A photovoltaic station component defect positioning method, device, equipment and medium

Abstract

This application discloses a method, apparatus, device, and medium for locating component defects in a photovoltaic station. The method includes: obtaining vertex pixel coordinates of a photovoltaic station image and the conversion relationship between the photovoltaic station pixel coordinate system and the geographic coordinate system, calculating the vertex geographic coordinates of the photovoltaic station; determining the station boundary length of the photovoltaic station based on the vertex geographic coordinates; determining the number of photovoltaic station images to be split based on the station boundary length and preset sub-station boundary lengths; splitting the photovoltaic station image to obtain multiple photovoltaic station sub-images and the positional relationship between each photovoltaic station sub-image and the photovoltaic station image; detecting component defect information in each photovoltaic station sub-image based on a pre-trained component defect detection model; and mapping the component defect information to the geographic coordinate system to obtain component defect location results for the photovoltaic station. This technical solution can improve the accuracy of component defect judgment results and the timeliness of defect location.

Description

Technical Field

[0001] The present application belongs to the field of image data processing technology, and specifically relates to a method, device, equipment and medium for locating component defects in a photovoltaic station. Background Art

[0002] With the rapid development of renewable energy, photovoltaic power generation, as an important component of green and clean energy, has been widely used in various fields. Photovoltaic modules are the basic components of photovoltaic stations. Their defects can directly affect the power generation efficiency of photovoltaic stations. To ensure the operational stability of photovoltaic stations, timely detection and location of module defects in photovoltaic stations based on image data has become a hot research topic in the field of photovoltaic power generation.

[0003] In the existing technology, the location of component defects in photovoltaic stations is often achieved by pre-setting infrared imaging equipment around the photovoltaic strings. By acquiring the thermal imaging data reported by the infrared imaging equipment in real time, it is determined whether the photovoltaic components in the photovoltaic string have component defects based on whether there is abnormal temperature data in the thermal imaging data. If it is determined that there is a component defect, the defective component is located based on the positional relationship between the infrared thermal imaging equipment and the various photovoltaic components in the photovoltaic string.

[0004] However, the infrared thermal imaging data in the existing technology is easily interfered by external environmental factors, resulting in inaccurate component defect detection results. At the same time, the existing technology can only locate the approximate position of the defective component and cannot convert the specific defect information in the component into a geographic coordinate system, which is not conducive to remote monitoring of photovoltaic sites. Summary of the Invention

[0005] The purpose of the embodiments of the present application is to provide a method, device, equipment and medium for locating component defects in a photovoltaic station, which solves the problems in the prior art of inaccurate component defect judgment results and inability to directly locate defect information. By splitting and detecting defects in photovoltaic station images, and mapping the component defect information in each photovoltaic station sub-image to a geographic coordinate system based on the positional relationship between the split image and the original photovoltaic station image and the conversion relationship between the image space and the geographic space, the component defect positioning results of the photovoltaic station are obtained, which can achieve the purpose of directly locating the component defect information of the photovoltaic station to the geographic coordinate system, thereby improving the accuracy of the component defect judgment results and the timeliness of defect positioning.

[0006] In a first aspect, an embodiment of the present application provides a method for locating component defects in a photovoltaic station, the method comprising:

[0007] Obtaining vertex pixel coordinates of the photovoltaic station image and the conversion relationship between the photovoltaic station pixel coordinate system and the geographic coordinate system, and calculating the vertex geographic coordinates of the photovoltaic station based on the vertex pixel coordinates and the conversion relationship;

[0008] Determine the station boundary length of the photovoltaic station based on the vertex geographic coordinates, determine the number of photovoltaic station images to be split based on the station boundary length and the preset sub-station boundary lengths, split the photovoltaic station image according to the number of sub-stations to be split, and obtain multiple photovoltaic station sub-images and the positional relationship between each photovoltaic station sub-image and the photovoltaic station image;

[0009] Inputting multiple PV site sub-maps into a pre-trained component defect detection model, and determining component defect information in each PV site sub-map based on the component defect detection model;

[0010] Based on the position relationship and transformation relationship, the component defect information is mapped to the geographic coordinate system to obtain the component defect positioning results of the photovoltaic station.

[0011] Furthermore, the number of to-be-split items includes the number of to-be-split rows and the number of to-be-split columns;

[0012] The number of PV station images to be split is determined based on the station boundary length and the preset sub-station boundary length, including:

[0013] Calculate the ratio of the total width in the station boundary length to the sub-width in the preset sub-station boundary length, and obtain the number of columns to be split in the photovoltaic station image;

[0014] The total height in the station boundary length and the sub-height in the preset sub-station boundary length are rounded off to calculate the ratio, and the number of rows to be split in the photovoltaic station image is obtained.

[0015] Furthermore, the ratio is rounded and calculated using the following formula:

[0016] ;

[0017] in, is the number of rows to be split, is the number of columns to be split, is the total height of the station boundary length, is the sub-height in the preset sub-station boundary length, is the total width of the station boundary length, is the sub-width in the preset sub-station boundary length, This is the rounding algorithm.

[0018] Furthermore, the photovoltaic station image is split according to the number of to-be-split images to obtain multiple photovoltaic station sub-images and the positional relationship between each photovoltaic station sub-image and the photovoltaic station image, including:

[0019] The photovoltaic station image is split according to the number of rows and columns to be split to obtain multiple photovoltaic station sub-images;

[0020] Calculate the pixel boundary length of the photovoltaic station image based on the vertex pixel coordinates, and determine the starting vertex pixel coordinates of each photovoltaic station sub-image in the photovoltaic station pixel coordinate system based on the pixel boundary length, the number of rows to be split, and the number of columns to be split;

[0021] The preset overlap ratio between adjacent photovoltaic station submaps in multiple photovoltaic station submaps is obtained, and the ending vertex pixel coordinates of each photovoltaic station submap in the photovoltaic station pixel coordinate system are determined based on the sub-pixel boundary length, the starting vertex pixel coordinates and the preset overlap ratio, so as to obtain the positional relationship between each photovoltaic station submap and the photovoltaic station image.

[0022] Furthermore, the component defect information includes the defect type of the component defect and the initial pixel coordinates of the component defect in the pixel coordinate system of the photovoltaic station sub-image;

[0023] Based on the position relationship and transformation relationship, the component defect information is mapped to the geographic coordinate system to obtain the component defect positioning results of the photovoltaic station, including:

[0024] Based on the pixel coordinates of the starting vertex and the initial pixel coordinates of the component defect in the pixel coordinate system of the photovoltaic station sub-map, the final pixel coordinates of the component defect in the pixel coordinate system of the photovoltaic station are determined;

[0025] Based on the conversion relationship and the final pixel coordinates, the defect geographic coordinates of the component defect in the geographic coordinate system are determined, and the defect type and defect geographic coordinates of the component defect are used as the component defect positioning result of the photovoltaic station.

[0026] Furthermore, before inputting the plurality of photovoltaic site sub-maps into the pre-trained component defect detection model, the method further includes:

[0027] Obtain the standard image resolution of the pre-trained module defect detection model and the actual image resolution of each PV site sub-image;

[0028] The photovoltaic station sub-map is resized based on the standard image resolution and the actual image resolution to obtain a standard photovoltaic station sub-map;

[0029] Accordingly, multiple PV site sub-maps are input into the pre-trained component defect detection model, including:

[0030] Each standard PV site sub-map is input into a pre-trained module defect detection model.

