Working face coal seam three-dimensional modeling method based on big data

Abstract

The invention discloses a working face coal seam three-dimensional modeling method based on big data, and belongs to the technical field of coal mine three-dimensional modeling. The invention aims to provide a working face coal seam three-dimensional modeling method based on big data, a working face coal seam three-dimensional model with higher accuracy is established, and the transparency degree of a coal face is improved. According to the technical scheme, the method comprises the following steps: S1, acquiring coal seam geological data of a working face coal seam; s2, processing the coal seam geological data, and calling three-dimensional modeling software to construct a working face coal seam three-dimensional model; s3, acquiring latest working face laser scanning data, top / bottom coal thickness data and coal cutter cutting track information, and fusing and comparing the data to acquire a correction value of the working face coal seam three-dimensional model; and S4, updating the working face coal seam three-dimensional model based on the correction value, returning to the step S3, and continuously updating the corrected working face coal seam three-dimensional model according to the latest data.

Description

Technical Field

[0001] The invention discloses a working face coal seam three-dimensional modeling method based on big data, belonging to the technical field of coal mine three-dimensional modeling. Background Art

[0002] As the first production site of coal, the coal mining face has the characteristics of small working space, many mechanical equipment, poor visual environment and high temperature, and is a frequent site of mine accidents. Coal mine roof accidents, water seepage accidents, coal spontaneous combustion accidents, gas explosion accidents, coal dust explosion accidents and occupational diseases all account for a considerable proportion in the coal mining face. Therefore, risk assessment research on coal mining faces has become an urgent problem to be solved in coal mine safety management.

[0003] Three-dimensional geological modeling is an extension of coal mine exploration work. Its purpose is to effectively realize the three-dimensional visualization and reconstruction of various irregular geological bodies. It can deeply analyze the spatial structure of geological bodies, extract ore control information, establish the distribution characteristics and distribution patterns of coal seams, and provide intuitive and accurate data support for further exploration, mining design, prediction and genetic research, and serve the later exploration and development work. At present, the construction method of three-dimensional geological model is to integrate the three-dimensional model of coal seams constructed by drilling, three-dimensional seismic, slot wave CT and three-dimensional scanning of tunnels on the basis of conventional geological exploration results, so as to comprehensively and uniformly recognize and reproduce the entire working face in a digital way, and finally realize the transparency of the working face. Compared with geological body modeling, there are relatively few three-dimensional modeling of coal seams specifically for working faces, and most of them use the method of three-dimensional modeling of geological bodies, which has the following problems:

[0004] (1) The simulation results of the currently constructed three-dimensional model of the coal seam working face have poor accuracy, and cannot directly construct a detailed three-dimensional complex model, and cannot achieve absolute transparency of the coal mining working face;

[0005] (2) In the process of three-dimensional modeling of the working face coal seam, the static modeling information is mainly used from the acquired working face coal seam data to construct a three-dimensional static model of the coal seam. There is a lack of sufficient attention to the information on the dynamic changes of the coal seam during the mining process, and the dynamic mining data that is of great significance to the local area is ignored. In addition, the constructed three-dimensional model of the coal seam is generally not dynamically updated. Summary of the invention

[0006] In view of the shortcomings of the prior art, the purpose of the present invention is to provide a three-dimensional modeling method of a working face coal seam based on big data, to correct the three-dimensional model of the working face coal seam constructed by static data through dynamic information, to establish a more accurate three-dimensional model of the working face coal seam, and to improve the transparency of the coal mining working face.

[0007] To achieve the above object, the present invention adopts the following technical solution, a three-dimensional modeling method of a working face coal seam based on big data, comprising the following steps:

[0008] S1. Obtain coal seam geological data of the coal seam at the working face, wherein the coal seam geological data includes coal seam distribution, coal seam thickness and geological structure data obtained through ground exploration drilling, underground drilling, tunnel sketch, cut-eye sketch and exploration line;

[0009] S2, processing the coal seam geological data, and calling 3D modeling software to construct a 3D model of the coal seam at the working face;

[0010] S3, obtaining the latest working face laser scanning data, top / bottom coal thickness data and coal mining machine cutting trajectory information, fusing and comparing the working face laser scanning data, the top / bottom coal thickness data and the coal mining machine cutting trajectory information, and obtaining a correction value of the working face coal seam three-dimensional model;

[0011] S4. Update the three-dimensional model of the coal seam at the working face based on the correction value, and return to step S3 to continue updating the corrected three-dimensional model of the coal seam at the working face according to the latest data.

