized mining equipment.
- Working condition monitoring data real-time correction of cutting model
- the transparent geological model is sectioned to obtain the incision roof interface curve and the incision bottom interface curve of the transparent geological model, and combined with the mining process, the planning cutting template is carried out. Correction in real time.
- Figure 3 is a schematic flow chart of the roof/bottom interface curve of the coal mining face provided by the application; as shown in Figure 3, based on the "CT" slicing technology, the transparent geological model is sectioned to obtain the cut-hole roof of the transparent geological model Interface curves and undercut floor interface curves include:
- Step S112A gridding the geological model: based on the "CT” slicing technology, divide the transparent geological model into a two-dimensional plane grid;
- the grid step size in the direction of the coal mining face and the inclination direction is set, the coal seam digital model is gridded in the two directions, and the grids are divided into grids.
- the grid is projected onto a 2D horizontal plane.
- the grid step in the length and width directions of the working face is set, and the coal seam is divided into grids on a two-dimensional plane to obtain a two-dimensional plane grid, a roof grid, and a bottom grid.
- Step S122A discretizing the cutting path: project the planned cutting route on the grid plane, and discretize the projected curve into a finite number of line segments, determine the plane coordinates of the intersection of each line segment and the grid line, and obtain the planned cutting route in the second step.
- the planned cutting route of the shearer By projecting the planned cutting route of the shearer onto the grid plane projection map, and approximately dividing the planned cutting route into a finite number of straight line segments, the planned cutting route is projected onto the grid plane, and the projected curve is discretized into n line segments; for the i-th line segment, the coordinates of the two end points are (x i , y i ) and (x i+1 , y i+1 ) respectively, and the equation of the straight line between the two points is calculated as:
- Step S132A calculate the plane coordinates of each discrete point: search for the grid point closest to the two-dimensional plane distance of the projection point in the top grid and the bottom grid respectively, and take the top and bottom elevations of the point as the projection point.
- Step S142A roof/bottom interface curve: connect the obtained roof/bottom control points sequentially in the direction of the straight line segment to obtain the roof/bottom interface curve of the coal mining face.
- the transparent geological model is sectioned to obtain the incised roof interface curve and the incised floor interface curve of the transparent geological model.
- the transparent geological model is sectioned to obtain the incised roof interface curve and the incised floor interface curve of the transparent geological model.
- the transparent geological model is sectioned. According to the different data, the accuracy of the model will also be different. That is, different data are used to build models with different steps, and the data update of the model is cut during the mining process. The exposed coal seam is re-realistic and the model is updated based on the newly generated geological data in the production process. With the continuous increase of data, the accuracy of the model is also continuously improved.
- the planning and cutting template is corrected in real time.
- the execution result is obtained based on inertial navigation technology and radar positioning technology.
- the learning and correction accuracy of the intervention is used for deviation analysis, and according to the deviation analysis results, the planning cutting template is revised in real time.
- FIG. 4 is a schematic flow chart of the correction of the planning cutting template provided by the application; as shown in FIG. 4 , based on inertial navigation technology, radar positioning technology and big data analysis and decision-making technology, combined with the mining process, the real-time correction of the planning cutting template includes: :
- Step S112B collecting the three-dimensional attitude data of the shearer in real time based on the inertial navigation technology
- an inertial navigation system is installed in the shearer, and the attitude information (pitch angle, roll angle, heading angle) of the shearer is collected in real time, and combined with the odometer data, the fully mechanized mining equipment can be used in a transparent geological model.
- the precise positioning in the working surface provides technical support for the automatic alignment control of the working face by recording the inertial navigation trajectory.
- the displacement changes in the three directions of inertial navigation X, Y, and Z will reflect the current three-dimensional position and attitude of the shearer in real time.
- the mining height and slope in the planned cutting model can be further corrected and updated. and other data to provide the basis for precise control.
- Step S122B based on the radar positioning technology, measure the distance between the nose and the tail of the scraper conveyor in real time, and the distance between the entry and return air lanes, and obtain the up and down sliding amount of the scraper conveyor in the coal mining face;
- the distance between the nose and tail of the conveyor from the inlet and return air lanes can be monitored in real time, so as to obtain the upward and downward sliding of the scraper conveyor on the working face, which is for precise control.
- laser reflectors are installed at equal distances in the inlet and return air lanes to monitor the advancing distance of the working face in real time, so as to achieve precise positioning in the transparent geological model and lay the foundation for the precise control of the next coal.
- Step S132B based on the big data analysis technology, according to the roof/bottom interface curve of the coal mining face, the upward and downward slippage of the scraper conveyor of the coal mining face, and the three-dimensional attitude data of the shearer, the cutting model is corrected in real time .
- the shearer cutting curve and hydraulic support are automatically adjusted. Correct and update key data such as the pulling frame, the pushing and sliding stroke of the scraper conveyor, and the control parameters of the fully mechanized mining equipment (cutting trajectory, cutting drum height adjustment, cutting drum undercover, bracket moving, pulling frame advancing, etc.) To achieve the purpose of precise control and continuous push of fully mechanized mining equipment in the dynamic production process.
- the position of the shearer on the working face can be accurately positioned, and the attitude information of the shearer in the working process can be detected; Carry out accurate mining height monitoring, so that the mining height error during mining is less than 10mm; using big data analysis and decision-making technology, the shearer is remotely controlled through the precise control center and the ground big data analysis and decision-making platform, and parameterized programming can be realized.
- the big data precision control center instructs to modify the shearer’s planned cutting path, adjust the speed according to the speed requirements of the big data precision control platform, and adjust the cutting height according to the big data precision control platform’s cutting height requirements.
- the correction of the cutting curve of the shearer is specifically: correcting the cutting height, slope, advancing direction, cutting eye direction, and undercover in the planning cutting template.
- the revised planning cutting template is sent to the fully mechanized mining machine at the coal mining face through the industrial Ethernet, so that the fully mechanized mining machine can cut it according to the revised plan.
- the cutting template runs, and the cutting height of the drum is adjusted adaptively. That is to use a transparent geological model to pre-build a refined digital elevation model of the roof and floor, use the real-time data perception system of the shearer to monitor the position and attitude of the shearer, calculate the current cutting boundary point of the drum, and stack it with the digital elevation model of the roof and floor. Set up analysis to determine the drum height adjustment value.
- the cutting curve obtained by planning combined with the coal mining process of the shearer, pre-set the mining of different process sections.
- the running speed of the coal machine and the position of the turning point, and the advance deceleration mechanism is set through the program to control the shearer to decelerate and reverse at the turning position. Due to human interference or other factors, the shearer exits the planned cutting mode. After entering the planned cutting mode again, the shearer program automatically adjusts the speed to the set speed of the process section through speed comparison, so as to realize the planned cutting of the shearer. Automatic adjustment of speed.
