Photovoltaic panel dust detection method, device, electronic device and storage medium

Abstract

The present invention discloses a method, device, electronic device, and storage medium for detecting dust accumulation on photovoltaic panels. The method comprises: acquiring a first image of a photovoltaic panel in a target area and determining a photovoltaic module image of each photovoltaic module in the first image; performing dust identification on the photovoltaic module image based on an image processing model to determine a first detection result for each photovoltaic module; the image processing model is a model based on an artificial neural network; performing dust identification on the photovoltaic module image based on a preset image processing method to determine a second detection result for each photovoltaic module; and determining whether the photovoltaic module is a dust module based on the first detection result and the second detection result. The technical solution of the present invention improves the accuracy of photovoltaic panel dust detection by combining the detection results of the photovoltaic module image using the neural network model with the detection results of the photovoltaic module image using the traditional image processing method to determine whether the photovoltaic module is a dust module.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to a method, device, electronic device and storage medium for detecting dust accumulation on photovoltaic panels. Background Art

[0002] With the rapid development of solar power generation technology, photovoltaic panels, as core components of solar power generation systems, have a significant impact on the overall system's power generation performance. However, during actual operation, dust, dirt, and other contaminants easily accumulate on the surface of photovoltaic panels. These contaminants block solar radiation, reducing the panels' photoelectric conversion efficiency and leading to a significant decrease in power generation. Therefore, timely, accurate, and efficient dust detection on photovoltaic panel surfaces is crucial.

[0003] Currently, deep learning models are commonly used to identify photovoltaic panel images and determine the presence of dust deposits based on the recognition results. However, the performance of deep learning models is highly dependent on the richness and quality of labeled data. In real-world scenarios, it is difficult to obtain sufficient and diverse photovoltaic panel dust image data. In addition, factors such as the uneven distribution of dust on the surface of photovoltaic modules and complex and variable lighting conditions further increase the difficulty of dust detection, resulting in the possibility of missed detections and false detections in real-world applications. Summary of the Invention

[0004] The present invention provides a photovoltaic panel dust accumulation detection method, device, electronic equipment and storage medium, so as to improve the accuracy of photovoltaic panel dust accumulation detection.

[0005] According to one aspect of the present invention, a method for detecting dust accumulation on photovoltaic panels is provided, the method comprising:

[0006] Acquire a first image of a photovoltaic panel in a target area, and determine a photovoltaic assembly image of each photovoltaic assembly in the first image; the photovoltaic panel includes a plurality of photovoltaic assemblies; and the first image is a visible light image;

[0007] performing dust recognition on the photovoltaic module image based on an image processing model to determine a first detection result for each photovoltaic module;

[0008] performing dust identification on the photovoltaic module image based on a preset image processing method to determine a second detection result for each photovoltaic module; the preset image processing method is a method for processing images based on statistical principles and mathematical analysis principles;

[0009] Based on the first detection result and the second detection result, it is determined whether the photovoltaic component is a dust component; the dust component is the photovoltaic component with accumulated dust.

[0010] According to another aspect of the present invention, a photovoltaic panel dust accumulation detection device is provided, the device comprising:

[0011] An image determination module is configured to acquire a first image of a photovoltaic panel in a target area and determine a photovoltaic assembly image of each photovoltaic assembly in the first image; the photovoltaic panel includes a plurality of photovoltaic assemblies; and the first image is a visible light image.

[0012] a first detection module, configured to perform dust recognition on the photovoltaic module image based on an image processing model, and determine a first detection result for each photovoltaic module;

[0013] a second detection module, configured to perform dust identification on the photovoltaic module image based on a preset image processing method, and determine a second detection result for each photovoltaic module; the preset image processing method is a method for processing images based on statistical principles and mathematical analysis principles;

[0014] The third detection module is configured to determine whether the photovoltaic component is a dust component based on the first detection result and the second detection result; the dust component is a photovoltaic component with accumulated dust.

[0015] According to another aspect of the present invention, an electronic device is provided, comprising:

[0016] at least one processor; and,

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor. The computer program is executed by the at least one processor so that the at least one processor can execute the photovoltaic panel dust accumulation detection method according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the photovoltaic panel dust accumulation detection method according to any embodiment of the present invention when executed.

[0020] The technical solution of the embodiment of the present invention is to obtain a first image of a photovoltaic panel in a target area, where the photovoltaic panel includes a plurality of photovoltaic modules, and determine the photovoltaic module image of each photovoltaic module in the first image, so that each photovoltaic module can be accurately located later to detect dust accumulation on each photovoltaic module; on the one hand, dust is identified on the photovoltaic module image based on an image processing model to determine a first detection result of each photovoltaic module; the image processing model is a model based on an artificial neural network; on the other hand, dust is identified on the photovoltaic module image based on a preset image processing method to determine a second detection result of each photovoltaic module; the preset image processing method is a method for processing images based on statistical principles and mathematical analysis principles; the first detection result and the second detection result are further combined to determine the photovoltaic module Whether it is a dust component; dust components are photovoltaic components with dust accumulation; due to the complexity of photovoltaic station scenes, the data volume and data diversity are limited, the dust detection performed by the artificial neural network model cannot achieve a high generalization ability, and the algorithm is actually applied to other stations and there are still cases of missed detection or false detection; and the preset image processing method, a traditional image processing method, can distinguish between dust areas and dust-free areas to a certain extent, but its adaptability is limited by light and weather conditions; therefore, combining the detection results of the two to analyze whether there is dust accumulation on the photovoltaic component can improve the algorithm accuracy when the model data volume is insufficient or the generalization ability is not strong, and at the same time can effectively overcome the dependence of traditional methods on light and weather conditions, effectively reduce missed detection and false detection problems, and improve the accuracy of photovoltaic panel dust detection.

[0021] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 This is a flow chart of a photovoltaic panel dust accumulation detection method provided in accordance with an embodiment of the present invention;

[0024] Figure 2 is a schematic diagram of a photovoltaic panel and a photovoltaic module applicable to an embodiment of the present invention;

[0025] Figure 3 is a flow chart of another photovoltaic panel dust accumulation detection method provided according to an embodiment of the present invention;

[0026] Figure 4 is a flow chart of another photovoltaic panel dust accumulation detection method provided according to an embodiment of the present invention;

[0027] Figure 5 is a schematic diagram of a binarized image applicable to an embodiment of the present invention;

[0028] Figure 6 This is a schematic structural diagram of a photovoltaic panel dust accumulation detection device provided according to an embodiment of the present invention;

[0029] Figure 7 3 is a schematic structural diagram of an electronic device for implementing a photovoltaic panel dust accumulation detection method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first," "second," "reference," and the like in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the numbers used in this way are interchangeable where appropriate so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to these processes, methods, products, or apparatus.