[0012] Further, the processing of the coal seam geological data in S2 includes:

[0013] Based on the coal seam geological data, the coal seam at the working face is divided into several strata, and according to the stratum boundary control point information, the several strata are divided into coal mining layers and interlayers, and each stratum is grid-divided;

[0014] The Kriging spatial interpolation algorithm is used to interpolate and fit the elevation and coal quality indicators of the grid points of each stratum to obtain a regular grid model;

[0015] Based on the regular grid model, a three-dimensional model of the coal seam at the working face is constructed.

[0016] Furthermore, dividing the coal seam at the working face into several strata based on the coal seam geological data includes: analyzing the coal seam geological data, and dividing the coal seam at the working face into several strata based on lithology and vertical position.

[0017] Furthermore, the gridding of each stratum includes: respectively calculating the maximum and minimum values ​​of the horizontal coordinates of the sampling points at the starting depth and the ending depth of each stratum of the coal seam of the working face, and dividing the size of the grid units based on the maximum and the minimum values.

[0018] Furthermore, the method of using the Kriging spatial interpolation algorithm to perform interpolation fitting processing on the elevation and coal quality index of each stratum grid point is:

[0019]

[0020] Among them, Z * (u) is the estimated value of the interpolation point to be found, Z(u α ) is the αth sampling point u α The value at, n(u) is the number of sampling points, λ α (u) is the sampling point u α and the difference weight coefficient between the interpolation point u to be determined, and the sum of the difference weight coefficients is 1.

[0021] Furthermore, the means for obtaining the working face laser scanning data, top / bottom coal thickness data and coal mining machine cutting trajectory information in S3 are respectively:

[0022] Use laser scanners to obtain laser scanning data of the spatial contour of the working face before and during mining;

[0023] Inject seismic waves into the top / bottom coal seam, reflect the superimposed composite waves through the top and bottom plates of the coal seam, obtain reflection wave parameters, and obtain the top / bottom coal thickness data in the mining stage according to the reflection wave parameters, wherein the reflection wave parameters include offset distance, reflection time and reflection wave velocity;

[0024] Positioning the coal mining machine model in the three-dimensional model of the coal seam of the working face, and obtaining the cutting trajectory information of the coal mining machine by using an airborne inertial navigation system and a rocker arm inclination sensor;

[0025] After obtaining the cutting trajectory information of the coal mining machine, the top and bottom plate curves of the three-dimensional model of the working face coal seam are extracted according to the established three-dimensional model of the working face coal seam. The relative position relationship between the actual cutting path of the coal mining machine and the top and bottom plate curves of the three-dimensional model of the working face coal seam is accurately compared to obtain the error value of the coal mining machine cutting trajectory in the vertical direction of the top and bottom plates.

[0026] Further, obtaining the correction value of the three-dimensional model of the coal seam at the working face in S3 includes:

[0027] According to the top / bottom coal thickness data and the error value of the shearer cutting trajectory in the vertical direction of the top and bottom plates, a top / bottom coal thickness data surface model and a shearer cutting trajectory vertical error surface model are respectively constructed;

[0028] According to the coordinate conversion relationship between the laser scanning data of the working face and the three-dimensional model of the coal seam of the working face, the top / bottom coal thickness data surface model and the vertical error surface model of the shearer cutting trajectory are merged with the three-dimensional model of the coal seam of the working face;

[0029] The fused models are compared using a quadratic sequence programming method to calculate the deviation difference between the top / bottom coal thickness data surface model and the coal mining machine cutting trajectory vertical error surface model and the working face coal seam three-dimensional model to obtain the correction value.

[0030] Furthermore, the updating of the three-dimensional model of the coal seam at the working face based on the correction value in S4 includes: inserting the correction value into the three-dimensional model of the coal seam at the working face using an inverse distance weighted interpolation method.

[0031] Furthermore, the calculation process of the inverse distance weighted interpolation method includes:

[0032] (1) Determine known points and unknown points: First, we need to determine n known points (x i ,y i ,z i ) and the unknown point (x, y, z) in the three-dimensional model of the coal seam at the working face; the known point (x i ,y i ,z i ) refers to the points that have been measured or observed, and their attribute values ​​are known. Unknown points (x, y, z) refer to the points that need to be interpolated, and their attribute values ​​are unknown.

