Photovoltaic power station component segmentation method, device, electronic equipment and storage medium
By generating the panoramic electronic map and elevation map of the photovoltaic power station, determining the regional coordinates and dividing the photovoltaic power generation group plate images, the problem of inaccurate component segmentation in the photovoltaic power station is solved, and the efficiency of fault location and power station digitization is improved.
Patent Information
- Application Number
- CN202210573522.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-05-25
- Publication Date
- 2025-05-09
- Estimated Expiration
- 2042-05-25
AI Technical Summary
The inaccurate component segmentation in photovoltaic power plants affects the resolution of problems such as fault location, power station digitalization and component operating status monitoring.
By generating the panoramic electronic map of the power station and the power station elevation map of the photovoltaic power station, the regional coordinates of the photovoltaic power generation group plate are determined, the group plate image is cut, and segmented based on the specification and scale information of the photovoltaic module to obtain the component segmentation results.
The accurate segmentation of the image of each photovoltaic power generation group in the photovoltaic power station is achieved, and the solution effect of fault location, power station digitization and component operating status monitoring is improved. The segmentation speed is fast, and deep learning is not required to occupy a large amount of resources.
Smart Images

Figure CN115035051B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of new energy technology, and in particular to a method, device, electronic equipment and storage medium for dividing components of a photovoltaic power station. Background Art
[0002] As countries around the world invest more and more in the development and research of clean and renewable energy, the solar energy industry is developing rapidly. At present, the scale of my country's photovoltaic industry continues to expand and the overall development of the industry is improving. With the development of my country's photovoltaic industry, it is expected that in the next few years, the market capacity of the photovoltaic industry will become the fastest growing business in the future power station sector.
[0003] Component segmentation is one of the key steps to solve many photovoltaic problems. The accuracy of component segmentation will affect the effectiveness of solving problems such as fault location, real-time monitoring of the operating status of each component during the power station digitalization process, and maintenance of the logical numbering of power station components. Therefore, how to achieve accurate component segmentation is an urgent problem to be solved in this field. Summary of the invention
[0004] In this regard, the present application provides a component segmentation method, device, electronic device and storage medium for a photovoltaic power station, which can accurately segment the image of each photovoltaic power generation panel in the photovoltaic power station according to the specification and scale information of the photovoltaic components, thereby improving the solution effect of problems such as fault location, real-time monitoring of the operating status of each component during the digitization process of the power station, and maintenance of the logical numbering of power station components.
[0005] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:
[0006] The first aspect of the present invention discloses a method for dividing components of a photovoltaic power station, comprising:
[0007] Generate a panoramic electronic map of the photovoltaic power station and an elevation map of the power station;
[0008] Determine the regional coordinates of each photovoltaic power generation panel in the photovoltaic power station from the power station elevation map; the photovoltaic power station includes at least one photovoltaic power generation panel; each photovoltaic power generation panel is composed of N photovoltaic modules arranged in sequence, where N is a positive integer;
[0009] According to the regional coordinates of the photovoltaic power generation panels, corresponding photovoltaic power generation panel images are cut out from the panoramic electronic map of the power station;
[0010] Based on the specification and dimension information of the photovoltaic components, each photovoltaic power generation panel image is segmented to obtain a component segmentation result of the photovoltaic power station.
[0011] Optionally, in the above-mentioned photovoltaic power station component segmentation method, after the corresponding photovoltaic power generation panel images are cut out from the panoramic electronic map of the power station according to the regional coordinates of the photovoltaic power generation panels, the method further includes:
[0012] Detecting the regional boundary lines of each of the cropped photovoltaic power generation panel images respectively to obtain the boundary line detection result of each of the photovoltaic power generation panel images;
[0013] According to the regional boundary line detection result, the regional coordinates corresponding to the photovoltaic power generation panel image are adjusted.
[0014] Optionally, in the above-mentioned photovoltaic power station component segmentation method, after segmenting each photovoltaic power generation panel image based on the specification and dimension information of the photovoltaic components to obtain the component segmentation result of the photovoltaic power station, it further includes:
[0015] Obtaining a hot spot detection result of the photovoltaic power station;
[0016] The photovoltaic components generating hot spots in the photovoltaic power station are located according to the hot spot detection result and the component segmentation result.
[0017] Optionally, in the above-mentioned method for segmenting components of a photovoltaic power station, generating a panoramic electronic map of the photovoltaic power station and a power station elevation map includes:
[0018] The images of each photovoltaic power generation panel in the photovoltaic power station are collected respectively to obtain the image of each photovoltaic power generation panel;
[0019] The images of all the photovoltaic power generation panels are processed by using image processing software to obtain a panoramic electronic map of the power station and an elevation map of the power station.
