Digital twin photovoltaic string modeling method, system, equipment and medium

Abstract

The invention discloses a digital twin photovoltaic string modeling method, system, equipment and medium, and particularly relates to the technical field of digital modeling, and the technical key points are as follows: obtaining a photovoltaic power station image, carrying out the detection and recognition of a plurality of photovoltaic strings in the photovoltaic power station image through a photovoltaic string recognition model, and carrying out the recognition of the plurality of photovoltaic strings in the photovoltaic power station image; physical parameters and multiple pieces of position point information of each photovoltaic string are obtained, the physical parameters comprise the size of the photovoltaic string and the angle of the photovoltaic string, and the multiple pieces of position point information comprise GPS data of four corner position points and GPS data of a center point; based on the obtained physical parameters of each photovoltaic string and the information of the plurality of position points, constructing a photovoltaic string three-dimensional model on a digital twin platform; and based on the information of the plurality of position points of each photovoltaic string, extracting a photovoltaic string image from the photovoltaic power station image, and performing mapping synthesis on the extracted photovoltaic string image and the photovoltaic string three-dimensional model to obtain a synthesized photovoltaic string three-dimensional model.

Description

Technical Field

[0001] The present invention relates to the field of digital modeling technology, and in particular to a digital twin photovoltaic string modeling method, system, equipment and medium. Background Art

[0002] Photovoltaic strings are an important part of photovoltaic power generation systems. They are formed by connecting multiple photovoltaic modules (solar panels) in series to form a unit. For example, in a typical small photovoltaic system, 10-20 photovoltaic modules may be connected in series to form a photovoltaic string. This series connection method makes the current in the string consistent, and the voltage is the sum of the voltages of each photovoltaic module.

[0003] At present, the digital twin modeling of photovoltaic power stations is costly and time-consuming. The main difficulty lies in the need to sample and model thousands of photovoltaic strings, and to accurately create and deploy them in the digital twin three-dimensional scene according to the CAD construction drawings, which requires a lot of manpower. At the same time, in the specific implementation process, the CAD construction drawings of many power stations are not the same as the actual physical layout, and there are not even CAD drawings to refer to.

[0004] Therefore, the present invention aims to provide a digital twin photovoltaic string modeling method, system, device and medium to solve the above-mentioned related problems. Summary of the invention

[0005] The technical problem to be solved by the present invention is that due to the accuracy or non-standardization of CAD construction drawings in the prior art, it is difficult to accurately restore the layout of photovoltaic strings in the digital twin scene. The purpose is to provide a digital twin photovoltaic string modeling method, system, equipment and medium, which collect images of photovoltaic power stations by drones, and use photovoltaic string recognition models to identify multiple photovoltaic strings in the photovoltaic power station images to obtain physical parameters and multiple location point information of each photovoltaic string; then, based on the obtained physical parameters of each photovoltaic string and multiple location point information, a three-dimensional model of the photovoltaic string is constructed on the digital twin platform, thereby completing the synthesis, creation and accurate deployment of the three-dimensional model of the photovoltaic string in the digital twin scene without the need for CAD construction drawings, saving a lot of manpower development and proofreading costs.

[0006] The present invention is achieved through the following technical solutions:

[0007] A digital twin photovoltaic string modeling method, the method comprising:

[0008] Acquire a photovoltaic power station image, use a photovoltaic string recognition model to detect and recognize multiple photovoltaic strings in the photovoltaic power station image, and obtain physical parameters of each photovoltaic string and multiple location point information, wherein the physical parameters include photovoltaic string size and photovoltaic string angle, and the multiple location point information includes four corner position point GPS data and center point GPS data;

[0009] Based on the obtained physical parameters of each PV string and multiple location point information, a 3D model of the PV string is constructed on the digital twin platform;

[0010] Based on the information of multiple location points of each photovoltaic string, the photovoltaic string image is extracted from the photovoltaic power station image, and the extracted photovoltaic string image is combined with the photovoltaic string three-dimensional model to obtain the synthesized photovoltaic string three-dimensional model.

[0011] Furthermore, the photovoltaic power station image is obtained, specifically:

[0012] Using a drone with high-precision GPS and a high-resolution camera, multiple local images of the photovoltaic power station are captured above the photovoltaic power station. The photovoltaic power station image is obtained after image correction, image enhancement and image stitching of the multiple local images; at the same time, the drone GPS data, flight parameters and camera parameters are recorded.

