Unmanned aerial vehicle coal inventory method based on 5G communication technology

Abstract

The invention discloses an unmanned aerial vehicle coal inventory method based on the 5G communication technology, and the method comprises the steps: obtaining a plurality of similar coal inventory logs according to the distribution condition of coal piles, and generating an application evaluation value of historical flight data according to historical coal inventory data in the similar coal inventory logs; screening out optimal flight data according to the application evaluation value, obtaining a real-time image according to the optimal flight data, processing the real-time image, and converting the real-time image into point cloud coordinates; constructing an initial coal pile three-dimensional model based on the point cloud coordinates, determining three-dimensional coordinates of features needing to be concerned according to the real-time image, comparing the three-dimensional coordinates with the corresponding point cloud coordinates, and generating credibility of the initial coal pile three-dimensional model according to a comparison result; whether a correction instruction is generated for the initial coal pile three-dimensional model or not is judged according to the credibility, if the correction instruction is not generated, the demand data of the coal pile is calculated, based on the mode of combining the 5G communication technology and the unmanned aerial vehicle, full-range dead-corner-free scanning of the stock ground can be achieved, and the coal inventory efficiency and the coal inventory accuracy are improved.

Description

Technical Field

[0001] The present application relates to the field of coal-rolling technology, and in particular to a method for coal-rolling by drone based on 5G communication technology. Background Art

[0002] Coal counting in coal yards is an important part of fuel management in thermal power plants. The accuracy of coal counting results will directly affect the profit and loss of coal stored in coal yards of thermal power plants and the accounting of fuel costs. The traditional coal counting method is labor-intensive, time-consuming, and has the risk of landslides. It is impossible to achieve full coverage of blind spots, has poor measurement accuracy, and cannot obtain accurate data on coal storage. Using 5G technology combined with drones to replace traditional coal counting methods is a future development trend, but how to further improve the efficiency and accuracy of drone coal counting is still a technical problem to be solved. Summary of the invention

[0003] To solve the above technical problems, the present application provides a coal counting method using a drone based on 5G communication technology. Similar coal counting logs are obtained according to the distribution of coal piles, and the application evaluation values ​​of historical flight data in the similar coal counting logs are calculated. The historical coal counting efficiency and historical coal counting accuracy corresponding to the historical flight data can be judged according to the application evaluation values, thereby screening out the optimal flight data for the current distribution of the coal piles. The drone is enabled to collect real-time images according to the optimal flight data through 5G communication technology. The control center integrates the real-time image of the coal pile and the three-dimensional GPS information when the image is acquired into the image to obtain point cloud coordinates, constructs an initial three-dimensional model of the coal pile, obtains the accuracy of the initial three-dimensional model of the coal pile according to the credibility, and obtains the volume and weight of the coal pile with higher accuracy. Based on the combination of 5G communication technology and drones, full-range scanning of the material yard without blind spots can be achieved, thereby improving the coal counting efficiency and accuracy.

[0004] In some embodiments of the present application, a method for coal handling by drone based on 5G communication technology is provided, comprising:

[0005] According to the distribution of coal piles, multiple similar coal pan logs are obtained, and the application evaluation value of the historical flight data of the UAV is generated according to the historical coal pan data in the similar coal pan logs;

[0006] Filter out the best flight data according to the application evaluation value, and use the UAV to obtain the real-time image of the coal pile according to the best flight data, process the real-time image, and convert it into point cloud coordinates;

[0007] An initial three-dimensional model of the coal pile is constructed based on the point cloud coordinates, the three-dimensional coordinates of the features to be concerned are determined according to the real-time image, the three-dimensional coordinates are compared with the corresponding point cloud coordinates in the initial three-dimensional model of the coal pile, and the credibility of the initial three-dimensional model of the coal pile is generated according to the comparison results;

[0008] Whether to generate correction instructions for the initial coal pile three-dimensional model is determined based on the credibility.

[0009] In some embodiments of the present application, a plurality of similar coal tray logs are obtained according to the distribution of the coal pile, including:

[0010] Acquire the distribution of the coal pile, wherein the distribution includes a first distribution location and a second distribution location;

[0011] comparing the first distribution positioning and the second distribution positioning with the first view and the second view of the three-dimensional model of the historical coal pile in the historical coal pan log of the different coal piles;

[0012] Determine a first similarity coefficient between the first distribution positioning and the plurality of first views and a second similarity coefficient between the second distribution positioning and the plurality of second views according to the comparison result;

[0013] Generate similarity between the current coal pile distribution and the first view and the second view of the plurality of historical coal pile three-dimensional models according to the first similarity coefficient and the second similarity coefficient;

[0014] The historical coal panning logs corresponding to the historical coal pile three-dimensional models having a similarity greater than a preset similarity are selected and set as similar coal panning logs of the current coal pile.