[0020] Optionally, in the above-mentioned photovoltaic power station component segmentation method, determining the regional coordinates of each photovoltaic power generation panel in the photovoltaic power station from the power station elevation map includes:
[0021] Determining an elevation threshold according to the elevation information of the elevation map of the power station;
[0022] According to the elevation threshold, the features of each continuous area in the elevation map of the power station are extracted to obtain the regional features of each continuous area;
[0023] Among the regional features of all the continuous regions, each continuous region whose regional features meet the preset photovoltaic power generation panel features is determined, and the regional coordinates corresponding to each of the determined continuous regions are respectively used as the regional coordinates of each of the photovoltaic power generation panels.
[0024] Optionally, in the above-mentioned photovoltaic power station component segmentation method, based on the specification and dimension information of the photovoltaic components, each photovoltaic power generation panel image is segmented to obtain the component segmentation result of the photovoltaic power station, including:
[0025] Determine the UTM coordinates of the corner points of each photovoltaic panel image;
[0026] For each of the photovoltaic power generation panel images, segmentation is performed according to the corresponding corner point UTM coordinates, the component height and the component width of the photovoltaic component to obtain the component segmentation result of the photovoltaic power station.
[0027] The second aspect of the present invention discloses a component separation device for a photovoltaic power station, comprising:
[0028] A generating unit, used to generate a panoramic electronic map of the photovoltaic power station and an elevation map of the power station;
[0029] A determination unit, used to determine the regional coordinates of each photovoltaic power generation panel in the photovoltaic power station from the power station elevation map; the photovoltaic power station includes at least one photovoltaic power generation panel; each photovoltaic power generation panel is composed of N photovoltaic modules arranged in sequence, where N is a positive integer;
[0030] A cutting unit, used for cutting out corresponding photovoltaic power generation panel images from the panoramic electronic map of the power station according to the regional coordinates of the photovoltaic power generation panels;
[0031] The segmentation unit is used to segment each of the photovoltaic power generation panel images based on the specification and dimension information of the photovoltaic components to obtain the component segmentation result of the photovoltaic power station.
[0032] Optionally, the above-mentioned photovoltaic power station component separation device further includes:
[0033] A detection unit, used to detect the regional boundary lines of each of the cropped photovoltaic power generation panel images respectively, to obtain the boundary line detection result of each of the photovoltaic power generation panel images;
[0034] The adjustment unit is used to adjust the regional coordinates corresponding to the photovoltaic power generation panel image according to the regional boundary line detection result.
[0035] Optionally, the above-mentioned photovoltaic power station component separation device further includes:
[0036] An acquisition unit, used to acquire a hot spot detection result of the photovoltaic power station;
[0037] A positioning unit is used to locate the photovoltaic components that generate hot spots in the photovoltaic power station according to the hot spot detection result and the component segmentation result.
[0038] The third aspect of the present invention discloses an electronic device, including a processor and a memory; wherein:
[0039] The memory is used to store computer instructions;
[0040] The processor is used to execute the computer instructions stored in the memory, specifically to execute the component segmentation method of the photovoltaic power station as described in any one of the items disclosed in the first aspect.
[0041] A fourth aspect of the present invention discloses a storage medium for storing a program, wherein when the program is executed, it is used to implement the component segmentation method of a photovoltaic power station as described in any one of the items disclosed in the first aspect.
[0042] The present invention provides a component segmentation method for a photovoltaic power station. After generating a panoramic electronic map and an elevation map of the photovoltaic power station, the method determines the regional coordinates of each photovoltaic power generation panel in the photovoltaic power station from the elevation map of the photovoltaic power station; the photovoltaic power station includes at least one photovoltaic power generation panel; each photovoltaic power generation panel is composed of N photovoltaic components arranged in sequence, and N is a positive integer; then the corresponding photovoltaic power generation panel image is cut out from the panoramic electronic map of the power station, and finally, based on the specification and scale information of the photovoltaic components, each photovoltaic power generation panel image is segmented to obtain the component segmentation result of the photovoltaic power station, that is, the solution provided by the present application can accurately segment each photovoltaic power generation panel image in the photovoltaic power station through the specification and scale information of the photovoltaic components, thereby improving the solution effect of problems such as fault location, real-time monitoring of the operating status of each component during the digitization process of the power station, and maintenance of the logical numbering of power station components; and the segmentation speed is fast, and there is no need for deep learning to occupy a large amount of resources, so the efficiency is higher. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.