[0013] Furthermore, the photovoltaic string recognition model is used to detect and identify multiple photovoltaic strings in the photovoltaic power station image, and the physical parameters of each photovoltaic string and multiple location point information are obtained respectively. The photovoltaic string recognition model is obtained by training the Mask R-CNN deep learning network, specifically:

[0014] The photovoltaic string recognition model is used to identify the four corner positions of each photovoltaic string in the photovoltaic power station image, and the GPS data of the four corner positions is calculated using the drone GPS data, camera parameters and flight parameters. The GPS data of the center point of each photovoltaic string is then calculated using the GPS data of the four corner positions.

[0015] Based on the parameters of the drone and the camera, combined with the GPS data of the four corner positions, the PV string size of each PV string is calculated;

[0016] Based on the drone parameters and the image position data of each photovoltaic string in the photovoltaic power station image, the photovoltaic string angle of each photovoltaic string is calculated.

[0017] Furthermore, the GPS data of the four corner positions are calculated using the drone GPS data, camera parameters and flight parameters, specifically:

[0018] The horizontal and vertical field of view angles of the camera at the flight altitude of the drone are calculated using the drone GPS data, camera parameters, and flight parameters. The drone GPS data includes the drone latitude and longitude and the drone altitude.

[0019] Obtain image position data of each photovoltaic string in the photovoltaic power station image, and calculate the image pixel coordinates of the center point of each photovoltaic string;

[0020] According to the camera parameters and the horizontal and vertical field of view angles of the camera at the UAV's flight altitude, the three-dimensional coordinate data of the center point of each photovoltaic string at the UAV's flight altitude is calculated;

[0021] The GPS data of the four corner positions of each photovoltaic string are calculated using the three-dimensional coordinate data of the center point of each photovoltaic string and the drone GPS data.

[0022] The present invention also provides a digital twin photovoltaic string modeling system, which is used in any one of the digital twin photovoltaic string modeling methods described above, and the system includes:

[0023] The first module is used to obtain a photovoltaic power station image, detect and identify multiple photovoltaic strings in the photovoltaic power station image using a photovoltaic string recognition model, and obtain physical parameters of each photovoltaic string and multiple location point information, wherein the physical parameters include photovoltaic string size and photovoltaic string angle, and the multiple location point information includes four corner position point GPS data and center point GPS data;

[0024] The second module is used to build a three-dimensional model of the photovoltaic string on the digital twin platform based on the obtained physical parameters of each photovoltaic string and multiple location point information;

[0025] The third module is used to extract the photovoltaic string image from the photovoltaic power station image based on the multiple location point information of each photovoltaic string, and to perform mapping synthesis on the extracted photovoltaic string image and the photovoltaic string three-dimensional model to obtain the synthesized photovoltaic string three-dimensional model.

[0026] Furthermore, the photovoltaic power station image is obtained, specifically:

[0027] Using a drone with high-precision GPS and a high-resolution camera, multiple local images of the photovoltaic power station are captured above the photovoltaic power station. The photovoltaic power station image is obtained after image correction, image enhancement and image stitching of the multiple local images; at the same time, the drone GPS data, flight parameters and camera parameters are recorded.

[0028] Furthermore, the photovoltaic string recognition model is used to detect and identify multiple photovoltaic strings in the photovoltaic power station image, and the physical parameters of each photovoltaic string and multiple location point information are obtained respectively. The photovoltaic string recognition model is obtained by training the Mask R-CNN deep learning network, specifically:

[0029] The photovoltaic string recognition model is used to identify the four corner positions of each photovoltaic string in the photovoltaic power station image, and the GPS data of the four corner positions is calculated using the drone GPS data, camera parameters and flight parameters. The GPS data of the center point of each photovoltaic string is then calculated using the GPS data of the four corner positions.

[0030] Based on the parameters of the drone and the camera, combined with the GPS data of the four corner positions, the PV string size of each PV string is calculated;

[0031] Based on the drone parameters and the image position data of each photovoltaic string in the photovoltaic power station image, the photovoltaic string angle of each photovoltaic string is calculated.

[0032] The present invention also provides a computer device, comprising a system memory and a processor, wherein the system memory stores a computer program, and the processor implements the steps of any one of the above-mentioned methods when executing the computer program.

[0033] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any one of the methods described above are implemented.

[0034] The present invention also provides a computer program product comprising instructions, and when the instructions are executed by a computer device cluster, the computer device cluster executes any of the above methods.

