Three-dimensional modeling system for coal yard

Abstract

The invention provides a coal yard three-dimensional modeling system, and relates to the technical field of coal yard management, and the system comprises a data collection module which is used for collecting coal yard image data through an unmanned plane; the coal yard image processing module is connected with the data acquisition module and is used for performing coal pile contour extraction, coal pile volume calculation and vector transformation analysis on the coal yard image data acquired by the unmanned aerial vehicle to generate a processing result; the coal quality parameter calculation module is connected with the coal yard image processing module and is used for calculating coal quality related parameters based on a processing result; the system function display module is connected with the coal yard image processing module and the coal quality parameter calculation module and used for generating a three-dimensional model according to a processing result and displaying the three-dimensional model and the coal quality related parameters in an associated manner; by deeply processing and analyzing the data acquired by the unmanned aerial vehicle, accurate modeling of the coal yard and accurate calculation of the coal quality parameters are realized, and meanwhile, visual system function display is provided to meet the actual demand of coal yard management.

Description

Technical Field

[0001] The invention relates to the technical field of coal yard management, and in particular to a three-dimensional modeling system for a coal yard. Background Art

[0002] In the process of coal production and use, the management of coal yards is crucial; accurately understanding the inventory, coal type distribution, regional temperature and other information of coal yards is of great significance for optimizing coal resource allocation, improving combustion efficiency and ensuring production safety; with the continuous development of science and technology, coal yard management technology is also gradually improving; at present, technologies such as drone coal handling systems have been applied in coal yards, providing certain convenience for obtaining coal yard data;

[0003] However, there are still some problems in the existing technology that need to be solved. For example, the traditional coal yard data collection method has the problems of low accuracy and incomplete data, which makes it difficult to accurately reflect the actual shape and volume of the coal pile; secondly, the existing methods for calculating coal quality parameters such as coal seam density, coal type identification and fuel value prediction are not accurate and timely enough, and cannot provide effective basis for coal loading for the main plant; in terms of display, the existing coal yard management system is difficult for operators to intuitively understand the detailed information of the coal yard, which is not conducive to control and adjustment;

[0004] Therefore, there is an urgent need in the art for a three-dimensional coal yard modeling system to solve the above problems. Summary of the invention

[0005] The present invention provides a three-dimensional modeling system for a coal yard, which realizes precise modeling of the coal yard and accurate calculation of coal quality parameters by in-depth processing and analysis of data collected by drones, while providing intuitive system function display to meet the actual needs of coal yard management.

[0006] The present invention provides a coal yard three-dimensional modeling system, comprising:

[0007] A data acquisition module, which is used to collect coal yard image data through drones;

[0008] A coal yard image processing module, which is connected to the data acquisition module and is used to extract coal pile contours, calculate coal pile volumes, and perform vector transformation analysis on the coal yard image data collected by the drone to generate processing results;

[0009] A coal quality parameter calculation module, which is connected to the coal yard image processing module and calculates coal quality related parameters based on the processing results;

[0010] The system function display module is connected to the coal yard image processing module and the coal quality parameter calculation module, and is used to generate a three-dimensional model according to the processing results, and associate the three-dimensional model with coal quality related parameters for display.

[0011] According to a coal yard three-dimensional modeling system provided by the present invention, the data acquisition module includes:

[0012] a drone unit for flying in a circle over the coal yard in a fixed flight path;

[0013] The image acquisition unit is mounted on the drone unit and is used to photograph the coal yard at a fixed shooting frequency to obtain coal yard image data including coal pile shape, coal pile surface texture, coal pile color and surrounding environment information.