[0044] Figure 1 A flowchart of a method for dividing components of a photovoltaic power station provided in an embodiment of the present application;
[0045] Figure 2 A flow chart for generating a panoramic electronic map of a power station and a power station elevation map provided in an embodiment of the present application;
[0046] Figure 3 A visible light panoramic electronic map of a power station provided in an embodiment of the present application;
[0047] Figure 4 A visible light elevation map of a power station provided in an embodiment of the present application;
[0048] Figure 5 A flowchart for obtaining regional coordinates of a photovoltaic power generation panel provided in an embodiment of the present application;
[0049] Figure 6 A power station elevation map under an elevation threshold provided in an embodiment of the present application;
[0050] Figure 7 A schematic diagram of a component area in a power station elevation diagram provided in an embodiment of the present application;
[0051] Figure 8 A schematic diagram of a photovoltaic power generation panel provided in an embodiment of the present application;
[0052] Fig. 9 A flow chart of component segmentation of a photovoltaic panel image provided in an embodiment of the present application;
[0053] Fig.10 A schematic diagram of component segmentation calculation of a photovoltaic power generation panel provided in an embodiment of the present application;
[0054] Fig.11 A display diagram of component segmentation results of a photovoltaic power generation panel provided in an embodiment of the present application;
[0055] Fig.12 and Fig.13 Flow charts of two other photovoltaic power station component segmentation methods provided in embodiments of the present application;
[0056] Fig.14 An image of a visible light photovoltaic power generation panel with garlands and vegetation blocking the image provided in an embodiment of the present application;
[0057] Fig.15 An infrared photovoltaic power generation panel image with blurred line components provided in an embodiment of the present application;
[0058] Fig.16 A schematic diagram of the structure of a component separation device for a photovoltaic power station provided in an embodiment of the present application. DETAILED DESCRIPTION
[0059] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field without creative work according to the embodiments of the present invention are within the scope of protection of the present invention.
[0060] The embodiment of the present application provides a component segmentation method for a photovoltaic power station, which can accurately segment the image of each photovoltaic power generation panel in the photovoltaic power station according to the specification and scale information of the photovoltaic components, thereby improving the solution effect of problems such as fault location, real-time monitoring of the operating status of each component during the digitization process of the power station, and maintenance of the logical numbering of power station components.
[0061] See also Figure 1 , the component segmentation method of the photovoltaic power station mainly includes the following steps:
[0062] S100: Generate a panoramic electronic map of the photovoltaic power station and an elevation map of the power station.
[0063] In practical applications, the specific method of generating a panoramic electronic map of a photovoltaic power station and a power station elevation map can be as follows: Figure 2 As shown, it mainly includes the following steps:
[0064] S200 , respectively collect images of each photovoltaic power generation panel in the photovoltaic power station to obtain an image of each photovoltaic power generation panel.
[0065] In practical applications, the image of the photovoltaic power generation panel can be obtained by inspecting the photovoltaic power station through a preset acquisition device according to a preset acquisition path. The preset acquisition device can be a drone or an aerial photography aircraft; of course, it can also be other existing devices with image acquisition functions, which are not specifically limited in this application and are within the protection scope of this application.
[0066] Specifically, the preset collection path can be manually formulated or obtained by intelligent planning using corresponding equipment based on the actual distribution characteristics of each photovoltaic power generation group panel in the photovoltaic power station and the distribution characteristics of the photovoltaic components within the group.
[0067] Assuming that the preset acquisition device is a drone, the drone can be allowed to inspect the photovoltaic power station according to the preset acquisition path, collect images of each photovoltaic power generation panel, and use the GPS geographic coordinates of each acquisition point as the GPS coordinates of the center of the image.
[0068] It should be noted that the image type of the image of the photovoltaic power generation panel can be a visible light image or an infrared light image; of course, it can also be other types of images, depending on the specific application environment and user needs, all of which are within the protection scope of this application.
[0069] S202: Process the images of all photovoltaic power generation panels using image processing software to obtain a panoramic electronic map of the photovoltaic power station and an elevation map of the power station.
[0070] In practical applications, the images of each photovoltaic power generation panel in the photovoltaic power station can be input into the image processing software for processing to generate a panoramic electronic map of the photovoltaic power station and an elevation map of the power station.
[0071] Among them, the image processing software can be pix4dMapper, or other image processing software that can generate a panoramic electronic map of the power station and a ground elevation map of the power station. This application does not specifically limit the specific type of image processing software, all of which are within the scope of protection of this application.
[0072] Assuming that the image type of the photovoltaic power generation panel is a visible light image, the panoramic electronic map of the photovoltaic power station generated by the pix4dMapper software can be as follows: Figure 3 As shown in the figure, the generated elevation map of the photovoltaic power station can be Figure 4 shown.
[0073] S102: Determine the regional coordinates of each photovoltaic power generation panel in the photovoltaic power station from the power station elevation map.
[0074] The photovoltaic power station includes at least one photovoltaic power generation panel; each photovoltaic power generation panel is composed of N photovoltaic components arranged in sequence, where N is a positive integer.
[0075] In practical applications, the specific process of executing step S102 and determining the regional coordinates of each photovoltaic power generation panel in the photovoltaic power station from the power station elevation map can be as follows: Figure 5 As shown, it mainly includes the following steps:
[0076] S300: Determine an elevation threshold according to elevation information of the power station elevation map.