- the big data decision-making analysis is carried out, and the planning cutting curve is formed, and the planning cutting curve is formed.
- the cutting curve is sent to the shearer control system, and the shearer control system automatically cuts according to the planned cutting curve.
- the precision control center sends the planned cutting curve to the shearer. Then, after the planned cutting curve is issued, the quadrant setting needs to be performed. After the quadrant setting is completed, it will enter the planned cutting mode, and the shearer will run in the planned direction.
- big data machine learning is used to correct the planning cutting template in real time.
- data aggregation is used to correct the planning cutting template in real time.
- interpolation is used to correct the planning cutting template in real time.
- unbounded flow algorithms are used to correct the planning cutting template in real time.
- a mining efficiency and safety index system is established. According to the evaluation results of the mining efficiency and safety index system, the parameter combination of the planning cutting process is trained, and the planning cutting model is revised.
- the correction and update of the data are realized by using mathematical algorithms (data aggregation, interpolation, compensation, and unbounded flow algorithm).
- mathematical algorithms data aggregation, interpolation, compensation, and unbounded flow algorithm.
- Y 1 ⁇ x 1 ,y 1 ,z 1 ,h 1 ,h 2 ⁇
- x 1 is the advancing direction
- y 1 is the incision direction
- z 1 is the mining height direction
- h 1 is the mining height
- h 2 is the undercover.
- the planning data are:
- Y 2 ⁇ x 2 ,y 2 ,z 2 ,h 3 ,h 4 ⁇
- x 2 is the advancing direction
- y 2 is the incision direction
- z 2 is the mining height direction
- h 3 is the mining height
- h 4 is the undercover.
- the expected high value is:
- b 1 is the data loss compensation value
- b 2 is the data loss compensation value
- the planning cutting template is evaluated, and the model evaluation strategy includes training set and test set, loss function and empirical risk; training error and test error.
- the loss function is used to measure the error size of the model prediction, and the model F(h) is selected as the decision function.
- a is the adjustment multiple of the empirical parameter
- b is the compensation value
- F(h) is the predicted result
- Y is the real result
- the deviation between F(h) and Y is measured by a loss function L(Y, F(h));
- geological data is collected and analyzed, a transparent geological model with multiple steps of transparent working face is established, and a big data analysis and decision-making system for intelligent mining of transparent working face is constructed.
- the overall design framework using the unification and correlation of various communication protocol data of different equipment in the coal mining face, based on the mining process, fully mechanized mining automation control technology, inertial navigation technology and radar ranging technology, the coal seam exposed by the incision during the mining process As well as the newly generated geological data in the production process, the transparent geological model is continuously revised and updated, and the precise control and decision-making information of the fully mechanized mining equipment is obtained.
- the big data is used to correct the planning and cutting model in real time, and the intelligent and accurate coal mining face is realized. mining.
- Fig. 5 is the structural representation of the transparent working face intelligent mining big data analysis decision-making system provided by the application; as shown in Fig. 5, the transparent working face intelligent mining big data analysis decision-making system includes:
