Coal dumping method and system, computing equipment and medium

Abstract

The invention relates to a coal dumping method and system, computing equipment and a medium. The method comprises the following steps: scanning a coal storage position in a storage yard by using a plurality of laser radars arranged in the storage yard to obtain first point cloud data of the coal storage position; based on the first point cloud data, determining a stacking model of the coal storage position; determining at least one to-be-dumped area based on the accumulation model; and the carrying vehicle is controlled to pour the coal materials to all the to-be-poured areas. According to the method, the carrying vehicle can be controlled to automatically pour the coal in the to-be-poured area, so that operators can be prevented from participating in material pouring and stacking, the danger of material pouring and stacking is reduced, the labor cost is saved, and the safety and economic benefits are improved.

Description

Background Art

[0002] At present, the coal generated by thermal power plants is usually transported to coal collection centers or yards by staff operating electric forklifts for dumping and stacking. However, with the significant improvement in the automation level of thermal power plants, the construction of intelligent power plants and the advancement of centralized control with fewer people and no one on duty, manual dumping and stacking are particularly abrupt, dangerous, and have high labor and training costs. Therefore, whether from the perspective of safety or economic benefits, the dumping and stacking of coal is an issue that needs to be solved urgently.

[0003] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present application, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0004] In order to overcome the problem that traditional coal dumping and stacking requires manual labor, resulting in low safety and economic benefits, the present invention provides a coal dumping method, system, computing equipment and medium.

[0005] In a first aspect, in order to solve the above technical problems, the present invention provides a method for dumping coal, comprising:

[0006] Scanning the coal storage location in the stockpile using a plurality of laser radars disposed in the stockpile to obtain first point cloud data of the coal storage location;

[0007] Determining a stacking model of the coal storage location based on the first point cloud data;

[0008] Based on the accumulation model, determining at least one area to be dumped;

[0009] Control the transport vehicle to dump the coal to various dumping areas.

[0010] In a second aspect, in order to solve the above technical problems, the present invention provides a coal dumping system, comprising:

[0011] An acquisition module, configured to scan the coal storage locations in the stockpile using a plurality of laser radars arranged in the stockpile to obtain first point cloud data of the coal storage locations;

[0012] A model determination module, used to determine a stacking model of the coal storage location based on the first point cloud data;

[0013] An area determination model, used to determine at least one area to be dumped based on the accumulation model;

[0014] The coal dumping module is used to control the transport vehicle to dump the coal to various dumping areas.

[0015] In a third aspect, in order to solve the above-mentioned technical problem, the present invention provides a computing device, including a memory, a processor, and a program stored in the memory and running on the processor, and when the processor executes the program, the steps of a coal dumping method as described above are implemented.

[0016] In a fourth aspect, in order to solve the above-mentioned technical problem, the present invention provides a computer-readable storage medium, in which instructions are stored. When the instructions are executed on a terminal device, the terminal device executes the steps of a coal dumping method as described above.

[0017] The beneficial effects of the present invention are as follows: a laser radar is arranged in the stockpile to scan the coal storage location in the stockpile to obtain the first point cloud data, and the stacking model of the coal storage location is determined based on the first point cloud data. Thus, the stacking situation of the coal in the coal storage location can be intuitively known. Then, the area where the coal needs to be dumped is determined according to the stacking situation of the coal in the coal storage location. In this way, by determining the stacking model of the coal storage location and thereby determining the area where the coal needs to be dumped, the transport truck can automatically dump the coal in the area to be dumped, thereby reducing the participation of operators in the dumping and stacking, thereby reducing the danger of dumping and stacking, saving labor costs, and improving safety and economic benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic flow chart of a coal dumping method provided by the present invention;

[0019] Figure 2 A schematic diagram of a storage yard provided by the present invention;

[0020] Figure 3 A schematic diagram of an embodiment provided by the present invention;

[0021] Figure 4 A top view of a stacking model provided by the present invention;

[0022] Figure 5 A schematic structural diagram of a coal dumping system provided by the present invention. DETAILED DESCRIPTION

[0023] The principles and features of the present invention are described below. The examples given are only used to explain the present invention and are not used to limit the scope of the present invention.