[0077] Among them, the elevation threshold of the power station elevation map can be set according to the elevation information of each photovoltaic power generation panel in the power station elevation map, so as to obtain the elevation threshold that can distinguish object features and non-object features in the power station elevation map.
[0078] It should be noted that the specific value of the elevation threshold can be determined according to the application environment and user needs. This application does not make any specific limitations and all values are within the protection scope of this application.
[0079] S302 , extracting features of each continuous area in the power station elevation map according to the elevation threshold, and obtaining regional features of each continuous area.
[0080] In practical applications, the elevation information of the power station elevation map can be adjusted to the elevation threshold, and then the features of each continuous area in the power station elevation map can be extracted to obtain the regional features of each continuous area in the map. Among them, if the power station elevation map is an infrared light power station elevation map, the power station elevation map adjusted to the elevation threshold can be as follows Figure 6 shown.
[0081] S304, among the regional features of all the continuous regions, determine each continuous region whose regional features meet the preset photovoltaic power generation panel features, and use the regional coordinates corresponding to each of the determined continuous regions as the regional coordinates of each photovoltaic power generation panel.
[0082] Since the regional features of photovoltaic panels in a photovoltaic power station are different from other regional features, it is possible to determine each continuous area whose regional features meet the preset photovoltaic panel features based on the regional features of each continuous area extracted, thereby obtaining the component area in the power station elevation map. Figure 7 shown.
[0083] In practical applications, since the characteristics of photovoltaic power generation panels are generally regular rectangles, it is possible to determine whether the regional characteristics of each continuous area in the power station elevation map are regular rectangles, thereby determining each continuous area whose regional characteristics meet the preset photovoltaic power generation panel characteristics, and use the regional coordinates corresponding to each determined continuous area as the regional coordinates of each photovoltaic power generation panel.
[0084] S104 , according to the regional coordinates of the photovoltaic power generation panels, respectively cut out corresponding photovoltaic power generation panel images from the panoramic electronic map of the power station.
[0085] In practical applications, the photovoltaic panel images corresponding to the regional coordinates of each photovoltaic panel can be cut out from the panoramic electronic map of the power station. Figure 8 shown.
[0086] S106 , based on the specification and dimension information of the photovoltaic components, segment the images of each photovoltaic power generation group panel to obtain the component segmentation result of the photovoltaic power station.
[0087] In practical applications, the specific process of executing step S106 and segmenting each photovoltaic power generation panel image based on the specification and dimension information of the photovoltaic components to obtain the component segmentation result of the photovoltaic power station can be as follows: Fig. 9 As shown, it mainly includes the following steps:
[0088] S400: Determine the UTM coordinates of the corner points of each photovoltaic panel image.
[0089] In practical applications, the UTM coordinates of the corner points of the photovoltaic panel image can be the UTM coordinates corresponding to each corner point of the photovoltaic panel image. Each photovoltaic panel image generally includes: the UTM coordinates of the upper left corner point of the image, the UTM coordinates of the upper right corner point of the image, the UTM coordinates of the lower left corner point of the image, and the UTM coordinates of the lower right corner point of the image, that is, Fig.10 and Fig.11 shown.
[0090] Generally, the UTM coordinates of the corner points of different photovoltaic panel images in a photovoltaic power station are different.
[0091] Specifically, the corresponding corner points can be found from the panoramic electronic map of the power station according to the corner point coordinates of the four corner points in the regional coordinates of each photovoltaic power generation panel, and then the UTM coordinates of each corresponding corner point can be obtained to determine the UTM coordinates of the corner points of each photovoltaic power generation panel image.
[0092] S402 , segment each photovoltaic power generation panel image according to its corresponding corner point UTM coordinates, component height and component width of the photovoltaic component, to obtain a component segmentation result of the photovoltaic power station.
[0093] In practical applications, the corresponding photovoltaic panel image can be automatically segmented according to the height and width of the photovoltaic module and the UTM coordinates of the corner points of each photovoltaic panel image, and the photovoltaic panel image can be segmented into M rows and N columns of grids, each grid representing a photovoltaic module, that is, Fig.10 shown.
[0094] Combination Fig.10 and Fig.11 The UTM coordinates of the corner points shown, assuming that the height of the photovoltaic module is 1.5m and the width of the module is 1m, then
[0095] Based on the above principles, a component segmentation method for a photovoltaic power station provided in an embodiment of the present application determines the regional coordinates of each photovoltaic power generation panel in the photovoltaic power station from the power station elevation map of the photovoltaic power station after generating a panoramic electronic map of the photovoltaic power station and a power station elevation map of the photovoltaic power station; the photovoltaic power station includes at least one photovoltaic power generation panel; each photovoltaic power generation panel is composed of N photovoltaic components arranged in sequence, N is a positive integer; then the corresponding photovoltaic power generation panel image is cut out from the panoramic electronic map of the power station, and finally, based on the specification and scale information of the photovoltaic components, each photovoltaic power generation panel image is segmented to obtain the component segmentation result of the photovoltaic power station, that is, the solution provided by the present application can accurately segment each photovoltaic power generation panel image in the photovoltaic power station through the specification and scale information of the photovoltaic components, thereby improving the solution effect of problems such as fault location, real-time monitoring of the operating status of each component during the digitization process of the power station, and maintenance of the logical numbering of power station components; and the segmentation speed is fast, and no deep learning requires a large amount of resources, so the efficiency is higher.