[0032] Example 1

[0033] Figure 1 This is a flow chart of a photovoltaic panel dust detection method provided by an embodiment of the present invention. This embodiment is applicable to the case of detecting whether there is dust accumulation on photovoltaic panels. The method can be performed by a photovoltaic panel dust detection device. The photovoltaic panel dust detection device can be implemented in the form of hardware and / or software. The photovoltaic panel dust detection device can be configured in any electronic device with network communication function. Figure 1 As shown, the photovoltaic panel dust accumulation detection method of the present invention includes the following process:

[0034] S110 , acquiring a first image of a photovoltaic panel in a target area, and determining a photovoltaic module image of each photovoltaic module in the first image; the photovoltaic panel includes a plurality of photovoltaic modules; and the first image is a visible light image.

[0035] The first image can be acquired by a drone photographing the photovoltaic panels in the target area. The drone is equipped with a camera capable of capturing visible light images. The drone is also equipped with a positioning module to accurately direct the drone to the target area for photography. The positioning module can be equipped with RTK positioning technology.

[0036] like Figure 2 As shown, the photovoltaic panel 1 is composed of multiple photovoltaic modules 2. The dotted box is the photovoltaic panel, and the solid box is a photovoltaic module on the photovoltaic panel. Figure 2 The photovoltaic panel consists of 22 photovoltaic modules. To more accurately locate dust accumulation areas on the photovoltaic panel, feature extraction is performed on each photovoltaic module in the first image to obtain a photovoltaic module image of each photovoltaic module. Dust accumulation detection is then performed on each photovoltaic module image to accurately locate dust accumulation areas and determine whether dust accumulation exists on each photovoltaic module, facilitating targeted cleaning.

[0037] Optionally, determining the photovoltaic assembly image of each photovoltaic assembly in the first image includes: processing the first image based on an image processing model to obtain the photovoltaic assembly image of each photovoltaic assembly in the first image. The image processing model is based on an artificial neural network. The artificial neural network model can efficiently and quickly extract feature information of each photovoltaic assembly in the first image, thereby accurately obtaining the photovoltaic assembly image of each photovoltaic assembly.

[0038] S120 , performing dust recognition on the photovoltaic module image based on an image processing model to determine a first detection result for each photovoltaic module; the image processing model is a model based on an artificial neural network.

[0039] Among them, the first detection result can be understood as the detection result of whether there is dust accumulation on the photovoltaic component, and the index information of the dust deposition situation. The index information includes but is not limited to the level information of the dust deposition situation. The more dust accumulation, the higher the level.

[0040] Specifically, the image processing model may identify dust features in the photovoltaic module image, thereby determining the first detection result of each photovoltaic module according to the dust features.

[0041] S130 , performing dust identification on the photovoltaic module image based on a preset image processing method to determine a second detection result for each photovoltaic module; the preset image processing method is a method for processing images based on statistical principles and mathematical analysis principles.

[0042] The second detection result can be understood as a detection result of whether dust is present on the photovoltaic module, as well as information indicating the dust accumulation. The information includes, but is not limited to, information indicating the level of dust accumulation, with more dust indicating a higher level. The preset image processing method can be a method for processing images using various algorithms and formulas based on mathematical analysis and statistical principles.

[0043] Specifically, the preset image processing method can identify the dust area in the photovoltaic module image, thereby determining the second detection result of each photovoltaic module according to the size information of the dust area.

[0044] S140. Determine whether the photovoltaic module is a dust module based on the first detection result and the second detection result; a dust module is a photovoltaic module with accumulated dust.

[0045] The present invention includes a first preset condition, a second preset condition, and a third preset condition. The first preset condition is used to instruct the image processing model to recognize that the photovoltaic component indicated by the first detection result obtained from the first image is definitely dusty. The second preset condition is used to instruct the image processing model to recognize that the photovoltaic component indicated by the first detection result obtained from the first image is not necessarily dusty and requires further testing. The third preset condition is used to instruct the preset image processing method to recognize that the photovoltaic component indicated by the second detection result obtained from the first image is definitely dusty.

[0046] Specifically, when the first detection result meets the first preset condition, the photovoltaic component corresponding to the first detection result that meets the first preset condition will be regarded as a dust component; when the first detection result meets the second preset condition, the photovoltaic component corresponding to the first detection result that meets the second preset condition will be further judged using the second detection result, and the photovoltaic component corresponding to the first detection result that meets the second preset condition will be regarded as a candidate photovoltaic component; if the candidate photovoltaic component meets the third preset condition, the candidate photovoltaic component is a dust component, otherwise it is not a dust component.

[0047] As an optional embodiment, the first detection result includes first position information of the photovoltaic component. After determining whether the photovoltaic component is a dust component based on the first detection result and the second detection result, the method further includes steps A1-A3:

[0048] Step A1: Acquire a second image of the photovoltaic panel in the target area and determine a hot spot defect in the second image; the second image is a thermal imaging image; the hot spot defect corresponds to hot spot information, and the hot spot information includes temperature information and second position information.

[0049] Specifically, an image processing model may be used to perform hot spot recognition on the second image to accurately determine the hot spot defects in the second image.

[0050] Step A2: Determine a reference hot spot defect that matches each dust component based on the second position information corresponding to the hot spot defect in the second image and the first position information of each dust component.

[0051] Specifically, the first position information is matched with the second position information to find the second position information corresponding to the first position information of each dust component, so that the reference hot spot defect matched by each dust component can be accurately determined.

[0052] Step A3: Determine the dust accumulation level of the dust component based on the temperature information corresponding to the reference hot spot defect matched by the dust component; the dust accumulation level is used to reflect the severity of the dust accumulation.

[0053] Specifically, a higher temperature indicates more severe dust accumulation in the dust component; therefore, the dust accumulation level of the dust component can be determined based on the preset temperature range and the temperature information corresponding to the reference hot spot defect matching the dust component. The preset temperature range can be understood as the temperature range corresponding to different dust accumulation levels.

[0054] Optionally, the dust accumulation level of the dust component is determined based on the temperature information corresponding to the reference hot spot defect matched by the dust component, including: if the temperature information corresponding to the reference hot spot defect matched by the dust component is less than the first preset temperature, the dust accumulation level of the dust component is the first level; if the temperature information corresponding to the reference hot spot defect matched by the dust component is greater than the first preset temperature, and the temperature information corresponding to the reference hot spot defect matched by the dust component is less than the second preset temperature, the dust accumulation level of the dust component is the second level; if the temperature information corresponding to the reference hot spot defect matched by the dust component is greater than the second preset temperature, the dust accumulation level of the dust component is the third level; the severity of the first level of dust accumulation is less than the severity of the second level of dust accumulation, and the severity of the second level of dust accumulation is less than the severity of the third level of dust accumulation.