[0015] In some embodiments of the present application, generating an application evaluation value of historical flight data of a drone based on historical coal pan data in a similar coal pan log includes:

[0016] Preset a first coal pan evaluation index and a second coal pan evaluation index, and calculate a first historical evaluation value of the first coal pan evaluation index and a second historical evaluation value of the second coal pan evaluation index for each similar coal pan log;

[0017] Subtracting the multiple first historical evaluation values, and filtering out the historical coal pan data in two similar coal pan logs corresponding to the first historical evaluation values ​​whose first evaluation value difference is greater than a preset difference threshold, to obtain a first comparison data group;

[0018] Subtracting the plurality of second historical evaluation values, and filtering out historical coal pan data in two similar coal pan logs corresponding to second historical evaluation values ​​whose second evaluation value difference is greater than a preset difference threshold, to obtain a second comparison data group;

[0019] Set a standard coal-collecting duration according to multiple historical coal-collecting durations in similar coal-collecting logs, establish a time reference line based on the standard coal-collecting duration, and set data collection nodes according to preset time intervals;

[0020] Based on multiple data collection nodes, historical coal pan data of multiple first comparison data groups are collected and mapped on a time reference line, and the average difference of the first coal pan data at multiple data collection points of the same historical coal pan data on the corresponding time reference line is calculated;

[0021] Generate the correlation degree between the corresponding historical coal pan data and the first coal pan evaluation index according to the mean value of the difference of the first coal pan data, and set the historical coal pan data with a correlation degree greater than a preset correlation degree as the first correlated coal pan data of the first coal pan evaluation index;

[0022] Based on multiple data collection nodes, historical pan coal data of multiple second comparison data groups are collected and mapped on a time reference line, and the average difference of the second pan coal data at multiple data collection points of the same historical pan coal data on the corresponding time reference line is calculated;

[0023] Generate the correlation degree between the corresponding historical coal pan data and the second coal pan evaluation index according to the mean value of the difference of the second coal pan data, and set the historical coal pan data with a correlation degree greater than a preset correlation degree as the second correlated coal pan data of the second coal pan evaluation index;

[0024] Generate first evaluation values ​​and second evaluation values ​​of the first pan of coal evaluation index and the second pan of coal evaluation index respectively according to the first associated pan of coal data and the second associated pan of coal data in each similar pan of coal log;

[0025] An application evaluation value corresponding to the historical flight data in the similar pan coal log is generated according to the first evaluation value and the second evaluation value.

[0026] In some embodiments of the present application, generating an application evaluation value corresponding to historical flight data in a similar pan coal log according to the first evaluation value and the second evaluation value includes:

[0027] Compare the first pan coal associated data in each similar pan coal log with the corresponding first preset standard pan coal data to obtain a first difference absolute value, and set a weight coefficient of the first difference absolute value according to the first pan coal data difference mean of the first pan coal associated data and the first evaluation value difference of the corresponding first comparison data group;

[0028] Generate a first evaluation value according to a plurality of first difference absolute values ​​and a weight coefficient;

[0029] The second pan coal associated data in each similar pan coal log is compared with the corresponding second preset standard pan coal data to obtain a second difference absolute value, and a weight coefficient of the second difference absolute value is set according to the second pan coal data difference mean of the second pan coal associated data and the second evaluation value difference of the corresponding second comparison data group;

[0030] Generate a second evaluation value according to a plurality of second difference absolute values ​​and a weight coefficient;

[0031] Generate an application evaluation value corresponding to the historical flight data in the similar pan coal log according to the first evaluation value and the second evaluation value;

[0032] The calculation formula of the application evaluation value is:

[0033]

[0034] Among them, Y is the application evaluation value, d is the evaluation conversion coefficient, n is the number of the first coal-related data, △P1i is the i-th first difference absolute value, b1i is the weight coefficient of the i-th first difference absolute value, △P2s is the s-th second difference absolute value, b2s is the weight coefficient of the s-th second difference absolute value, m is the number of the second coal-related data, is the first evaluation value, is the second evaluation value.

[0035] In some embodiments of the present application, the real-time image is processed and converted into point cloud coordinates, including:

[0036] Classify and process the real-time images according to the flight path in the optimal flight data to obtain directly related real-time images and indirectly related real-time images;

[0037] Judging whether the image overlap, image integrity and image clarity of the corresponding flight path are satisfied at the same time according to the boundary continuity and boundary range of the directly associated real-time image; if not satisfied, reacquiring the real-time image of the corresponding flight path;

[0038] If both conditions are met, it is determined whether the image overlap between the corresponding flight path and the adjacent flight path is met according to the boundary overlap of the indirectly associated real-time image;

[0039] If the conditions are met, a panoramic image of the current coal pile is generated and converted into point cloud coordinates of the current coal pile through professional image analysis software, and an initial three-dimensional model of the coal pile is constructed based on the point cloud coordinates.