[0096] It is worth noting that in the existing method of segmenting the panoramic electronic map of the power station through machine learning, if the panoramic electronic map of the power station used for segmentation is a visible light image, there will often be line distortion, breakage and other streaking phenomena in some local areas of the image, or there will be a phenomenon of grass and trees blocking components, such as Fig.14 As shown; if the panoramic electronic map of the power station used for segmentation is an infrared image, if the solar irradiance is insufficient, the component lines will be blurred in the infrared image, such as Fig.15 As shown, the above situations will reduce the accuracy of the method of using machine learning to segment components. The method provided in this application is to first segment the area where the photovoltaic power generation panels are located through the ground elevation model, and then segment the segmented photovoltaic power generation panel area based on the actual scale information corresponding to the component specifications. This can completely avoid misdetecting objects outside the photovoltaic power generation panel area as components, thereby improving the accuracy of component segmentation.
[0097] In practical applications, since there will be certain calculation errors in the process of generating the power station elevation map by image processing software such as pix4dMapper, there will be certain errors in the regional edges of the photovoltaic power generation panels in the obtained power station elevation map. In this regard, another embodiment of the present application executes step S104 and cuts out the corresponding photovoltaic power generation panel images from the panoramic electronic map of the power station according to the regional coordinates of the photovoltaic power generation panels. Fig.12 , and may also include the following steps:
[0098] S500 , detecting the regional boundary lines of each cropped photovoltaic power generation panel image respectively, and obtaining the boundary line detection result of each photovoltaic power generation panel image.
[0099] The process of obtaining the regional boundary line detection result of each photovoltaic panel image is as follows:
[0100] A: The photovoltaic panel image is subjected to grayscale processing and edge processing in sequence to obtain an edge image of the photovoltaic panel image.
[0101] Among them, the algorithm used for edge processing can be the Canny edge detection algorithm; of course, it is not limited to this and other existing edge processing algorithms can also be used. This application does not make specific limitations on them and they are all within the protection scope of this application.
[0102] B: Use Hough transform to extract straight line features in the edge image of photovoltaic panels and obtain all straight lines in the edge image.
[0103] C: Determine the four boundary lines of the photovoltaic panel image based on the spacing between the straight lines in the edge image.
[0104] S502: Adjust the regional coordinates of the corresponding photovoltaic panel image according to the regional boundary line detection result.
[0105] In practical applications, the pixel coordinates of the corner points where every two boundary lines intersect can be calculated based on the four boundary lines determined in the regional boundary line detection results, and the regional coordinates of the corresponding photovoltaic power generation panel image can be adjusted according to the calculated pixel coordinates, so that the regional coordinates of the photovoltaic power generation panels in the photovoltaic power station are more accurate.
[0106] It should be noted that in the process of adjusting the regional coordinates of the corresponding photovoltaic power generation panel image according to the boundary line detection results, in addition to adjusting the regional coordinates of the visible light photovoltaic power generation panel image according to the boundary line area detection results of the visible light photovoltaic power generation panel image, or adjusting the regional coordinates of the infrared light photovoltaic power generation panel image according to the boundary line area detection results of the infrared light photovoltaic power generation panel image, it is also possible to adjust the regional coordinates of the infrared light photovoltaic panel image according to the boundary line area detection results of the visible light photovoltaic power generation panel image; or, adjust the regional coordinates of the visible light photovoltaic panel image according to the boundary line area detection results of the infrared light photovoltaic power generation panel image; it can be determined according to the specific application environment and user needs, and are all within the protection scope of the present application.
[0107] In this embodiment, regional boundary line detection can be performed on the photovoltaic power generation panel image cut out from the panoramic electronic map of the power station to adjust the regional coordinates of the corresponding photovoltaic power generation panel image, so that the photovoltaic power generation panel image involved in subsequent component segmentation is closer to the actual situation, further improving the accuracy of component segmentation.
[0108] During the long-term use of photovoltaic modules, flying birds, dust, fallen leaves and other obstructions will fall on the modules, causing the modules to form hot spot effects. Domestic photovoltaic power stations are generally built on large hillsides, Gobi, plains, swamps, waters, factory roofs, residential roofs, etc. The scale, form, and distribution of different photovoltaic power stations are quite different, resulting in many inconveniences in the later operation and maintenance inspection process. In particular, the larger the scale of the photovoltaic power generation project, the more complicated the inspection.