[0035] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0036] In the present invention, images of photovoltaic power stations are collected by drones, and a photovoltaic string recognition model is used to identify multiple photovoltaic strings in the photovoltaic power station image to obtain physical parameters and multiple location point information of each photovoltaic string; then, based on the obtained physical parameters of each photovoltaic string and multiple location point information, a three-dimensional model of the photovoltaic string is constructed on the digital twin platform, thereby completing the synthesis, creation, and accurate deployment of the three-dimensional model of the photovoltaic string into the digital twin scene without the need for CAD construction drawings, thereby saving a lot of manpower development and proofreading costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without creative work. In the drawings:

[0038] Figure 1 is a method flow chart of a digital twin photovoltaic string modeling method in this embodiment;

[0039] Figure 2 This is a schematic diagram of module connections of a digital twin photovoltaic string modeling system in this embodiment;

[0040] Figure 3 A schematic diagram of the structure of a computer device. DETAILED DESCRIPTION

[0041] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0042] In the present disclosure, unless otherwise specified, the use of the terms "first", "second", etc. to describe various elements is not intended to limit the positional relationship, timing relationship, or importance relationship of these elements, and such terms are only used to distinguish one element from another element. In some examples, the first element and the second element may refer to the same instance of the element, and in some cases, based on the description of the context, they may also refer to different instances.

[0043] The terms used in the description of various examples in this disclosure are only for the purpose of describing specific examples and are not intended to be limiting. Unless the context clearly indicates otherwise, if the number of elements is not specifically limited, the element can be one or more. In addition, the term "and / or" used in this disclosure covers any one of the listed items and all possible combinations.

[0044] Example 1

[0045] See also Figure 1 As shown, this embodiment provides a digital twin photovoltaic string modeling method, the method comprising:

[0046] S1: Obtain a photovoltaic power station image, use a photovoltaic string recognition model to detect and recognize multiple photovoltaic strings in the photovoltaic power station image, and obtain the physical parameters of each photovoltaic string and multiple location point information, where the physical parameters include the size of the photovoltaic string and the angle of the photovoltaic string, and the multiple location point information includes the GPS data of the four corner positions and the GPS data of the center point. The photovoltaic string recognition model is obtained by training the Mask R-CNN deep learning network, specifically:

[0047] Using a drone with high-precision GPS and high-resolution camera, take multiple local images of the photovoltaic power station from above the photovoltaic power station, and obtain the photovoltaic power station image after image correction, image enhancement and image stitching processing of the multiple local images; at the same time, record the drone GPS data, flight parameters and camera parameters;

[0048] Specifically, in this embodiment, the GPS and camera of the drone are first calibrated before the drone takes off to ensure the accuracy of the image data; then the flight path of the drone is planned according to the geographical location of the photovoltaic power station and the layout of the photovoltaic strings to ensure that the top surface viewing angle of all strings can be covered; under suitable weather conditions, the drone is used to collect orthophotos along a preset path to ensure that the multiple local images obtained are clear and unobstructed; the multiple local images collected are then automatically aligned and spliced ​​to form a photovoltaic power station image; the spliced ​​photovoltaic power station image is then geometrically corrected and color corrected to eliminate lens distortion and chromatic aberration, while improving the contrast and clarity of the panoramic image, providing a high-quality data source for subsequent AI recognition.

[0049] The photovoltaic string recognition model is used to identify the four corner positions of each photovoltaic string in the photovoltaic power station image, and the GPS data of the four corner positions is calculated using the drone GPS data, camera parameters and flight parameters. The GPS data of the center point of each photovoltaic string is then calculated using the GPS data of the four corner positions, specifically:

[0050] The photovoltaic string recognition model is used to identify the four corner position points of each photovoltaic string in the photovoltaic power station image;

[0051] The horizontal and vertical field of view angles of the camera at the flight altitude of the drone are calculated using the drone GPS data, camera parameters, and flight parameters. The drone GPS data includes the drone latitude and longitude and the drone altitude.