[0040] In some embodiments of the present application, determining features requiring attention based on real-time images includes:

[0041] Scanning and analyzing the real-time image to determine the structural features of the coal pile expressed by the real-time image, wherein the structural features of the coal pile include an undulating structure and a contour structure of the coal pile;

[0042] Analyze the structural features of the coal pile, determine the protruding structural features, and judge whether the protruding structural features meet the attention requirements. If they meet the requirements, set the protruding structural features as the features that need attention;

[0043] A plane coordinate system is established for the center point of the coal pile, and the plane coordinates of the features that need attention are obtained and converted into three-dimensional coordinates.

[0044] In some embodiments of the present application, generating the credibility of the initial coal pile three-dimensional model according to the comparison result includes:

[0045] The three-dimensional coordinates of the features to be concerned are compared with the point cloud coordinates of the corresponding real-time image conversion in the initial coal pile three-dimensional model to obtain the coordinate difference;

[0046] The credibility of the initial coal pile three-dimensional model is generated according to the comparison results of multiple coordinate difference quantities and the preset coordinate difference quantity threshold.

[0047] In some embodiments of the present application, the credibility of the initial coal pile three-dimensional model is generated according to the mapping result, including:

[0048] Generate a compensation coefficient according to the reception time and image clarity of the real-time images corresponding to the multiple features requiring attention;

[0049] The credibility of the initial coal pile 3D model generated based on the comparison results and compensation coefficients;

[0050] The calculation formula of the credibility is:

[0051]

[0052] Among them, K is the credibility, u is the number of features that need attention, △Te is the mean value of the coordinate difference of the e-th feature that needs attention, R0 is the standard coordinate difference threshold, and j is the compensation coefficient.

[0053] In some embodiments of the present application, judging whether to generate a correction instruction for the initial coal pile three-dimensional model according to the credibility includes:

[0054] Pre-set credibility threshold;

[0055] If the credibility is less than the credibility threshold, a correction instruction is generated for the initial coal pile three-dimensional model, wherein the correction instruction includes screening out the position that needs to be corrected in the initial coal pile three-dimensional model according to the comparison result, and updating the corresponding position in the initial coal pile three-dimensional model according to the coordinate difference in the comparison result, and calculating the credibility of the updated initial coal pile three-dimensional model until the credibility is greater than the preset credibility threshold, setting it as the coal pile three-dimensional model, and calculating the required data of the coal pile according to the coal pile three-dimensional model;

[0056] If the credibility is greater than the credibility threshold, no correction instruction is generated, and the demand data of the coal pile is calculated based on the initial three-dimensional model of the coal pile.

[0057] Compared with the prior art, the unmanned aerial vehicle coal handling method based on 5G communication technology in the embodiment of the present application has the following beneficial effects:

[0058] According to the distribution position of the coal pile, similar coal counting logs are obtained, and the application evaluation values ​​of the historical flight data in the similar coal counting logs are calculated. According to the application evaluation values, the historical coal counting efficiency and historical coal counting accuracy corresponding to the historical flight data can be judged, so as to screen out the optimal flight data for the current distribution position of the coal pile. Through 5G communication technology, the drone collects real-time images according to the optimal flight data. The control center fuses the real-time image of the coal pile and the GPS three-dimensional information when the image is acquired into the image to obtain the point cloud coordinates, and constructs an initial three-dimensional model of the coal pile. The accuracy of the initial three-dimensional model of the coal pile is obtained according to the credibility, and the volume and weight of the coal pile with higher accuracy are obtained. Based on the combination of 5G communication technology and drones, full-range scanning of the material yard without blind spots can be achieved, thereby improving the coal counting efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 It is a flow chart of a drone coal handling method based on 5G communication technology in the preferred embodiment of the present application. DETAILED DESCRIPTION

[0060] The specific implementation methods of the present application are further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present application but are not intended to limit the scope of the present application.

[0061] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0062] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0063] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0064] like Figure 1 As shown, a preferred embodiment of the present application embodiment is a method for unmanned aerial vehicle coal handling based on 5G communication technology, comprising:

[0065] Step S101: obtaining a plurality of similar coal pan logs according to the distribution of the coal pile, and generating an application evaluation value of the historical flight data of the UAV according to the historical coal pan data in the similar coal pan logs;

[0066] Step S102: Filter out the optimal flight data according to the application evaluation value, and enable the UAV to obtain the real-time image of the coal pile according to the optimal flight data, process the real-time image, and convert it into point cloud coordinates;

[0067] Step S103: constructing an initial three-dimensional model of the coal pile based on the point cloud coordinates, determining the three-dimensional coordinates of the features to be concerned about according to the real-time image, comparing the three-dimensional coordinates with the corresponding point cloud coordinates in the initial three-dimensional model of the coal pile, and generating the credibility of the initial three-dimensional model of the coal pile according to the comparison result;

[0068] Step S104: Determine whether to generate a correction instruction for the initial coal pile three-dimensional model based on the credibility.