[0033] (2) Calculate the distance weight: Based on the positions of the known and unknown points, the distance between the known and unknown points can be calculated. Then, the weight is calculated based on the inverse of the distance. The closer the distance, the greater the weight, and the farther the distance, the smaller the weight. If the distance between the known and unknown points is zero, a division by zero error should be avoided by setting a very small value instead of zero distance, or setting the weight of the unknown point to infinity.

[0034] (3) Calculate interpolation results: Based on the attribute values ​​and distance weights of the known points, use the weighted average method to perform interpolation calculations;

[0035] The interpolation result can be calculated by the following formula:

[0036]

[0037] Among them, f i is the value of the known point, u is the weight index, n is the number of known points,

[0038] Represents the distance from an unknown point (x, y, z) to a known point (x i ,y i ,z i ) distance;

[0039] (4) Visualization and application: After the interpolation is completed, the results are visualized.

[0040] Compared with the prior art, the present invention has the following beneficial effects.

[0041] The coal seam geological data acquired in S2 of the present invention includes multiple data, and the multiple data are processed in combination with the regular grid method and the Kriging spatial interpolation algorithm, so that a more accurate three-dimensional model of the working face coal seam can be established; in addition, in the present invention, not only a variety of static data are collected, but S3 and S4 also obtain information on the dynamic changes of the coal seam during the mining process, and the three-dimensional model of the working face coal seam constructed by the static data is corrected through the dynamic information, which can further improve the accuracy of the three-dimensional model of the working face coal seam according to the changes of the working face coal seam, so that it can more accurately express the information of the actual working face, provide accurate working face coal seam data for the automation and intelligence of the comprehensive mining working face, and provide technical support for complex mining conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required to be used in the embodiments are briefly introduced below.

[0043] Figure 1 It is a flow chart of the present invention. DETAILED DESCRIPTION

[0044] The technical solution of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other implementation methods obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] The present invention provides the following embodiments.

[0046] The present invention provides a three-dimensional modeling method of a working face coal seam based on big data, comprising the following steps:

[0047] S1. Obtain coal seam geological data of the coal seam at the working face, wherein the coal seam geological data includes coal seam distribution, coal seam thickness and geological structure data obtained through ground exploration drilling, underground drilling, tunnel sketch, cut-eye sketch and exploration line;

[0048] S2, processing the coal seam geological data, and calling 3D modeling software to construct a 3D model of the coal seam at the working face, wherein the 3D modeling software may be 3Dmine 3D mining engineering software, etc.;

[0049] Specifically, the processing of the coal seam geological data in S2 includes:

[0050] The coal seam of the working face is divided into several strata based on the coal seam geological data, and the several strata are divided into coal mining layers and interlayered gangue layers according to the stratum boundary control point information, and each stratum is grid-divided; the elevation and coal quality indicators of the grid points of each stratum are interpolated and fitted using the Kriging spatial interpolation algorithm to obtain a regular grid model; based on the regular grid model, a three-dimensional model of the coal seam of the working face is constructed.

[0051] Dividing the coal seam at the working face into several strata based on the coal seam geological data comprises: analyzing the coal seam geological data, and dividing the coal seam at the working face into several strata based on lithology and vertical position.

[0052] Gridding each stratum includes: calculating the maximum and minimum values ​​of the horizontal coordinates of the sampling points at the starting depth and the ending depth of each stratum of the coal seam at the working face, and dividing the size of the grid unit based on the maximum and the minimum values.

[0053] Kriging interpolation method, also known as spatial autocovariance optimal interpolation method, is a regression algorithm for spatial modeling and prediction (interpolation) of random processes / random fields based on covariance functions. According to the spatial position and correlation between the sampling point and the prediction point, a distance range that affects the value of the point to be interpolated is determined. A certain weight is given to each sample, and finally a weighted average is performed to estimate the attribute value of the point to be predicted.