[0055] For example, the first preset temperature can be 40 degrees Celsius, and the second preset temperature can be 60 degrees Celsius; if the temperature information corresponding to the reference hot spot defect matched by the dust component is less than 40 degrees Celsius, the dust accumulation level of the dust component is the first level; if the temperature information corresponding to the reference hot spot defect matched by the dust component is greater than 40 degrees Celsius, and the temperature information corresponding to the reference hot spot defect matched by the dust component is less than 60 degrees Celsius, the dust accumulation level of the dust component is the second level; if the temperature information corresponding to the reference hot spot defect matched by the dust component is greater than 60 degrees Celsius, the dust accumulation level of the dust component is the third level.

[0056] This embodiment of the technical solution acquires a second image of the photovoltaic panel in the target area and identifies hot spot defects in the second image; the second image is a thermal imaging image; the hot spot defects correspond to hot spot information, which includes temperature information and second position information. Based on the second position information corresponding to the hot spot defect in the second image and the first position information of each dust component, a matching reference hot spot defect is determined for each dust component. Furthermore, based on the temperature information corresponding to the matching reference hot spot defect, the dust accumulation level of the dust component is determined, and the dust severity is graded based on the hot spot temperature, thereby providing operational and maintenance guidance for subsequent photovoltaic panel cleaning plans.

[0057] The technical solution of the embodiment of the present invention is to obtain a first image of a photovoltaic panel in a target area, where the photovoltaic panel includes a plurality of photovoltaic modules, and determine the photovoltaic module image of each photovoltaic module in the first image, so that each photovoltaic module can be accurately located later to detect dust accumulation on each photovoltaic module; on the one hand, dust is identified on the photovoltaic module image based on an image processing model to determine a first detection result of each photovoltaic module; the image processing model is a model based on an artificial neural network; on the other hand, dust is identified on the photovoltaic module image based on a preset image processing method to determine a second detection result of each photovoltaic module; the preset image processing method is a method for processing images based on statistical principles and mathematical analysis principles; the first detection result and the second detection result are further combined to determine the photovoltaic module Whether it is a dust component; dust components are photovoltaic components with dust accumulation; due to the complexity of photovoltaic station scenes, the data volume and data diversity are limited, the dust detection performed by the artificial neural network model cannot achieve a high generalization ability, and the algorithm is actually applied to other stations and there are still cases of missed detection or false detection; and the preset image processing method, a traditional image processing method, can distinguish between dust areas and dust-free areas to a certain extent, but its adaptability is limited by light and weather conditions; therefore, combining the detection results of the two to analyze whether there is dust accumulation on the photovoltaic component can improve the algorithm accuracy when the model data volume is insufficient or the generalization ability is not strong, and at the same time can effectively overcome the dependence of traditional methods on light and weather conditions, effectively reduce missed detection and false detection problems, and improve the accuracy of photovoltaic panel dust detection.

[0058] Example 2

[0059] Figure 3 This is a flow chart of another photovoltaic panel dust detection method provided by an embodiment of the present invention. The technical solution of this embodiment further optimizes the process of S140 in the above embodiment on the basis of the above embodiment. This embodiment can be combined with various optional solutions in one or more of the above embodiments. Figure 3 As shown, the photovoltaic panel dust accumulation detection method includes:

[0060] S210, acquiring a first image of a photovoltaic panel in a target area, and determining a photovoltaic module image of each photovoltaic module in the first image; the photovoltaic panel includes a plurality of photovoltaic modules; the first image is a visible light image.

[0061] S220. Dust is identified on the photovoltaic module image based on an image processing model to determine a first detection result for each photovoltaic module; the image processing model is a model based on an artificial neural network; the first detection result includes a first evaluation index of the photovoltaic module, and the first evaluation index is used to describe a probability value of dust accumulation on the photovoltaic module.

[0062] The first evaluation indicator may be a confidence value.

[0063] S230. Perform dust recognition on the photovoltaic module image based on a preset image processing method to determine a second detection result for each photovoltaic module; the preset image processing method is a method for processing images based on statistical principles and mathematical analysis principles.

[0064] S240: If the first evaluation index of the photovoltaic component is greater than a first preset threshold, determine that the photovoltaic component is a dust component.

[0065] The first preset threshold value may be obtained based on analysis of experimental data. For example, the first preset threshold value may be 0.65.

[0066] S250: If the first evaluation index of the photovoltaic module is less than the first preset threshold, use the photovoltaic module whose first evaluation index is less than the preset threshold as a reference photovoltaic module, and determine whether the reference photovoltaic module is a dust module based on the second detection result.

[0067] Among them, if the first evaluation index of the photovoltaic component is less than the first preset threshold, it means that the photovoltaic component does not necessarily have dust. It is necessary to further determine whether the photovoltaic component with the first evaluation index less than the preset threshold is a dust component based on the second detection result.

[0068] Specifically, the present invention includes a third preset condition, which indicates that dust accumulation must be present on the photovoltaic assembly indicated by the second detection result obtained by the preset image processing method when identifying the first image. Determining whether a reference photovoltaic assembly is a dust assembly based on the second detection result may include: if the reference photovoltaic assembly meets the third preset condition, determining that the reference photovoltaic assembly is a dust assembly; otherwise, determining that the reference photovoltaic assembly is not a dust assembly.

[0069] In this embodiment, optionally, the second detection result includes a second evaluation index of the photovoltaic component, and the second evaluation index is a score for evaluating the dust accumulation on the photovoltaic component. Based on the second detection result, determining whether the reference photovoltaic component is a dust component includes: taking the reference photovoltaic component whose first evaluation index is zero as the first reference photovoltaic component, and taking the reference photovoltaic component whose first evaluation index is not zero as the second reference photovoltaic component; if the second evaluation index of the first reference photovoltaic component is greater than the second preset threshold, the first reference photovoltaic component is a dust component; if the second evaluation index of the second reference photovoltaic component is greater than the third preset threshold, the second reference photovoltaic component is a dust component; the second preset threshold is greater than the third preset threshold.

[0070] The second evaluation index can be understood as a score for the contamination level of the photovoltaic module. The second preset threshold and the third preset threshold can be obtained based on experimental data analysis.

[0071] In this embodiment, the photovoltaic modules whose first evaluation index is less than the first preset threshold are further tested in combination with the second evaluation index, thereby achieving more precise detection and effectively reducing the problems of missed detection and false detection.