[0052] It should be noted that, in this embodiment, the flight parameter is specifically the flight altitude, and the camera parameter includes the camera focal length setting; the flight altitude of the drone and the camera parameters are used to calculate the horizontal field of view (HFOV) and vertical field of view (VFOV) of the camera at the flight altitude of the drone;

[0053] Obtain image position data of each photovoltaic string in the photovoltaic power station image, and calculate the image pixel coordinates of the center point of each photovoltaic string;

[0054] According to the camera parameters and the horizontal and vertical field of view angles of the camera at the UAV's flight altitude, the XYZ three-dimensional coordinate data of the center point of each photovoltaic string at the UAV's flight altitude is calculated;

[0055] Using the XYZ three-dimensional coordinate data of the center point of each photovoltaic string and the GPS data of the drone, the GPS data of the four corner positions of each photovoltaic string are calculated;

[0056] The GPS data of the four corner positions of each PV string are recorded as (x1, y1, z1), (x2, y2, z2), (x3, y3, z3), and (x4, y4, z4). The average values ​​of the X, Y, and Z coordinates of the four corner positions are calculated as the X, Y, and Z coordinates of the center point to obtain the center point GPS data, recorded as (x_center, y_center, z_center).

[0057] Based on the parameters of the drone and the camera, combined with the GPS data of the four corner positions, the PV string size of each PV string is calculated, specifically:

[0058] Obtain the flight altitude of the UAV and the focal length of the camera; use the flight altitude of the UAV and the camera parameters to calculate the horizontal field of view (HFOV) and vertical field of view (VFOV) of the camera at the flight altitude of the UAV; obtain the image position data of each PV string in the PV power station image, and calculate the image pixel coordinates of the center point of each PV string; calculate the XYZ three-dimensional coordinate data of the center point of each PV string at the flight altitude of the UAV based on the camera parameters and the horizontal field of view and vertical field of view of the camera at the flight altitude of the UAV; use the XYZ three-dimensional coordinate data of the center point of each PV string and the altitude of the UAV to calculate the GPS data of the four corner positions of each PV string.

[0059] Based on the drone parameters and the image position data of each photovoltaic string in the photovoltaic power station image, the photovoltaic string angle of each photovoltaic string is calculated. It should be noted that, in this embodiment, the photovoltaic string angle of each photovoltaic string includes an azimuth angle and a tilt angle; specifically:

[0060] The current heading information is obtained from the drone parameters, usually expressed as an angle ranging from 0° to 360°. In the digital twin environment, a reference point is selected as the true north direction. The angle of each PV string relative to the true north direction is calculated using the heading information of the drone and the image position data of each PV string in the PV power station image. The calculated azimuth angle and tilt angle are output.

[0061] It should be noted that, in this embodiment, the Mask R-CNN deep learning network is trained by collecting data from more than 40 photovoltaic power stations, covering mountain power stations, surface power stations, Gobi power stations and distributed power stations. This photovoltaic string model detection and recognition is used to obtain the four rectangular vertex position information of the photovoltaic string in the drone photo and the specification length and width information of the photovoltaic string.

[0062] It should be noted that in this embodiment, the calculated size needs to be corrected according to factors such as terrain undulation and lens distortion to ensure accuracy, specifically: use the map service API to obtain terrain undulation data, or obtain elevation data through field measurement; use GIS software (such as ArcGIS) to create a digital elevation model (DEM); overlay the information of multiple location points of the photovoltaic string with the DEM to calculate the actual position after considering the terrain undulation; based on the actual position and the size calculated by the photovoltaic power station image, adjust the calculated size to reflect the influence of the terrain undulation; use the tools or image processing software provided by the camera manufacturer to obtain the lens distortion parameters; use the distortion correction function in the OpenCV library to correct the distortion of the photovoltaic power station image; recalculate the size of the string on the distortion-corrected image. Based on the distortion-corrected size, adjust the size calculated by the photovoltaic power station image to reflect the influence of lens distortion.

[0063] S2: Based on the obtained physical parameters of each photovoltaic string and multiple location point information, a three-dimensional model of the photovoltaic string is constructed on the digital twin platform;

[0064] Specifically, in this embodiment, the extracted GPS position, size, angle and other information of each PV string are integrated into a unified data structure to provide data support for the creation of the digital twin model; the extracted feature information data is then used to create a three-dimensional model of the PV string on the digital twin platform, and the spatial coordinates, volume and posture of the model are ensured to be consistent with the actual string.

[0065] S3: Based on the information of multiple location points of each photovoltaic string, a photovoltaic string image is extracted from the photovoltaic power station image, and the extracted photovoltaic string image is combined with the photovoltaic string three-dimensional model to obtain a combined photovoltaic string three-dimensional model.