[0054] The method of using Kriging spatial interpolation algorithm to interpolate and fit the elevation and coal quality indicators of the grid points of each stratum is as follows:

[0055]

[0056] Among them, Z * (u) is the estimated value of the interpolation point to be found, Z(u α ) is the αth sampling point u α The value at, n(u) is the number of sampling points, λ α (u) is the sampling point u α The difference weight coefficient between and the interpolation point u to be found, and the sum of the difference weight coefficients is 1, that is:

[0057]

[0058] The realization of the three-dimensional model of the coal seam at the working face includes:

[0059] Coal seam is a layered geological entity in space. Its spatial form and distribution are relatively simple compared to non-layered entities, and it has strong global regularity. According to the geological conditions of coal seams in coal mining working faces, it can be divided into mining coal layers and interlayers. Based on the sampling point data, JetBrains WebStorm 2018 is used as the development tool, and JavaScript and Three.js are used for development. With the help of regular grid method and Kriging interpolation method, a regular grid data model is formed, and the coal mining layer model and interlayer model are gradually realized according to the principle of points clustering into lines, lines clustering into surfaces, and surfaces clustering into bodies.

[0060] The interaction between the three-dimensional model of the coal seam of the working face established based on Three.js and the user is realized by the THREE.OrbitControls control: In this control mode, the left, middle and right mouse buttons are used to change the viewpoint of the camera in the scene, and the rotation, scaling and translation of the three-dimensional model are realized. The distribution of the coal seam of the coal mining working face is observed from different angles, and the rotation, translation, scaling and layered display of the three-dimensional model are realized, which has good human-computer interaction performance.

[0061] S3, obtaining the latest working face laser scanning data, top / bottom coal thickness data and coal mining machine cutting trajectory information, fusing and comparing the working face laser scanning data, the top / bottom coal thickness data and the coal mining machine cutting trajectory information, and obtaining a correction value of the working face coal seam three-dimensional model;

[0062] Specifically, the means of obtaining the latest working face laser scanning data, top / bottom coal thickness data and coal mining machine cutting trajectory information are:

[0063] Use laser scanners to obtain laser scanning data of the spatial contour of the working face before and during mining;

[0064] Seismic waves are emitted to the top / bottom coal seam, and composite waves are reflected and superimposed by the top and bottom plates of the coal seam to obtain reflection wave parameters, and the top / bottom coal thickness data in the mining stage are obtained according to the reflection wave parameters, wherein the reflection wave parameters include offset distance, reflection time and reflection wave velocity; the principle is:

[0065] The time taken for the reflected wave to travel is:

[0066]

[0067] Where h is the thickness of the coal seam, x is the offset distance of the reflected wave, and v is m is the velocity of the reflected wave in the coal seam. Among the above parameters, t can be obtained based on the time difference between the reflected wave being emitted and received; x can be measured by measuring tools in actual detection; v m It can be obtained based on the difference between two points.

[0068] Positioning the coal mining machine model in the three-dimensional model of the coal seam of the working face, and obtaining the cutting trajectory information of the coal mining machine by using an airborne inertial navigation system and a rocker arm inclination sensor;

[0069] After obtaining the cutting trajectory information of the coal mining machine, the top and bottom plate curves of the three-dimensional model of the working face coal seam are extracted according to the established three-dimensional model of the working face coal seam. The relative position relationship between the actual cutting path of the coal mining machine and the top and bottom plate curves of the three-dimensional model of the working face coal seam is accurately compared to obtain the error value of the coal mining machine cutting trajectory in the vertical direction of the top and bottom plates.

[0070] The step of obtaining the correction value of the three-dimensional model of the coal seam at the working face in S3 includes:

[0071] According to the top / bottom coal thickness data and the error value of the shearer cutting trajectory in the vertical direction of the top and bottom plates, a top / bottom coal thickness data surface model and a shearer cutting trajectory vertical error surface model are respectively constructed;

[0072] According to the coordinate conversion relationship between the laser scanning data of the working face and the three-dimensional model of the coal seam of the working face, the top / bottom coal thickness data surface model and the vertical error surface model of the shearer cutting trajectory are merged with the three-dimensional model of the coal seam of the working face;

[0073] The fused models are compared using a quadratic sequence programming method to calculate the deviation difference between the top / bottom coal thickness data surface model and the coal mining machine cutting trajectory vertical error surface model and the working face coal seam three-dimensional model to obtain the correction value.

[0074] The calculation process of the quadratic sequence programming method is as follows: The quadratic sequence programming method is a method that transforms complex nonlinear constrained optimization problems into simple quadratic programming problems. This method has fast convergence and high speed when solving surface deviation difference problems. According to the constructed top / bottom coal thickness data surface model and the vertical error surface model of the shearer cutting trajectory, according to the evaluation criteria of the quadratic sequence programming method, the maximum gap between the two surface models should be minimized to minimize the maximum gap.