[0031] Furthermore, the conversion relationship is an affine transformation matrix between the photovoltaic station pixel coordinate system and the geographic coordinate system, wherein the affine transformation matrix includes the geographic coordinates of the origin of the photovoltaic station pixel coordinate system in the geographic coordinate system, the pixel resolution of the photovoltaic station image, and the rotation degree of the photovoltaic station image;

[0032] Calculate the vertex geographic coordinates of the photovoltaic station based on the vertex pixel coordinates and transformation relationship, including:

[0033] The pixel boundary length of the photovoltaic station image is calculated based on the vertex pixel coordinates, and the vertex geographic coordinates of the photovoltaic station are calculated based on the origin geographic coordinates, pixel resolution, rotation degree and pixel boundary length.

[0034] In a second aspect, an embodiment of the present application provides a device for locating component defects in a photovoltaic station, the device comprising:

[0035] A coordinate calculation module is used to obtain the vertex pixel coordinates of the photovoltaic station image and the conversion relationship between the photovoltaic station pixel coordinate system and the geographic coordinate system, and calculate the vertex geographic coordinates of the photovoltaic station based on the vertex pixel coordinates and the conversion relationship;

[0036] A positional relationship determination module is configured to determine the station boundary length of the photovoltaic station based on the vertex geographic coordinates, determine the number of photovoltaic station images to be split based on the station boundary length and the preset sub-station boundary lengths, split the photovoltaic station image according to the number of sub-stations to be split, and obtain multiple photovoltaic station sub-images and the positional relationship between each photovoltaic station sub-image and the photovoltaic station image;

[0037] a defect detection module, configured to input the plurality of PV site sub-maps into a pre-trained component defect detection model, and determine component defect information in each PV site sub-map based on the component defect detection model;

[0038] The defect location module is used to map component defect information to a geographic coordinate system based on positional and transformation relationships to obtain component defect location results for photovoltaic stations.

[0039] In a third aspect, an embodiment of the present application provides an electronic device comprising a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the method described in the first aspect.

[0040] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.

[0041] In the fifth aspect, an embodiment of the present application also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. At least one processor of the device reads and executes the computer program from the computer-readable storage medium, so that the device performs the method described in the first aspect.

[0042] In an embodiment of the present application, the vertex pixel coordinates of the photovoltaic station image and the conversion relationship between the photovoltaic station pixel coordinate system and the geographic coordinate system are obtained, and the vertex geographic coordinates of the photovoltaic station are calculated based on the vertex pixel coordinates and the conversion relationship; the station boundary length of the photovoltaic station is determined based on the vertex geographic coordinates, and the number of photovoltaic station images to be split is determined based on the station boundary length and the preset sub-station boundary length, and the photovoltaic station image is split according to the number to be split to obtain multiple photovoltaic station sub-maps and the positional relationship between each photovoltaic station sub-map and the photovoltaic station image; the multiple photovoltaic station sub-maps are respectively input into a pre-trained component defect detection model, and the component defect information in each photovoltaic station sub-map is determined based on the component defect detection model; the component defect information is mapped to the geographic coordinate system based on the positional relationship and the conversion relationship to obtain the component defect positioning result of the photovoltaic station. The above-mentioned component defect positioning method for photovoltaic stations solves the problems in the prior art of inaccurate component defect judgment results and inability to directly locate defect information. By splitting and detecting defects in photovoltaic station images, and mapping the component defect information in each photovoltaic station sub-image to the geographic coordinate system based on the positional relationship between the split image and the original photovoltaic station image and the conversion relationship between the image space and the geographic space, the component defect positioning result of the photovoltaic station is obtained. This can achieve the purpose of directly locating the component defect information of the photovoltaic station to the geographic coordinate system, thereby improving the accuracy of the component defect judgment results and the timeliness of defect positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 This is a flow chart of a method for locating component defects in a photovoltaic station provided by an embodiment of the present application;

[0044] Figure 2 This is a flow chart for determining the number of photovoltaic station images to be split, provided in an embodiment of the present application;

[0045] Figure 3 This is a flow chart of another method for locating component defects in a photovoltaic station provided by an embodiment of the present application;

[0046] Figure 4 It is a schematic diagram of the overlapping area of ​​the photovoltaic station sub-map provided in this application;

[0047] Figure 5 This is a structural block diagram of a component defect location device for a photovoltaic station provided by an embodiment of the present application;

[0048] Figure 6 This is a structural block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0049] To further clarify the objectives, technical solutions, and advantages of this application, specific embodiments of the present application are described in further detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are intended only to illustrate this application and are not intended to limit it. It should also be noted that, for ease of description, the drawings only illustrate portions relevant to this application, not all of them. Before discussing the exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts depict the various operations (or steps) as sequential processes, many of the operations can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the operations can be rearranged. The process may terminate upon completion of its operations, but may also include additional steps not shown in the accompanying drawings. The process may correspond to a method, function, procedure, subroutine, subprogram, or the like.

[0050] The following will be combined with the accompanying drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the embodiments described are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of this application.

[0051] The terms "first," "second," and the like in the specification and claims of this application are used to distinguish similar objects, and are not used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of this application can be implemented in an order other than that illustrated or described herein, and that the objects distinguished by "first," "second," and the like are generally of the same type, and do not limit the number of objects; for example, the first object can be one or more. In addition, the term "and / or" in the specification and claims refers to at least one of the connected objects, and the character " / " generally indicates that the objects connected are in an "or" relationship.

[0052] First of all, the usage scenario of this solution can be the scenario of locating component defects in photovoltaic stations, especially the scenario of locating the defect locations of component defects in photovoltaic stations, so as to directly obtain the specific geographical location of the component defects in the station. By splitting and detecting defects in the photovoltaic station image, and mapping the component defect information in each photovoltaic station sub-image to the geographic coordinate system based on the positional relationship between the split image and the original photovoltaic station image and the conversion relationship between the image space and the geographic space, the component defect location results of the photovoltaic station are obtained, which can achieve the purpose of directly locating the component defect information of the photovoltaic station to the geographic coordinate system, thereby improving the accuracy of the component defect judgment results and the timeliness of defect location. Based on the above usage scenarios, it can be understood that the executor of this solution can be an electronic device, such as: smart terminals such as mobile phones, tablets and desktop computers.

[0053] In the following, in conjunction with the accompanying drawings, a method, device, equipment and medium for locating component defects in a photovoltaic station provided by the embodiments of the present application are described in detail through specific embodiments and their application scenarios.

[0054] Figure 1 This is a flow chart of a method for locating component defects in a photovoltaic station provided by an embodiment of the present application. Figure 1 As shown, the specific steps include:

[0055] S101 , obtaining vertex pixel coordinates of a photovoltaic station image and a conversion relationship between a photovoltaic station pixel coordinate system and a geographic coordinate system, and calculating vertex geographic coordinates of the photovoltaic station based on the vertex pixel coordinates and the conversion relationship.