[0109] At present, infrared images of photovoltaic modules are generally collected by drones carrying infrared cameras, and the temperature distribution of photovoltaic panels under different working conditions is analyzed to achieve hot spot detection. However, the existing solution can only detect whether photovoltaic panels have hot spots, but cannot locate the specific location of the components where the hot spots are located, making operation and maintenance difficult.
[0110] In this regard, in another embodiment provided by the present application, after executing step S106, segmenting each photovoltaic power generation panel image based on the specification and dimension information of the photovoltaic module to obtain the component segmentation result of the photovoltaic power station, refer to Fig.13 The photovoltaic power station component segmentation method may further include the following steps:
[0111] S700: Obtain hot spot detection results of the photovoltaic power station.
[0112] In actual applications, the infrared image of the photovoltaic power station can be obtained first, and then hot spot detection can be performed on the infrared image of the power station to obtain the hot spot detection result of the photovoltaic power station; of course, the specific method of obtaining the hot spot detection result of the photovoltaic power station can also be determined according to the specific application environment and user needs. This application does not make any specific limitations and is within the protection scope of this application.
[0113] S702: Locate the photovoltaic components that generate hot spots in the photovoltaic power station according to the hot spot detection result and the component segmentation result.
[0114] In practical applications, the hot spot detection results of the photovoltaic power station can be used to first determine the photovoltaic panels that produce hot spots in the photovoltaic power station; then, for each hot spot photovoltaic power generation panel that produces a hot spot, the hot spot photovoltaic power generation panel is compared with the component segmentation results of the corresponding panel, and the photovoltaic component that produces the hot spot in the photovoltaic power station is located according to the position of the hot spot in the hot spot photovoltaic power generation panel.
[0115] It should be noted that since visible light images have less noise than infrared light images, they can more clearly show the component areas and non-component areas in photovoltaic power stations. Therefore, the positioning results of photovoltaic components that produce hot spots in photovoltaic power stations can be located through the visible light image segmentation results. Compared with the positioning results obtained based on the infrared light image segmentation results, the accuracy is higher and the operation and maintenance efficiency can be further improved.
[0116] It should also be noted that, in the specific application process, the photovoltaic components that produce hot spots in the photovoltaic power station can be located first by using the infrared light image component segmentation results and the hot spot detection results, and then the photovoltaic components that produce hot spots in the photovoltaic power station can be relocated based on the mapping relationship between the visible light photovoltaic image component segmentation results and the infrared light image component segmentation results, so that the positioning of the hot spot photovoltaic components is more accurate.
[0117] In the component segmentation method of the photovoltaic power station provided in the present embodiment, each photovoltaic power generation panel image can be segmented based on the specification and scale information of the photovoltaic components. After obtaining the component segmentation result of the photovoltaic power station, the photovoltaic components that produce hot spots in the photovoltaic power station can be located in combination with the hot spot detection result of the photovoltaic power station. This solves the problem that the prior art can only detect whether the photovoltaic power generation panels have hot spots but cannot locate the specific position of the component where the hot spots are located, making operation and maintenance difficult.
[0118] Based on the photovoltaic power station component segmentation method proposed in the above embodiment, another embodiment of the present application also provides a photovoltaic power station component segmentation device, see Fig.16 , the device mainly includes:
[0119] The generating unit 100 is used to generate a panoramic electronic map of the photovoltaic power station and a power station elevation map.
[0120] The determination unit 102 is used to determine the regional coordinates of each photovoltaic power generation panel in the photovoltaic power station from the power station elevation map; the photovoltaic power station includes at least one photovoltaic power generation panel; each photovoltaic power generation panel is composed of N photovoltaic components arranged in sequence, and N is a positive integer.
[0121] The cropping unit 104 is used to crop corresponding photovoltaic power generation panel images from the panoramic electronic map of the power station according to the regional coordinates of the photovoltaic power generation panels.
[0122] The segmentation unit 106 is used to segment each photovoltaic power generation panel image based on the specification and dimension information of the photovoltaic components to obtain the component segmentation result of the photovoltaic power station.
[0123] Optionally, the generating unit 100 is specifically used for:
[0124] The images of each photovoltaic power generation panel in the photovoltaic power station are collected respectively to obtain the image of each photovoltaic power generation panel;
[0125] The images of all the photovoltaic power generation panels are processed by using image processing software to obtain a panoramic electronic map of the power station and an elevation map of the power station.
[0126] Optionally, the determining unit 102 is specifically configured to:
[0127] The elevation threshold is determined based on the elevation information of the power station elevation map.
[0128] According to the elevation threshold, the features of each continuous area in the power station elevation map are extracted to obtain the regional features of each continuous area.
[0129] Among the regional features of all continuous regions, each continuous region whose regional features meet the preset photovoltaic power generation panel features is determined, and the regional coordinates corresponding to each determined continuous region are respectively used as the regional coordinates of each photovoltaic power generation panel.