[0014] According to a coal yard three-dimensional modeling system provided by the present invention, the coal yard image processing module comprises:

[0015] The coal pile contour extraction unit is connected to the image acquisition unit and is used to extract coal pile contour information from the coal yard image data. The specific extraction steps include:

[0016] S1, selecting an image matrix I(x, y), wherein the image matrix I(x, y) represents the grayscale value of a pixel at the (x, y) coordinate in the coal yard image data;

[0017] S2, using the Sobel operator for edge detection; wherein the template G of the Sobel operator in the x direction is pre-set x and the template G in the y direction y ;

[0018] S3, calculate the gradient G of the image matrix I(x, y) in the x direction xI (x, y) and the gradient G in the y direction yI (x, y);

[0019] Among them, G xI (x, y) = I (x, y) * G x ,

[0020] G yI (x, y) = I (x, y) * G y ;

[0021] S4, calculate the edge strength E(x, y) based on the gradient value, the calculation formula is:

[0022]

[0023] S5, pre-set a threshold value T, when E(x, y)>T, determine that the point is an edge point of the coal pile;

[0024] S6, repeating steps S1 to S5, summarizing the edge points of the coal pile, thereby extracting the contour information of the coal pile;

[0025] a first coal pile volume calculation unit, which is connected to the coal pile contour extraction unit and calculates the volume of the coal pile by approximately regarding the coal pile as a combination of multiple triangular prisms or quadrangular prisms based on the extracted coal pile contour information;

[0026] A vector change calculation unit is connected to the coal pile contour extraction unit, and determines the coordinate set P of the coal pile surface points at the current time t based on the extracted coal pile contour information. 2 ; Obtain the coordinate set P of the coal pile surface points at the previous time t-1 from the historical database 1 ; Combine the coordinates P 1 and P 2 Substitute it into the vector change analysis model to analyze the overall vector change degree of the coal pile between two coal handling operations in order to locate the change area;

[0027] Among them, the coordinate set P of the coal pile surface points at the current time t is 2 ={(x 2l ,y 2l , z 2l )}, l = 1, 2, · · ·, N 2 ;x 2l ,y 2l , z 2l are the x, y, and z coordinates of the lth point on the surface of the coal pile in three-dimensional space during the current coal stacking, N 2 is the number of coal pile surface points at the current coal stack; similarly, the coordinate set P of the coal pile surface points at the previous time t-1 1 ={(x 1k ,y 1k , z 1k )},k=1,2,···,N 1 ;

[0028] The vector change analysis model is:

[0029]

[0030] Vector change value ΔV(P 1 , P 2 ) is larger, which means the change of coal pile between two coal handling is greater, thus locating the change area.

[0031] According to a coal yard three-dimensional modeling system provided by the present invention, the coal yard image processing module further includes:

[0032] The second coal pile volume calculation unit is connected to the coal pile contour extraction unit and is used to calculate the volume of the coal pile in the horizontal stratified state. The specific calculation steps are as follows:

[0033] Get the coordinates of the polygon vertices (x ij ,yij ), and the height of the coal pile h i ;

[0034] Where j is the number of vertices, j = 1, 2, ···, n;

[0035] The shoelace algorithm is used to calculate the area of ​​the coal pile in this layer. The calculation formula is:

[0036]

[0037] Calculate the volume of the coal layer based on the area of ​​the coal pile

[0038] According to a coal yard three-dimensional modeling system provided by the present invention, the coal quality parameter calculation module includes:

[0039] A coal seam density calculation unit, which is connected to the coal pile contour extraction unit, is used to obtain historical coal pile information, including the initial height H of the coal pile. 1 、The height after a period of sedimentation H 2 , the bottom area S of the coal pile are obtained from the coal pile contour information; the coal seam density data ρ is calculated based on the above historical coal pile information; the calculation formula is: Where, M is the total mass of the coal pile;

[0040] A fuel value calculation unit, which is connected to the coal pile contour extraction unit and is used to pre-establish a multivariate regression model, train it through coal sample data in a historical database, and generate a trained fuel value prediction model;

[0041] The fuel value prediction model is Q = β 0 +β 1 d 1 +β 2 d 2 +β 3 d 3 +ε;

[0042] Among them, Q is the predicted value of fuel value, d 1 d 2 d 3 is the characteristic vector related to coal type, β 0 , β 1 , β 2 , β 3 is the regression coefficient, and ε is the error term; both the regression coefficient and the error term are obtained during the training process;

[0043] Get the feature vector currently associated with the coal type Substitute it into the trained fuel value prediction model to calculate the fuel value prediction value Q of the coal corresponding to the coal pile.

