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

Abstract

The invention discloses a photovoltaic panel dust retention detection method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a first image of a photovoltaic panel in a target region, 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, and determining a first detection result of 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, and determining a second detection result of each photovoltaic module; and determining whether the photovoltaic module is a dust module based on the first detection result and the second detection result. According to the technical scheme, the detection result of the photovoltaic module image by adopting the neural network model and the detection result of the photovoltaic module image by adopting a traditional image processing method are combined to determine whether the photovoltaic module is a dust module, so that the accuracy of dust accumulation detection of the photovoltaic panel is improved.

Description

Technical Field

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

[0002] With the rapid development of solar power generation technology, as the core component of a solar power generation system, the operating efficiency of a photovoltaic panel is directly related to the power generation performance of the entire system. However, during actual operation, contaminants such as dust and dirt are likely to deposit on the surface of the photovoltaic panel. These contaminants will block solar radiation, reduce the photoelectric conversion efficiency of the component, and thus lead to a significant decrease in power generation. Therefore, it is particularly important to detect dust accumulation on the surface of the photovoltaic panel in a timely, accurate, and efficient manner.

[0003] Currently, a deep learning model is usually used to identify photovoltaic panel images and determine whether there is dust deposition on the photovoltaic panel based on the recognition result. However, the performance of the deep learning model highly depends on the richness and quality of the labeled data. In actual business scenarios, it is difficult to obtain sufficiently rich and diverse photovoltaic panel dust image data. In addition, factors such as the uneven dust distribution on the surface of the photovoltaic module and the complex and changeable lighting conditions further increase the difficulty of dust detection, resulting in possible problems such as missed detection and false detection in actual applications of the algorithm. Summary of the Invention

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

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

[0006] Obtaining a first image of a photovoltaic panel in a target area and determining photovoltaic module images 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;

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

[0008] Identifying dust 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 an image based on statistical principles and mathematical analysis principles;

[0009] Based on the first detection result and the second detection result, determining whether the photovoltaic module is a dust module; the dust module is a photovoltaic module with dust accumulation.

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

[0011] An image determination module, configured to obtain a first image of a photovoltaic panel in a target area and determine photovoltaic module images 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;

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

[0013] A second detection module, configured to perform dust recognition on the photovoltaic module images based on a preset image processing method and 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;

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

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

[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 executable by the at least one processor, and when the computer program is executed by the at least one processor, the at least one processor can execute the photovoltaic panel dust detection method according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, there is provided a computer-readable storage medium, which stores computer instructions for causing a processor to implement the photovoltaic panel dust 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. The photovoltaic panel includes a plurality of photovoltaic modules. Determine the photovoltaic module images of each photovoltaic module in the first image, so as to accurately locate each photovoltaic module subsequently for detecting the dust accumulation on each photovoltaic module; on the one hand, perform dust recognition on the photovoltaic module image based on an image processing model to determine the first detection result of each photovoltaic module; the image processing model is a model based on an artificial neural network; on the other hand, perform dust recognition on the photovoltaic module image based on a preset image processing method to determine the 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; further, combine the first detection result and the second detection result to determine whether the photovoltaic module is a dust module; a dust module is a photovoltaic module with dust accumulation; because due to the complex photovoltaic power station scenario and the limitations of data volume and data diversity, the dust detection using a model based on an artificial neural network cannot achieve a high generalization ability, and there are still missed detection or false detection situations when the algorithm is actually applied to other power stations; while the preset image processing method, a traditional image processing method, can distinguish the dust area and the dust-free area to a certain extent, but its adaptability is limited by lighting and weather conditions; therefore, combining the detection results of the two to analyze whether there is dust accumulation on the photovoltaic module 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 the traditional method on lighting and weather conditions, effectively reduce the problems of missed detection and false detection, and improve the accuracy of photovoltaic panel dust detection.