[0024] A method, system, computing device and medium for dumping coal according to an embodiment of the present invention will be described below in conjunction with the accompanying drawings.

[0025] The coal dumping method provided in the embodiment of the present disclosure is applied to an electronic device. The electronic device can be connected to the Internet to communicate with a laser radar, a transport vehicle, etc. In some embodiments, the electronic device is, for example, a computer or a server.

[0026] like Figure 1 As shown, the present invention provides a method for dumping coal, comprising:

[0027] Step S101, using multiple laser radars arranged in the stockpile to scan the coal storage locations in the stockpile to obtain first point cloud data of the coal storage locations.

[0028] Combination Figure 2 As shown, Figure 2 A schematic diagram of a stockpile is provided. The laser radar is set on the inner wall of the stockpile, and the scanning range of multiple laser radars can cover the coal storage position of the entire stockpile. Figure 3 As shown, Figure 3 An embodiment is provided. Figure 3 There are multiple coal storage locations in the middle yard for storing coal. Two groups of laser radars are set in the yard, such as laser radar 1 and laser radar 2, and each group of laser radars is responsible for detecting four coal storage locations.

[0029] Step S102: determining a coal storage accumulation model based on the first point cloud data.

[0030] Step S103: determining at least one area to be dumped based on the accumulation model.

[0031] Step S104, controlling the transport vehicle to dump the coal into various dumping areas.

[0032] In some embodiments, the transport vehicle is an AGV (Automated Guided Vehicle, transport robot).

[0033] A method for dumping coal provided by an embodiment of the present disclosure is adopted, in which a laser radar arranged in a stockpile is used to scan the coal storage location in the stockpile to obtain first point cloud data, and a stacking model of the coal storage location is determined based on the first point cloud data. Thus, the stacking situation of the coal in the coal storage location can be intuitively known. Then, the area where the coal needs to be dumped is determined according to the stacking situation of the coal in the coal storage location. In this way, by determining the stacking model of the coal storage location and thereby determining the area where the coal needs to be dumped, so that the transport truck can automatically dump the coal in the area to be dumped, the participation of operators in the dumping and stacking can be reduced, thereby reducing the danger of the dumping and stacking, saving labor costs, and improving safety and economic benefits.

[0034] Preferably, a camera is also provided in the stockpile yard, and the camera is used to take images of the coal storage location. Based on the first point cloud data, the stacking model of the coal storage location is determined, including: obtaining a stacking image of the coal storage location, and determining the stacking type of the coal in the coal storage location based on the stacking image; determining a target segmentation algorithm based on the stacking type, and using the target segmentation algorithm to process the first point cloud data to obtain second point cloud data; performing three-dimensional reconstruction of the coal storage location based on the second point cloud data to obtain a stacking model of the coal storage location. The second point cloud data represents the point cloud data corresponding to the coal pile in the coal storage location.

[0035] The coal pile forms are different, and there will be some differences in the segmentation algorithm when processing the first point cloud data, so that the coal pile point cloud in the coal storage location can be accurately segmented and extracted from the first point cloud data. In this way, the accumulation type is determined based on the accumulation image of the coal storage location and the corresponding target segmentation algorithm is selected to segment and extract the first point cloud data, so that the coal pile point cloud in the coal storage location can be accurately segmented and extracted from the first point cloud data, so that the accumulation model of the coal storage location can be more accurately reconstructed based on the point cloud data of the coal pile.

[0036] In some embodiments, the stacking type includes a single coal pile and multiple coal piles. A single coal pile indicates that the coal pile in the coal storage location is in the form of an independent coal pile. Multiple coal piles indicate that the coal pile in the coal storage location is in the form of multiple independent coal piles.

[0037] Preferably, determining the accumulation type of coal in the coal storage location based on the accumulation image includes: inputting the accumulation image into a preset target detection model to obtain the accumulation type of the coal pile in the coal storage location output by the detection model.