[0044] According to a three-dimensional modeling system of a coal yard provided by the present invention, the feature vector related to the type of coal includes color features of the burning coal, regional temperature features, and storage date features, wherein each feature is quantified into a numerical value.

[0045] According to a coal yard three-dimensional modeling system provided by the present invention, the system function display module includes:

[0046] A three-dimensional model display unit is connected to the coal pile contour extraction unit and is used to map each coal pile edge point in the coal pile contour information in a three-dimensional space to generate a three-dimensional model; establish a perspective transformation matrix B, transform the original three-dimensional coordinates (x, y, z) in the three-dimensional model into (x, y, z,) through the perspective transformation matrix B, and remap the transformed coordinates in the three-dimensional space to generate a scaled model of the three-dimensional model;

[0047] Wherein, (x, y, z) = (x, y, z) - B; by adjusting the elements in the perspective transformation matrix B, the zooming-in and zooming-out effect of a specific area of ​​the three-dimensional model is achieved while maintaining the original proportional relationship;

[0048] An interpolation unit is connected to the three-dimensional model display unit and is used to insert the coal pile volume, vector change value and fuel value prediction value into corresponding positions of the three-dimensional model.

[0049] According to a coal yard three-dimensional modeling system provided by the present invention, the interpolation unit further includes:

[0050] The coal pile is graded based on the predicted fuel value, and the graded results are inserted into the corresponding positions of the three-dimensional model.

[0051] Compared with the prior art, the present invention has the following beneficial effects:

[0052] The improved Sobel operator and shoelace formula can more accurately extract the coal pile contour and calculate the coal pile volume, accurately reflecting the actual shape and volume of the coal pile, and improving the precision and accuracy of the data compared with traditional methods.

[0053] By establishing multiple regression models and other methods, it is possible to more accurately calculate coal seam density, identify coal types and predict fuel value, providing a more effective basis for coal loading for the main plant and improving the reliability of blending and combustion;

[0054] It provides functions such as partial zooming in and out of 3D graphics, storage time, coal sample and coal type, calorific value, storage temperature display, and data insertion display, which allows operators to view detailed information of the coal yard more intuitively and facilitates management, control and adjustment;

[0055] Accurately calculate the form and total amount of coal stored in the coal yard, facilitate the coal transportation program control system to accurately control the coal mining points and coal mining areas, prompt the main plant to operate the current reasonable coal blending ratio and combustion value, reduce the spontaneous combustion of coal samples caused by excessive temperature, excessive storage time, etc., and improve the safety of coal yard management;

[0056] It provides an effective basis for the main plant's metering, facilitates the main plant's operation to make better and more reasonable coal loading decisions, optimizes coal resource allocation, and improves combustion efficiency.

[0057] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0058] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0060] Figure 1 The present invention is a schematic structural diagram of a three-dimensional modeling system for a coal yard provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0061] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0062] Embodiment 1:

[0063] This embodiment provides a three-dimensional modeling system for a coal yard. Figure 1 ,include:

[0064] A data acquisition module, which is used to collect coal yard image data through drones;

[0065] The coal yard image processing module is connected to the data acquisition module and is used to extract the coal pile contour, calculate the coal pile volume and perform vector transformation analysis on the coal yard image data collected by the drone to generate processing results;

[0066] A coal quality parameter calculation module, which is connected to the coal yard image processing module and calculates coal quality related parameters based on the processing results;

[0067] The system function display module is connected with the coal yard image processing module and the coal quality parameter calculation module, and is used to generate a three-dimensional model according to the processing results, and associate the three-dimensional model with coal quality related parameters for display.

[0068] The principle of the above embodiment is: the coal yard image data collected by the drone is acquired through the data acquisition module, the coal yard image processing module processes these data, extracts the coal pile contour, calculates the volume and analyzes the vector change, and then the coal quality parameter calculation module calculates the coal quality related parameters according to the processing results, and finally the system function display module generates a three-dimensional model and associates it with the coal quality related parameters for display, thereby realizing comprehensive and accurate modeling and display of the coal yard.