[0075] S4. Update the three-dimensional model of the coal seam at the working face based on the correction value, and return to step S3 to continue updating the corrected three-dimensional model of the coal seam at the working face according to the latest data.

[0076] The updating of the three-dimensional model of the coal seam at the working face based on the correction value includes: inserting the correction value into the three-dimensional model of the coal seam at the working face by using an inverse distance weighted interpolation method.

[0077] The calculation process of the inverse distance weighted interpolation method includes:

[0078] (1) Determine known points and unknown points: First, we need to determine n known points (xi ,y i ,z i ) and the unknown point (x, y, z) in the three-dimensional model of the coal seam at the working face; the known point (x i ,y i ,z i ) refers to the points that have been measured or observed, and their attribute values ​​are known. Unknown points (x, y, z) refer to the points that need to be interpolated, and their attribute values ​​are unknown.

[0079] (2) Calculate the distance weight: Based on the positions of the known and unknown points, the distance between the known and unknown points can be calculated. Common calculation methods include Euclidean distance and Manhattan distance. Then, the weight is calculated based on the inverse of the distance. The closer the distance, the greater the weight, and the farther the distance, the smaller the weight. If the distance between the known and unknown points is zero, a division by zero error should be avoided by setting a very small value instead of zero distance, or setting the weight of the unknown point to infinity.

[0080] (3) Calculate the interpolation result: Based on the attribute value and distance weight of the known point, use the weighted average method to perform interpolation calculation, that is, multiply the attribute value of the known point by the corresponding weight, then sum and divide by the sum of the weights to obtain the attribute value of the unknown point;

[0081] The interpolation result can be calculated by the following formula:

[0082]

[0083] Among them, f i is the value of the known point, u is the weight index, n is the number of known points,

[0084] Represents the distance from an unknown point (x, y, z) to a known point (x i ,y i ,z i ) distance;

[0085] (4) Visualization and application: After the interpolation is completed, the results are visualized.

[0086] The present invention fully considers the difficulties faced by intelligent mining in mines, such as the opacity of geological information of coal seam working faces and the lack of geological information guidance in the mining process. A set of efficient and high-precision methods for constructing and dynamically correcting high-precision transparent three-dimensional geological models of coal seams at the mining working face is designed. This method facilitates dynamic correction of the model while providing high-precision data, greatly improving the advancement speed of intelligent mining in mines and having good promotion value.

[0087] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A three-dimensional modeling method for coal seams at working faces based on big data, characterized in that The following steps are involved: S1. Obtain coal seam geological data of the coal seam at the working face, wherein the coal seam geological data includes coal seam distribution, coal seam thickness and geological structure data obtained through ground exploration drilling, underground drilling, tunnel sketch, cut-eye sketch and exploration line; S2, processing the coal seam geological data, and calling 3D modeling software to construct a 3D model of the coal seam at the working face; S3, obtaining the latest working face laser scanning data, top / bottom coal thickness data and coal mining machine cutting trajectory information, fusing and comparing the working face laser scanning data, the top / bottom coal thickness data and the coal mining machine cutting trajectory information, and obtaining a correction value of the working face coal seam three-dimensional model; S4. Update the three-dimensional model of the coal seam at the working face based on the correction value, and return to step S3 to continue updating the corrected three-dimensional model of the coal seam at the working face according to the latest data.

2. The method for three-dimensional modeling of coal seams at a working face based on big data according to claim 1, characterized in that: The processing of the coal seam geological data in S2 includes: Based on the coal seam geological data, the coal seam at the working face is divided into several strata, and according to the stratum boundary control point information, the several strata are divided into coal mining layers and interlayers, and each stratum is grid-divided; The Kriging spatial interpolation algorithm is used to interpolate and fit the elevation and coal quality indicators of the grid points of each stratum to obtain a regular grid model; Based on the regular grid model, a three-dimensional model of the coal seam at the working face is constructed.

3. The method for three-dimensional modeling of coal seams at a working face based on big data according to claim 2 is characterized in that: The dividing the working face coal seam into several strata based on the coal seam geological data comprises: analyzing the coal seam geological data, and dividing the working face coal seam into several strata based on lithology and vertical position.

4. A method for three-dimensional modeling of a working face coal seam based on big data according to claim 2 or 3, characterized in that: The grid division of each stratum includes: calculating the maximum and minimum values ​​of the horizontal coordinates of the sampling points at the starting depth and the ending depth of each stratum of the coal seam of the working face, and dividing the size of the grid unit based on the maximum and the minimum values.