- the model building unit 501 is configured to build a transparent geological model of the coal mining face and a planning cutting template; the model building unit 501 includes: a geological model building subunit and a planning cutting template building subunit, wherein the geological model building subunit, It is configured to construct a cascade model of the coal mining face based on the geological data obtained from the fine measurement of the roadway, channel wave seismic exploration and downhole drilling, based on the implicit iterative interpolation algorithm, and obtain a transparent geological model with multiple steps of the coal mining face.
- the geological data at least include: geological structure data, coal thickness floor data, coal seam undulation state data, coal seam hidden structure data, coal thickness distribution data, and drilling hole penetration coal seam roof and floor position data; planning and cutting template construction sub-unit, configuration Based on the "CT" slicing technology, according to the transparent geological model, the planning cutting template is generated;
- the model correction unit 502 is configured to cut the transparent geological model based on the "CT" slicing technology to obtain the incision roof interface curve and the incision bottom interface curve of the transparent geological model, and based on inertial navigation technology and radar positioning technology, according to The working condition monitoring data of the fully mechanized mining equipment is used to correct the cutting model in real time; wherein, the model correction unit 502 includes: a first correction subunit, a second correction subunit and a third correction subunit; the first correction subunit, configured In order to cut the transparent geological model based on the "CT" slicing technology, obtain the interface curve of the incision roof and the interface curve of the incision floor of the transparent geological model, and combine the mining process to correct the control parameters of the planned cutting template in real time; The second correction sub-unit is configured to perform real-time correction on the planned cutting template based on inertial navigation technology, radar positioning technology and big data analysis and decision-making technology, combined with the mining process; the third correction sub-unit is configured according to the working conditions
- the model issuing unit 503 is configured to issue the revised planning cutting template to the fully mechanized mining machine, so that the fully mechanized mining machine can automatically cut the coal working face in real time according to the revised planning cutting template.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Mining & Mineral Resources (AREA)
- Geometry (AREA)
- Computer Graphics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Remote Sensing (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Geology (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Architecture (AREA)
- Geophysics And Detection Of Objects (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
一种矿山智能化无人开采大数据分析决策方法和系统。通过开采过程中切眼揭露的煤层以及生产过程中新产生的地质数据不断的对透明地质模型进行修正更新，得到综采设备的精准控制决策信息，利用大数据对规划截割模型进行实时修正，实现了采煤工作面的智能精准开采。
Description
本申请涉及智能采矿技术领域，特别涉及一种矿山智能化无人开采大数据分析决策方法和系统。
能源是人类社会存在法阵的基石，是经济发展和文明进步的基本条件。煤炭是我国主体能源和重要工业原料，是我国经济健康发展的重要支撑；在我国一次能源资源中，煤炭占90％。我国“贫油、富煤、少气”资源禀赋特点，决定了煤炭在我国能源结构中占主体地位。
2020年02月，国家八部委联合印发《关于加快煤矿智能化发展的指导意见》，意见要求到2021年基本实现综采工作面少人或无人操作。因此，对煤矿井下综采工作面动态复杂环境下及煤层变化不规律等条件下的智能精准开采已经成为亟需解决的问题。
发明内容