[0069] In this embodiment, the historical flight data includes the historical flight path, historical flight frequency, historical flight angle, historical flight altitude, historical single flight time, historical total flight time and historical fixed-point hovering time of the UAV. The historical coal panning data refers to data associated with the historical images of the coal pile collected by the UAV. The historical coal panning data includes the historical images of the coal pile, historical image data corresponding to the historical images, the overlap of adjacent historical image data and bypass historical image data, historical point cloud coordinates, historical coal pile three-dimensional model, historical volume, historical weight, historical volume difference and historical weight difference, etc.

[0070] In this embodiment, similar coal panning logs are obtained according to the distribution positions of the coal piles, and the application evaluation values ​​of each historical flight data in the similar coal panning logs are calculated. The historical coal panning efficiency and the historical coal panning accuracy corresponding to the historical flight data can be judged according to the application evaluation values, so as to screen out the optimal flight data for the current distribution position of the coal piles. The 5G communication technology is used to enable the drone to collect real-time images according to the optimal flight data. The control center integrates the real-time image of the coal pile and the three-dimensional GPS information when the image is acquired into the image to obtain point cloud coordinates, constructs an initial three-dimensional model of the coal pile, and calculates the credibility. The accuracy of the initial three-dimensional model of the coal pile is obtained according to the credibility, and it is determined whether to generate a correction instruction to obtain the volume and weight of the coal pile with higher accuracy. Based on the combination of 5G communication technology and drones, it is possible to achieve full-range scanning of the material yard without blind spots, thereby improving the coal panning efficiency and accuracy.

[0071] In some embodiments of the present application, a plurality of similar coal tray logs are obtained according to the distribution of the coal pile, including:

[0072] Acquire the distribution of the coal pile, wherein the distribution includes a first distribution location and a second distribution location;

[0073] comparing the first distribution positioning and the second distribution positioning with the first view and the second view of the three-dimensional model of the historical coal pile in the historical coal pan log of the different coal piles;

[0074] Determine a first similarity coefficient between the first distribution positioning and the plurality of first views and a second similarity coefficient between the second distribution positioning and the plurality of second views according to the comparison result;

[0075] Generate similarity between the current coal pile distribution and the first view and the second view of the plurality of historical coal pile three-dimensional models according to the first similarity coefficient and the second similarity coefficient;

[0076] The historical coal panning logs corresponding to the historical coal pile three-dimensional models having a similarity greater than a preset similarity are selected and set as similar coal panning logs of the current coal pile.

[0077] In this embodiment, the distribution situation refers to the approximate distribution position of the coal pile. The first distribution position is determined based on the front view of the coal pile, and the second distribution position is determined based on the top view of the coal pile. The first view refers to the front view of the three-dimensional model of the historical coal pile, and the second view refers to the top view of the three-dimensional model of the historical coal pile. Similar coal counting logs are selected based on the distribution situation of the coal pile to improve the accuracy of the optimal flight data of subsequent drones, reduce the amount of data processing, and speed up coal counting efficiency.

[0078] In some embodiments of the present application, generating an application evaluation value of historical flight data of a drone based on historical coal pan data in a similar coal pan log includes:

[0079] Preset a first coal pan evaluation index and a second coal pan evaluation index, and calculate a first historical evaluation value of the first coal pan evaluation index and a second historical evaluation value of the second coal pan evaluation index for each similar coal pan log;

[0080] Subtracting the multiple first historical evaluation values, and filtering out the historical coal pan data in two similar coal pan logs corresponding to the first historical evaluation values ​​whose first evaluation value difference is greater than a preset difference threshold, to obtain a first comparison data group;

[0081] Subtracting the plurality of second historical evaluation values, and filtering out historical coal pan data in two similar coal pan logs corresponding to second historical evaluation values ​​whose second evaluation value difference is greater than a preset difference threshold, to obtain a second comparison data group;

[0082] Set a standard coal-collecting duration according to multiple historical coal-collecting durations in similar coal-collecting logs, establish a time reference line based on the standard coal-collecting duration, and set data collection nodes according to preset time intervals;

[0083] Based on multiple data collection nodes, historical coal pan data of multiple first comparison data groups are collected and mapped on a time reference line, and the average difference of the first coal pan data at multiple data collection points of the same historical coal pan data on the corresponding time reference line is calculated;

[0084] Generate the correlation degree between the corresponding historical coal pan data and the first coal pan evaluation index according to the mean value of the difference of the first coal pan data, and set the historical coal pan data with a correlation degree greater than a preset correlation degree as the first correlated coal pan data of the first coal pan evaluation index;