[0066] Specifically, in this embodiment, a photovoltaic string model is used to detect and identify photovoltaic strings. For each identified photovoltaic string, the photovoltaic string image of the top surface of each photovoltaic string is accurately intercepted from the photovoltaic power station image based on the GPS data of its four corner position points; a mapping interface is preset on the photovoltaic string three-dimensional model for subsequent application of the extracted photovoltaic string image as a mapping; the intercepted photovoltaic string image is adjusted in resolution, color correction and other processing to ensure compatibility with the photovoltaic string three-dimensional model; the processed photovoltaic string image is mapped to the mapping interface of the photovoltaic string three-dimensional model to achieve the fusion of the top surface image and the photovoltaic string three-dimensional model; the size and posture of the three-dimensional model are adjusted according to the actual size and angle of the string to ensure that the model is consistent with the actual string; through mapping replacement and model adjustment, a realistic photovoltaic string three-dimensional model is created for each identified string separately, and finally the synthesized three-dimensional model is optimized by lighting rendering, shadow effects and other optimization processing to improve the realism of the model.

[0067] It should be noted that, in this embodiment, it also includes generating a digital twin deployment code for the three-dimensional model of the photovoltaic string, specifically: GPS spherical coordinate conversion: converting the GPS coordinates (longitude and latitude) of the photovoltaic string into three-dimensional coordinates in the spherical coordinate system; using the radius of the earth and the GPS coordinates of the photovoltaic string, converting the spherical coordinates into coordinates in a three-dimensional rectangular coordinate system (XYZ) based on the center of the earth; selecting a reference point in the digital twin environment as the origin (0 point), usually the center point of the photovoltaic power station or a fixed reference point; translating the three-dimensional rectangular coordinates of the string relative to the origin to obtain the position of the string in the digital twin coordinate system; volume calculation: obtaining the actual size of the string based on the drone image and AI recognition results; using the length, width and height of the string to calculate its volume in the digital twin coordinate system; three-axis rotation angle calculation: calculating the direction vector of the string according to the direction of the string in the photovoltaic power station image; calculating the pitch angle of the string relative to the horizontal plane; calculating the yaw angle of the string relative to the north direction; calculating the roll angle according to the actual installation of the string.

[0068] Specifically, in this embodiment, an unmanned aerial vehicle is used to collect images of the photovoltaic power station, and a photovoltaic string recognition model is used to identify multiple photovoltaic strings in the photovoltaic power station image to obtain physical parameters and multiple location point information of each photovoltaic string; based on the obtained physical parameters of each photovoltaic string and multiple location point information, a three-dimensional model of the photovoltaic string is constructed on the digital twin platform, thereby completing the synthesis, creation, and accurate deployment of the three-dimensional model of the photovoltaic string into the digital twin scene without the need for CAD construction drawings, thereby saving a lot of manpower development and proofreading costs.

[0069] Example 2

[0070] See also Figure 2 As shown, the present invention also provides a digital twin photovoltaic string modeling system, which is used in any one of the digital twin photovoltaic string modeling methods described above, and the system includes:

[0071] The first module 100 is used to obtain a photovoltaic power station image, detect and identify multiple photovoltaic strings in the photovoltaic power station image using a photovoltaic string recognition model, and obtain physical parameters of each photovoltaic string and multiple location point information, wherein the physical parameters include photovoltaic string size and photovoltaic string angle, and the multiple location point information includes four corner position point GPS data and center point GPS data;

[0072] The second module 200 is used to construct a three-dimensional model of the photovoltaic string on the digital twin platform based on the obtained physical parameters of each photovoltaic string and multiple location point information;

[0073] The third module 300 is used to extract the photovoltaic string image from the photovoltaic power station image based on multiple location point information of each photovoltaic string, and to perform mapping synthesis on the extracted photovoltaic string image and the photovoltaic string three-dimensional model to obtain the synthesized photovoltaic string three-dimensional model.

[0074] Furthermore, the photovoltaic power station image is obtained, specifically:

[0075] Using a drone with high-precision GPS and a high-resolution camera, multiple local images of the photovoltaic power station are captured above the photovoltaic power station. The photovoltaic power station image is obtained after image correction, image enhancement and image stitching of the multiple local images; at the same time, the drone GPS data, flight parameters and camera parameters are recorded.