[0038] In this way, the preset target detection model is used to identify the accumulation image, so that the accumulation type of the coal can be determined more accurately.

[0039] In some embodiments, the preset target detection models include Faster R-CNN, SSD, and YOLO, etc.

[0040] Preferably, determining the target segmentation algorithm based on the stacking type includes: using the stacking type to perform a search operation in a preset data table to find an alternative segmentation algorithm corresponding to the stacking type as the target segmentation algorithm; wherein the preset data table stores the correspondence between the stacking type and the alternative segmentation algorithm.

[0041] In this way, by looking up the table in the stacking type, the target segmentation algorithm can be quickly determined with high efficiency.

[0042] In some embodiments, when the stacking type is a single coal pile, the corresponding candidate segmentation algorithm is a RANSAC-normal constraint algorithm, also known as a RANSAC algorithm and a normal constraint algorithm. When the stacking type is multiple coal piles, the corresponding segmentation algorithm is a Euclidean distance clustering segmentation algorithm.

[0043] Preferably, the accumulation type includes a single pile of coal, and the target segmentation algorithms corresponding to the single independent coal pile are the RANSAC algorithm and the normal constraint algorithm; the first point cloud data is processed by using the target segmentation algorithm to obtain the second point cloud data, including: performing plane fitting processing on the first point cloud data based on the RANSAC algorithm to obtain plane point cloud data; obtaining the normals of each fitting plane in the plane point cloud data based on the normal constraint algorithm, and determining the normal components of each normal in the Z axis, determining the normals whose normal components do not meet the normal threshold requirements as noise normals, and determining the fitting planes corresponding to the noise normals as noise planes; filtering the point cloud data corresponding to the noise planes in the plane point cloud data to obtain the second point cloud data.

[0044] It can be understood that the coordinate system of the plane point cloud data is an XYZ coordinate system. The Z axis is the Z axis in the plane point cloud data coordinate system. That is, in this embodiment, the Z axis is the corresponding axis in the vertical direction along the side wall (not the top wall) of the storage yard.

[0045] When the coal in the coal storage location presents a separate coal pile, it is easy to regard the ground as part of the coal when performing point cloud segmentation. However, the ground of the yard is very large, and usually multiple coal storage locations are set up in the yard.

[0046] Therefore, when performing point cloud segmentation and extraction, removing the point cloud noise on the ground can make the obtained coal storage location accumulation model more accurate. The RANSAC (RANdom SAmple Consensus) algorithm is used to perform plane fitting on the first point cloud data to obtain plane point cloud data. At this time, the plane point cloud data includes the ground and inner wall of the stockpile. The planes in the plane point cloud data constitute an irregular stockpile body, so the planes that usually enclose the irregular stockpile body are not vertical or horizontal planes. However, the ground of the stockpile is a horizontal plane, and the inner wall of the stockpile is a vertical plane. The normal component of the horizontal plane on the Z axis is 1, and the normal component of the vertical plane on the Z axis is 0. In this way, by determining the normal component of each fitting plane in the plane point cloud data on the Z axis, if the normal component is close to 1 or close to 0, it means that the plane corresponding to the normal is very likely to be the ground or inner wall of the stockpile, that is, the noise plane. The point cloud corresponding to the noise plane is filtered from the plane point cloud data, so that the point cloud data corresponding to the coal pile in the coal storage location can be obtained more accurately.

[0047] In some embodiments, the normal threshold requirement includes a normal component of 1 or a normal component of 0.

[0048] Preferably, the accumulation type includes multiple piles of coal; the target segmentation algorithm corresponding to the multiple piles of coal is a Euclidean distance clustering segmentation algorithm. The first point cloud data is processed using the target segmentation algorithm to obtain the second point cloud data, including: clustering the first point cloud data based on the Euclidean distance clustering segmentation algorithm to obtain multiple cluster sets; extracting all point clouds in each cluster set respectively to obtain third point cloud data corresponding to each cluster set; and determining the set of all third point cloud data as the second point cloud data.