[0085] Based on multiple data collection nodes, historical pan coal data of multiple second comparison data groups are collected and mapped on a time reference line, and the average difference of the second pan coal data at multiple data collection points of the same historical pan coal data on the corresponding time reference line is calculated;

[0086] Generate the correlation degree between the corresponding historical coal pan data and the second coal pan evaluation index according to the mean value of the difference of the second coal pan data, and set the historical coal pan data with a correlation degree greater than a preset correlation degree as the second correlated coal pan data of the second coal pan evaluation index;

[0087] Generate first evaluation values ​​and second evaluation values ​​of the first pan of coal evaluation index and the second pan of coal evaluation index respectively according to the first associated pan of coal data and the second associated pan of coal data in each similar pan of coal log;

[0088] An application evaluation value corresponding to the historical flight data in the similar pan coal log is generated according to the first evaluation value and the second evaluation value.

[0089] In this embodiment, the first coal counting evaluation index refers to the coal counting efficiency, and the second coal counting evaluation index refers to the coal counting accuracy. The first historical evaluation value is calculated based on the weight of the coal pile obtained under the standard coal counting time in similar coal counting logs. The higher the coal counting efficiency, the larger the first historical evaluation value. The second historical evaluation value is calculated based on the difference between the weight or volume of the coal pile obtained by the drone and the actual weight or volume of the coal pile. The higher the coal counting accuracy, the larger the second historical evaluation value.

[0090] In this embodiment, the historical coal pan data of the same first comparison data group are mapped to the same time reference line, and the correlation degree between the historical coal pan data and the first coal pan evaluation index and the second coal pan evaluation index is judged according to the mean value of the difference between the first coal pan data and the second coal pan evaluation index at multiple data acquisition nodes on the time reference line, so as to obtain the first coal pan associated data and the second coal pan associated data, which can accurately evaluate the coal pan efficiency and coal pan accuracy in similar coal pan logs, and lay a data foundation for the subsequent screening of the optimal flight data.

[0091] In some embodiments of the present application, generating an application evaluation value corresponding to historical flight data in a similar pan coal log according to the first evaluation value and the second evaluation value includes:

[0092] Compare the first pan coal associated data in each similar pan coal log with the corresponding first preset standard pan coal data to obtain a first difference absolute value, and set a weight coefficient of the first difference absolute value according to the first pan coal data difference mean of the first pan coal associated data and the first evaluation value difference of the corresponding first comparison data group;

[0093] Generate a first evaluation value according to a plurality of first difference absolute values ​​and a weight coefficient;

[0094] The second pan coal associated data in each similar pan coal log is compared with the corresponding second preset standard pan coal data to obtain a second difference absolute value, and a weight coefficient of the second difference absolute value is set according to the second pan coal data difference mean of the second pan coal associated data and the second evaluation value difference of the corresponding second comparison data group;

[0095] Generate a second evaluation value according to a plurality of second difference absolute values ​​and a weight coefficient;

[0096] Generate an application evaluation value corresponding to the historical flight data in the similar pan coal log according to the first evaluation value and the second evaluation value;

[0097] The calculation formula of the application evaluation value is:

[0098]

[0099] Among them, Y is the application evaluation value, d is the evaluation conversion coefficient, n is the number of the first coal-related data, △P1i is the i-th first difference absolute value, b1i is the weight coefficient of the i-th first difference absolute value, △P2s is the s-th second difference absolute value, b2s is the weight coefficient of the s-th second difference absolute value, m is the number of the second coal-related data, is the first evaluation value, is the second evaluation value.

[0100] In this embodiment, the absolute value of the first difference= ∣The first coal pan associated data - the corresponding first preset standard coal pan data ∣ The weight coefficient of the absolute value of the first difference is set according to the size of the mean value of the first plate of coal data difference of each first plate of coal associated data in the multiple first comparison data groups involved in the same similar coal plate log / the difference of the first evaluation value of the corresponding first comparison data group. When the mean value of the first plate of coal data difference of the first plate of coal associated data / the difference of the first evaluation value of the corresponding first comparison data group is the largest, the weight coefficient is larger.

[0101] In this embodiment, an application evaluation value of historical flight data corresponding to similar coal counting logs is generated based on the first evaluation value and the second evaluation value. Based on the coal counting efficiency evaluation results and the coal counting accuracy evaluation results corresponding to the historical flight data, the optimal flight data of the UAV is subsequently determined to achieve energy-saving coal counting time. The UAV is controlled according to the optimal flight data to further improve the coal counting efficiency and accuracy.