[0076] Furthermore, the photovoltaic string recognition model is used to detect and identify multiple photovoltaic strings in the photovoltaic power station image, and the physical parameters of each photovoltaic string and multiple location point information are obtained respectively. The photovoltaic string recognition model is obtained by training the Mask R-CNN deep learning network, specifically:

[0077] The photovoltaic string recognition model is used to identify the four corner positions of each photovoltaic string in the photovoltaic power station image, and the GPS data of the four corner positions is calculated using the drone GPS data, camera parameters and flight parameters. The GPS data of the center point of each photovoltaic string is then calculated using the GPS data of the four corner positions.

[0078] Based on the parameters of the drone and the camera, combined with the GPS data of the four corner positions, the PV string size of each PV string is calculated;

[0079] Based on the drone parameters and the image position data of each photovoltaic string in the photovoltaic power station image, the photovoltaic string angle of each photovoltaic string is calculated.

[0080] It should be noted that the modules in the system of Example 2 correspond to the steps in the method of Example 1. The steps in the method of Example 1 have been described in detail in Example 1. In this Example 2, the contents of the modules in the system will not be described in detail.

[0081] Example 3

[0082] See also Figure 3 As shown, this embodiment further provides a computer device, including a system memory 1005 and a processor 1001, wherein the system memory 1005 stores a computer program, and the processor 1001 implements the steps of any of the above methods when executing the computer program.

[0083] It should be noted that the processor 1001 is used to execute the steps in the above method embodiments according to the instructions in the program code. Alternatively, the processor 1001 implements the functions of each module / unit in the above system / device embodiments when executing the computer program.

[0084] Specifically, in this embodiment, the computer program may be divided into one or more modules / units, one or more modules / units are stored in the system memory 1005, and are executed by the processor 1001 to complete the present application. One or more modules / units may be a series of computer program instruction segments that can complete specific functions, and the instruction segments are used to describe the execution process of the computer program in the terminal device.

[0085] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The terminal device may include, but is not limited to, a processor 1001 and a system memory 1005. Those skilled in the art will appreciate that this does not constitute a limitation on the terminal device, and may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal device may also include an input / output device 1003, a network access device 1002, a bus 1006, etc.

[0086] The processor 1001 may be a central processing unit (CPU), or other general-purpose processors 1001, digital signal processors 1001 (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor 1001 may be a microprocessor or any conventional processor, etc.

[0087] The system memory 1005 may be an internal storage unit of the terminal device, such as a hard disk or memory of the terminal device. The system memory 1005 may also be a storage device 1004 of the terminal device, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the terminal device. Further, the system memory 1005 may also include both the internal storage unit of the terminal device and the storage device 1004. The system memory 1005 is used to store computer programs and other programs and data required by the terminal device. The system memory 1005 may also be used to temporarily store data that has been output or is to be output.

[0088] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0089] Example 4

[0090] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any one of the above methods are implemented.

[0091] Among them, the computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared or semiconductor system, system or device, or any combination of the above. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk. Random Access Memory (RAM), Read-Only Memory (ROM), Erasable Programmable Read Only Memory (EPROM), registers, hard disks, optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above, or any other form of computer-readable storage medium known in the art.

[0092] An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an application-specific integrated circuit (ASIC). In an embodiment of the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system, or device.

[0093] Example 5

[0094] This embodiment also provides a computer program product including instructions. When the instructions are executed by a computer device cluster, the computer device cluster executes the method described in Embodiment 1.

[0095] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A digital twin photovoltaic string modeling method, characterized in that: Methods include: Acquire a photovoltaic power station image, use a photovoltaic string recognition model to detect and recognize multiple photovoltaic strings in the photovoltaic power station image, and obtain physical parameters of each photovoltaic string and multiple location point information, wherein the physical parameters include photovoltaic string size and photovoltaic string angle, and the multiple location point information includes four corner position point GPS data and center point GPS data; Based on the obtained physical parameters of each PV string and multiple location point information, a 3D model of the PV string is constructed on the digital twin platform; Based on the information of multiple location points of each photovoltaic string, the photovoltaic string image is extracted from the photovoltaic power station image, and the extracted photovoltaic string image is combined with the photovoltaic string three-dimensional model to obtain the synthesized photovoltaic string three-dimensional model.

2. A digital twin photovoltaic string modeling method according to claim 1, characterized in that: Get the photovoltaic power station image, specifically: Using a drone with high-precision GPS and a high-resolution camera, multiple local images of the photovoltaic power station are captured above the photovoltaic power station. The photovoltaic power station image is obtained after image correction, image enhancement and image stitching of the multiple local images; at the same time, the drone GPS data, flight parameters and camera parameters are recorded.