本申请的目的在于提供一种矿山智能化无人开采大数据分析决策方法和系统，具体是矿山透明工作面的智能无人化开采，以解决或缓解上述现有技术中存在的问题。
为了实现上述目的，本申请提供如下技术方案：
本申请提供了一种透明工作面智能开采大数据分析决策方法，包括：步骤S101、构建采煤工作面的透明地质模型和规划截割模板；步骤S102、基于“CT”切片技术，对透明地质模型进行剖切，得到透明地质模型的切眼顶板界面曲线和切眼底板界面曲线，并基于惯性导航技术、雷达定位技术，根据综采设备的工况监测数据，对截割模型进行实时修正；步骤S103、综采机械根据修正后的规划截割模板，对采煤工作面进行实时自动截割。
本申请提供了一种透明工作面智能开采大数据分析决策系统包括：
模型构建单元，配置为构建采煤工作面的透明地质模型和规划截割模板；模型构建单元包括：地质模型构建子单元和规划截割模板构建子单元，模型 修正单元包括：第一修正子单元，第二修正子单元和第三修正子单元。
本申请通过巷道精细测量、钻孔探测、槽波地震勘探等技术，对地质数据进行收集和分析，建立了透明工作面具有多个梯级的透明地质模型，构建了透明工作面智能开采大数据分析决策的总体设计架构；利用采煤工作面不同设备的多种通信协议数据的统一、关联，基于开采工艺，综采自动化控制技术、惯性导航技术和雷达测距技术，通过开采过程中切眼揭露的煤层以及生产过程中新产生的地质数据不断的对透明地质模型进行修正更新，得到综采设备的精准控制决策信息，利用大数据对规划截割模型进行实时修正，实现了采煤工作面的智能精准开采。
图1透明工作面智能开采大数据分析决策方法的流程示意图；
图2构建采煤工作面的透明地质模型的流程示意图；
图3采煤工作面的顶板/底板界面曲线的流程示意图；
图4规划截割模板修正的流程示意图；
图5透明工作面智能开采大数据分析决策系统的结构示意图。
首先，需要说明的是，“CT”切片技术就是根据截割计划将待开采工作面的煤层数字化模型进行剖切，然后根据煤层数字化模型的剖切面及智能化开采要求优化采煤机截割路径及参数，控制采煤机按照规划截割路径开采。
图1为本申请提供的智能开采大数据分析决策方法的流程示意图；如图1所示，该透明工作面智能开采大数据分析决策方法包括：
步骤S101、构建采煤工作面的透明地质模型和规划截割模型；
根据巷道精细测量、槽波地震勘探和井下钻探得到的地质数据，基于隐式迭代插值算法，对采煤工作面进行梯级模型构建，得到采煤工作面的具有多个梯级的透明地质模型；其中，地质数据至少包括：地质构造数据、煤厚底板数据、煤层起伏状态数据、煤层隐伏构造数据、煤厚分布数据、钻孔穿煤层顶底板位置数据。其中，通过巷道精细测量能够得到地质构造数据、煤厚底板数据、煤层起伏状态数据；通过槽波地震勘探能够得到煤层隐伏构造数据；通过井下钻探能够得到煤厚分布数据、钻孔穿煤层顶底板位置数据。 此外，基于隐式迭代插值算法，能够使构建的透明地质模型更加光滑，与底层的实际情况更加相符，模型精度更高。
在对透明地质模型进行构建时，需要对地质条件进行分析，包括煤层起伏形态、断层发育情况、陷落柱存在情况、冲刷带展布、煤层分叉等多种煤层构造信息。其中，煤层起伏形态的分析，主要通过绘制顶底板等高线图、煤厚等值线图，一方面，通过可能多的地质资料(巷道精细测量、三维地震勘探)对顶底板等高线进行约束；另一方面，通过类比盘区顶底板等高线，增加顶底板约束信息，基本确定煤层的起伏形态。断层发育情况，通过槽波地震勘探、坑透等物探手段，并结合煤层顶底板等高线进行判断。通过观测巷道两侧、切眼断层证据和瓦斯抽采钻孔窥视等手段对断层进行再次确认。最后结合区域构造地质条件(构造应力展布情况、古环境、盘区内已揭露断层)，进行断层。陷落柱存在情况，通过三维地震勘探、槽波地震勘探、坑透等物探方法，探测工作面内可能存在的陷落柱，并以钻孔窥视、补打钻孔、岩性分析等手段，进行确认。冲刷带展布，首先需要确定冲刷带的性质(同生等)，冲刷带的形状通常为透镜体形或葫芦串形，根据冲刷带的形态进行趋势面分析，预测冲刷带的范围。结合岩性(含泥量)等信息判断冲刷带的两翼。煤层分叉，根据写实情况，对煤层分叉进行定义，判断煤层分叉的性质。
图2为本申请提供的构建采煤工作面的透明地质模型的流程示意图；如图2所示，步骤S101中，构建采煤工作面的透明地质模型包括：
步骤S111、根据进回风巷的数据、地面钻孔数据、切眼写实数据，构建采煤工作面的一级透明地质模型；
进回风巷的数据、切眼写实数据包含于通过巷道精细测量得到的煤层起伏状态数据和煤厚分布数据中；地面钻孔数据包含于通过井下钻探得到的钻孔穿煤层顶底板位置数据中，主要是指工作面在采煤之前实施的大量的钻孔工程，用于瓦斯抽放、构造探测和探放水等。
步骤S121、基于一级透明地质模型，根据进回风巷的数据、地面钻孔数据、切眼写实数据、钻孔测量数据、槽波地震勘探数据，构建采煤工作面的二级透明地质模型；其中，钻孔测量数据至少包括：煤厚分布数据、钻孔穿煤层顶底板位置数据；槽波地震勘探数据至少包括：煤层隐伏构造数据；
在构建的一级透明地质模型的基础上，通过钻孔观测量数据、槽波地震 勘探数据对一级透明地质模型进行动态更新，提高模型精度，使得二级透明地质模型的模型精度在150毫米以内。
钻孔测量数据包含于通过井下钻探得到的钻孔穿煤层顶底板位置数据中，主要是指采用探测仪器设备进行钻孔轨迹、不同岩性的地层标记，得到钻孔的岩性分析柱状图、对钻孔穿层点进行统计整理，为分析煤层空间展布形态及煤层厚度分布、构建三维地质模型提供约束条件。
步骤S131、基于二级透明地质模型，根据进回风巷的数据、地面钻孔数据、切眼写实数据、钻孔测量数据、更新写实数据、槽波地震勘探数据，构建采煤工作面的三级透明地质模型，其中，更新写实数据为开采过程中切眼揭露的煤层再次写实的数据以及生产过程中新产生的地质数据。
通过更新写实数据对二级透明地质模型进行梯级构建和动态更新，提高模型精度，随着更新写实数据的不断增加，透明地质模型的精度也不断提高。其中，更新写实数据具体包括切眼写实数据以及生产过程中新产生的钻孔测量数据、曹波地震勘探数据等地质数据。
基于“CT”切片技术，根据透明地质模型，生成规划截割模板。即根据截割计划将待开采工作面的煤层数字化模型(透明地质模型)进行剖切，根据煤层数字化模型的剖切面得到采煤机的截割路径。具体的，基于“CT”切片技术，对透明地质模型网格化，选择进风巷停采点处煤层底板作为基准零点，进行相对坐标传递，在相对坐标系中依据煤层底板、推进度、俯仰角、采高、开采倾角、开采速度、开采方向建立采煤工作面的规划截割模板。
其中，规划截割模板至少包括：采煤机的规划截割模型、液压支架规划控制模型和刮板输送机规划模型；采煤机的规划截割模型包括：采煤机基本状态信息和采煤机的关联设备关系；其中，采煤机基本状态信息包括：采煤机运行状态、采煤机姿态传感器、采煤机编码器实际位移、采高及卧底值精准度、采煤机视频信息；采煤机的关联设备关系包括：采煤机和透明地质模型“CT”切片、液压支架、刮板输送机的关联关系。
液压支架规划控制模型包括：支架信息和支架的关联设备关系；其中，支架信息包括：支架支护状态、支架姿态传感器、支架行程传感器和支架视频信息；支架的关联设备关系包括：液压支架和刮板输送机、采煤机的关联关系。
刮板输送机规划模型包括：运输机基本状态信息和运输机的关联设备关系；其中，运输机基本状态信息包括：平直度测量数据、运输机俯仰角度、运输机负载、运输机电机运行数据和运输机视频信息；运输机的关联设备关系包括：运输机和液压支架的关联关系、运输机和采煤机的关联关系；运输机和液压支架的关联关系包括：运输机、液压支架推移位置和运输机相对支架上窜下滑幅度。
步骤S102、基于“CT”切片技术，对透明地质模型进行剖切，得到透明地质模型的切眼顶板界面曲线和切眼底板界面曲线，并基于惯性导航技术、雷达定位技术，根据综采设备的工况监测数据，对截割模型进行实时修正；
在一些可选实施例中，基于“CT”切片技术，对透明地质模型进行剖切，得到透明地质模型的切眼顶板界面曲线和切眼底板界面曲线，结合开采工艺，对规划截割模板进行实时修正。
图3为本申请提供的采煤工作面的顶板/底板界面曲线的流程示意图；如图3所示，基于“CT”切片技术，对透明地质模型进行剖切，得到透明地质模型的切眼顶板界面曲线和切眼底板界面曲线包括：
步骤S112A、地质模型网格化：基于“CT”切片技术，对透明地质模型进行二维平面网格划分；
在本申请实施例中，在地质模型网格化过程中，设定采煤工作面走向和倾向方向上的网格步长，在两个方向上对煤层数字化模型进行网格划分，并将网格投影到二维水平面。具体的，设定工作面长度和宽度方向的网格步长，在二维平面上对煤层进行网格划分，得到二维平面网格、顶板网格、底板网格。
步骤S122A、离散化截割路径：将计划截割路线投影到网格平面上，并将投影曲线离散成有限个线段，确定各线段与网格线交点的平面坐标，得到计划截割路线在二维平面上的投影点序列；