[0102] In some embodiments of the present application, the real-time image is processed and converted into point cloud coordinates, including:

[0103] Classify and process the real-time images according to the flight path in the optimal flight data to obtain directly related real-time images and indirectly related real-time images;

[0104] Judging whether the image overlap, image integrity and image clarity of the corresponding flight path are satisfied at the same time according to the boundary continuity and boundary range of the directly associated real-time image; if not satisfied, reacquiring the real-time image of the corresponding flight path;

[0105] If both conditions are met, it is determined whether the image overlap between the corresponding flight path and the adjacent flight path is met according to the boundary overlap of the indirectly associated real-time image;

[0106] If the conditions are met, a panoramic image of the current coal pile is generated and converted into point cloud coordinates of the current coal pile through professional image analysis software, and an initial three-dimensional model of the coal pile is constructed based on the point cloud coordinates.

[0107] In this embodiment, directly associated real-time images refer to continuous real-time images obtained from the same flight path, and indirectly associated real-time images refer to overlapping real-time images obtained from each flight path and an adjacent flight path.

[0108] In some embodiments of the present application, determining features requiring attention based on real-time images includes:

[0109] Scanning and analyzing the real-time image to determine the structural features of the coal pile expressed by the real-time image, wherein the structural features of the coal pile include an undulating structure and a contour structure of the coal pile;

[0110] Analyze the structural features of the coal pile, determine the protruding structural features, and judge whether the protruding structural features meet the attention requirements. If they meet the requirements, set the protruding structural features as the features that need attention;

[0111] A plane coordinate system is established for the center point of the coal pile, and the plane coordinates of the features that need attention are obtained and converted into three-dimensional coordinates.

[0112] In this embodiment, the center point is determined based on the first distribution positioning and the second distribution positioning, and a plane coordinate system is constructed based on the center point. The attention requirement is that the protrusion degree of the protruding structural feature is greater than a preset protrusion degree threshold. The protrusion degree refers to the relative distance difference between the adjacent structure and the plane coordinate system. The plane coordinates are converted into three-dimensional coordinates according to the seven-parameter model or the UCS transformation method.

[0113] In this embodiment, the features that need attention are determined based on the real-time image and the three-dimensional coordinates of the features that need attention are obtained. The three-dimensional coordinates of the features that need attention are compared with the point cloud coordinates in the initial three-dimensional model of the coal pile to obtain the coordinate difference characteristics of the two, thereby obtaining the credibility to judge the accuracy of the initial three-dimensional model of the coal pile, thereby improving the coal counting accuracy.

[0114] 7. The method for coal handling by drone based on 5G communication technology according to claim 6 is characterized in that the credibility of the initial three-dimensional model of the coal pile is generated according to the comparison result, including:

[0115] The three-dimensional coordinates of the features to be concerned are compared with the point cloud coordinates of the corresponding real-time image conversion in the initial coal pile three-dimensional model to obtain the coordinate difference;

[0116] The credibility of the initial coal pile three-dimensional model is generated according to the comparison results of multiple coordinate difference quantities and the preset coordinate difference quantity threshold.

[0117] In this embodiment, the coordinate difference is obtained based on the Euclidean distance between the three-dimensional coordinates and the point cloud coordinates in space. The difference between the three-dimensional coordinates and the corresponding point cloud coordinates is obtained based on the coordinate difference, thereby judging the accuracy of the initial three-dimensional model of the coal pile and further improving the coal panning accuracy.

[0118] In some embodiments of the present application, the credibility of the initial coal pile three-dimensional model is generated according to the mapping result, including:

[0119] Generate a compensation coefficient according to the reception time and image clarity of the real-time images corresponding to the multiple features requiring attention;

[0120] The credibility of the initial coal pile 3D model generated based on the comparison results and compensation coefficients;

[0121] The calculation formula of the credibility is:

[0122]

[0123] Among them, K is the credibility, u is the number of features that need attention, △Te is the mean value of the coordinate difference of the e-th feature that needs attention, R0 is the standard coordinate difference threshold, and j is the compensation coefficient.

[0124] In this embodiment, the credibility of the initial three-dimensional model of the coal pile is generated based on the coordinate difference between the three-dimensional coordinates of the feature that needs attention and the point cloud coordinates and the compensation coefficient, so as to determine whether to generate a correction instruction, improve the accuracy of the three-dimensional model of the coal pile, and further improve the accuracy of the coal handling by the drone.

[0125] In some embodiments of the present application, judging whether to generate a correction instruction for the initial coal pile three-dimensional model according to the credibility includes:

[0126] Pre-set credibility threshold;

[0127] If the credibility is less than the credibility threshold, a correction instruction is generated for the initial coal pile three-dimensional model, wherein the correction instruction includes screening out the position that needs to be corrected in the initial coal pile three-dimensional model according to the comparison result, and updating the corresponding position in the initial coal pile three-dimensional model according to the coordinate difference in the comparison result, and calculating the credibility of the updated initial coal pile three-dimensional model until the credibility is greater than the preset credibility threshold, setting it as the coal pile three-dimensional model, and calculating the required data of the coal pile according to the coal pile three-dimensional model;

[0128] If the credibility is greater than the credibility threshold, no correction instruction is generated, and the demand data of the coal pile is calculated based on the initial three-dimensional model of the coal pile.