[0072] The technical solution of an embodiment of the present invention obtains a first image of a photovoltaic panel in a target area and determines the photovoltaic module image of each photovoltaic module in the first image; the photovoltaic panel includes a plurality of photovoltaic modules; and the first image is a visible light image. Dust is identified on the photovoltaic module image based on an image processing model to determine a first detection result for each photovoltaic module; the image processing model is a model based on an artificial neural network; the first detection result includes a first evaluation index of the photovoltaic module, which is used to describe the probability value of dust accumulation on the photovoltaic module. The present invention displays the degree of dust accumulation on the photovoltaic module through numerical values, achieving quantification and comparability of the data and being more objective. Dust is identified on the photovoltaic module image based on a preset image processing method to determine a second detection result for each photovoltaic module; the preset image processing method is a method for processing images based on statistical principles and mathematical analysis principles. If the first evaluation index of the photovoltaic module is greater than a first preset threshold, the photovoltaic module is determined to be a dust module. If the first evaluation index of the photovoltaic component is less than the first preset threshold, the photovoltaic component with the first evaluation index less than the preset threshold is used as a reference photovoltaic component. Based on the second detection result, it is determined whether the reference photovoltaic component is a dust component. The present invention combines the second detection result to further detect the photovoltaic component with the first evaluation index less than the first preset threshold, thereby achieving more precise detection, effectively reducing the problems of missed detection and false detection, and improving the accuracy of dust accumulation detection on photovoltaic panels.

[0073] Example 3

[0074] Figure 4 This is a flow chart of another photovoltaic panel dust detection method provided by an embodiment of the present invention. The technical solution of this embodiment further optimizes the process of performing dust recognition on photovoltaic module images based on a preset image processing method in the above embodiment and determining the second detection result of each photovoltaic module. This embodiment can be combined with various optional solutions in one or more of the above embodiments. Figure 4 As shown, the photovoltaic panel dust accumulation detection method includes:

[0075] S310, acquiring a first image of a photovoltaic panel in a target area, and determining a photovoltaic module image of each photovoltaic module in the first image; the photovoltaic panel includes a plurality of photovoltaic modules; the first image is a visible light image.

[0076] S320: Perform dust recognition on the photovoltaic module image based on an image processing model to determine a first detection result of each photovoltaic module; the image processing model is a model based on an artificial neural network.

[0077] S330 , preprocessing the photovoltaic module image to obtain a preprocessed photovoltaic module image; the preprocessing includes at least one of grayscale conversion, Gaussian filtering, and morphological operation.

[0078] Grayscale conversion is the process of converting a color image into a single-channel grayscale image. The grayscale value of each pixel is usually calculated by weighted averaging. The grayscale value calculation formula is as follows:

[0079] ;

[0080] Among them, R, G, and B represent the red, green, and blue channel values ​​of the color image respectively, and I gray is the pixel value after grayscale conversion.

[0081] Gaussian filtering is a linear smoothing filter that can effectively suppress high-frequency noise in an image while preserving the main edge information of the image. The core of Gaussian filtering is to use the Gaussian kernel function to perform weighted averaging on the image through convolution operation. The formula of the Gaussian kernel function is as follows:

[0082] ;

[0083] Where σ is the standard deviation of the Gaussian kernel, which controls the smoothness of the filter. Gaussian filtering can reduce the interference of noise on subsequent steps.

[0084] Morphological operations can include erosion and dilation. After removing noise, morphological operations are used to further process the image. The specific processing process is as follows: First, the erosion operation is used to remove small interference such as white stripes on the surface of the photovoltaic panel. The erosion operation can reduce the bright areas in the image and eliminate small white stripes or noise points. Next, the dilation operation is used to amplify the small dust areas in the image, making them more prominent. The dilation operation can expand the bright areas in the image and enhance the connectivity of the dust areas. The mathematical expressions of the erosion and dilation operations are as follows:

[0085]

[0086] Among them, A is the input image, B is the structural element, is the reflection of the structural element.

[0087] S340: Analyze the pre-processed photovoltaic module image based on a histogram analysis method to obtain a grayscale histogram.

[0088] The histogram analysis method may be a method of calculating a histogram of a pre-processed photovoltaic module image and then performing Gaussian smoothing on the histogram to obtain a grayscale histogram.

[0089] S350 , performing binarization processing on the grayscale histogram based on a preset threshold value to obtain a binarized image of the photovoltaic module.

[0090] The preset threshold value can be a threshold value pre-set or calculated according to the requirements of image processing. Specifically, the pixels in the grayscale histogram are binarized by the preset threshold value, and the pixels in the grayscale histogram are divided into two areas corresponding to two values, and the binary image of the photovoltaic module is obtained. For example, Figure 5 Schematic diagram of the binarized image shown.

[0091] In an embodiment of the present invention, optionally, the preset thresholds include a first grayscale threshold and a second grayscale threshold, and binarization processing is performed on the grayscale histogram based on the preset thresholds to obtain a binarized image of the photovoltaic module, including steps B1-B3:

[0092] Step B1: determining the minimum grayscale value between the two largest peaks in the grayscale histogram based on the grayscale histogram, and using the minimum grayscale value as a first grayscale threshold; the first grayscale threshold is used to distinguish between normal areas and dust areas in the photovoltaic module image.

[0093] Specifically, determining the minimum grayscale value between the two largest peaks in the grayscale histogram based on the grayscale histogram may include: searching for two peak points within a preset grayscale range; if two peaks exist within the preset grayscale range, calculating the minimum grayscale value between the two peaks; if not, searching for the minimum grayscale value between the two largest peaks within a global range. The preset grayscale range may be a grayscale value interval of 100-150.

[0094] Step B2: setting pixels in the grayscale histogram that are greater than a second grayscale threshold to a first grayscale value; the second grayscale threshold is greater than the first grayscale threshold.

[0095] The second grayscale threshold may be a minimum pixel value corresponding to a normal area set according to actual needs. For example, the second grayscale threshold may be 235.

[0096] Step B3: Set the pixels in the grayscale histogram that are less than the first grayscale threshold as the first grayscale value; set the pixels in the grayscale histogram that are greater than the first grayscale threshold as the second grayscale value; the area corresponding to the first grayscale value is the normal area, and the area corresponding to the second grayscale value is the dust area.

[0097] The first grayscale value and the second grayscale value may be two grayscale values ​​that clearly distinguish the color areas. For example, the first grayscale value is 100 and the second grayscale value is 200.

[0098] In addition, it should be noted that in order to avoid the influence of the white edge expansion of the photovoltaic panel on the detection results, the reference dust area in the binary image is removed; wherein, the reference dust area is the dust area in which the number of pixel rows and / or columns is less than 8% of the total area.

[0099] The technical solution of this embodiment performs binarization processing on the grayscale histogram through the first grayscale threshold and the second grayscale threshold, thereby obtaining a more accurate binarization image of the photovoltaic module.

[0100] S360: Taking the ratio of the corresponding dust area in the binarized image to the entire area of ​​the binarized image as the second detection result of the photovoltaic assembly.

[0101] S370: Determine whether the photovoltaic module is a dust module based on the first detection result and the second detection result; a dust module is a photovoltaic module with accumulated dust.