通过将采煤机计划截割路线投影到网格平面投影图中，并将计划截割路线近似划分为有限个直线段，即将计划截割路线投影到网格平面上，并将投影曲线离散成n条线段；对于第i条线段，两端点坐标分别为(x
i，y
i)和(x
i+1，y
i+1)，计算两点之间的直线方程为：
y＝k
ix+b
i
其中，x∈[min(x
i，x
i+1)，max(x
i，x
i+1)]，
i＝1，2，3，…n，n为正整数。
计算直线方程y＝k
ix+b
i在区间x∈[min(x
i，x
i+1)，max(x
i，x
i+1)]与网格线之间的交点。对所有线段执行上述步骤，即可得到计划截割路线在二维平面上的近似投影点序列。
步骤S132A、计算各离散点的平面坐标：分别在顶板网格和底板网格中搜索到该投影点二维平面距离最近的网格点，并取该点的顶、底板标高作为投影点处的煤层顶点序列和底板点序列；
将煤层顶板/底板曲面分别投影至二维水平面，对每一直线段，根据计算截割序列起始点和终点两点间直线方程y＝k
ix+b
i，并计算步骤S122A中的直线段与网格线的交点平面坐标及该点对应的顶板/底板标高。即对对每一个投影点，分别在顶板网格和底板网格中搜索到该投影点二维平面距离最近的网格点，并取该点的顶底板标高作为投影点处的煤层顶底板标高值，得到顶板点和底板点。
对于第j个投影点(x
j，y
j)设定邻域参数r，分别搜索顶板网格和地板网格点平面坐标落在邻域区域{x
j+r<x<x
j+1+r,y
j+r<y<y
j+1+r}内的所有点；第j个投影点(x
j，y
j)对应的顶底板标高z
1i和z
2i，可以按照最近距离法和距离加权法两种方法确定。
步骤S142A、顶板/底板界面曲线：将得到的顶板/底板控制点按照直线段方向顺序连接，得到采煤工作面的顶板/底板界面曲线。
基于“CT”切片技术，对透明地质模型进行剖切，得到透明地质模型的切眼顶板界面曲线和切眼底板界面曲线——将煤层顶板/底板曲面分别投影至二维水平面，对每一直线段，根据计算截割序列起始点和终点两点间直线方程y＝k
ix+b
i，并计算直线段与网格线的交点平面坐标及该点对应的顶板/底板标高，将得到的顶板/底板控制点按照直线段方向顺序连接，得到顶板/底板界面曲线。
基于“CT”切片技术，对透明地质模型进行剖切，根据数据的不同，建立模型精度也会有一定的差别，即用不同的数据建立不同梯级的模型，模型的数据更新是开采过程中切眼揭露的煤层进行再次写实并结合生产过程中 新产生的地质数据更新模型，随着数据的不断增加，模型的精度也不断提高。
在一些可选实施例中，基于惯性导航技术、雷达定位技术和大数据分析决策技术，结合开采工艺，对规划截割模板进行实时修正，具体的，基于惯性导航技术、雷达定位技术获取执行结果，根据执行结果与截割模板的对比差值，基于大数据分析决策技术，对透明地质模型“CT”切片数据精度、角度转换修正精度、工况导航位置精度、机械特性定差准确度、人工干预的学习修正准确度进行偏差分析，并根据偏差分析结果，实时修正规划截割模板。
图4为本申请提供的规划截割模板修正的流程示意图；如图4所示，基于惯性导航技术、雷达定位技术和大数据分析决策技术，结合开采工艺，对规划截割模板进行实时修正包括：
步骤S112B、基于惯性导航技术，实时采集采煤机的三维姿态数据；
在本申请实施例中，在采煤机中安装惯性导航系统，实时采集采煤机的姿态信息(俯仰角、横滚角、航向角)，结合里程仪数据，实现综采设备在透明地质模型中的精准定位，通过记录惯性导航运行轨迹，为工作面自动找直控制提供技术支撑。同时惯性导航X、Y、Z三个方向的位移变化，将能实时反映当前采煤机的三维位姿状况，通过位姿的变化情况，来进一步修正更新规划截割模型中的采高、坡度等数据，为精准控制提供依据。
步骤S122B、基于雷达定位技术，实时测量刮板输送机机头和机尾距离进、回风巷巷帮的距离，得到采煤工作面刮板输送机的上窜下滑量；
通过在刮板输送机机头和机尾安装激光雷达，实时监测运输机机头和机尾距进、回风巷巷帮的距离，从而得出工作面刮板输送机上窜下滑量，为精准控制提供决策依据。同时在进、回风巷两巷帮等距离安装激光反射板，实时监测工作面向前推进距离，从而实现在透明地质模型中的精准定位，为下一刀煤的精准控制奠定了基础。
步骤S132B、基于大数据分析技术，根据采煤工作面的顶板/底板界面曲线、采煤工作面刮板输送机的上窜下滑量和采煤机的三维姿态数据，对截割模型进行实时修正。
在透明地质模型、工作面实时监测数据的基础上，结合雷达测距数据和惯性导航三维姿态监测数据，通过大数据分析后得出的决策数据，来对采煤机截割曲线和液压支架自动跟机拉架、刮板输送机的推溜行程以及综采设备 的控制参数(截割轨迹、截割滚筒调高、截割滚筒卧底、支架推移、拉架推进等)等关键数据进行修正更新，从而达到动态生产过程中对综采设备精准控制和连续推的目的。
籍此，通过惯性导航技术、雷达定位技术，利用传感器，精确定位采煤机在工作面的位置，并检测采煤机在工作过程中的姿态信息；利用倾角传感器和角度位移传感器冗余系统，进行精确采高监测，使开采时的采高误差小于10mm；利用大数据分析决策技术，通过精准控制中心和地面大数据分析决策平台对采煤机进行远程控制，并能够实现参数化编程，根据大数据精准控制中心指令修改采煤机规划截割路径，根据大数据精准控制平台速度要求进行调速，根据大数据精准控制平台采高要求进行采高调整。
其中，对采煤机的截割曲线进行修正具体为：对规划截割模板中的采高、坡度、推进方向、切眼方向、卧底进行修正。
在根据大数据精准控制平台采高要求进行采高调整时，通过工业以太网将修正后的规划截割模板发送至采煤工作面的综采机械，以由综采机械按照修正后的规划截割模板运行，并自适应调整滚筒截割高度。即利用透明地质模型预先构建精细化顶底板数字高程模型，利用采煤机实时数据感知系统，监测采煤机位置和姿态，计算出滚筒当前截割边界点，并与顶底板数字高程模型进行叠置分析，确定滚筒高度调整值。
在根据大数据精准控制平台速度要求进行调速时，根据透明地质模型融合大数据智能分析决策系统，规划得到的截割曲线，结合采煤机的采煤工艺，预先设定不同工艺段的采煤机运行速度及折返点位置，并通过程序设定提前减速机制，控制采煤机在折返位置减速换向。因人为干扰或其他因素导致采煤机退出规划截割模式，再次进入规划截割模式后，采煤机程序通过速度比较自动调速至该工艺段设定速度，从而实现采煤机规划截割速度的自动调整。
在根据大数据精准控制中心指令修改采煤机规划截割路径时，通过建立的采煤工作面地质数据模型，结合工作面多种传感器进行大数据决策分析，形成规划截割曲线，将规划截割曲线下发至采煤机控制系统，由采煤机控制系统根据规划截割曲线进行自动截割。
首先，采煤机在进行规划截割之前，首先需确认采煤机与精准控制中心是否通讯正常，以及采煤机与惯性导航系统是否通讯正常。其次，采煤机与 精准控制中心及采煤机与惯性导航系统通讯确认正常后，精准控制中心下发规划截割曲线至采煤机。然后，规划截割曲线下发完毕后，需要进行象限设定。象限设定结束后，即进入规划截割模式，采煤机按照规划方向运行。
在一些可选实施例中，根据综采设备的工况监测数据，利用大数据机器学习、数据聚合、插值、补偿、无界流算法对规划截割模板进行实时修正。
通过规划截割工艺，建立开采效率和安全指标体系，根据开采效率和安全指标体系评定结果，训练规划截割工艺的参数组合，修正规划截割模型。
通过传感器采集工作面数据，通过历史数据迭代训练，实时对传感器监测数据进行过滤、补偿、更新；通过对比规划截割模型与执行结果的差值，实时反馈到大数据智能分析决策中心，利用执行效果评价体系和数据挖掘技术，对透明地质模型“CT”切片数据精度、角度转换修正精度、工况导航位置精度、机械特性定差准确度、人工干预的学习修正准确度进行偏差原因分析，适时修正规划截割模型，修正后再次下发验证，直至偏差消失
通过对采煤机的工况监测数据和预期规划数据进行学习分析，利用数学算法(数据聚合、插值、补偿、无界流算法)实现数据的修正和更新。其中，工况监测数据集合为：
Y
1＝{x
1,y
1,z
1,h
1,h
2}
其中，x
1为推进方向，y
1为切眼方向，z
1为采高方向，h
1为采高，h
2为卧底。
规划数据为：
Y
2＝{x
2,y
2,z
2,h
3,h
4}
其中，x
2为推进方向，y
2为切眼方向，z
2为采高方向，h
3为采高，h
4为卧底。
预期采高值为：
h
5＝h
1-h
3+b
1
其中，b
1为数据损失补偿值；
预期卧底值为：
h
6＝h
4-h
2+b
2
其中，b
2为数据损失补偿值；
对规划截割模板进行评估，模型评估策略包括训练集和测试集、损失函 数和经验风险；训练误差和测试误差。