[0049] When the coal in the coal storage location is presented as multiple separate coal piles, each coal pile exists independently, and the Euclidean distance clustering segmentation algorithm can more accurately extract the point cloud corresponding to each coal pile in the coal storage location. After the Euclidean distance clustering segmentation algorithm performs clustering processing on the first point cloud data, each cluster set is obtained, which is each separate coal pile. At this time, the second point cloud data includes a set of point cloud data of multiple separate coal piles.

[0050] Preferably, three-dimensional reconstruction of the coal storage location is performed based on the second point cloud data to obtain a stacking model of the coal storage location, including: acquiring ground point cloud data of the coal storage location as third point cloud data, and performing three-dimensional reconstruction of the coal storage location based on the second point cloud data and the third point cloud data to obtain the stacking model of the coal storage location.

[0051] Since the second point cloud data represents the point cloud data of the coal in the coal storage location, the coal in the coal storage location will not always cover the entire coal storage location at the first time. Therefore, by acquiring the third point cloud data of the ground of the coal storage location and performing three-dimensional reconstruction based on the second point cloud data and the third point cloud data, a real-time accumulation model of the coal storage location can be obtained, so as to control the transport vehicle to dump the coal.

[0052] Preferably, based on the accumulation model, at least one area to be dumped is determined, including: dividing the surface of the accumulation model into multiple sub-planes, and determining the average height of each sub-plane respectively; if the first height difference between the maximum average height and the minimum average height is less than or equal to the preset first height threshold, all sub-planes are used as planes to be dumped; if the first height difference is greater than the preset first height threshold, the second height difference between each average height and the maximum average height is determined, and the sub-plane corresponding to the second height difference greater than the preset second height threshold is used as the plane to be dumped; and the area corresponding to each plane to be dumped is determined as the area to be dumped. Wherein, the preset first height threshold is less than the preset second height threshold.

[0053] If the height difference between the maximum average height and the minimum average height is less than or equal to the preset first height threshold, it means that the height difference between each sub-plane is small, that is, the coal is piled up relatively flat on the coal storage position at this time. The transport truck can dump the coal into the area corresponding to any sub-plane. If the height difference between the maximum average height and the minimum average height is greater than the preset first height threshold, it means that there is a sub-plane with a large height difference, that is, the coal accumulation in the coal storage position is not flat at this time. Then, by obtaining the second height difference between the average height of each sub-plane and the maximum average height, when the second height difference is greater than the preset second height threshold, it means that the height of the corresponding sub-plane is lower, and the transport truck can preferentially dump the coal into the area corresponding to the sub-plane.

[0054] In this way, by determining the first height difference, it can be determined whether the coal is relatively flatly piled on the coal storage position. If so, the transport vehicle can dump the coal in the area corresponding to any sub-plane in turn, so as to achieve reasonable stacking of coal, reduce the area occupied by coal in the coal storage position in the stockpile, and improve the storage rate of the coal storage position. If not, by calculating the second height difference, it is determined that the area corresponding to the sub-plane with a lower height in the coal storage position is the area to be dumped, and the transport vehicle can dump the coal in each area to be dumped in turn to achieve reasonable stacking of coal, reduce the area occupied by coal in the coal storage position in the stockpile, and improve the storage rate of the coal storage position.

[0055] It can be understood that the surface of the stacking model represents the collection of various faces of various inner walls of the stacking yard except the stacking yard ground. Figure 4 As shown, Figure 4 A top view of a stacking model is provided. Figure 4 The area surrounded by ABCD is a coal storage location. The coal storage location includes a first coal pile and a second coal pile, and an empty area except for the first coal pile and the second coal pile, in which no coal is accumulated. The surface of the accumulation model in this embodiment includes the top surface 1 and the side surface 1 of the first coal pile, the top surface 2 and the side surface 2 of the second coal pile, and the upper surface 3 of the empty area.