[0102] The technical solution of an embodiment of the present invention obtains a first image of a photovoltaic panel in a target area and determines a photovoltaic module image of each photovoltaic module in the first image; the photovoltaic panel includes multiple photovoltaic modules; and the first image is a visible light image. Dust is identified in the photovoltaic module image based on an image processing model to determine a first detection result for each photovoltaic module; the image processing model is based on an artificial neural network. The photovoltaic module image is preprocessed to obtain a preprocessed photovoltaic module image; the preprocessing includes grayscale conversion, Gaussian filtering, and morphological operations to effectively simplify the image while preserving the image's primary structural information. The preprocessed photovoltaic module image is analyzed using a histogram analysis method to obtain a grayscale histogram, which facilitates subsequent determination of preset thresholds for dust and normal regions. The grayscale histogram is binarized based on the preset threshold to obtain a binary image of the photovoltaic module, effectively distinguishing between dust and normal regions. The ratio of the dust region in the binarized image to the entire region of the binarized image is used as a second detection result for the photovoltaic module, thereby quantifying the second detection result. Finally, based on the first and second detection results, it is determined whether the photovoltaic module is a dust module, which effectively overcomes the dependence of traditional methods on light and weather conditions, effectively reduces missed detection and false detection problems, and improves the accuracy of photovoltaic panel dust detection.

[0103] Example 4

[0104] In this embodiment, the image processing model is a model for image processing based on the YOLO11S-OBB algorithm; the YOLO11S-OBB algorithm is an algorithm formed by combining the YOLO11S algorithm with the directed bounding box algorithm; the image obtained by using the YOLO11S-OBB algorithm for image processing has directional information.

[0105] Specifically, the directional information can be described using a directional rotating box. The YOLO11S-OBB algorithm can output the directional rotating box through robust angle prediction. Because photovoltaic panels are tilted to a certain degree in the image, the YOLO11S-OBB algorithm can detect the first image using the directional rotating box to clearly distinguish the boundaries of each photovoltaic module and accurately locate the position of each photovoltaic module, thereby accurately obtaining the photovoltaic module image of each photovoltaic module in the first image.

[0106] In this embodiment, optionally, the YOLO11S-OBB algorithm also includes a C3K2-T module and a C2PSA-S module; the C3K2-T module has the ability to capture the detailed features of the photovoltaic panel in the image; the C2PSA-S module has the ability to segment the background information of the image; the C3K2-T module is formed by integrating the triple attention mechanism into the C3K2 module; the C2PSA-S module is formed by integrating the PSA attention layer in the C2PSA module into the SEAM module, and the rejection loss of the SEAM module includes classification loss, equivariant regularization loss and equivariant cross regularization loss.

[0107] The triple attention mechanism includes channel attention, spatial attention, and contextual attention. The SEAM (Semantic Encoding with Attention Modules) module can effectively segment the background of an image.

[0108] Specifically, the C3K2 module and the C2PSA module are both part of the YOLO11S algorithm architecture.

[0109] While the C3K2 module has certain advantages in photovoltaic panel detection, it has certain limitations when processing complex weather conditions, especially in accurately capturing the detailed features of photovoltaic panels. To further improve detection, this paper integrates a triple attention mechanism into the C3K2 module, combining it into the C3K2-T module. By integrating channel attention, spatial attention, and contextual attention, the C3K2-T module enhances the image processing model's sensitivity to complex features, thereby improving the accuracy and robustness of photovoltaic panel detection.

[0110] Furthermore, the channel attention mechanism mainly strengthens the influence of key feature channels by adjusting the weight of each channel. Its formula is as follows:

[0111]

[0112] Among them, C is the parameter corresponding to the channel attention mechanism, X is the input image, and Wc is the weight of the channel attention mechanism, σ1 is the first activation function;

[0113] The spatial attention mechanism focuses on the key areas in the image by weighting each pixel position. Its formula is as follows:

[0114]

[0115] Among them, S is the parameter corresponding to the spatial attention mechanism, X is the input image, W is the weight of the spatial attention mechanism, and σ2 is the second activation function;

[0116] The contextual attention mechanism captures more long-distance dependencies by integrating global information. It is usually calculated in the following way, and its formula is as follows:

[0117]

[0118] Among them, S context is the parameter corresponding to the contextual attention mechanism, X is the input image, W context is the weight of the contextual attention mechanism.

[0119] Finally, the weighted feature formula of the triple attention mechanism can be expressed as follows:

[0120] .

[0121] Furthermore, it should be noted that although the YOLO11S algorithm performs well in feature extraction and target detection, when faced with illumination, shadow, and background interference, the model is prone to overlap or misjudgment of the predicted frame and the real frame, resulting in missed detection and false detection. The SEAM module can enhance the correlation between different channels by optimizing the convolution structure, combine spatial attention and feature enhancement mechanisms, focus on the importance of unobstructed areas, and improve the overall feature representation to enhance the detection effect under object occlusion. This method not only improves the recognition accuracy under illumination and shadow conditions, but also improves the ability to understand features in complex scenes. It helps the model to accurately locate and identify photovoltaic modules. Therefore, the PSA attention layer in the C2PSA module of the YOLO11S algorithm is integrated into the SEAM module to form the C2PSA-S module of the present invention.

[0122] The SEAM module's rejection loss consists of a classification loss, an equivariant regularization loss, and an equivariant cross regularization loss. The classification loss is used to roughly localize objects, while the ER loss is used to bridge the gap between pixel-level and image-level supervision. The ECR loss is used to integrate the PCM with the network to make consistent predictions across various affine transformations.

[0123] The feature map of the classification loss is globally averaged and then pooled with the classification label to calculate the loss, Z 0 and Z t They are two different sets of prediction results, l is the real classification label, l cls The output of the basic classification loss function (such as cross entropy loss, FocalLoss, etc.) is the classification error of a single sample and view, and the classification loss L cls The formula is as follows:

[0124]

[0125] The equivariant regularization loss is an indicator of the similarity between the CAM of the original image and the CAM of the image after affine transformation. Map it to a certain space through matrix A, and then compare it with the target value The absolute value of the difference (L1 norm) is used as the error metric. ER The formula is as follows:

[0126]

[0127] The equivariant cross regularization loss transforms the observation value y 0 After mapping through matrix A, the target value The difference between the two values ​​is used to calculate the L1 norm, and then the predicted value is With another set of target values ​​y t The L1 norm is calculated by taking the absolute value of the difference and summing it up to measure the absolute error between the two vectors, which is the equivariant cross regularization loss. ECR It is expressed as follows:

[0128]

[0129] Finally, the total loss function formula of the SEAM module is expressed as follows:

[0130] .

[0131] Optionally, the superiority of the YOLO11S-OBB algorithm of the present invention can be demonstrated through a light panel detection comparison experiment.