[0069] The beneficial effects of the above embodiment are: it can accurately obtain the image data of the coal yard, and generate an intuitive three-dimensional model and related parameter display through precise image processing and coal quality parameter calculation, so that the operating personnel can more clearly understand the inventory, coal type distribution, regional temperature and other information of the coal yard, which is convenient for management and adjustment, and improves the efficiency and safety of coal yard management. At the same time, it provides accurate control basis for the coal transportation program control system, provides reasonable coal blending ratio and combustion value suggestions for the main plant operation, and improves the utilization efficiency and combustion reliability of coal resources.

[0070] In order to further optimize the above embodiment, the data acquisition module includes:

[0071] a drone unit for flying in a circle over the coal yard in a fixed flight path;

[0072] The image acquisition unit is mounted on the drone unit and is used to photograph the coal yard at a fixed shooting frequency to obtain coal yard image data including coal pile shape, coal pile surface texture, coal pile color and surrounding environment information.

[0073] It should be noted that the drone unit flies around in a fixed flight path, which can ensure full coverage of the coal yard area and avoid missing important information; at the same time, the fixed flight path helps to improve the stability and repeatability of data acquisition, providing a reliable basis for subsequent data processing and analysis; the image acquisition unit shoots at a fixed shooting frequency, which can ensure the acquisition of continuous and accurate coal yard image data; these data contain many aspects of the coal pile shape, surface texture, color and surrounding environment information, which helps to fully understand the condition of the coal yard; the shape and surface texture information of the coal pile is crucial for coal pile contour extraction and volume calculation; the color of the coal pile can provide preliminary clues about the type of coal; the surrounding environment information helps to comprehensively consider the overall situation of the coal yard, such as the impact of factors such as temperature and humidity on coal quality.

[0074] In order to further optimize the above embodiment, the coal yard image processing module includes:

[0075] The coal pile contour extraction unit is connected to the image acquisition unit and is used to extract coal pile contour information from the coal yard image data. The specific extraction steps include:

[0076] S1, select an image matrix I(x, y), where the image matrix I(x, y) represents the pixel grayscale value at the (x, y) coordinate in the coal yard image data;

[0077] S2, using the Sobel operator for edge detection; wherein the template G of the Sobel operator in the x direction is pre-set x and the template G in the y direction y ;

[0078] S3, calculate the gradient G of the image matrix I(x, y) in the x direction xI (x, y) and the gradient G in the y direction yI (x, y);

[0079] Among them, G xI (x, y) = I (x, y) * G x ,

[0080] G yI (x, y) = I (x, y) * G y ;

[0081] S4, calculate the edge strength E(x, y) based on the gradient value, the calculation formula is:

[0082]

[0083] S5, pre-set a threshold value T, when E(x, y)>T, determine that the point is an edge point of the coal pile;

[0084] S6, repeating steps S1 to S5, summarizing the edge points of the coal pile, thereby extracting the contour information of the coal pile;

[0085] a first coal pile volume calculation unit, which is connected to the coal pile contour extraction unit, and calculates the volume of the coal pile by approximately regarding it as a combination of a plurality of triangular prisms or quadrangular prisms based on the extracted coal pile contour information;

[0086] The vector change calculation unit is connected to the coal pile contour extraction unit, and determines the coordinate set P of the coal pile surface points at the current time t based on the extracted coal pile contour information. 2 ; Obtain the coordinate set P of the coal pile surface points at the previous time t-1 from the historical database 1 ; Combine the coordinates P 1 and P 2 Substitute it into the vector change analysis model to analyze the overall vector change degree of the coal pile between two coal handling operations in order to locate the change area;

[0087] Among them, the coordinate set P of the coal pile surface points at the current time t is 2 ={(x 2l ,y 2l , z 2l )}, l = 1, 2, · · ·, N 2 ;x 2l ,y 2l , z 2l are the x, y, and z coordinates of the lth point on the surface of the coal pile in three-dimensional space during the current coal stacking, N 2 is the number of coal pile surface points at the current coal stack; similarly, the coordinate set P of the coal pile surface points at the previous time t-1 1 ={(x 1k ,y 1k , z 1k )},k=1,2,···,N 1 ;

[0088] The vector change analysis model is:

[0089]

[0090] Vector change value ΔV(P 1 , P 2 ) is larger, which means the change of coal pile between two coal handling is greater, thus locating the change area.