[0056] Among them, the photovoltaic station image can be a remote sensing image taken of the photovoltaic station as a whole. In this scheme, the photovoltaic station image is an orthophoto of the photovoltaic station in TIF format. The orthophoto data includes the pixel value of the photovoltaic station image, the geospatial coordinate reference system (CRS) where the photovoltaic station image is located, and the mapping relationship between the pixel coordinate system of the photovoltaic station image and the geospatial coordinate system. The geospatial coordinate reference system where the photovoltaic station image is located is used to correspond the image data of the photovoltaic station image to the geospatial position. The vertex pixel coordinates can be the pixel coordinates of the vertex pixel point of the photovoltaic station image in the photovoltaic station pixel coordinate system. In this scheme, the upper left corner vertex of the photovoltaic station image is used as the origin of the photovoltaic station pixel coordinate system, and its pixel coordinates are , the vertex pixel coordinates of the upper right vertex are , the vertex pixel coordinates of the lower left vertex are , W is the number of pixels of the width of the photovoltaic station image, and H is the number of pixels of the height of the photovoltaic station image. The geographic coordinate system in this solution includes a latitude and longitude coordinate system and a projection coordinate system. After mapping the pixel coordinates in the photovoltaic station image to the geographic space coordinate system, they are uniformly converted into latitude and longitude coordinates in the latitude and longitude coordinate system for storage. The conversion relationship between the photovoltaic station pixel coordinate system and the geographic coordinate system can be a conversion matrix that maps the pixel coordinates of the pixel points in the photovoltaic station image to the corresponding latitude and longitude coordinates in the geographic space. The vertex geographic coordinates can be the latitude and longitude coordinates of the range vertex of the geographic space coverage range corresponding to the photovoltaic station image in the geographic space.

[0057] In one embodiment, the vertex pixel coordinates of the photovoltaic station image and the conversion relationship between the photovoltaic station pixel coordinate system and the geographic coordinate system can be obtained by reading the image data of the photovoltaic station image, and the vertex pixel coordinates are mapped to the geographic space according to the vertex pixel coordinates and the conversion relationship to obtain the vertex geographic coordinates of the photovoltaic station.

[0058] In one embodiment, the conversion relationship is an affine transformation matrix between the photovoltaic station pixel coordinate system and the geographic coordinate system, wherein the affine transformation matrix includes the origin geographic coordinates of the photovoltaic station pixel coordinate system in the geographic coordinate system, the pixel resolution of the photovoltaic station image, and the rotation degree of the photovoltaic station image; the vertex geographic coordinates of the photovoltaic station are calculated based on the vertex pixel coordinates and the conversion relationship, including: calculating the pixel boundary length of the photovoltaic station image based on the vertex pixel coordinates, and calculating the vertex geographic coordinates of the photovoltaic station based on the origin geographic coordinates, pixel resolution, rotation degree, and pixel boundary length.

[0059] The affine transformation matrix is ​​a transformation equation used to align the pixel coordinates of a photovoltaic station image with geographic coordinates. The origin geographic coordinates can be the latitude and longitude coordinates obtained by converting the origin pixel coordinates in the photovoltaic station pixel coordinate system to the geographic coordinate system. The pixel resolution of a photovoltaic station image is the actual ground distance represented by one pixel in the image. The pixel resolution of a photovoltaic station image is measured in meters per pixel (m / pixel). The rotation of a photovoltaic station image is the angle by which the photovoltaic station image is rotated relative to a geographic coordinate axis (e.g., true north). The rotation of a photovoltaic station image is measured in degrees (°), with a positive value being counterclockwise. The pixel boundary length of a photovoltaic station image can be the total number of pixels corresponding to each image edge of the photovoltaic station image. The pixel boundary length includes the number of pixels in the image width and height.

[0060] In one embodiment, the pixel boundary length of the photovoltaic station image can be calculated based on the vertex pixel coordinates of two adjacent vertices on the photovoltaic station image, and the vertex geographic coordinates of the photovoltaic station can be calculated based on the origin geographic coordinates, pixel resolution, rotation degree and pixel boundary length.

[0061] In one embodiment, the affine transformation matrix can be expressed by the following formula:

[0062] ;

[0063] in, and are the geographic coordinates (longitude and latitude) of the upper left corner of the photovoltaic station image, and are the pixel resolutions of the photovoltaic station image in the x and y directions (unit: meter / pixel), and Indicates the degree of rotation of the photovoltaic station image, usually 0.

[0064] The vertex pixel coordinates of the upper left corner of the photovoltaic station image can be calculated based on the origin geographic coordinates, pixel resolution, rotation degree and pixel boundary length , the vertex pixel coordinates of the upper right vertex , the vertex pixel coordinates of the lower left vertex The corresponding longitude and latitude coordinates in the geographic coordinate system are used to obtain the vertex geographic coordinates of the photovoltaic station.

[0065] The geographic coordinates of the top left corner of the photovoltaic station can be calculated using the following formula:

[0066] ;

[0067] ;

[0068] ;

[0069] Among them, LT is the vertex geographic coordinate of the upper left corner of the photovoltaic station, RT is the vertex geographic coordinate of the upper right corner of the photovoltaic station, LB is the vertex geographic coordinate of the lower left corner of the photovoltaic station, W is the width pixel number of the photovoltaic station image, and H is the height pixel number of the photovoltaic station image.

[0070] S102, determining the station boundary length of the photovoltaic station based on the vertex geographic coordinates, determining the number of photovoltaic station images to be split based on the station boundary length and the preset sub-station boundary length, splitting the photovoltaic station image according to the number of sub-stations to be split, and obtaining multiple photovoltaic station sub-images and the positional relationship between each photovoltaic station sub-image and the photovoltaic station image.

[0071] Among them, the station boundary length can be the length of each side of the photovoltaic station range covered by the photovoltaic station image. The preset sub-station boundary length can be the length of each side of the station range of each sub-station after the photovoltaic station is pre-set to be split into multiple sub-stations. The number to be split can be the number of photovoltaic station sub-images obtained after splitting the photovoltaic station image according to the sub-station splitting method. The photovoltaic station sub-image can be the station image corresponding to the sub-station. The positional relationship between each photovoltaic station sub-image and the photovoltaic station image can be the image position of each photovoltaic station sub-image in the photovoltaic station image. For example: the photovoltaic station image is split into photovoltaic station sub-images with M rows and N columns, then the positional relationship between the i-th photovoltaic station sub-image and the photovoltaic station image can be expressed as .

[0072] In one embodiment, the boundary length of the photovoltaic station can be obtained by calculating the distance between two adjacent vertices based on the geographic coordinates of the vertices of the photovoltaic station. If the geographic coordinate reference system of the photovoltaic station image is a projected coordinate system, the distance between two adjacent vertices can be calculated using the following formula:

[0073] ;

[0074] in, and They are the geographic coordinates of adjacent vertices of the photovoltaic station in the projected coordinate system.

[0075] If the geographic coordinate reference system of the photovoltaic station image is a longitude and latitude coordinate system, the Haversine formula can be used to calculate the distance between two adjacent longitude and latitude vertices:

[0076] ;

[0077] ;

[0078] ;

[0079] in, and They are the geographical coordinates of the adjacent vertices of the photovoltaic station in the longitude and latitude coordinate system.

[0080] The ratio of the station boundary length to the pre-set substation boundary length can be calculated, and the maximum number of substations included in the PV station can be determined based on this ratio. Since the PV station image corresponds to the entire PV station's geographic spatial extent, the maximum number of substations can be used as the number of sub-stations to be split into. The PV station image area is evenly split according to the number of sub-stations to be split, resulting in multiple PV station sub-images. The positional relationship between each PV station sub-image and the PV station image is determined based on its position within the PV station image.