[0132] Table 1 compares the YOLO11S-OBB algorithm of our invention with popular algorithms from recent years, using the same dataset. To demonstrate the model's generalization capabilities, data from different photovoltaic stations and weather conditions were used for testing. The method of our invention demonstrates significant advantages in detection accuracy, robustness, and adaptability. Specifically, the YOLO11S-OBB algorithm is able to efficiently and accurately locate photovoltaic panel components.

[0133] Table 1 Comparison experiment with mainstream algorithms

[0134]

[0135] Table 2 shows the ablation experiment of the algorithm of the present invention. Analysis of Table 2 shows that (1) YOLO11s-OBB+C2PSA-S, (2) YOLO11s-OBB+C3K2-T, and (3) YOLO11s-OBB+C2PSA-s+C3K2-T improve the average precision by 1.2%, 2.4%, and 7.3%, respectively, compared with YOLO11s-OBB. After comparison, the improved model in this paper achieves a maximum precision improvement of 0.88, which improves the precision without increasing the computational complexity. This shows that the YOLO11s-OBB algorithm of the present invention is more superior in photovoltaic module detection tasks.

[0136] Table 2 Comparative ablation experiments

[0137]

[0138] Alternatively, the superiority of the YOLO11S-OBB algorithm can be demonstrated through a comparative experiment on dust detection on photovoltaic panels. Table 3 below compares the dust detection results of the proposed method with those of mainstream algorithms. The results show that the proposed algorithm has significant advantages in detection effectiveness and accuracy.

[0139] Table 3 Dust detection comparison experiment

[0140]

[0141] Due to the scarcity of dust data on photovoltaic panels, traditional single-module dust detection methods struggle to achieve high accuracy. To address this issue, this paper employs the YOLO11s-OBB algorithm to first detect the photovoltaic strings of photovoltaic panels and then segment the strings into modules. This strategy, which performs dust detection on the modules, reduces background noise interference and provides high-quality data for dust detection. This method not only improves detection accuracy but also further optimizes detection results, providing more reliable data support for photovoltaic system maintenance.

[0142] The technical solution of this embodiment detects the first image using the YOLO11S-OBB algorithm formed by combining the YOLO11S algorithm with the OBB algorithm. The boundary information of each photovoltaic module can be well distinguished through a directional rotation frame, and the position information of each photovoltaic module can be accurately located, thereby accurately obtaining the photovoltaic module image of each photovoltaic module in the first image. Further improvements are made to the C3K2 module and C2PSA module in YOLO11S to enhance the sensitivity of the image processing model to complex features, thereby improving the accuracy and robustness of photovoltaic panel detection, and eliminating the impact of complex weather on photovoltaic panel dust detection. This effectively improves recognition accuracy under lighting and shadow conditions and enhances the ability to understand features in complex scenes.

[0143] Example 5

[0144] Figure 6 This is a schematic diagram of the structure of a photovoltaic panel dust detection device provided by an embodiment of the present invention. This embodiment is applicable to the situation where dust is detected on photovoltaic panels. The photovoltaic panel dust detection device can be implemented in the form of hardware and / or software. The photovoltaic panel dust detection device can be configured in any electronic device with network communication function. Figure 3 As shown, the photovoltaic panel dust detection device includes:

[0145] An image determination module 410 is configured to acquire a first image of a photovoltaic panel in a target area and determine a photovoltaic module image of each photovoltaic module in the first image; the photovoltaic panel includes a plurality of photovoltaic modules; and the first image is a visible light image.

[0146] A first detection module 420 is configured to perform dust recognition on the photovoltaic module image based on an image processing model to determine a first detection result for each photovoltaic module; the image processing model is a model based on an artificial neural network;

[0147] A second detection module 430 is configured to perform dust recognition on the photovoltaic module image based on a preset image processing method to determine a second detection result for each photovoltaic module; the preset image processing method is a method for processing images based on statistical principles and mathematical analysis principles;

[0148] The third detection module 440 is configured to determine whether the photovoltaic assembly is a dust assembly based on the first detection result and the second detection result; the dust assembly is a photovoltaic assembly with accumulated dust.

[0149] Based on the above embodiment, optionally, the image determination module is configured to process the first image based on an image processing model to obtain a photovoltaic assembly image of each photovoltaic assembly in the first image.

[0150] Based on the above embodiment, optionally, the image processing model is a model for performing image processing based on the YOLO11S-OBB algorithm; wherein the YOLO11S-OBB algorithm is an algorithm formed by combining the YOLO11S algorithm with a directed bounding box algorithm. Images obtained by performing image processing using the YOLO11S-OBB algorithm have directional information.

[0151] Based on the above embodiment, optionally, the YOLO11S-OBB algorithm also includes a C3K2-T module and a C2PSA-S module; the C3K2-T module has the ability to capture the detailed features of the photovoltaic panel in the image; the C2PSA-S module has the ability to segment the image background information; the C3K2-T module is formed by integrating the triple attention mechanism into the C3K2 module; the C2PSA-S module is formed by integrating the PSA attention layer in the C2PSA module into the SEAM module, and the rejection loss of the SEAM module includes classification loss, equivariant regularization loss and equivariant cross regularization loss.

[0152] Based on the above embodiment, optionally, the first detection result includes a first evaluation index of the photovoltaic component, and the first evaluation index is used to describe the probability value of dust accumulation on the photovoltaic component; the third detection module includes a first judgment unit, a second judgment unit and the first detection unit;

[0153] a first judgment unit, configured to determine that the photovoltaic component is a dust component if a first evaluation index of the photovoltaic component is greater than a first preset threshold;

[0154] a second judgment unit, configured to, if the first evaluation index of the photovoltaic module is less than a first preset threshold, use the photovoltaic module with the first evaluation index less than the preset threshold as a reference photovoltaic module;

[0155] The first detection unit is configured to determine whether the reference photovoltaic assembly is a dust assembly based on the second detection result.

[0156] Based on the above embodiment, optionally, the second detection result includes a second evaluation index of the photovoltaic component, and the second evaluation index is a score for evaluating the dust accumulation on the photovoltaic component; the first detection unit is used to: use the reference photovoltaic component with a first evaluation index of zero as the first reference photovoltaic component, and use the reference photovoltaic component with a first evaluation index not zero as the second reference photovoltaic component; if the second evaluation index of the first reference photovoltaic component is greater than a second preset threshold, the first reference photovoltaic component is a dust component; if the second evaluation index of the second reference photovoltaic component is greater than a third preset threshold, the second reference photovoltaic component is a dust component; the second preset threshold is greater than the third preset threshold.