[0091] It should be noted that the Sobel operator uses the preset template G in the x and y directions respectively. x and G y Perform convolution operation with the image matrix to obtain the gradient G of the image in the x and y directions xI (x, y) and G yI (x, y); the gradient reflects the degree of change of the gray value of the pixel in the image, and the edge strength E(x, y) combines the gradient information in the x and y directions; by setting the threshold, the point with edge strength greater than the threshold can be determined as the edge point of the coal pile, thereby effectively extracting the contour information of the coal pile;

[0092] Based on the extracted coal pile contour information, the coal pile is approximately regarded as a combination of multiple triangular prisms or quadrangular prisms. The total volume of the coal pile is estimated by calculating and summing the volumes of these geometric bodies. This method can take into account the actual shape of the coal pile and more accurately reflect the volume of the coal pile than simple approximate calculations, providing a more reliable basis for subsequent calculation and management of coal quality parameters.

[0093] According to the information provided by the coal pile contour extraction unit, the coordinate set P of the coal pile surface points at the current time t and the previous time t-1 is determined 1 and P 2; Substitute these coordinate sets into the vector change analysis model, calculate the spatial distance (Euclidean distance) between each pair of corresponding points and sum them up to obtain the vector change value ΔV (P 1 , P 2 ); The larger the vector change value, the greater the change in the coal pile between two coal handlings; in this way, the changed area of ​​the coal pile can be accurately located, whether it is the newly added or consumed part, providing important information for the management and monitoring of the coal yard.

[0094] In order to further optimize the above embodiment, the coal yard image processing module further includes:

[0095] The second coal pile volume calculation unit is connected to the coal pile contour extraction unit and is used to calculate the volume of the coal pile in the horizontal layered state. The specific calculation steps are as follows:

[0096] Get the coordinates of the polygon vertices (x ij ,y ij ), and the height of the coal pile h i ;

[0097] Where j is the number of vertices, j = 1, 2, ···, n;

[0098] The shoelace algorithm is used to calculate the area of ​​the coal pile in this layer. The calculation formula is:

[0099]

[0100] Calculate the volume of the coal layer based on the area of ​​the coal pile

[0101] It should be noted that this unit is connected to the coal pile contour extraction unit to provide another method for calculating the volume of the coal pile, namely, to perform volume calculation on the coal pile in a horizontally stratified state; this calculation method can serve as a supplement or verification to the first coal pile volume calculation unit to improve the accuracy and reliability of the volume calculation; wherein, the principle of this formula is based on the geometric meaning of the vector cross product, decomposing the polygon into multiple triangles, and obtaining the area of ​​the polygon by calculating the sum of the directed areas of these triangles; by simultaneously using the first coal pile volume calculation unit and the second coal pile volume calculation unit, the volume of the coal pile can be calculated from different angles and methods, verifying and supplementing each other, thereby improving the accuracy and reliability of the volume calculation.

[0102] In order to further optimize the above embodiment, the coal quality parameter calculation module includes:

[0103] The coal seam density calculation unit is connected to the coal pile contour extraction unit to obtain historical coal pile information, including the initial height H of the coal pile. 1 、The height after a period of sedimentation H 2, the bottom area S of the coal pile are obtained from the coal pile contour information; the coal seam density data ρ is calculated based on the above historical coal pile information; the calculation formula is: Where, M is the total mass of the coal pile;

[0104] A fuel value calculation unit, which is connected to the coal pile contour extraction unit, is used to pre-establish a multivariate regression model, train it through coal sample data in a historical database, and generate a trained fuel value prediction model;

[0105] The fuel value prediction model is Q = β 0 +β 1 d 1 +β 2 d 2 +β 3 d 3 +ε;

[0106] Among them, Q is the predicted value of fuel value, d 1 d 2 d 3 is the characteristic vector related to coal type, β 0 , β 1 , β 2 , β 3 is the regression coefficient, and ε is the error term; both the regression coefficient and the error term are obtained during the training process;

[0107] Get the feature vector currently associated with the coal type Substitute it into the trained fuel value prediction model to calculate the fuel value prediction value Q of the coal corresponding to the coal pile.