[0081] S103: Input the plurality of photovoltaic site sub-maps into a pre-trained component defect detection model respectively, and determine component defect information in each photovoltaic site sub-map based on the component defect detection model.

[0082] The module defect detection model can be a pre-trained model for detecting and locating module defects in a photovoltaic station based on photovoltaic station images, such as a YOLOv8 model. The module defect information can be information describing the defect type and location of the module defect within the photovoltaic station sub-image.

[0083] In one embodiment, multiple PV station sub-images can be fed into a pre-trained component defect detection model based on the order in which each sub-image is distributed within the PV station image. The component defect detection model then automatically identifies component defects within each PV station sub-image. The component defect detection model in this solution directly outputs the coordinates of a defect box annotating the component defects within each PV station sub-image, along with the defect type corresponding to the defect box.

[0084] During defect detection, module defect detection models may experience false positives (incorrectly labeled defects), false negatives (missed defects), and subtle defect features. This solution incorporates the CBAM channel attention mechanism into the YOLOv8 model. CBAM consists of two main components: a channel attention module and a spatial attention module. Combined, they effectively reduce false positives and missed detections. Furthermore, this solution adds a small object detection head to the Head layer of the YOLOv8 network architecture and incorporates the CBAM mechanism to further enhance the model's ability to detect subtle defects in photovoltaic modules.

[0085] Before training the component defect detection model, a large number of PV module images can be collected in advance and annotated using LabelImg. Defect types such as point hot spots, strip hot spots, vegetation obstruction, snow cover, and missing PV panels can be marked to create a dataset. OpenCV is used to clean the dataset to remove erroneous or irrelevant data. The dataset is enhanced through operations such as rotation, cropping, flipping, and translation to improve the model's accuracy and generalization. After the model structure of the component defect detection model is constructed, the dataset is divided into training, test, and validation sets in an 8:1:1 ratio. The test and validation sets are randomly sampled from the original dataset to ensure data diversity. Finally, the dataset is imported into the YOLOv8 model for defect detection training. After adjusting some network hyperparameters, 300 epochs of training are initiated to obtain the final component defect detection model.

[0086] In one embodiment, before inputting multiple photovoltaic site sub-maps into a pre-trained component defect detection model, the method further includes: obtaining a standard image resolution of the pre-trained component defect detection model and an actual image resolution of each photovoltaic site sub-map; resizing the photovoltaic site sub-map based on the standard image resolution and the actual image resolution to obtain a standard photovoltaic site sub-map; and accordingly, inputting multiple photovoltaic site sub-maps into the pre-trained component defect detection model, including: inputting each standard photovoltaic site sub-map into the pre-trained component defect detection model.

[0087] The standard image resolution can be a parameter used to describe the minimum clarity of the input image required by the component defect detection model. The actual image resolution can be a parameter used to describe the actual clarity of each PV plant sub-image. The standard PV plant sub-image can be a PV plant sub-image whose clarity meets the standard image resolution.

[0088] In one embodiment, the standard image resolution of a pre-trained component defect detection model and the actual image resolution of each photovoltaic station sub-image can be obtained, and the scaling ratio of the photovoltaic station sub-image is determined according to the ratio of the standard image resolution to the actual image resolution. The photovoltaic station sub-image is resized according to the scaling ratio to obtain a standard photovoltaic station sub-image that meets the model requirements, and each standard photovoltaic station sub-image is input into the pre-trained component defect detection model to use the component defect detection model to accurately detect and locate component defects in the photovoltaic station sub-image.

[0089] S104: Mapping the component defect information to a geographic coordinate system based on the position relationship and the conversion relationship to obtain a component defect positioning result of the photovoltaic station.

[0090] The component defect positioning result may be the location information of the component defect in the photovoltaic station in geographic space.

[0091] In one embodiment, the component defect information in each photovoltaic station sub-image can be mapped to the entire photovoltaic station image based on the position relationship, and then the component defect information in the photovoltaic station image can be mapped to the geographic coordinate system based on the conversion relationship to obtain the component defect positioning result of the photovoltaic station.

[0092] The technical solution provided in the embodiment of the present application obtains the vertex pixel coordinates of the photovoltaic station image and the conversion relationship between the photovoltaic station pixel coordinate system and the geographic coordinate system, and calculates the vertex geographic coordinates of the photovoltaic station based on the vertex pixel coordinates and the conversion relationship; determines the station boundary length of the photovoltaic station based on the vertex geographic coordinates, determines the number of photovoltaic station images to be split based on the station boundary length and the preset sub-station boundary length, splits the photovoltaic station image according to the number to be split, and obtains multiple photovoltaic station sub-images and the positional relationship between each photovoltaic station sub-image and the photovoltaic station image; inputs the multiple photovoltaic station sub-images into a pre-trained component defect detection model, and determines the component defect information in each photovoltaic station sub-image based on the component defect detection model; maps the component defect information to the geographic coordinate system based on the positional relationship and the conversion relationship to obtain the component defect positioning result of the photovoltaic station. The above-mentioned component defect positioning method for photovoltaic stations solves the problems in the prior art of inaccurate component defect judgment results and inability to directly locate defect information. By splitting and detecting defects in photovoltaic station images, and mapping the component defect information in each photovoltaic station sub-image to the geographic coordinate system based on the positional relationship between the split image and the original photovoltaic station image and the conversion relationship between the image space and the geographic space, the component defect positioning result of the photovoltaic station is obtained. This can achieve the purpose of directly locating the component defect information of the photovoltaic station to the geographic coordinate system, thereby improving the accuracy of the component defect judgment results and the timeliness of defect positioning.

[0093] Figure 2 This is a flow chart of determining the number of photovoltaic station images to be split according to an embodiment of the present application. The number of images to be split includes the number of rows to be split and the number of columns to be split, such as Figure 2 As shown, the specific steps include:

[0094] S201 , performing rounding calculation on the ratio of the total width in the station boundary length to the sub-width in the preset sub-station boundary length, to obtain the number of columns to be split in the photovoltaic station image.

[0095] The station boundary includes the wide and high boundaries of the photovoltaic station. The total width in the station boundary length can be the boundary length value of the photovoltaic station's wide boundary. The sub-width in the preset sub-station boundary length can be the preset boundary length value of the wide boundary of each sub-station. The ratio rounding calculation can include rounding up and rounding forensics. The number of columns to be split can be the total number of columns to be split into for the photovoltaic station image.

[0096] In one embodiment, the ratio of the total width in the station boundary length to the sub-width in the preset sub-station boundary length may be calculated, and the ratio may be rounded to obtain the number of columns to be split in the photovoltaic station image.

[0097] S202 , performing rounding calculation on the ratio of the total height in the station boundary length to the sub-height in the preset sub-station boundary length, to obtain the number of rows to be split in the photovoltaic station image.

[0098] The total height in the station boundary length can be the boundary length value of the high boundary of the photovoltaic station. The sub-height in the preset sub-station boundary length can be the preset boundary length value of the high boundary of each sub-station. The number of rows to be split can be the total number of rows to be split into for the photovoltaic station image.

[0099] In one embodiment, the ratio of the total height in the station boundary length to the sub-height in the preset sub-station boundary length may be calculated, and the ratio may be rounded to obtain the number of rows to be split in the photovoltaic station image.