[0130] Optionally, the segmentation unit 106 is specifically configured to:
[0131] Determine the UTM coordinates of the corner points of each photovoltaic panel image.
[0132] For each photovoltaic power generation panel image, segmentation is performed according to the corresponding corner point UTM coordinates, the component height and component width of the photovoltaic component to obtain the component segmentation result of the photovoltaic power station.
[0133] Based on the component segmentation device of the photovoltaic power station provided by the above-mentioned embodiment, the generating unit 100 can be used to generate a panoramic electronic map and an elevation map of the photovoltaic power station; the determining unit 102 is used to determine the regional coordinates of each photovoltaic power generation panel in the photovoltaic power station from the elevation map of the power station; the photovoltaic power station includes at least one photovoltaic power generation panel; each photovoltaic power generation panel is composed of N photovoltaic components arranged in sequence, and N is a positive integer; the cutting unit 104 is used to cut out the corresponding photovoltaic power generation panel images from the panoramic electronic map of the power station according to the regional coordinates of the photovoltaic power generation panel; the segmentation unit 106 is used to segment each photovoltaic power generation panel image based on the specification and scale information of the photovoltaic component to obtain the component segmentation result of the photovoltaic power station; each photovoltaic power generation panel image in the photovoltaic power station can be accurately segmented according to the specification and scale information of the photovoltaic component, thereby improving the solution effect of problems such as fault location, real-time monitoring of the operating status of each component during the digitization process of the power station, and maintenance of the logical numbering of the power station components; and the segmentation speed is fast, and there is no need for deep learning to occupy a large amount of resources, so the efficiency is higher.
[0134] Optionally, based on the component segmentation device of the photovoltaic power station provided in the above embodiment, the component segmentation device of the photovoltaic power station provided in this embodiment further includes:
[0135] The detection unit is used to detect the regional boundary lines of each cropped photovoltaic power generation panel image respectively to obtain the boundary line detection result of each photovoltaic power generation panel image.
[0136] The adjustment unit is used to adjust the regional coordinates of the corresponding photovoltaic power generation panel image according to the regional boundary line detection result.
[0137] In this embodiment, the detection unit can be used to perform regional boundary line detection on the photovoltaic power generation panel image cut out from the panoramic electronic map of the power station, and then the adjustment unit can be used to adjust the regional coordinates of the corresponding photovoltaic power generation panel image, so that the photovoltaic power generation panel image subsequently involved in component segmentation is closer to the actual situation, further improving the accuracy of component segmentation.
[0138] Optionally, based on the component segmentation device of the photovoltaic power station provided in the above embodiment, the component segmentation device of the photovoltaic power station provided in this embodiment further includes:
[0139] The acquisition unit is used to obtain the hot spot detection result of the photovoltaic power station.
[0140] The positioning unit is used to locate the photovoltaic components that generate hot spots in the photovoltaic power station according to the hot spot detection result and the component segmentation result.
[0141] In this embodiment, the hot spot detection results of the photovoltaic power station can be obtained by the acquisition unit, and then the photovoltaic components that produce hot spots in the photovoltaic power station can be located by the positioning unit in combination with the hot spot detection results of the photovoltaic power station and the component segmentation results. This solves the problem that the existing technology can only detect whether the photovoltaic power generation panel has a hot spot but cannot locate the specific position of the component where the hot spot is located, making operation and maintenance difficult.
[0142] Optionally, another embodiment of the present application further provides an electronic device, including: a processor and a memory, wherein:
[0143] The memory is used to store computer instructions;
[0144] The processor is used to execute the computer instructions stored in the memory, specifically to execute the component segmentation method of the photovoltaic power station as described in any of the above embodiments.
[0145] It should be noted that for the relevant description of the component segmentation method of the photovoltaic power station, please refer to Figures 1 to 15 The corresponding embodiments are sufficient and will not be described in detail here.
[0146] Optionally, another embodiment of the present application further provides a storage medium for storing a program, and when the program is executed, it is used to implement the component segmentation method of the photovoltaic power station as described in any of the above embodiments.
[0147] It should be noted that for the relevant description of the component segmentation method of the photovoltaic power station, please refer to Figures 1 to 15 The corresponding embodiments are not described in detail here.
[0148] The features recorded in the various embodiments in this specification can be replaced or combined with each other, and the same and similar parts between the various embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. The system and system embodiments described above are only schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative work.
[0149] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.
[0150] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.
[0151] It should also be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including 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, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.