[0157] Based on the above embodiment, optionally, the first detection result includes first position information of the photovoltaic assembly, and the photovoltaic panel dust accumulation detection device includes a fourth detection module, which includes an image determination unit, a hot spot defect determination unit, and a dust accumulation level determination unit;

[0158] an image determination unit, configured to acquire a second image of the photovoltaic panel in the target area and determine a hot spot defect in the second image; the hot spot defect corresponds to hot spot information, the hot spot information including temperature information and second position information;

[0159] a hot spot defect determining unit, configured to determine a reference hot spot defect matching each of the dust components based on second position information corresponding to the hot spot defect in the second image and the first position information of each of the dust components;

[0160] A dust accumulation level determination unit is used to determine the dust accumulation level of the dust component based on temperature information corresponding to a reference hot spot defect matched by the dust component; the dust accumulation level is used to reflect the severity of the dust accumulation.

[0161] On the basis of the above embodiment, optionally, a dust accumulation level determination unit is used: if the temperature information corresponding to the reference hot spot defect matched by the dust component is less than a first preset temperature, the dust accumulation level of the dust component is a first level; if the temperature information corresponding to the reference hot spot defect matched by the dust component is greater than the first preset temperature, and the temperature information corresponding to the reference hot spot defect matched by the dust component is less than a second preset temperature, the dust accumulation level of the dust component is a second level; if the temperature information corresponding to the reference hot spot defect matched by the dust component is greater than the second preset temperature, the dust accumulation level of the dust component is a third level; the severity of the dust accumulation of the first level is less than the severity of the dust accumulation of the second level, and the severity of the dust accumulation of the second level is less than the severity of the dust accumulation of the third level.

[0162] Based on the above embodiment, optionally, it is characterized in that the preset image processing method is a histogram analysis method, and the second detection module includes a first image processing unit, an image analysis unit, a second image processing unit and a second detection unit;

[0163] a first image processing unit, configured to preprocess the photovoltaic module image to obtain a preprocessed photovoltaic module image; the preprocessing comprising at least one of grayscale conversion, Gaussian filtering, and morphological operations;

[0164] An image analysis unit, configured to analyze the pre-processed photovoltaic module image based on the histogram analysis method to obtain a grayscale histogram;

[0165] a second image processing unit, configured to perform binarization processing on the grayscale histogram based on a preset threshold value to obtain a binarized image of the photovoltaic module;

[0166] The second detection unit is configured to use a ratio of a corresponding dust area in the binarized image to the entire area of ​​the binarized image as a second detection result of the photovoltaic assembly.

[0167] Based on the above embodiment, optionally, the preset threshold includes a first grayscale threshold and a second grayscale threshold, and the second image processing unit is configured to:

[0168] Determining a minimum grayscale value between two maximum peaks in the grayscale histogram based on the grayscale histogram, and using the minimum grayscale value as a first grayscale threshold; the first grayscale threshold is used to distinguish between a normal area and a dust area in the photovoltaic assembly image;

[0169] Setting pixels in the grayscale histogram that are greater than a second grayscale threshold to a first grayscale value; the second grayscale threshold is greater than the first grayscale threshold;

[0170] Setting pixels in the grayscale histogram that are less than a first grayscale threshold as a first grayscale value;

[0171] Setting pixels in the grayscale histogram that are greater than the first grayscale threshold to a second grayscale value;

[0172] The area corresponding to the first grayscale value is a normal area, and the area corresponding to the second grayscale value is a dust area.

[0173] The photovoltaic panel dust accumulation detection device provided in the embodiment of the present invention can execute the photovoltaic panel dust accumulation detection method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0174] Example 6

[0175] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0176] Figure 7 The following is a schematic diagram of an electronic device that can be used to implement the photovoltaic panel dust accumulation detection method according to an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided for example only and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0177] like Figure 7 As shown, electronic device 10 includes at least one processor 11 and memory, such as read-only memory (ROM) 12 and random access memory (RAM) 13, communicatively connected to at least one processor 11. The memory stores computer programs executable by the at least one processor. Processor 11 can perform various appropriate actions and processes based on the computer programs stored in ROM 12 or loaded from storage unit 18 into RAM 13. RAM 13 can also store various programs and data required for the operation of electronic device 10. Processor 11, ROM 12, and RAM 13 are interconnected via bus 14. An input / output (I / O) interface 15 is also connected to bus 14.

[0178] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0179] Processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any other suitable processor, controller, microcontroller, etc. Processor 11 executes the various methods and processes described above, such as the photovoltaic panel dust accumulation detection method.

[0180] In some embodiments, the photovoltaic panel dust accumulation detection method can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the photovoltaic panel dust accumulation detection method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to execute the photovoltaic panel dust accumulation detection method via any other suitable means (e.g., via firmware).

[0181] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0182] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0183] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or apparatus. A computer-readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or apparatus, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media may include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0184] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device that has: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0185] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0186] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0187] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0188] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for detecting dust accumulation on photovoltaic panels, characterized in that: The method comprises: Acquire a first image of a photovoltaic panel in a target area, and determine a photovoltaic assembly image of each photovoltaic assembly in the first image; the photovoltaic panel includes a plurality of photovoltaic assemblies; and the first image is a visible light image; Performing dust recognition on the photovoltaic module image based on an image processing model to determine a first detection result for each photovoltaic module; the image processing model is a model based on an artificial neural network; performing dust identification on the photovoltaic module image based on a preset image processing method to determine a second detection result for each photovoltaic module; the preset image processing method is a method for processing images based on statistical principles and mathematical analysis principles; Based on the first detection result and the second detection result, determining whether the photovoltaic component is a dust component; the dust component is a photovoltaic component with accumulated dust; The first detection result includes a first evaluation index of the photovoltaic component, the first evaluation index is a confidence value, and the first evaluation index is used to describe the probability value of dust accumulation on the photovoltaic component; and determining whether the photovoltaic component is a dust component based on the first detection result and the second detection result includes: If the first evaluation index of the photovoltaic component is greater than a first preset threshold, determining that the photovoltaic component is a dust component; If the first evaluation index of the photovoltaic module is less than a first preset threshold, the photovoltaic module with the first evaluation index less than the preset threshold is used as a reference photovoltaic module; determining, based on the second detection result, whether the reference photovoltaic assembly is a dust assembly; The second detection result includes a second evaluation index of the photovoltaic module, and the second evaluation index is a score for evaluating dust accumulation on the photovoltaic module. The determining whether the reference photovoltaic module is a dust module based on the second detection result includes: The reference photovoltaic assembly whose first evaluation index is zero is used as a first reference photovoltaic assembly, and the reference photovoltaic assembly whose first evaluation index is not zero is used as a second reference photovoltaic assembly; If the second evaluation index of the first reference photovoltaic component is greater than a second preset threshold, the first reference photovoltaic component is a dust component; If the second evaluation index of the second reference photovoltaic assembly is greater than a third preset threshold, the second reference photovoltaic assembly is a dust assembly; and the second preset threshold is greater than the third preset threshold.