[0100] In one embodiment, the ratio is rounded and calculated using the following formula:

[0101] ;

[0102] in, is the number of rows to be split, is the number of columns to be split, is the total height of the station boundary length, is the sub-height in the preset sub-station boundary length, is the total width of the station boundary length, is the sub-width in the preset sub-station boundary length, This is the rounding algorithm.

[0103] In one embodiment, the ratio rounding calculation may be a rounding algorithm, which is expressed by the following formula:

[0104] ;

[0105] When the ratio of the total height in the station boundary length to the sub-height in the preset sub-station boundary length is less than 1, the number of split rows is taken as 1. When the ratio of the total width in the station boundary length to the sub-width in the preset sub-station boundary length is less than 1, the number of split columns is taken as 1.

[0106] This solution ensures that the number of rows and columns of the photovoltaic station image split is at least 1 through the ratio rounding algorithm, avoiding the problem of being unable to calculate the number of photovoltaic station splits due to the preset photovoltaic station sub-image boundary value being too large.

[0107] The technical solution provided in the embodiment of the present application obtains the number of columns to be split of the photovoltaic station image by performing rounding calculation on the ratio of the total width in the station boundary length and the sub-width in the preset sub-station boundary length, and obtains the number of rows to be split of the photovoltaic station image by performing rounding calculation on the total height in the station boundary length and the sub-height in the preset sub-station boundary length. This can improve the rationality of the splitting of the photovoltaic station image, and is conducive to improving the accuracy of subsequent component defect detection on the photovoltaic station image sub-image.

[0108] Figure 3 This is a flow chart of another method for locating component defects in a photovoltaic station provided by an embodiment of the present application. Figure 3 As shown, the specific steps include:

[0109] S301 , obtaining vertex pixel coordinates of a photovoltaic station image and a conversion relationship between a photovoltaic station pixel coordinate system and a geographic coordinate system, and calculating vertex geographic coordinates of the photovoltaic station based on the vertex pixel coordinates and the conversion relationship.

[0110] S302 , determining the station boundary length of the photovoltaic station based on the vertex geographic coordinates, performing rounding calculation on the ratio of the total width in the station boundary length to the sub-width in the preset sub-station boundary length, and obtaining the number of columns to be split in the photovoltaic station image.

[0111] S303 , performing rounding calculation on the ratio of the total height in the station boundary length to the sub-height in the preset sub-station boundary length, to obtain the number of rows to be split in the photovoltaic station image.

[0112] S304 , splitting the photovoltaic station image according to the number of rows and columns to be split, to obtain a plurality of photovoltaic station sub-images.

[0113] The photovoltaic station sub-image may be an image obtained by splitting the photovoltaic station image.

[0114] In one embodiment, the photovoltaic station image may be preliminarily split according to the number of rows and columns to be split, to obtain a plurality of photovoltaic station sub-images.

[0115] S305 , calculating the pixel boundary length of the photovoltaic station image based on the vertex pixel coordinates, and determining the starting vertex pixel coordinates of each photovoltaic station sub-image in the photovoltaic station pixel coordinate system based on the pixel boundary length, the number of rows to be split, and the number of columns to be split.

[0116] The pixel boundary length may be the total pixel length of each boundary of the photovoltaic station image. The pixel boundary length includes the total pixel length of the wide boundary and the total pixel length of the high boundary of the photovoltaic station image. The starting vertex pixel coordinates include the vertex pixel coordinates of the upper left corner vertex of the upper boundary of the photovoltaic station sub-image.

[0117] In one embodiment, the pixel distance between two adjacent vertices can be calculated based on their vertex pixel coordinates to obtain the pixel boundary length of the photovoltaic station image. The starting vertex pixel coordinates of the first row of photovoltaic station sub-images in the photovoltaic station image can be calculated based on the total length of the wide boundary pixels and the number of columns to be split. The starting vertex pixel coordinates of each row of photovoltaic station sub-images below the first row in the photovoltaic station image can be calculated based on the total length of the high boundary pixels and the number of rows to be split.

[0118] S306, obtaining a preset overlap ratio between adjacent photovoltaic station sub-maps in a plurality of photovoltaic station sub-maps, determining the ending vertex pixel coordinates of each photovoltaic station sub-map in the photovoltaic station pixel coordinate system based on the sub-pixel boundary length, the starting vertex pixel coordinates and the preset overlap ratio, and obtaining the positional relationship between each photovoltaic station sub-map and the photovoltaic station image.

[0119] The sub-pixel boundary length may be the pixel boundary length of a preset sub-station in a pixel coordinate system. The sub-pixel boundary length may be determined by calculating the total number of pixels corresponding to the preset sub-station boundary length, or by calculating the ratio of the pixel boundary length of the photovoltaic station image to the number of rows to be split, and the ratio of the pixel boundary length to the number of columns to be split. The preset overlap ratio may be a pre-set parameter for the degree of overlap between images of adjacent photovoltaic station sub-images. The ending vertex pixel coordinates may be the vertex pixel coordinates obtained by adding the preset overlap ratio to the original ending vertex coordinates of each photovoltaic station sub-image after splitting according to the number of rows and columns to be split.

[0120] Figure 4 It is a schematic diagram of the overlapping area of ​​the photovoltaic station sub-map provided in this application.

[0121] like Figure 4As shown, area A in the figure is a PV station subimage. The dotted line encloses the overlap between area A and the adjacent subimage on the right. The upper left vertex represents the starting vertex pixel coordinate of area A, and the lower right vertex represents the ending vertex pixel coordinate of area A. To avoid the problem of splitting the PV station image into PV station subimages that separate identical components, which in turn prevents the subsequent component defect detection model from accurately identifying component defects in the PV station subimages, this solution creates a certain overlap between adjacent PV station subimages. The size of this overlap is the preset overlap ratio, which is 10% of the size of each subimage.

[0122] In one embodiment, a preset overlap ratio between adjacent photovoltaic station sub-maps in a plurality of photovoltaic station sub-maps can be obtained, and the original end vertex coordinates of each photovoltaic station sub-map are determined based on the sub-pixel boundary length and the starting vertex pixel coordinates. The overlap pixel length that each photovoltaic station sub-map needs to overlap with the adjacent photovoltaic station sub-map is determined based on the sub-pixel boundary length and the preset overlap ratio. The original end vertex coordinates are added to the overlap pixel length to obtain the end vertex pixel coordinates of each photovoltaic station sub-map in the photovoltaic station pixel coordinate system. Since the photovoltaic station pixel coordinate system in this solution is constructed based on the photovoltaic station image, and the origin of the coordinate system coincides with the upper left corner vertex of the photovoltaic station image, the start vertex pixel coordinates and the end vertex pixel coordinates of each photovoltaic station sub-map can be used as the positional relationship between each photovoltaic station sub-map and the photovoltaic station image.

[0123] In one embodiment, the sub-pixel boundary length can be calculated using the following formula:

[0124] ;

[0125] ;

[0126] in, is the width pixel boundary length in the sub-pixel boundary length, Sub-pixel boundary length, mid-high pixel boundary length, is the number of columns to be split, Number of rows to be split, and Determines how many sub-images the PV station image needs to be split into.