[0056] Further, determining the average height of each sub-plane includes: for each sub-plane, obtaining height values ​​of multiple points in the sub-plane, and calculating an average value of the height values ​​of the multiple points as the average height of the sub-plane.

[0057] In some embodiments, controlling the transport vehicle to dump the coal to each area to be dumped includes: if the first height difference is less than or equal to the preset first height threshold, controlling the transport vehicle to dump the coal to each area to be dumped in turn. And / or, if the first height difference is greater than the preset first height threshold, the average heights of each plane to be dumped are arranged in order, and the transport vehicle is controlled to dump the coal to each area to be dumped in order from low to high in average height. In this way, the transport vehicle is controlled to dump the coal in order from low to high in average height, so that reasonable stacking of the coal can be achieved. It can be understood that the transport vehicle dumps the coal to each area to be dumped in turn or in sequence means that the transport vehicle dumps all the coal it carries to one area to be dumped, and then carries new coal for the next dumping, thereby achieving dumping in turn or in sequence.

[0058] In other embodiments, controlling the transport truck to dump the coal into various areas to be dumped includes: after controlling the transport truck to dump the coal into an area to be dumped, re-determining the stacking model of the coal storage position, determining a new area to be dumped, and controlling the transport truck to dump the coal into a new area to be dumped. When the transport truck dumps the coal into an area to be dumped once, the stacking model will inevitably change, thereby generating a new area to be dumped. Therefore, after the transport truck completes a dumping, by re-determining the new area to be dumped, the transport truck can dump the coal according to the real-time stacking situation of the coal storage position, so as to achieve reasonable stacking of the coal.

[0059] In other embodiments, controlling the transport vehicle to dump the coal into each area to be dumped includes: after controlling the transport vehicle to dump the coal into all areas to be dumped in sequence, re-determining the stacking model of the coal storage position, determining a new area to be dumped, and controlling the transport vehicle to dump the coal into each new area to be dumped. In this way, after controlling the transport vehicle to dump the coal into all current areas to be dumped in sequence, a new area to be dumped is determined, thereby improving the dumping efficiency.

[0060] In other embodiments, controlling the transport truck to dump coal into each area to be dumped includes: determining the area to be dumped that the transport truck is pointing to, and prohibiting other transport trucks from dumping coal into the area to be dumped before the transport truck completes dumping the coal into the area to be dumped. In this way, when a dumping area is occupied by a transport truck, other transport trucks are prohibited from dumping coal, thereby reducing collisions between transport trucks and further improving the safety of coal dumping.

[0061] like Figure 5As shown, the present invention provides a coal dumping system, including: an acquisition module, a model determination module, an area determination model and a coal dumping module. Among them, the acquisition module is used to use multiple laser radars arranged in the yard to scan the coal storage locations in the yard to obtain the first point cloud data of the coal storage locations. The model determination module is used to determine the stacking model of the coal storage locations based on the first point cloud data. The area determination model is used to determine at least one area to be dumped based on the stacking model. The coal dumping module is used to control the transport vehicle to dump the coal to each area to be dumped.

[0062] A coal dumping system provided by an embodiment of the present disclosure is adopted. A laser radar arranged in the stockpile is used to scan the coal storage location in the stockpile to obtain first point cloud data, and a stacking model of the coal storage location is determined based on the first point cloud data. Thus, the stacking situation of the coal in the coal storage location can be intuitively known. Then, the area where the coal needs to be dumped is determined according to the stacking situation of the coal in the coal storage location. In this way, by determining the stacking model of the coal storage location and thereby determining the area where the coal needs to be dumped, the transport truck can automatically dump the coal in the area to be dumped, thereby reducing the participation of operators in the dumping and stacking, thereby reducing the danger of the dumping and stacking, saving labor costs, and improving safety and economic benefits.

[0063] Preferably, the model determination module is specifically used to obtain a stacking image of a coal storage location, and determine the stacking type of coal in the coal storage location based on the stacking image; determine a target segmentation algorithm based on the stacking type, and use the target segmentation algorithm to process the first point cloud data to obtain second point cloud data; perform three-dimensional reconstruction of the coal storage location based on the second point cloud data to obtain a stacking model of the coal storage location.