[0108] It should be noted that this embodiment takes into account the settlement of the coal pile and can more realistically reflect the density characteristics of the coal seam; the coal seam density calculation unit and the fuel value calculation unit in the coal quality parameter calculation module cooperate with each other to provide important parameters about coal quality, which are of great significance to the management of the coal yard, the use of coal and the effective use of energy; accurate coal seam density and fuel value prediction information can help coal yard managers better understand the quality characteristics of coal, reasonably arrange the storage, allocation and use of coal, improve the utilization efficiency of coal, and also help to ensure the stability and safety of energy supply in the production process.

[0109] In order to further optimize the above embodiment, the feature vector related to the type of coal includes the color feature of the burning coal, the regional temperature feature, and the storage date feature, wherein each feature is quantified into a numerical value.

[0110] It should be noted that the color characteristics of the coal are quantified into numerical values. For example, the color of the coal can be matched to a specific numerical range through a color sensor or image processing technology. In this way, the color characteristics can be more accurately incorporated into the fuel value prediction model, because coal of different colors may reflect differences in its composition and properties, thereby affecting the fuel value. Temperature affects the chemical reactions and physical properties of coal, thereby affecting the fuel value. By quantifying regional temperature characteristics, the effect of temperature on coal quality can be more accurately considered, thereby improving the accuracy of fuel value prediction. The storage date of the coal is converted into a specific numerical value, such as the number of days of storage. The length of the storage date will affect changes in the quality of the coal, such as water evaporation, oxidation, etc., thereby affecting the fuel value. By quantifying the storage date characteristics, the effect of storage time on coal quality can be better reflected in the fuel value prediction model.

[0111] In order to further optimize the above embodiment, the system function display module includes:

[0112] A three-dimensional model display unit is connected to the coal pile contour extraction unit and is used to map each coal pile edge point in the coal pile contour information in the three-dimensional space to generate a three-dimensional stereo model; establish a perspective transformation matrix B, transform the original three-dimensional coordinates (x, y, z) in the three-dimensional stereo model into (x, y, z,) through the perspective transformation matrix B, and remap the transformed coordinates in the three-dimensional space to generate a scaled model of the three-dimensional stereo model;

[0113] Wherein, (x, y, z) = (x, y, z) * B; by adjusting the elements in the perspective transformation matrix B, the zooming-in and zooming-out effect of a specific area of ​​the three-dimensional model is achieved while maintaining the original proportional relationship;

[0114] The interpolation unit is connected to the three-dimensional model display unit and is used to insert the coal pile volume, vector change value and fuel value prediction value into corresponding positions of the three-dimensional model.

[0115] It should be noted that the three-dimensional model display unit converts the coal pile contour information into a three-dimensional model, so that the operating personnel can intuitively see the shape, spatial position and distribution of the coal pile, enhancing their understanding of the overall layout of the coal yard; the interpolation unit inserts important information such as the coal pile volume, vector change value and fuel value prediction value into the three-dimensional model, and the operating personnel can obtain these detailed parameter information while viewing the model, which helps to more accurately grasp the inventory, coal quality changes and combustion value of the coal yard;

[0116] Operators can more conveniently manage, control and make adjustment decisions based on intuitive three-dimensional models and detailed parameter information; for example, they can reasonably arrange storage space according to the volume information of the coal pile, timely discover changes in the coal pile and take corresponding measures according to the vector change value, and optimize the use and allocation of coal according to the fuel value prediction value to improve energy utilization efficiency; by adjusting the elements in the perspective transformation matrix B to achieve the effect of zooming in and out, and maintain the original proportional relationship, the authenticity and reliability of the model display are ensured, so that operators can obtain accurate visual information and avoid misunderstandings and wrong decisions caused by proportional distortion; based on the comprehensive coal yard information provided, operators can make more scientific decisions, improve the efficiency and quality of coal yard management, reduce operating costs, and ensure the stability and safety of the production process;