[0127] The pixel coordinates of the starting vertex of the photovoltaic station sub-graph in the i-th row and j-th column can be calculated according to the following formula:

[0128] ;

[0129] ;

[0130] ;

[0131] ;

[0132] Where i is the number of rows of the PV station sub-map on the PV station image, j is the number of columns of the PV station sub-map on the PV station image, is the pixel coordinate value of the starting vertex of the upper left corner of the photovoltaic station sub-graph in the i-th row and j-th column on the x-axis, is the pixel coordinate value of the starting vertex of the upper left corner of the photovoltaic station sub-graph in the i-th row and j-th column on the y-axis, is the i-th row, Column j.

[0133] The pixel coordinates of the ending vertex of the photovoltaic station subgraph in the i-th row and j-th column can be calculated according to the following formula:

[0134] ;

[0135] ;

[0136] in, is the pixel coordinate value of the terminal vertex pixel coordinate of the lower right corner vertex of the photovoltaic station sub-graph in the i-th row and j-th column on the x-axis, The pixel coordinate value of the terminal vertex pixel coordinate of the lower right corner vertex of the photovoltaic station sub-graph in the i-th row and j-th column on the y-axis.

[0137] S307 , inputting the plurality of photovoltaic site sub-maps into a pre-trained component defect detection model respectively, and determining component defect information in each photovoltaic site sub-map based on the component defect detection model.

[0138] S308 , mapping the component defect information to a geographic coordinate system based on the position relationship and the conversion relationship, and obtaining a component defect positioning result of the photovoltaic station.

[0139] In one embodiment, the component defect information includes the defect type of the component defect and the initial pixel coordinates of the component defect in the pixel coordinate system of the photovoltaic station sub-map; the component defect information is mapped to the geographic coordinate system based on the position relationship and the conversion relationship to obtain the component defect positioning result of the photovoltaic station, including: determining the final pixel coordinates of the component defect in the photovoltaic station pixel coordinate system based on the starting vertex pixel coordinates and the initial pixel coordinates of the component defect in the pixel coordinate system of the photovoltaic station sub-map; determining the defect geographic coordinates of the component defect in the geographic coordinate system based on the conversion relationship and the final pixel coordinates, and using the defect type and defect geographic coordinates of the component defect as the component defect positioning result of the photovoltaic station.

[0140] Among them, defect types may include point-shaped hot spots, strip-shaped hot spots, obstruction by grass and trees, snow cover, and missing photovoltaic panels.

[0141] In one embodiment, the sum of the starting vertex pixel coordinates of the photovoltaic station sub-map and the initial pixel coordinates of the component defect in the photovoltaic station sub-map pixel coordinate system can be calculated to obtain the final pixel coordinates of the component defect in the photovoltaic station pixel coordinate system. The defect geographic coordinates of the component defect in the geographic coordinate system are determined based on the conversion relationship and the final pixel coordinates, and the defect type and defect geographic coordinates of the component defect are used as the component defect positioning result of the photovoltaic station.

[0142] In one embodiment, the row and column index of each photovoltaic station sub-image in the photovoltaic station image can be recorded. , obtain the defect information output by the YOLOv8 model for component defect detection on the photovoltaic station sub-image, and obtain the component defect category and defect frame coordinates in the photovoltaic station sub-image. Since the defect frame coordinates are relative to the scaled sub-image, they need to be converted back to the pixel coordinates in the original sub-image and then mapped to the photovoltaic station pixel coordinate system of the entire photovoltaic station image. The coordinates of the defect frame can be mapped to the photovoltaic station image coordinate system using the following formula:

[0143] ;

[0144] ;

[0145] in, To map the defect frame coordinates to the coordinate values ​​on the x-axis of the photovoltaic station image coordinate system, To map the defect frame coordinates to the coordinate values ​​on the y-axis of the photovoltaic station image coordinate system, is the coordinate value of the defect frame on the x-axis in the pixel coordinate system of the photovoltaic station sub-image, is the coordinate value of the defect frame on the y-axis in the pixel coordinate system of the photovoltaic station sub-image.

[0146] The pixel coordinates in the photovoltaic station image coordinate system can be mapped to the geographic coordinate system using the following formula:

[0147] ;

[0148] Where T is the conversion relationship between the photovoltaic station pixel coordinate system and the geographic coordinate system. is the pixel coordinate of the i-th row and j-th column sub-image in the photovoltaic station image in the photovoltaic station pixel coordinate system, For the above The geographic coordinates corresponding to the pixel location.

[0149] To unify the storage format of geographic coordinates and facilitate subsequent component defect analysis, it is necessary to convert geographic coordinates that are not in the longitude and latitude format EPSG:4326 (WGS84) to the longitude and latitude format using the following formula:

[0150] ;

[0151] in, is the converted WGS84 geographic coordinates (latitude and longitude), is the original coordinate system code (such as UTM32650), represents the WGS84 coordinate system, Represents the transformation function from the original coordinate system to the WGS84 coordinate system.

[0152] This solution determines the final pixel coordinates of the component defect in the photovoltaic station pixel coordinate system based on the starting vertex pixel coordinates and the initial pixel coordinates of the component defect in the photovoltaic station sub-map pixel coordinate system, determines the defect geographic coordinates of the component defect in the geographic coordinate system based on the conversion relationship and the final pixel coordinates, and uses the defect type and defect geographic coordinates of the component defect as the component defect positioning result of the photovoltaic station. This can achieve the purpose of accurately mapping the component defect information to the geographic coordinate system, thereby improving the timeliness of component defect positioning.

[0153] The technical solution provided in the embodiment of the present application calculates the pixel boundary length of the photovoltaic station image based on the vertex pixel coordinates, determines the starting vertex pixel coordinates of each photovoltaic station sub-image in the photovoltaic station pixel coordinate system based on the pixel boundary length, the number of rows to be split and the number of columns to be split, and determines the ending vertex pixel coordinates of each photovoltaic station sub-image in the photovoltaic station pixel coordinate system based on the sub-pixel boundary length, the starting vertex pixel coordinates and the preset overlap ratio, thereby obtaining the positional relationship between each photovoltaic station sub-image and the photovoltaic station image. This can avoid the problem of the photovoltaic station sub-image splitting the same components in the photovoltaic station image, thereby improving the accuracy of the component defect detection results.

[0154] Figure 5 This is a structural block diagram of a photovoltaic station component defect location device provided by an embodiment of the present application. Figure 5 As shown, specifically including the following:

[0155] A coordinate calculation module 501 is used to obtain the vertex pixel coordinates of the photovoltaic station image and the conversion relationship between the photovoltaic station pixel coordinate system and the geographic coordinate system, and calculate the geographic coordinates of the vertex of the photovoltaic station based on the vertex pixel coordinates and the conversion relationship;

[0156] A positional relationship determination module 502 is configured to determine the station boundary length of the photovoltaic station based on the vertex geographic coordinates, determine the number of photovoltaic station image segments to be split based on the station boundary length and the preset sub-station boundary lengths, split the photovoltaic station image according to the number of segments to be split, and obtain multiple photovoltaic station sub-images and the positional relationship between each photovoltaic station sub-image and the photovoltaic station image;

[0157] A defect detection module 503 is configured to input the plurality of photovoltaic site sub-maps into a pre-trained component defect detection model, and determine component defect information in each photovoltaic site sub-map based on the component defect detection model;

[0158] The defect location module 504 is used to map the component defect information to the geographic coordinate system based on the position relationship and the conversion relationship to obtain the component defect location result of the photovoltaic station.