5. The method for three-dimensional modeling of coal seams at a working face based on big data according to claim 2, characterized in that: The method of using the Kriging spatial interpolation algorithm to perform interpolation fitting processing on the elevation and coal quality index of each stratum grid point is as follows: Among them, Z * (u) is the estimated value of the interpolation point to be found, Z(u α ) is the αth sampling point u α The value at, n(u) is the number of sampling points, λ α (u) is the sampling point u α and the difference weight coefficient between the interpolation point u to be determined, and the sum of the difference weight coefficients is 1.

6. The method for three-dimensional modeling of coal seams at a working face based on big data according to claim 1, characterized in that: The means for obtaining the working face laser scanning data, top / bottom coal thickness data and coal mining machine cutting trajectory information in S3 are: Use laser scanners to obtain laser scanning data of the spatial contour of the working face before and during mining; Inject seismic waves into the top / bottom coal seam, reflect the superimposed composite waves through the top and bottom plates of the coal seam, obtain reflection wave parameters, and obtain the top / bottom coal thickness data in the mining stage according to the reflection wave parameters, wherein the reflection wave parameters include offset distance, reflection time and reflection wave velocity; Positioning the coal mining machine model in the three-dimensional model of the coal seam of the working face, and obtaining the cutting trajectory information of the coal mining machine by using an airborne inertial navigation system and a rocker arm inclination sensor; After obtaining the cutting trajectory information of the coal mining machine, the top and bottom plate curves of the three-dimensional model of the working face coal seam are extracted according to the established three-dimensional model of the working face coal seam. The relative position relationship between the actual cutting path of the coal mining machine and the top and bottom plate curves of the three-dimensional model of the working face coal seam is accurately compared to obtain the error value of the coal mining machine cutting trajectory in the vertical direction of the top and bottom plates.

7. The method for three-dimensional modeling of coal seams at a working face based on big data according to claim 6, characterized in that: The step of obtaining the correction value of the three-dimensional model of the coal seam at the working face in S3 includes: According to the top / bottom coal thickness data and the error value of the shearer cutting trajectory in the vertical direction of the top and bottom plates, a top / bottom coal thickness data surface model and a shearer cutting trajectory vertical error surface model are respectively constructed; According to the coordinate conversion relationship between the laser scanning data of the working face and the three-dimensional model of the coal seam of the working face, the top / bottom coal thickness data surface model and the vertical error surface model of the shearer cutting trajectory are merged with the three-dimensional model of the coal seam of the working face; The fused models are compared using a quadratic sequence programming method to calculate the deviation difference between the top / bottom coal thickness data surface model and the coal mining machine cutting trajectory vertical error surface model and the working face coal seam three-dimensional model to obtain the correction value.

8. The method for three-dimensional modeling of coal seams at a working face based on big data according to claim 1, characterized in that: The updating of the three-dimensional model of the coal seam at the working face based on the correction value in S4 includes: inserting the correction value into the three-dimensional model of the coal seam at the working face using an inverse distance weighted interpolation method.

9. The method for three-dimensional modeling of coal seams at a working face based on big data according to claim 8, characterized in that: The calculation process of the inverse distance weighted interpolation method includes: (1) Determine known points and unknown points: First, we need to determine n known points (x i ,y i ,z i ) and the unknown point (x, y, z) in the three-dimensional model of the coal seam at the working face; the known point (x i ,y i ,z i ) refers to the points that have been measured or observed, and their attribute values ​​are known. Unknown points (x, y, z) refer to the points that need to be interpolated, and their attribute values ​​are unknown. (2) Calculate the distance weight: Based on the positions of the known and unknown points, the distance between the known and unknown points can be calculated. Then, the weight is calculated based on the inverse of the distance. The closer the distance, the greater the weight, and the farther the distance, the smaller the weight. If the distance between the known and unknown points is zero, a division by zero error should be avoided by setting a very small value instead of zero distance, or setting the weight of the unknown point to infinity. (3) Calculate interpolation results: Based on the attribute values ​​and distance weights of known points, use the weighted average method to interpolate unknown points; The interpolation result can be calculated by the following formula: Among them, f i is the value of the known point, u is the weight index, n is the number of known points, Represents the distance from an unknown point (x, y, z) to a known point (x i ,y i ,z i ) distance; (4) Visualization and application: After the interpolation is completed, the results are visualized.

Images