[0117] Specifically, the viewing transformation matrix B is a 4*4 matrix, which defines the mapping relationship from the three-dimensional space to the two-dimensional screen space; when the original three-dimensional coordinates (x, y, z) in the three-dimensional model are perspectively transformed, the transformed coordinates (x, y, z) are obtained by matrix multiplication (x, y, z) = (x, y, z)*B;

[0118]

[0119] Among them, the element a in the matrix ij It determines the specific effects of perspective transformation, such as the scaling, translation, rotation and perspective effect of objects; by adjusting the elements in the perspective transformation matrix, the display effect of the three-dimensional model on the screen can be changed; for example, by increasing or decreasing the values ​​of certain elements, the model can be enlarged or reduced; by changing the combination of elements, the model can be rotated or translated.

[0120] In order to further optimize the above embodiment, the interpolation unit further includes:

[0121] The coal pile is graded based on the predicted fuel value, and the graded results are inserted into the corresponding positions of the three-dimensional model.

[0122] It should be noted that the predicted calorific value reflects the combustion energy characteristics of the coal in the coal pile, and the coal pile is divided into different levels according to the preset calorific value range or standard. For example, a coal pile with a higher calorific value can be classified into a high level, and a coal pile with a lower calorific value can be classified into a low level.

[0123] Grading coal piles helps to more intuitively understand the quality distribution of coal in the coal yard; operators can quickly determine which areas of coal have higher combustion value and which areas of coal need further optimization or adjustment by viewing the grading results of coal piles in the three-dimensional model; for example, when allocating coal, priority can be given to coal piles with higher fuel value to improve energy utilization efficiency; for coal piles with lower fuel value, measures can be considered to optimize or reasonably arrange their use.

[0124] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A three-dimensional modeling system for a coal yard, characterized in that: include: A data acquisition module, which is used to collect coal yard image data through drones; A coal yard image processing module, which is connected to the data acquisition module and is used to extract coal pile contours, calculate coal pile volumes, and perform vector transformation analysis on the coal yard image data collected by the drone to generate processing results; A coal quality parameter calculation module, which is connected to the coal yard image processing module and calculates coal quality related parameters based on the processing results; The system function display module is connected to the coal yard image processing module and the coal quality parameter calculation module, and is used to generate a three-dimensional model according to the processing results, and associate the three-dimensional model with coal quality related parameters for display.

2. A three-dimensional modeling system for a coal yard according to claim 1, characterized in that: The data acquisition module comprises: a drone unit for flying in a circle over the coal yard in a fixed flight path; The image acquisition unit is mounted on the drone unit and is used to photograph the coal yard at a fixed shooting frequency to obtain coal yard image data including coal pile shape, coal pile surface texture, coal pile color and surrounding environment information.

3. A three-dimensional modeling system for a coal yard according to claim 2, characterized in that: The coal yard image processing module includes: The coal pile contour extraction unit is connected to the image acquisition unit and is used to extract coal pile contour information from the coal yard image data. The specific extraction steps include: S1, selecting an image matrix I(x, y), wherein the image matrix I(x, y) represents the grayscale value of a pixel at the (x, y) coordinate in the coal yard image data; S2, using the Sobel operator for edge detection; wherein the template G of the Sobel operator in the x direction is pre-set x and the template G in the y direction y ; S3, calculate the gradient G of the image matrix I(x, y) in the x direction xI (x, y) and the gradient G in the y direction yI (x, y); where G xI (x, y) = I(x, y) * G x , G yI (x,y)=I(x,y)*G y ; S4, calculate the edge strength E(x, y) based on the gradient value, the calculation formula is: S5, pre-set a threshold value T, when E(x, y)>T, determine that the point is an edge point of the coal pile; S6, repeating steps S1 to S5, summarizing the edge points of the coal pile, thereby extracting the contour information of the coal pile; a first coal pile volume calculation unit, which is connected to the coal pile contour extraction unit and calculates the volume of the coal pile by approximately regarding the coal pile as a combination of multiple triangular prisms or quadrangular prisms based on the extracted coal pile contour information; A vector change calculation unit is connected to the coal pile contour extraction unit, and determines a coordinate set P2 of the coal pile surface points at the current time t based on the extracted coal pile contour information; obtains a coordinate set P1 of the coal pile surface points at the previous time t-1 from the historical database; substitutes the coordinate sets P1 and P2 into the vector change analysis model to analyze the overall vector change degree of the coal pile between two coal handling operations, so as to locate the change area; Among them, the coordinate set of the coal pile surface points at the current time t is P2 = {(x 2l ,y 2l , z 2l )}, l=1,2,···,N2;x 2l ,y 2l , x 2l are the x, y, and z coordinates of the lth point on the surface of the coal pile in the current coal stacking time in three-dimensional space, and N2 is the number of points on the surface of the coal pile in the current coal stacking time; similarly, the coordinate set of the surface points of the coal pile at the previous time t-1, P1 = {(x 1k ,y 1k , z 1k )}, k=1,2,···,N1; The vector change analysis model is: The larger the vector change value ΔV(P1, P2), the greater the change in the coal pile between two coal handling operations, thereby locating the change area.