3. A digital twin photovoltaic string modeling method according to claim 2, characterized in that: The photovoltaic string recognition model is used to detect and identify multiple photovoltaic strings in the photovoltaic power station image, and the physical parameters of each photovoltaic string and multiple location point information are obtained respectively. The photovoltaic string recognition model is obtained by training the Mask R-CNN deep learning network, specifically: The photovoltaic string recognition model is used to identify the four corner positions of each photovoltaic string in the photovoltaic power station image, and the GPS data of the four corner positions is calculated using the drone GPS data, camera parameters and flight parameters. The GPS data of the center point of each photovoltaic string is then calculated using the GPS data of the four corner positions. Based on the parameters of the drone and the camera, combined with the GPS data of the four corner positions, the PV string size of each PV string is calculated; Based on the drone parameters and the image position data of each photovoltaic string in the photovoltaic power station image, the photovoltaic string angle of each photovoltaic string is calculated.

4. A digital twin photovoltaic string modeling method according to claim 3, characterized in that: The GPS data of the four corner positions are calculated using the drone GPS data, camera parameters and flight parameters, specifically: The horizontal and vertical field of view angles of the camera at the flight altitude of the drone are calculated using the drone GPS data, camera parameters, and flight parameters. The drone GPS data includes the drone latitude and longitude and the drone altitude. Obtain image position data of each photovoltaic string in the photovoltaic power station image, and calculate the image pixel coordinates of the center point of each photovoltaic string; According to the camera parameters and the horizontal and vertical field of view angles of the camera at the UAV's flight altitude, the three-dimensional coordinate data of the center point of each photovoltaic string at the UAV's flight altitude is calculated; The GPS data of the four corner positions of each photovoltaic string are calculated using the three-dimensional coordinate data of the center point of each photovoltaic string and the drone GPS data.

5. A digital twin photovoltaic string modeling system, characterized in that: The system is used in a digital twin photovoltaic string modeling method according to any one of claims 1 to 4, and the system includes: The first module is used to obtain a photovoltaic power station image, detect and identify multiple photovoltaic strings in the photovoltaic power station image using a photovoltaic string recognition model, and obtain physical parameters of each photovoltaic string and multiple location point information, wherein the physical parameters include photovoltaic string size and photovoltaic string angle, and the multiple location point information includes four corner position point GPS data and center point GPS data; The second module is used to build a three-dimensional model of the photovoltaic string on the digital twin platform based on the obtained physical parameters of each photovoltaic string and multiple location point information; The third module is used to extract the photovoltaic string image from the photovoltaic power station image based on the multiple location point information of each photovoltaic string, and to perform mapping synthesis on the extracted photovoltaic string image and the photovoltaic string three-dimensional model to obtain the synthesized photovoltaic string three-dimensional model.

6. A digital twin photovoltaic string modeling method according to claim 5, characterized in that: Get the photovoltaic power station image, specifically: Using a drone with high-precision GPS and a high-resolution camera, multiple local images of the photovoltaic power station are captured above the photovoltaic power station. The photovoltaic power station image is obtained after image correction, image enhancement and image stitching of the multiple local images; at the same time, the drone GPS data, flight parameters and camera parameters are recorded.

7. A digital twin photovoltaic string modeling method according to claim 6, characterized in that: The photovoltaic string recognition model is used to detect and identify multiple photovoltaic strings in the photovoltaic power station image, and the physical parameters of each photovoltaic string and multiple location point information are obtained respectively. The photovoltaic string recognition model is obtained by training the Mask R-CNN deep learning network, specifically: The photovoltaic string recognition model is used to identify the four corner positions of each photovoltaic string in the photovoltaic power station image, and the GPS data of the four corner positions is calculated using the drone GPS data, camera parameters and flight parameters. The GPS data of the center point of each photovoltaic string is then calculated using the GPS data of the four corner positions. Based on the parameters of the drone and the camera, combined with the GPS data of the four corner positions, the PV string size of each PV string is calculated; Based on the drone parameters and the image position data of each photovoltaic string in the photovoltaic power station image, the photovoltaic string angle of each photovoltaic string is calculated.

8. A computer device comprising a system memory and a processor, wherein the system memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

10. A computer program product comprising instructions, characterized in that When the instructions are executed by a computer device cluster, the computer device cluster executes the method according to any one of claims 1 to 4.

Images