损失函数用来衡量模型预测的误差大小，选取模型F(h)为决策函数，
F(h)＝a×h+b
其中，a为经验参数调整倍数，b为补偿值；
对于给定的输入参数h,F(h)为预测结果，Y为真实结果；F(h)和Y之间的偏差用一个损失函数来度量预测偏差程度L(Y,F(h))；
L(Y,F(h))＝|Y-F(h)|
应用惯性导航技术，实时测量刮板输送机的直线度和采煤机在三轴(X、Y、Z)方向的位移变化，为工作面自动找直和精准定位提供技术依据；应用激光雷达测距技术，实时监测运输机机头和机尾距进、回风巷巷帮的距离，得出工作面刮板输送机上窜下滑量，为精准控制提供决策依据；在进、回风巷两巷帮等距离安装激光反射板，实时监测工作面向前推进距离，实现在透明地质模型中的精准定位。
通过巷道精细测量、钻孔探测、槽波地震勘探等技术，对地质数据进行收集和分析，建立了透明工作面具有多个梯级的透明地质模型，构建了透明工作面智能开采大数据分析决策的总体设计架构；利用采煤工作面不同设备的多种通信协议数据的统一、关联，基于开采工艺，综采自动化控制技术、惯性导航技术和雷达测距技术，通过开采过程中切眼揭露的煤层以及生产过程中新产生的地质数据不断的对透明地质模型进行修正更新，得到综采设备的精准控制决策信息，利用大数据对规划截割模型进行实时修正，实现了采煤工作面的智能精准开采。
图5为本申请提供的透明工作面智能开采大数据分析决策系统的结构示意图；如图5所示，该透明工作面智能开采大数据分析决策系统包括：
模型构建单元501，配置为构建采煤工作面的透明地质模型和规划截割模板；模型构建单元501包括：地质模型构建子单元和规划截割模板构建子单元，其中，地质模型构建子单元，配置为根据巷道精细测量、槽波地震勘探和井下钻探得到的地质数据，基于隐式迭代插值算法，对采煤工作面进行梯级模型构建，得到采煤工作面的具有多个梯级的透明地质模型；其中，地质数据至少包括：地质构造数据、煤厚底板数据、煤层起伏状态数据、煤层隐伏构造数据、煤厚分布数据、钻孔穿煤层顶底板位置数据；规划截割模板 构建子单元，配置为基于“CT”切片技术，根据透明地质模型，生成规划截割模板；
模型修正单元502，配置为基于“CT”切片技术，对透明地质模型进行剖切，得到透明地质模型的切眼顶板界面曲线和切眼底板界面曲线，并基于惯性导航技术、雷达定位技术，根据综采设备的工况监测数据，对截割模型进行实时修正；其中，模型修正单元502包括：第一修正子单元，第二修正子单元和第三修正子单元；第一修正子单元，配置为基于“CT”切片技术，对透明地质模型进行剖切，得到透明地质模型的切眼顶板界面曲线和切眼底板界面曲线，结合开采工艺，对规划截割模板的控制参数进行实时修正；第二修正子单元，配置为基于惯性导航技术、雷达定位技术和大数据分析决策技术，结合开采工艺，对规划截割模板进行实时修正；第三修正子单元，配置为根据综采设备的工况监测数据，利用大数据机器学习、数据聚合、插值、补偿、无界流算法对规划截割模板进行实时修正；
模型下发单元503，配置为向综采机械下发修正后的规划截割模板，以由综采机械根据修正后的规划截割模板，对采煤工作面进行实时自动截割。
Claims (5)
- 一种透明工作面智能开采大数据分析决策方法，其特征在于，包括：步骤S101、构建采煤工作面的透明地质模型和规划截割模板，包括：构建透明地质模型：根据巷道精细测量、槽波地震勘探和井下钻探得到的地质数据，基于隐式迭代插值算法，对采煤工作面进行梯级模型构建，得到采煤工作面的具有多个梯级的透明地质模型；其中，地质数据至少包括：地质构造数据、煤厚底板数据、煤层起伏状态数据、煤层隐伏构造数据、煤厚分布数据、钻孔穿煤层顶底板位置数据；构建规划截割模板：基于“CT”切片技术，根据透明地质模型，生成规划截割模板；步骤S102、基于“CT”切片技术，对透明地质模型进行剖切，得到透明地质模型的切眼顶板界面曲线和切眼底板界面曲线，并基于惯性导航技术、雷达定位技术，根据综采设备的工况监测数据，对截割模型进行实时修正，包括：基于“CT”切片技术，对透明地质模型进行剖切，得到透明地质模型的切眼顶板界面曲线和切眼底板界面曲线，结合开采工艺，对规划截割模板进行实时修正；基于惯性导航技术、雷达定位技术和大数据分析决策技术，结合开采工艺，对规划截割模板进行实时修正；根据综采设备的工况监测数据，利用大数据机器学习、数据聚合、插值、补偿、无界流算法对规划截割模板进行实时修正；步骤S103、综采机械根据修正后的规划截割模板，对采煤工作面进行实时自动截割。
- 根据权利要求1所述的透明工作面智能开采大数据分析决策方法，其特征在于，步骤S101中，构建采煤工作面的透明地质模型包括：根据进回风巷的数据、地面钻孔数据、切眼写实数据，构建采煤工作面的一级透明地质模型；基于一级透明地质模型，根据进回风巷的数据、地面钻孔数据、切眼写实数据、钻孔测量数据、槽波地震勘探数据，构建采煤工作面的二级透明地 质模型；其中，钻孔测量数据至少包括：煤厚分布数据、钻孔穿煤层顶底板位置数据；槽波地震勘探数据至少包括：煤层隐伏构造数据；基于二级透明地质模型，根据进回风巷的数据、地面钻孔数据、切眼写实数据、钻孔测量数据、更新写实数据、槽波地震勘探数据，构建采煤工作面的三级透明地质模型，其中，更新写实数据为开采过程中切眼揭露的煤层再次写实的数据以及生产过程中新产生的地质数据。
- 根据权利要求1所述的透明工作面智能开采大数据分析决策方法，其特征在于，在步骤S101中，基于“CT”切片技术，对透明地质模型网格化，选择进风巷停采点处煤层底板作为基准零点，进行相对坐标传递，在相对坐标系中依据煤层底板、推进度、俯仰角、采高、开采倾角、开采速度、开采方向建立采煤工作面的规划截割模板。
- 根据权利要求3所述的透明工作面智能开采大数据分析决策方法，其特征在于，在步骤S101中，规划截割模板至少包括：采煤机的规划截割模型、液压支架规划控制模型和刮板输送机规划模型；采煤机的规划截割模型包括：采煤机基本状态信息和采煤机的关联设备关系；其中，采煤机基本状态信息包括：采煤机运行状态、采煤机姿态传感器、采煤机编码器实际位移、采高及卧底值精准度、采煤机视频信息；采煤机的关联设备关系包括：采煤机和透明地质模型“CT”切片、液压支架、刮板输送机的关联关系；液压支架规划控制模型包括：支架信息和支架的关联设备关系；其中，支架信息包括：支架支护状态、支架姿态传感器、支架行程传感器和支架视频信息；支架的关联设备关系包括：液压支架和刮板输送机、采煤机的关联关系；刮板输送机规划模型包括：运输机基本状态信息和运输机的关联设备关系；其中，运输机基本状态信息包括：平直度测量数据、运输机俯仰角度、运输机负载、运输机电机运行数据和运输机视频信息；运输机的关联设备关系包括：运输机和液压支架的关联关系、运输机和采煤机的关联关系；运输机和液压支架的关联关系包括：运输机、液压支架推移位置和运输机相对支 架上窜下滑幅度。
- 一种透明工作面智能开采大数据分析决策系统，其特征在于，包括：模型构建单元，配置为构建采煤工作面的透明地质模型和规划截割模板；模型构建单元包括：地质模型构建子单元和规划截割模板构建子单元，其中，地质模型构建子单元，配置为根据巷道精细测量、槽波地震勘探和井下钻探得到的地质数据，基于隐式迭代插值算法，对采煤工作面进行梯级模型构建，得到采煤工作面的具有多个梯级的透明地质模型；其中，地质数据至少包括：地质构造数据、煤厚底板数据、煤层起伏状态数据、煤层隐伏构造数据、煤厚分布数据、钻孔穿煤层顶底板位置数据；规划截割模板构建子单元，配置为基于“CT”切片技术，根据透明地质模型，生成规划截割模板；模型修正单元，配置为基于“CT”切片技术，对透明地质模型进行剖切，得到透明地质模型的切眼顶板界面曲线和切眼底板界面曲线，并基于惯性导航技术、雷达定位技术，根据综采设备的工况监测数据，对截割模型进行实时修正；其中，模型修正单元包括：第一修正子单元，第二修正子单元和第三修正子单元；第一修正子单元，配置为基于“CT”切片技术，对透明地质模型进行剖切，得到透明地质模型的切眼顶板界面曲线和切眼底板界面曲线，结合开采工艺，对规划截割模板的控制参数进行实时修正；第二修正子单元，配置为基于惯性导航技术、雷达定位技术和大数据分析决策技术，结合开采工艺，对规划截割模板进行实时修正；第三修正子单元，配置为根据综采设备的工况监测数据，利用大数据机器学习、数据聚合、插值、补偿、无界流算法对规划截割模板进行实时修正；模型下发单元，配置为向综采机械下发修正后的规划截割模板，以由综采机械根据修正后的规划截割模板，对采煤工作面进行实时自动截割。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110501326.2 | 2021-05-08 | ||