2. The method according to claim 1, characterized in that The determining of the photovoltaic assembly image of each photovoltaic assembly in the first image includes: The first image is processed based on the image processing model to obtain a photovoltaic assembly image of each photovoltaic assembly in the first image.

3. The method according to claim 1 or 2, characterized in that The image processing model is a model for image processing based on the YOLO11S-OBB algorithm; the YOLO11S-OBB algorithm is an algorithm formed by combining the YOLO11S algorithm with a directed bounding box algorithm; the image obtained by image processing using the YOLO11S-OBB algorithm has directional information.

4. The method according to claim 3, characterized in that The YOLO11S-OBB algorithm also includes a C3K2-T module and a C2PSA-S module; the C3K2-T module has the ability to capture the detailed features of the photovoltaic panels in the image; the C2PSA-S module has the ability to segment the background information of the image; the C3K2-T module is formed by integrating the triple attention mechanism into the C3K2 module; the C2PSA-S module is formed by integrating the PSA attention layer in the C2PSA module into the SEAM module, and the rejection loss of the SEAM module includes classification loss, equivariant regularization loss and equivariant cross regularization loss.

5. The method according to claim 1, wherein The first detection result includes first position information of the photovoltaic component. After determining whether the photovoltaic component is a dust component based on the first detection result and the second detection result, the method further includes: Acquire a second image of the photovoltaic panel in the target area, and determine a hot spot defect in the second image; the second image is a thermal imaging image; the hot spot defect corresponds to hot spot information, and the hot spot information includes temperature information and second position information; determining a reference hot spot defect matching each of the dust components based on second position information corresponding to the hot spot defect in the second image and the first position information of each of the dust components; The dust accumulation level of the dust component is determined based on the temperature information corresponding to the reference hot spot defect matched by the dust component; the dust accumulation level is used to reflect the severity of the dust accumulation.

6. The method according to claim 5, characterized in that The determining of the dust accumulation level of the dust component based on the temperature information corresponding to the reference hot spot defect matched by the dust component includes: If the temperature information corresponding to the reference hot spot defect matched by the dust component is lower than a first preset temperature, the dust accumulation level of the dust component is the first level; If the temperature information corresponding to the reference hot spot defect matched by the dust component is greater than a first preset temperature, and the temperature information corresponding to the reference hot spot defect matched by the dust component is less than a second preset temperature, the dust accumulation level of the dust component is the second level; If the temperature information corresponding to the reference hot spot defect matched by the dust component is greater than the second preset temperature, the dust accumulation level of the dust component is the third level; the severity of the dust accumulation of the first level is less than the severity of the dust accumulation of the second level, and the severity of the dust accumulation of the second level is less than the severity of the dust accumulation of the third level.

7. The method according to claim 1, characterized in that The preset image processing method is a histogram analysis method. The dust recognition is performed on the photovoltaic module image based on the preset image processing method to determine the second detection result of each photovoltaic module, including: Preprocessing the photovoltaic module image to obtain a preprocessed photovoltaic module image; the preprocessing includes at least one of grayscale, Gaussian filtering, and morphological operation; Analyzing the pre-processed photovoltaic module image based on the histogram analysis method to obtain a grayscale histogram; Binarizing the grayscale histogram based on a preset threshold to obtain a binary image of the photovoltaic module; The ratio of the dust area corresponding to the binarized image to the entire area of ​​the binarized image is used as the second detection result of the photovoltaic assembly.

8. The method according to claim 7, characterized in that The preset thresholds include a first grayscale threshold and a second grayscale threshold, and binarization processing is performed on the grayscale histogram based on the preset thresholds to obtain a binarized image of the photovoltaic module, including: determining, based on the grayscale histogram, a minimum grayscale value between two maximum peaks in the grayscale histogram, and using the minimum grayscale value as a first grayscale threshold; the first grayscale threshold is used to distinguish between a normal area and a dust area in the photovoltaic assembly image; Setting pixels in the grayscale histogram that are greater than the second grayscale threshold to the first grayscale value; the second grayscale threshold is greater than the first grayscale threshold; Setting pixels in the grayscale histogram that are less than the first grayscale threshold as a first grayscale value; Setting pixels in the grayscale histogram that are greater than the first grayscale threshold to a second grayscale value; The area corresponding to the first grayscale value is a normal area, and the area corresponding to the second grayscale value is a dust area.

9. A photovoltaic panel dust detection device, characterized in that: The device comprises: An image determination module is configured to acquire a first image of a photovoltaic panel in a target area and determine a photovoltaic assembly image of each photovoltaic assembly in the first image; the photovoltaic panel includes a plurality of photovoltaic assemblies; and the first image is a visible light image. a first detection module, configured to perform dust recognition on the photovoltaic module image based on an image processing model to determine a first detection result for each photovoltaic module; the image processing model being a model based on an artificial neural network; a second detection module, configured to perform dust recognition on the photovoltaic module image based on a preset image processing method, and determine a second detection result for each photovoltaic module; the preset image processing method is a method for processing images based on statistical principles and mathematical analysis principles; a third detection module, configured to determine whether the photovoltaic assembly is a dust assembly based on the first detection result and the second detection result; the dust assembly is a photovoltaic assembly on which dust has accumulated; The first detection result includes a first evaluation index of the photovoltaic module, the first evaluation index is a confidence value, and the first evaluation index is used to describe the probability value of dust accumulation on the photovoltaic module; the third detection module includes a first judgment unit, a second judgment unit and a first detection unit; The first judgment unit is configured to determine that the photovoltaic component is a dust component if the first evaluation index of the photovoltaic component is greater than a first preset threshold; The second judgment unit is configured to use, if the first evaluation index of the photovoltaic module is less than a first preset threshold, the photovoltaic module with the first evaluation index less than the preset threshold as a reference photovoltaic module; The first detection unit is configured to determine whether the reference photovoltaic assembly is a dust assembly based on the second detection result; The second detection result includes a second evaluation index of the photovoltaic component, and the second evaluation index is a score for evaluating the dust accumulation on the photovoltaic component; the first detection unit is used to: use the reference photovoltaic component whose first evaluation index is zero as the first reference photovoltaic component, and use the reference photovoltaic component whose first evaluation index is not zero as the second reference photovoltaic component; if the second evaluation index of the first reference photovoltaic component is greater than a second preset threshold, the first reference photovoltaic component is a dust component; if the second evaluation index of the second reference photovoltaic component is greater than a third preset threshold, the second reference photovoltaic component is a dust component; the second preset threshold is greater than the third preset threshold.

10. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor. The computer program is executed by the at least one processor to enable the at least one processor to perform the photovoltaic panel dust accumulation detection method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the photovoltaic panel dust accumulation detection method according to any one of claims 1 to 8 when executed.

Images