4. A three-dimensional modeling system for a coal yard according to claim 3, characterized in that: The coal yard image processing module also includes: The second coal pile volume calculation unit is connected to the coal pile contour extraction unit and is used to calculate the volume of the coal pile in the horizontal stratified state. The specific calculation steps are as follows: Get the coordinates of the polygon vertices (x ij ,y ij ), and the height of the coal pile h i ; Where j is the number of vertices, j = 1, 2, ···, n; The shoelace algorithm is used to calculate the area of ​​the coal pile in this layer. The calculation formula is: Calculate the volume of the coal pile based on the area of ​​the coal pile 5. A three-dimensional modeling system for a coal yard according to claim 4, characterized in that: The coal quality parameter calculation module includes: The coal seam density calculation unit is connected to the coal pile contour extraction unit and is used to obtain historical coal pile information, including the initial height H1 of the coal pile, the height H2 after a period of settlement, and the bottom area S of the coal pile, all of which are obtained from the coal pile contour information; the coal seam density data ρ is calculated based on the above historical coal pile information; the calculation formula is: Where, M is the total mass of the coal pile; A fuel value calculation unit, which is connected to the coal pile contour extraction unit and is used to pre-establish a multivariate regression model, train it through coal sample data in a historical database, and generate a trained fuel value prediction model; The fuel value prediction model is Q=β0+β1d1+β2d2+β3d3+ε; Among them, Q is the predicted value of the fuel value, d1, d2, d3 are the characteristic vectors related to the coal type, β0, β1, β2, β3 are the regression coefficients, and ε is the error term; the regression coefficients and error terms are obtained during the training process; Get the feature vector currently associated with the coal type Substitute it into the trained fuel value prediction model to calculate the fuel value prediction value Q of the coal corresponding to the coal pile.

6. A three-dimensional modeling system for a coal yard according to claim 5, characterized in that: The characteristic vectors related to the type of coal include color characteristics of the burning coal, regional temperature characteristics, and storage date characteristics, wherein each characteristic is quantified into a numerical value.

7. A three-dimensional modeling system for a coal yard according to claim 6, characterized in that: The system function display module includes: A three-dimensional model display unit is connected to the coal pile contour extraction unit and is used to map each coal pile edge point in the coal pile contour information in a three-dimensional space to generate a three-dimensional model; establish a perspective transformation matrix B, transform the original three-dimensional coordinates (x, y, z) in the three-dimensional model into (x, y, z,) through the perspective transformation matrix B, and remap the transformed coordinates in the three-dimensional space to generate a scaled model of the three-dimensional model; Wherein, (x, y, z) = (x, y, z) * B; by adjusting the elements in the perspective transformation matrix B, the zooming-in and zooming-out effect of a specific area of ​​the three-dimensional model is achieved while maintaining the original proportional relationship; An interpolation unit is connected to the three-dimensional model display unit and is used to insert the coal pile volume, vector change value and fuel value prediction value into corresponding positions of the three-dimensional model.

8. A three-dimensional modeling system for a coal yard according to claim 7, characterized in that: The interpolation unit further includes: The coal pile is graded based on the predicted fuel value, and the graded results are inserted into the corresponding positions of the three-dimensional model.

Images