[0159] Furthermore, the number of to-be-split items includes the number of to-be-split rows and the number of to-be-split columns;

[0160] The position relationship determination module 502 is specifically configured to:

[0161] Calculate the ratio of the total width in the station boundary length to the sub-width in the preset sub-station boundary length, and obtain the number of columns to be split in the photovoltaic station image;

[0162] The total height in the station boundary length and the sub-height in the preset sub-station boundary length are rounded off to calculate the ratio, and the number of rows to be split in the photovoltaic station image is obtained.

[0163] Furthermore, the ratio is rounded and calculated using the following formula:

[0164] ;

[0165] in, is the number of rows to be split, is the number of columns to be split, is the total height of the station boundary length, is the sub-height in the preset sub-station boundary length, is the total width of the station boundary length, is the sub-width in the preset sub-station boundary length, This is the rounding algorithm.

[0166] Furthermore, the position relationship determination module 502 is specifically configured to:

[0167] The photovoltaic station image is split according to the number of rows and columns to be split to obtain multiple photovoltaic station sub-images;

[0168] Calculate the pixel boundary length of the photovoltaic station image based on the vertex pixel coordinates, and determine the starting vertex pixel coordinates of each photovoltaic station sub-image in the photovoltaic station pixel coordinate system based on the pixel boundary length, the number of rows to be split, and the number of columns to be split;

[0169] The preset overlap ratio between adjacent photovoltaic station submaps in multiple photovoltaic station submaps is obtained, and the ending vertex pixel coordinates of each photovoltaic station submap in the photovoltaic station pixel coordinate system are determined based on the sub-pixel boundary length, the starting vertex pixel coordinates and the preset overlap ratio, so as to obtain the positional relationship between each photovoltaic station submap and the photovoltaic station image.

[0170] Furthermore, the component defect information includes the defect type of the component defect and the initial pixel coordinates of the component defect in the pixel coordinate system of the photovoltaic station sub-image;

[0171] The defect location module 504 is specifically configured to:

[0172] Based on the pixel coordinates of the starting vertex and the initial pixel coordinates of the component defect in the pixel coordinate system of the photovoltaic station sub-map, the final pixel coordinates of the component defect in the pixel coordinate system of the photovoltaic station are determined;

[0173] Based on the conversion relationship and the final pixel coordinates, the defect geographic coordinates of the component defect in the geographic coordinate system are determined, and the defect type and defect geographic coordinates of the component defect are used as the component defect positioning result of the photovoltaic station.

[0174] Furthermore, the device also includes:

[0175] The resolution acquisition module is used to obtain the standard image resolution of the pre-trained component defect detection model and the actual image resolution of each PV site sub-image;

[0176] A size adjustment module is used to adjust the size of the photovoltaic station sub-image based on the standard image resolution and the actual image resolution to obtain a standard photovoltaic station sub-image;

[0177] Accordingly, the defect detection module 503 is specifically configured to:

[0178] Each standard PV site sub-map is input into a pre-trained module defect detection model.

[0179] Furthermore, the conversion relationship is an affine transformation matrix between the photovoltaic station pixel coordinate system and the geographic coordinate system, wherein the affine transformation matrix includes the geographic coordinates of the origin of the photovoltaic station pixel coordinate system in the geographic coordinate system, the pixel resolution of the photovoltaic station image, and the rotation degree of the photovoltaic station image;

[0180] The coordinate calculation module 501 is specifically used for:

[0181] The pixel boundary length of the photovoltaic station image is calculated based on the vertex pixel coordinates, and the vertex geographic coordinates of the photovoltaic station are calculated based on the origin geographic coordinates, pixel resolution, rotation degree and pixel boundary length.

[0182] The technical solution provided in the embodiments of the present application includes a coordinate calculation module for obtaining the vertex pixel coordinates of the photovoltaic station image and the conversion relationship between the photovoltaic station pixel coordinate system and the geographic coordinate system, and calculating the vertex geographic coordinates of the photovoltaic station based on the vertex pixel coordinates and the conversion relationship; a position relationship determination module for determining the station boundary length of the photovoltaic station based on the vertex geographic coordinates, and determining the number of photovoltaic station images to be split based on the station boundary length and the preset sub-station boundary length, and splitting the photovoltaic station image according to the number of splits to obtain multiple photovoltaic station sub-images and the positional relationship between each photovoltaic station sub-image and the photovoltaic station image; a defect detection module for inputting the multiple photovoltaic station sub-images into a pre-trained component defect detection model, and determining the component defect information in each photovoltaic station sub-image based on the component defect detection model; and a defect positioning module for mapping the component defect information to the geographic coordinate system based on the positional relationship and the conversion relationship to obtain the component defect positioning result of the photovoltaic station. The above-mentioned component defect locating device for a photovoltaic station solves the problems in the prior art of inaccurate component defect judgment results and inability to directly locate defect information. By splitting and detecting defects in the photovoltaic station image, and mapping the component defect information in each photovoltaic station sub-image to the geographic coordinate system based on the positional relationship between the split image and the original photovoltaic station image and the conversion relationship between the image space and the geographic space, the component defect locating result of the photovoltaic station is obtained. This can achieve the purpose of directly locating the component defect information of the photovoltaic station to the geographic coordinate system, thereby improving the accuracy of the component defect judgment result and the timeliness of defect locating.

[0183] In the embodiments of the present application, a component defect location device for a photovoltaic station can be configured in a device or in a component, integrated circuit, or chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. For example, the mobile electronic device can be a mobile phone, tablet computer, laptop computer, PDA, in-vehicle electronic device, wearable device, ultra-mobile personal computer (UMPC), netbook, or personal digital assistant (PDA), etc. The non-mobile electronic device can be a server, network attached storage (NAS), personal computer (PC), television (TV), ATM, or self-service machine, etc., and the embodiments of the present application do not specifically limit this.

[0184] In an embodiment of the present application, a device for locating component defects in a photovoltaic station may be an operating system, which may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0185] The photovoltaic station component defect location device provided in the embodiment of the present application can implement each process implemented in the above-mentioned method embodiments. To avoid repetition, it will not be described here.

[0186] like Figure 6 As shown, an embodiment of the present application also provides an electronic device 600, including a processor 601, a memory 602, and a program or instruction stored in the memory 602 and executable on the processor 601. When the program or instruction is executed by the processor 601, each process of the above-mentioned embodiment of the component defect location method for a photovoltaic station is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0187] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.

[0188] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, each process of the above-mentioned embodiment of the component defect locating method for a photovoltaic station is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0189] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer-readable storage medium, such as a computer read-only memory (ROM), random access memory (RAM), a magnetic disk, or an optical disk.

[0190] The present application also provides a program product comprising program code. When the program product is executed on a computer device, the program code is used to cause the computer device to execute the steps of the methods described above in accordance with various exemplary embodiments of the present application. For example, the computer device can execute a method for locating component defects in a photovoltaic station as described in an embodiment of the present application. The program product can be implemented using any combination of one or more readable media.

[0191] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, it should be noted that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the opposite order according to the functions involved. For example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0192] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of this application, or the part that contributes to the existing technology, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of this application.