[0129] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and substitutions can be made without departing from the technical principles of the present application. These improvements and substitutions should also be regarded as the scope of protection of the present application.

Claims

1. A method for unmanned aerial vehicle coal handling based on 5G communication technology, characterized in that: include: According to the distribution of coal piles, multiple similar coal pan logs are obtained, and the application evaluation value of the historical flight data of the UAV is generated according to the historical coal pan data in the similar coal pan logs; Filter out the best flight data according to the application evaluation value, and use the UAV to obtain the real-time image of the coal pile according to the best flight data, process the real-time image, and convert it into point cloud coordinates; An initial three-dimensional model of the coal pile is constructed based on the point cloud coordinates, the three-dimensional coordinates of the features to be concerned are determined according to the real-time image, the three-dimensional coordinates are compared with the corresponding point cloud coordinates in the initial three-dimensional model of the coal pile, and the credibility of the initial three-dimensional model of the coal pile is generated according to the comparison results; Whether to generate correction instructions for the initial coal pile three-dimensional model is determined based on the credibility.

2. The method for coal handling by unmanned aerial vehicle based on 5G communication technology as claimed in claim 1, characterized in that: According to the distribution of coal piles, multiple similar coal logs are obtained, including: Acquire the distribution of the coal pile, wherein the distribution includes a first distribution location and a second distribution location; comparing the first distribution positioning and the second distribution positioning with the first view and the second view of the three-dimensional model of the historical coal pile in the historical coal pan log of the different coal piles; Determine a first similarity coefficient between the first distribution positioning and the plurality of first views and a second similarity coefficient between the second distribution positioning and the plurality of second views according to the comparison result; Generate similarity between the current coal pile distribution and the first view and the second view of the plurality of historical coal pile three-dimensional models according to the first similarity coefficient and the second similarity coefficient; The historical coal panning logs corresponding to the historical coal pile three-dimensional models having a similarity greater than a preset similarity are selected and set as similar coal panning logs of the current coal pile.

3. The method for coal handling by unmanned aerial vehicle based on 5G communication technology as claimed in claim 2, characterized in that: The application evaluation value of the historical flight data of the drone is generated based on the historical coal pan data in the similar coal pan log, including: Preset a first coal pan evaluation index and a second coal pan evaluation index, and calculate a first historical evaluation value of the first coal pan evaluation index and a second historical evaluation value of the second coal pan evaluation index for each similar coal pan log; Subtracting the multiple first historical evaluation values, and filtering out the historical coal pan data in two similar coal pan logs corresponding to the first historical evaluation values ​​whose first evaluation value difference is greater than a preset difference threshold, to obtain a first comparison data group; Subtracting the plurality of second historical evaluation values, and filtering out historical coal pan data in two similar coal pan logs corresponding to second historical evaluation values ​​whose second evaluation value difference is greater than a preset difference threshold, to obtain a second comparison data group; Set a standard coal-collecting duration according to multiple historical coal-collecting durations in similar coal-collecting logs, establish a time reference line based on the standard coal-collecting duration, and set data collection nodes according to preset time intervals; Based on multiple data collection nodes, historical coal pan data of multiple first comparison data groups are collected and mapped on a time reference line, and the average difference of the first coal pan data at multiple data collection points of the same historical coal pan data on the corresponding time reference line is calculated; Generate the correlation degree between the corresponding historical coal pan data and the first coal pan evaluation index according to the mean value of the difference of the first coal pan data, and set the historical coal pan data with a correlation degree greater than a preset correlation degree as the first correlated coal pan data of the first coal pan evaluation index; Based on multiple data collection nodes, historical pan coal data of multiple second comparison data groups are collected and mapped on a time reference line, and the average difference of the second pan coal data at multiple data collection points of the same historical pan coal data on the corresponding time reference line is calculated; Generate the correlation degree between the corresponding historical coal pan data and the second coal pan evaluation index according to the mean value of the difference of the second coal pan data, and set the historical coal pan data with a correlation degree greater than a preset correlation degree as the second correlated coal pan data of the second coal pan evaluation index; Generate first evaluation values ​​and second evaluation values ​​of the first pan of coal evaluation index and the second pan of coal evaluation index respectively according to the first associated pan of coal data and the second associated pan of coal data in each similar pan of coal log; An application evaluation value corresponding to the historical flight data in the similar pan coal log is generated according to the first evaluation value and the second evaluation value.