| CN202110501326.2A CN113379909B (zh) | 2021-05-08 | 2021-05-08 | 一种透明工作面智能开采大数据分析决策方法和系统 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2022057397A1 true WO2022057397A1 (zh) | 2022-03-24 |
Family
ID=77570773
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2021/104829 WO2022057397A1 (zh) | 2021-05-08 | 2021-07-06 | 一种矿山智能化无人开采大数据分析决策方法和系统 |
Country Status (3)
| Country | Link |
|---|---|
| CN (1) | CN113379909B (zh) |
| LU (1) | LU501938B1 (zh) |
| WO (1) | WO2022057397A1 (zh) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112433245A (zh) * | 2020-11-04 | 2021-03-02 | 陕西彬长孟村矿业有限公司 | 一种煤矿断层构造预测预报方法 |
| CN114719904A (zh) * | 2022-04-01 | 2022-07-08 | 天地上海采掘装备科技有限公司 | 多类型传感器融合的采煤机采高检测方法 |
| CN114997482A (zh) * | 2022-05-24 | 2022-09-02 | 徐州大屯工程咨询有限公司 | 一种煤矿井下工作面数字化透明地质技术方法 |
| CN116291434A (zh) * | 2023-05-18 | 2023-06-23 | 煤炭科学研究总院有限公司 | 高精地质模型采煤截割导航方法和装置 |
| CN116739203A (zh) * | 2023-08-16 | 2023-09-12 | 华夏天信物联科技有限公司 | 一种煤矿开采的路径规划及设计方法 |
| WO2023185734A1 (zh) * | 2022-03-28 | 2023-10-05 | 中国矿业大学 | 一种基于三维点云数据库的矿山数字模型建立方法 |
| CN117408123A (zh) * | 2023-12-14 | 2024-01-16 | 晋能控股煤业集团同忻煤矿山西有限公司 | 一种采运装备时空推进健康状态评估系统及方法 |
| CN118114844A (zh) * | 2024-04-23 | 2024-05-31 | 西安华创马科智能控制系统有限公司 | 采煤机截割轨迹规划方法和装置 |
| CN118167404A (zh) * | 2024-05-16 | 2024-06-11 | 中北智造工程技术(山西)有限公司 | 一种瓦斯抽采钻孔的智能控制方法 |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114033365A (zh) * | 2021-09-29 | 2022-02-11 | 武汉长盛煤安科技有限公司 | 采煤机、采煤机预警方法及电子设备 |
| CN113962008A (zh) * | 2021-11-09 | 2022-01-21 | 华北科技学院(中国煤矿安全技术培训中心) | 一种矿山三维井巷模型生成及透明工作面构建方法 |
| CN114320291A (zh) * | 2022-01-05 | 2022-04-12 | 山东能源重装集团中矿采煤机制造有限公司 | 一种采煤机自动找平方法 |
| CN117348500B (zh) * | 2023-12-04 | 2024-02-02 | 济南华科电气设备有限公司 | 一种煤矿综采工作面自动化控制方法及系统 |
| CN117780346B (zh) * | 2024-02-23 | 2024-05-24 | 太原矿机物联科技有限公司 | 基于3d可视化模型的远程煤机控制方法 |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102279980A (zh) * | 2010-06-13 | 2011-12-14 | 中国地质科学院矿产资源研究所 | 地质勘探矿体三维建模方法及其装置 |
| CN103726844A (zh) * | 2013-11-01 | 2014-04-16 | 神华集团有限责任公司 | 基于采煤工作面的自动采煤方法 |
| CN109630110A (zh) * | 2019-01-18 | 2019-04-16 | 天地科技股份有限公司 | 一种综采工作面煤层厚度自适应截割控制方法及电子设备 |
| US20200355075A1 (en) * | 2019-05-10 | 2020-11-12 | JRL Coal, Inc. | High wall mining method |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107905786A (zh) * | 2017-10-24 | 2018-04-13 | 北京天地玛珂电液控制系统有限公司 | 一种基于透明工作面的采煤方法和系统 |
| AU2019100273A4 (en) * | 2019-03-15 | 2019-05-02 | Data One Technologies Pty Ltd | BinWin is a modern-day waste collection technology enabling councils and waste management authorities to manage waste effectively. The framework consists of IoT, AI, mobile & web applications integrated to monitor, track, and plan. The bins ensure eco-friendliness by keeping a constant check on fill levels enabling waste collection on a needs basis preventing over-flow, maintaining a hygienic environment using solar self-charging capability. BinWin promises to increase operational efficiencies in the waste collection chain, reducing cost and labour associated with rubbish collection & removal. |
| CN112001982B (zh) * | 2020-09-04 | 2024-03-19 | 陕西陕煤黄陵矿业有限公司 | 基于煤层数字化模型ct剖切的采煤机智能截割方法及系统 |
| CN112360558A (zh) * | 2020-10-14 | 2021-02-12 | 西安合智宇信息科技有限公司 | 综采工作面可视化控制系统和方法 |
| CN112392485B (zh) * | 2020-11-12 | 2021-08-17 | 临沂矿业集团菏泽煤电有限公司 | 煤矿综采工作面透明化数字孪生自适应开采系统和方法 |
| CN112762963A (zh) * | 2021-01-27 | 2021-05-07 | 西安重装智慧矿山工程技术有限公司 | 基于激光雷达的惯性导航标校方法及系统 |
-
2021
- 2021-05-08 CN CN202110501326.2A patent/CN113379909B/zh active Active
- 2021-07-06 WO PCT/CN2021/104829 patent/WO2022057397A1/zh active Application Filing
- 2021-07-06 LU LU501938A patent/LU501938B1/en active IP Right Grant
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102279980A (zh) * | 2010-06-13 | 2011-12-14 | 中国地质科学院矿产资源研究所 | 地质勘探矿体三维建模方法及其装置 |