[0193] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of this application, ordinary technicians in this field can also make many forms without departing from the purpose of this application and the scope of protection of the claims, all of which are within the protection of this application.

[0194] The above are only preferred embodiments of the present application and the technical principles employed. The present application is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions that are possible for those skilled in the art will not depart from the scope of protection of the present application. Therefore, although the present application has been described in more detail through the above embodiments, the present application is not limited to the above embodiments and may include more other equivalent embodiments without departing from the concept of the present application. The scope of the present application is determined by the scope of the claims.

Claims

1. A method for locating component defects in a photovoltaic station, characterized in that: The method comprises: Acquire vertex pixel coordinates of the photovoltaic station image and a conversion relationship between the photovoltaic station pixel coordinate system and the geographic coordinate system, and calculate the vertex geographic coordinates of the photovoltaic station based on the vertex pixel coordinates and the conversion relationship; Determine the station boundary length of the photovoltaic station based on the vertex geographic coordinates, determine the number of to-be-split photovoltaic station images based on the station boundary length and a preset sub-station boundary length, the number to-be-split includes the number of rows to be split and the number of columns to be split, split the photovoltaic station image according to the number of rows to be split and the number of columns to be split to obtain a plurality of photovoltaic station subgraphs, calculate the pixel boundary length of the photovoltaic station image based on the vertex pixel coordinates, determine the starting vertex pixel coordinates of each photovoltaic station subgraph in the photovoltaic station pixel coordinate system based on the pixel boundary length, the number of rows to be split and the number of columns to be split, obtain a preset overlap ratio between adjacent photovoltaic station subgraphs in the plurality of photovoltaic station subgraphs, determine the ending vertex pixel coordinates of each photovoltaic station subgraph in the photovoltaic station pixel coordinate system based on the sub-pixel boundary length, the starting vertex pixel coordinates and the preset overlap ratio, and obtain a positional relationship between each photovoltaic station subgraph and the photovoltaic station image; Inputting the plurality of photovoltaic site sub-maps into a pre-trained component defect detection model respectively, and determining component defect information in each of the photovoltaic site sub-maps based on the component defect detection model; The component defect information is mapped to the geographic coordinate system based on the position relationship and the conversion relationship to obtain a component defect positioning result of the photovoltaic station.

2. The method for locating component defects in a photovoltaic station according to claim 1, characterized in that: The determining the number of photovoltaic station images to be split based on the station boundary length and the preset sub-station boundary length includes: Calculating the ratio of the total width in the station boundary length to the sub-width in the preset sub-station boundary length by rounding, to obtain the number of columns to be split in the photovoltaic station image; The total height in the station boundary length and the sub-height in the preset sub-station boundary length are rounded off to obtain the number of rows to be split in the photovoltaic station image.

3. The method for locating component defects in a photovoltaic station according to claim 2, characterized in that: The ratio is rounded off and calculated using the following formula: ； in, is the number of rows to be split, is the number of columns to be split, is the total height of the station boundary length, is the sub-height in the preset sub-station boundary length, is the total width of the station boundary length, is the sub-width in the preset sub-station boundary length, This is the rounding algorithm.

4. The method for locating component defects in a photovoltaic station according to claim 3, characterized in that: The component defect information includes the defect type of the component defect and the initial pixel coordinates of the component defect in the photovoltaic station sub-map pixel coordinate system; The mapping of the component defect information to the geographic coordinate system based on the position relationship and the conversion relationship to obtain a component defect positioning result of the photovoltaic station includes: Determining the final pixel coordinates of the component defect in the photovoltaic station pixel coordinate system based on the starting vertex pixel coordinates and the initial pixel coordinates of the component defect in the photovoltaic station sub-image pixel coordinate system; The defect geographic coordinates of the component defect in the geographic coordinate system are determined based on the conversion relationship and the final pixel coordinates, and the defect type of the component defect and the defect geographic coordinates are used as the component defect positioning result of the photovoltaic station.

5. The method for locating component defects in a photovoltaic station according to claim 1, characterized in that: Before inputting the plurality of photovoltaic site submaps into a pre-trained component defect detection model, the method further includes: Obtaining a standard image resolution of a pre-trained component defect detection model and an actual image resolution of each of the photovoltaic site sub-images; resizing the photovoltaic station sub-image based on the standard image resolution and the actual image resolution to obtain a standard photovoltaic station sub-image; Accordingly, the step of inputting the plurality of photovoltaic site sub-maps into a pre-trained component defect detection model includes: Each of the standard photovoltaic site sub-maps is input into a pre-trained component defect detection model.

6. The method for locating component defects in a photovoltaic station according to claim 1, characterized in that: The conversion relationship is an affine transformation matrix between the photovoltaic station pixel coordinate system and the geographic coordinate system, wherein the affine transformation matrix includes the geographic coordinates of the origin of the photovoltaic station pixel coordinate system in the geographic coordinate system, the pixel resolution of the photovoltaic station image, and the rotation degree of the photovoltaic station image; The calculating of the vertex geographic coordinates of the photovoltaic station based on the vertex pixel coordinates and the conversion relationship includes: The pixel boundary length of the photovoltaic station image is calculated based on the vertex pixel coordinates, and the vertex geographic coordinates of the photovoltaic station are calculated based on the origin geographic coordinates, the pixel resolution, the rotation degree and the pixel boundary length.

7. A photovoltaic station component defect location device, characterized in that: The device comprises: A coordinate calculation module is used to obtain the vertex pixel coordinates of the photovoltaic station image and the conversion relationship between the photovoltaic station pixel coordinate system and the geographic coordinate system, and calculate the vertex geographic coordinates of the photovoltaic station based on the vertex pixel coordinates and the conversion relationship; a positional relationship determination module, configured to determine a station boundary length of the photovoltaic station based on the vertex geographic coordinates, determine the number of to-be-split photovoltaic station images based on the station boundary length and a preset sub-station boundary length, the number of to-be-split includes the number of rows to be split and the number of columns to be split, split the photovoltaic station image according to the number of rows to be split and the number of columns to be split to obtain a plurality of photovoltaic station subgraphs, calculate the pixel boundary length of the photovoltaic station image based on the vertex pixel coordinates, determine the starting vertex pixel coordinates of each photovoltaic station subgraph in the photovoltaic station pixel coordinate system based on the pixel boundary length, the number of rows to be split and the number of columns to be split, obtain a preset overlap ratio between adjacent photovoltaic station subgraphs in the plurality of photovoltaic station subgraphs, determine the ending vertex pixel coordinates of each photovoltaic station subgraph in the photovoltaic station pixel coordinate system based on the sub-pixel boundary length, the starting vertex pixel coordinates and the preset overlap ratio, and obtain a positional relationship between each photovoltaic station subgraph and the photovoltaic station image; a defect detection module, configured to input the plurality of photovoltaic site sub-maps into a pre-trained component defect detection model, and determine component defect information in each of the photovoltaic site sub-maps based on the component defect detection model; A defect positioning module is used to map the component defect information to the geographic coordinate system based on the position relationship and the conversion relationship to obtain a component defect positioning result of the photovoltaic station.

8. An electronic device, characterized in that: The method comprises a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of a component defect locating method for a photovoltaic station as described in any one of claims 1 to 6.

9. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by a processor, the steps of the component defect locating method for a photovoltaic station according to any one of claims 1 to 6 are implemented.

Images