4. The method for coal handling by unmanned aerial vehicle based on 5G communication technology as claimed in claim 3, characterized in that: Generating an application evaluation value of the historical flight data in the similar pan coal log according to the first evaluation value and the second evaluation value, including: Compare the first pan coal associated data in each similar pan coal log with the corresponding first preset standard pan coal data to obtain a first difference absolute value, and set a weight coefficient of the first difference absolute value according to the first pan coal data difference mean of the first pan coal associated data and the first evaluation value difference of the corresponding first comparison data group; Generate a first evaluation value according to a plurality of first difference absolute values ​​and a weight coefficient; The second pan coal associated data in each similar pan coal log is compared with the corresponding second preset standard pan coal data to obtain a second difference absolute value, and a weight coefficient of the second difference absolute value is set according to the second pan coal data difference mean of the second pan coal associated data and the second evaluation value difference of the corresponding second comparison data group; Generate a second evaluation value according to a plurality of second difference absolute values ​​and a weight coefficient; Generate an application evaluation value corresponding to the historical flight data in the similar pan coal log according to the first evaluation value and the second evaluation value; The calculation formula of the application evaluation value is: Among them, Y is the application evaluation value, d is the evaluation conversion coefficient, n is the number of the first coal-related data, △P1i is the i-th first difference absolute value, b1i is the weight coefficient of the i-th first difference absolute value, △P2s is the s-th second difference absolute value, b2s is the weight coefficient of the s-th second difference absolute value, m is the number of the second coal-related data, is the first evaluation value, is the second evaluation value.

5. The method for coal handling by unmanned aerial vehicle based on 5G communication technology as claimed in claim 4, characterized in that: Process the real-time image and convert it into point cloud coordinates, including: Classify and process the real-time images according to the flight path in the optimal flight data to obtain directly related real-time images and indirectly related real-time images; Judging whether the image overlap, image integrity and image clarity of the corresponding flight path are satisfied at the same time according to the boundary continuity and boundary range of the directly associated real-time image; if not satisfied, reacquiring the real-time image of the corresponding flight path; If both conditions are met, it is determined whether the image overlap between the corresponding flight path and the adjacent flight path is met according to the boundary overlap of the indirectly associated real-time image; If the conditions are met, a panoramic image of the current coal pile is generated and converted into point cloud coordinates of the current coal pile through professional image analysis software, and an initial three-dimensional model of the coal pile is constructed based on the point cloud coordinates.

6. The method for coal handling by unmanned aerial vehicle based on 5G communication technology as claimed in claim 5, characterized in that: Identify features of interest based on real-time images, including: Scanning and analyzing the real-time image to determine the structural features of the coal pile expressed by the real-time image, wherein the structural features of the coal pile include an undulating structure and a contour structure of the coal pile; Analyze the structural features of the coal pile, determine the protruding structural features, and judge whether the protruding structural features meet the attention requirements. If they meet the requirements, set the protruding structural features as the features that need attention; A plane coordinate system is established for the center point of the coal pile, and the plane coordinates of the features that need attention are obtained and converted into three-dimensional coordinates.

7. The method for coal handling by unmanned aerial vehicle based on 5G communication technology as claimed in claim 6, characterized in that: The credibility of the initial coal pile 3D model generated based on the comparison results includes: The three-dimensional coordinates of the features to be concerned are compared with the point cloud coordinates of the corresponding real-time image conversion in the initial coal pile three-dimensional model to obtain the coordinate difference; The credibility of the initial coal pile three-dimensional model is generated according to the comparison results of multiple coordinate difference quantities and the preset coordinate difference quantity threshold.

8. The method for coal handling by unmanned aerial vehicle based on 5G communication technology as claimed in claim 7, characterized in that: The credibility of the initial coal pile 3D model generated based on the mapping results includes: Generate a compensation coefficient according to the reception time and image clarity of the real-time images corresponding to the multiple features requiring attention; Credibility of the initial coal pile 3D model generated based on the comparison results and compensation coefficients; The calculation formula of the credibility is: Among them, K is the credibility, u is the number of features that need attention, △Te is the mean value of the coordinate difference of the e-th feature that needs attention, R0 is the standard coordinate difference threshold, and j is the compensation coefficient.

9. The method for coal handling by unmanned aerial vehicle based on 5G communication technology as claimed in claim 8, characterized in that: Determine whether to generate a correction instruction for the initial coal pile three-dimensional model according to the credibility, including: Pre-set credibility threshold; If the credibility is less than the credibility threshold, a correction instruction is generated for the initial coal pile three-dimensional model, wherein the correction instruction includes selecting the position that needs to be corrected in the initial coal pile three-dimensional model according to the comparison result, and updating the corresponding position in the initial coal pile three-dimensional model according to the coordinate difference in the comparison result, and calculating the credibility of the updated initial coal pile three-dimensional model until the credibility is greater than the preset credibility threshold and is set as the coal pile three-dimensional model; If the credibility is greater than the credibility threshold, no correction instruction is generated, and the demand data of the coal pile is calculated based on the initial three-dimensional model of the coal pile.

Images