Claims
1. A method for dividing components of a photovoltaic power station, characterized in that: include: Generate a panoramic electronic map of the photovoltaic power station and an elevation map of the power station; Determine the regional coordinates of each photovoltaic power generation panel in the photovoltaic power station from the power station elevation map; the photovoltaic power station includes at least one photovoltaic power generation panel; each photovoltaic power generation panel is composed of N photovoltaic modules arranged in sequence, where N is a positive integer; According to the regional coordinates of the photovoltaic power generation panels, corresponding photovoltaic power generation panel images are cut out from the panoramic electronic map of the power station; Based on the specification and dimension information of the photovoltaic components, each photovoltaic power generation panel image is segmented to obtain a component segmentation result of the photovoltaic power station; Wherein, after the corresponding photovoltaic power generation panel images are cut out from the panoramic electronic map of the power station according to the regional coordinates of the photovoltaic power generation panel, the method further includes: Detecting the regional boundary lines of each of the cropped photovoltaic power generation panel images respectively to obtain the boundary line detection result of each of the photovoltaic power generation panel images; According to the regional boundary line detection result, the regional coordinates corresponding to the photovoltaic power generation panel image are adjusted.
2. The method for dividing components of a photovoltaic power station according to claim 1, characterized in that: After segmenting each photovoltaic power generation panel image based on the specification and dimension information of the photovoltaic components to obtain the component segmentation result of the photovoltaic power station, the method further includes: Obtaining a hot spot detection result of the photovoltaic power station; The photovoltaic components generating hot spots in the photovoltaic power station are located according to the hot spot detection result and the component segmentation result.
3. The method for dividing components of a photovoltaic power station according to claim 1, characterized in that: Generating a panoramic electronic map of the photovoltaic power station and a power station elevation map, including: The images of each photovoltaic power generation panel in the photovoltaic power station are collected respectively to obtain the image of each photovoltaic power generation panel; The images of all the photovoltaic power generation panels are processed by using image processing software to obtain a panoramic electronic map of the power station and an elevation map of the power station.
4. The method for dividing components of a photovoltaic power station according to claim 1, characterized in that: Determining the regional coordinates of each photovoltaic power generation panel in the photovoltaic power station from the power station elevation map includes: Determining an elevation threshold according to the elevation information of the elevation map of the power station; According to the elevation threshold, the features of each continuous area in the elevation map of the power station are extracted to obtain the regional features of each continuous area; Among the regional features of all the continuous regions, each continuous region whose regional features meet the preset photovoltaic power generation panel features is determined, and the regional coordinates corresponding to each of the determined continuous regions are respectively used as the regional coordinates of each of the photovoltaic power generation panels.
5. The method for dividing components of a photovoltaic power station according to claim 1, characterized in that: Based on the specification and dimension information of the photovoltaic components, each photovoltaic power generation panel image is segmented to obtain the component segmentation result of the photovoltaic power station, including: Determine the UTM coordinates of the corner points of each photovoltaic panel image; For each of the photovoltaic power generation panel images, segmentation is performed according to the corresponding corner point UTM coordinates, the component height and the component width of the photovoltaic component to obtain the component segmentation result of the photovoltaic power station.
6. A component separation device for a photovoltaic power station, characterized in that: include: A generating unit, used to generate a panoramic electronic map of the photovoltaic power station and an elevation map of the power station; A determination unit, used to determine the regional coordinates of each photovoltaic power generation panel in the photovoltaic power station from the power station elevation map; the photovoltaic power station includes at least one photovoltaic power generation panel; each photovoltaic power generation panel is composed of N photovoltaic modules arranged in sequence, where N is a positive integer; A cutting unit, used for cutting out corresponding photovoltaic power generation panel images from the panoramic electronic map of the power station according to the regional coordinates of the photovoltaic power generation panels; A segmentation unit, configured to segment each photovoltaic power generation panel image based on the specification and dimension information of the photovoltaic components, to obtain a component segmentation result of the photovoltaic power station; A detection unit, used to detect the regional boundary lines of each of the cropped photovoltaic power generation panel images respectively, to obtain the boundary line detection result of each of the photovoltaic power generation panel images; The adjustment unit is used to adjust the regional coordinates corresponding to the photovoltaic power generation panel image according to the regional boundary line detection result.
7. The photovoltaic power station component separation device according to claim 6, characterized in that: Also includes: An acquisition unit, used for acquiring a hot spot detection result of the photovoltaic power station; A positioning unit is used to locate the photovoltaic components that generate hot spots in the photovoltaic power station according to the hot spot detection result and the component segmentation result.
8. An electronic device, characterized in that: comprising a processor and a memory; wherein: The memory is used to store computer instructions; The processor is used to execute the computer instructions stored in the memory, specifically to execute the component segmentation method for a photovoltaic power station as described in any one of claims 1 to 5.
9. A storage medium, characterized in that: Used to store a program, which, when executed, is used to implement the component segmentation method for a photovoltaic power station as claimed in any one of claims 1 to 5.
Citation Information
Patent Citations
Photovoltaic power station assembly defect inspection system and defect processing method thereof
CN112862777A
Fault positioning method and device of photovoltaic module and storage medium
CN114140421A
Photovoltaic module defect detection method and system
CN114187260A