[0064] Preferably, the model determination module is specifically used to input the accumulation image into a preset target detection model to obtain the accumulation type of the coal pile in the coal storage location output by the detection model.

[0065] Preferably, the model determination module is specifically used to perform a search operation in a preset data table using the stacking type to find an alternative segmentation algorithm corresponding to the stacking type as the target segmentation algorithm; wherein the preset data table stores the correspondence between the stacking type and the alternative segmentation algorithm.

[0066] Preferably, the accumulation type includes a single pile of coal, and the target segmentation algorithm corresponding to the single pile of coal is the RANSAC algorithm and the normal constraint algorithm. The model determination module is specifically used to perform plane fitting processing on the first point cloud data based on the RANSAC algorithm to obtain plane point cloud data; obtain the normals of each fitting plane in the plane point cloud data based on the normal constraint algorithm, and determine the normal components of each normal in the Z axis, determine the normal whose normal component meets the normal threshold requirement as the noise normal, and determine the fitting plane corresponding to the noise normal as the noise plane; filter the point cloud data corresponding to the noise plane in the plane point cloud data to obtain the second point cloud data.

[0067] Preferably, the accumulation type includes multiple piles of coal; the target segmentation algorithm corresponding to the multiple piles of coal is the Euclidean distance clustering segmentation algorithm. The model determination module is specifically used to perform clustering processing on the first point cloud data based on the Euclidean distance clustering segmentation algorithm to obtain multiple cluster sets; extract all point clouds in each cluster set respectively to obtain third point cloud data corresponding to each cluster set; and determine the set of all third point cloud data as the second point cloud data.

[0068] Preferably, the area determination model is specifically used to divide the surface of the accumulation model into multiple sub-planes, and determine the average height of each sub-plane respectively; if the first height difference between the maximum average height and the minimum average height is less than or equal to the preset first height threshold, all sub-planes are used as planes to be dumped; if the first height difference is greater than the preset first height threshold, the second height difference between each average height and the maximum average height is determined, and the sub-plane corresponding to the second height difference greater than the preset second height threshold is used as the plane to be dumped; the area corresponding to each plane to be dumped is respectively determined as the area to be dumped.

[0069] A computing device according to an embodiment of the present invention includes a memory, a processor, and a program stored in the memory and running on the processor. When the processor executes the program, part or all of the steps of the above-mentioned coal dumping method are implemented.

[0070] Among them, the computing device can be a computer, and correspondingly, its program is computer software. The above-mentioned parameters and steps in a computing device of the present invention can refer to the parameters and steps in an embodiment of a coal dumping method mentioned above, and will not be repeated here.

[0071] In an embodiment of the present invention, a computer-readable storage medium is provided, in which instructions are stored. When the instructions are executed, the steps of the above-mentioned method for dumping coal are executed.

[0072] The computer-readable storage medium may be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.

[0073] The technical solution of the embodiment of the present disclosure can be embodied in the form of a software product, which is stored in a storage medium and includes one or more instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method of the embodiment of the present disclosure. The aforementioned computer-readable storage medium may be a non-transitory computer-readable storage medium, including: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes, or a transient computer-readable storage medium.

[0074] Those skilled in the art know that the present invention can be implemented as a system, method or computer program product. Therefore, the present disclosure can be specifically implemented in the following forms, namely: it can be complete hardware, it can be complete software (including firmware, resident software, microcode, etc.), or it can be a combination of hardware and software, generally referred to as "circuit", "module" or "system" herein. In addition, in some embodiments, the present invention can also be implemented in the form of a computer program product in one or more computer-readable media, and the computer-readable medium contains computer-readable program code. Computer-readable storage media can be, for example, but not limited to - electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above.