| CN103726844A (zh) * | 2013-11-01 | 2014-04-16 | 神华集团有限责任公司 | 基于采煤工作面的自动采煤方法 |
| CN109630110A (zh) * | 2019-01-18 | 2019-04-16 | 天地科技股份有限公司 | 一种综采工作面煤层厚度自适应截割控制方法及电子设备 |
| US20200355075A1 (en) * | 2019-05-10 | 2020-11-12 | JRL Coal, Inc. | High wall mining method |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112433245B (zh) * | 2020-11-04 | 2024-03-22 | 陕西彬长孟村矿业有限公司 | 一种煤矿断层构造预测预报方法 |
| CN112433245A (zh) * | 2020-11-04 | 2021-03-02 | 陕西彬长孟村矿业有限公司 | 一种煤矿断层构造预测预报方法 |
| GB2623664A (en) * | 2022-03-28 | 2024-04-24 | Univ China Mining | Mine digital model construction method based on three-dimensional point cloud database |
| WO2023185734A1 (zh) * | 2022-03-28 | 2023-10-05 | 中国矿业大学 | 一种基于三维点云数据库的矿山数字模型建立方法 |
| CN114719904A (zh) * | 2022-04-01 | 2022-07-08 | 天地上海采掘装备科技有限公司 | 多类型传感器融合的采煤机采高检测方法 |
| CN114719904B (zh) * | 2022-04-01 | 2024-03-29 | 天地上海采掘装备科技有限公司 | 多类型传感器融合的采煤机采高检测方法 |
| CN114997482A (zh) * | 2022-05-24 | 2022-09-02 | 徐州大屯工程咨询有限公司 | 一种煤矿井下工作面数字化透明地质技术方法 |
| CN116291434A (zh) * | 2023-05-18 | 2023-06-23 | 煤炭科学研究总院有限公司 | 高精地质模型采煤截割导航方法和装置 |
| CN116291434B (zh) * | 2023-05-18 | 2023-08-18 | 煤炭科学研究总院有限公司 | 高精地质模型采煤截割导航方法和装置 |
| CN116739203B (zh) * | 2023-08-16 | 2023-11-03 | 华夏天信物联科技有限公司 | 一种煤矿开采的路径规划及设计方法 |
| CN116739203A (zh) * | 2023-08-16 | 2023-09-12 | 华夏天信物联科技有限公司 | 一种煤矿开采的路径规划及设计方法 |
| CN117408123A (zh) * | 2023-12-14 | 2024-01-16 | 晋能控股煤业集团同忻煤矿山西有限公司 | 一种采运装备时空推进健康状态评估系统及方法 |
| CN117408123B (zh) * | 2023-12-14 | 2024-03-15 | 晋能控股煤业集团同忻煤矿山西有限公司 | 一种采运装备时空推进健康状态评估系统及方法 |
| CN118114844A (zh) * | 2024-04-23 | 2024-05-31 | 西安华创马科智能控制系统有限公司 | 采煤机截割轨迹规划方法和装置 |
| CN118167404A (zh) * | 2024-05-16 | 2024-06-11 | 中北智造工程技术(山西)有限公司 | 一种瓦斯抽采钻孔的智能控制方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113379909B (zh) | 2023-10-27 |
| LU501938B1 (en) | 2022-11-08 |
| CN113379909A (zh) | 2021-09-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022057397A1 (zh) | 一种矿山智能化无人开采大数据分析决策方法和系统 | |
| CN112883559B (zh) | 基于大数据体系的规划截割方法和装置、存储介质及电子装置 | |
| CN106285476B (zh) | 一种水平钻井实时地震地质综合导向方法 | |
| CN106089201B (zh) | 一种用于无人化采煤工作面的截割路径规划方法 | |
| CN108763752B (zh) | 一种盾构隧道下穿水道确定施工掘进参数的方法 | |
| CN111485880B (zh) | 一种煤矿回采工作面智能开采预测截割线生成方法及装置 | |
| RU2012105576A (ru) | Способ получения призабойного пространства с применением систем автоматизации | |
| CN102900366A (zh) | 一种水平定向钻自由轨迹规划及纠偏方法 | |
| CN105184864A (zh) | 一种用于天然地基换填工程量计算的场地地层三维地质结构模型生成方法 | |
| CN114120785B (zh) | 一种煤矿掘进设备与地质模型、巷道设计模型的耦合系统 | |
| CN109469484A (zh) | 基于上位机规划的自动化采煤方法 | |
| CN110107295B (zh) | 一种基于工作面高精度导航模型的无人采煤路径规划方法 | |
| CN111445170A (zh) | 一种无人碾压机群自主作业系统及方法 | |
| CN110500081A (zh) | 一种基于深度学习的自动钻井方法 | |
| AU2021101934A4 (en) | Intelligent prediction of shield existing tunnels and multi objective optimization control method of construction parameters based on data drive | |
| CN111060022A (zh) | 一种盾构下穿结构物形变的激光自动化分析系统及方法 | |
| CN115908727A (zh) | 一种建立智能化露天矿设计施工一体化的方法 | |
| CN106256991A (zh) | 一种采煤机记忆截割与记忆定位联合学习方法 | |
| CN113236249A (zh) | 一种融合地质基线的自适应截割方法 | |
| CN114842159B (zh) | 一种沉积地层复杂构造三维地质模型拼接方法 | |
| Wu et al. | Double-face intelligent hole position planning method for precision blasting in roadways using a computer-controlled drill jumbo | |
| CN114091233B (zh) | 综采工作面采煤机自适应跟随煤层截割路径优化方法 | |
| CN115796019A (zh) | 一种基于数据驱动盾构施工参数多目标优化的方法 | |
| Dong et al. | A Virtual Planning Method for Spatial Pose and Performance Fusion Advancement of Mining and Transportation Equipment in Complex Geological Environment | |
| CN116291434B (zh) | 高精地质模型采煤截割导航方法和装置 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21868226 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 21868226 Country of ref document: EP Kind code of ref document: A1 |