[0075] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0076] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A method for dumping coal, characterized in that: include: Scanning the coal storage location in the stockpile using a plurality of laser radars arranged in the stockpile to obtain first point cloud data of the coal storage location; Determining a stacking model of the coal storage location based on the first point cloud data; Based on the accumulation model, determining at least one area to be dumped; Control the transport vehicle to dump the coal to various dumping areas.

2. The method according to claim 1, characterized in that The step of determining the accumulation model of the coal storage location based on the first point cloud data includes: Acquiring a stacking image of the coal storage location, and determining a stacking type of coal in the coal storage location based on the stacking image; Determining a target segmentation algorithm based on the accumulation type, and processing the first point cloud data using the target segmentation algorithm to obtain second point cloud data; The coal storage location is three-dimensionally reconstructed based on the second point cloud data to obtain a stacking model of the coal storage location.

3. The method according to claim 2, characterized in that The determining the accumulation type of coal in the coal storage location based on the accumulation image includes: The accumulation image is input into a preset target detection model to obtain the accumulation type of the coal pile in the coal storage location output by the detection model.

4. The method according to claim 2, characterized in that: The determining of the target segmentation algorithm based on the accumulation type comprises: The stacking type is used to perform a search operation in a preset data table to find out an alternative segmentation algorithm corresponding to the stacking type as a target segmentation algorithm; wherein the preset data table stores a corresponding relationship between the stacking type and the alternative segmentation algorithm.

5. The method according to claim 2, characterized in that: The stacking type includes a single pile of coal, and the target segmentation algorithm corresponding to the single pile of coal is a RANSAC algorithm and a normal constraint algorithm; and the processing of the first point cloud data by using the target segmentation algorithm to obtain the second point cloud data includes: Performing plane fitting processing on the first point cloud data based on the RANSAC algorithm to obtain plane point cloud data; Based on the normal constraint algorithm, the normals of each fitting plane in the planar point cloud data are obtained, and the normal components of each normal on the Z axis are determined, and the normals whose normal components meet the normal threshold requirements are determined as noise normals, and the fitting planes corresponding to the noise normals are determined as noise planes; The point cloud data corresponding to the noise plane in the plane point cloud data is filtered to obtain the second point cloud data.

6. The method according to claim 2, characterized in that The accumulation type includes multiple piles of coal; the target segmentation algorithm corresponding to the multiple piles of coal is a Euclidean distance clustering segmentation algorithm; The step of processing the first point cloud data by using the target segmentation algorithm to obtain second point cloud data includes: Performing clustering processing on the first point cloud data based on the Euclidean distance clustering segmentation algorithm to obtain multiple cluster sets; Extract all point clouds in each cluster set respectively to obtain the third point cloud data corresponding to each cluster set; A set of all third point cloud data is determined as second point cloud data.

7. The method according to any one of claims 1 to 6, characterized in that: The step of determining at least one area to be dumped based on the accumulation model comprises: Dividing the surface of the stacking model into a plurality of sub-planes, and determining the average height of each sub-plane respectively; If a first height difference between the maximum average height and the minimum average height is less than or equal to a preset first height threshold, all sub-planes are taken as planes to be dumped; If the first height difference is greater than the preset first height threshold, determine the second height difference between each average height and the maximum average height, and use the sub-plane corresponding to the second height difference greater than the preset second height threshold as the plane to be dumped; The areas corresponding to the planes to be dumped are respectively determined as areas to be dumped.

8. A coal dumping system, characterized in that: include: An acquisition module, configured to scan the coal storage locations in the stockpile using a plurality of laser radars arranged in the stockpile to obtain first point cloud data of the coal storage locations; A model determination module, used to determine a stacking model of the coal storage location based on the first point cloud data; An area determination model, used to determine at least one area to be dumped based on the accumulation model; The coal dumping module is used to control the transport vehicle to dump the coal to various dumping areas.

9. A computing device comprising a memory, a processor, and a program stored in the memory and running on the processor, characterized in that: When the processor executes the program, the steps of a coal dumping method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed on a terminal device, the terminal device executes the steps of a coal dumping method as claimed in any one of claims 1 to 7.

Images