[0021] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily 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 will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0023] Figure 1 is a flowchart of a method for detecting dust accumulation on a photovoltaic panel provided according to 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 flowchart of another method for detecting dust accumulation on a photovoltaic panel provided according to an embodiment of the present invention;

[0026] Figure 4 is a flowchart 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 binary image applicable to an embodiment of the present invention;

[0028] Figure 6 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 is a schematic structural diagram of an electronic device for implementing the photovoltaic panel dust accumulation detection method according to an embodiment of the present invention. Detailed implementation manners

[0030] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

[0031] It should be noted that the terms "first", "second", "reference", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances 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 "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0032] Embodiment 1

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

[0034] S110. Obtain a first image of the photovoltaic panels in the target area, and determine the photovoltaic module images of each photovoltaic module in the first image; the photovoltaic panels include multiple photovoltaic modules; the first image is a visible light image.

[0035] Among them, the first image can be obtained by a drone taking pictures of the photovoltaic panels in the target area. The drone is equipped with a shooting device that can take visible light images. The drone is also equipped with a positioning module to facilitate accurately flying the drone to the target area to perform the shooting task. The positioning module can be configured with RTK positioning technology.

[0036] As Figure 2 shown, the photovoltaic panel 1 is composed of multiple photovoltaic modules 2. The dashed box encloses the photovoltaic panel, and the solid box encloses a photovoltaic module on the photovoltaic panel. Figure 2 The photovoltaic panel includes 22 photovoltaic modules. In order to be able to more accurately locate the areas with dust accumulation on the photovoltaic panel, feature extraction is performed on each photovoltaic module in the first image to obtain the photovoltaic module images of each photovoltaic module, so as to perform dust accumulation detection on the photovoltaic module images of each photovoltaic module subsequently, so as to accurately locate the areas with dust accumulation. And whether there is dust accumulation on each photovoltaic module, which is convenient for targeted cleaning.

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

[0038] S120. Based on the image processing model, perform dust recognition on the photovoltaic module images to determine the first detection result of 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 module and the index information of the dust deposition situation. The index information includes but is not limited to the grade information of the dust deposition situation, and the more dust there is, the higher the grade.

[0040] Specifically, the image processing model can recognize the dust features in the photovoltaic module images, so as to determine the first detection result of each photovoltaic module according to the dust features.

[0041] S130. Identify dust on the PV module images based on a preset image processing method, and determine the second detection result for each PV module. The preset image processing method is a method for processing images based on statistical principles and mathematical analysis principles.

[0042] Among them, the second detection result can be understood as the detection result of whether there is dust accumulation on the PV module and the index information of the dust deposition situation. The index information includes, but is not limited to, the grade information of the dust deposition situation. The more dust there is, the higher the grade. The preset image processing method can be a method for processing images using various algorithms and formulas based on mathematical analysis principles and statistical principles.

[0043] Specifically, the preset image processing method can identify the dust area in the PV module image, and then determine the second detection result for each PV module according to the size information of the dust area.

[0044] S140. Determine whether the PV module is a dust module based on the first detection result and the second detection result. A dust module is a PV module with dust accumulation.

[0045] Among them, the present invention includes a first preset condition, a second preset condition, and a third preset condition. The first preset condition is used to indicate that the PV module indicated by the first detection result obtained by the image processing model for identifying the first image must have dust accumulation. The second preset condition is used to indicate that the PV module indicated by the first detection result obtained by the image processing model for identifying the first image may not have dust accumulation and further detection is required. The third preset condition is used to indicate that the PV module indicated by the second detection result obtained by the preset image processing method for identifying the first image must have dust accumulation.

[0046] Specifically, when the first detection result meets the first preset condition, the PV module corresponding to the first detection result that meets the first preset condition is regarded as a dust module. When the first detection result meets the second preset condition, the PV module corresponding to the first detection result that meets the second preset condition is further judged using the second detection result, and the PV module corresponding to the first detection result that meets the second preset condition is regarded as a candidate PV module. If the candidate PV module meets the third preset condition, the candidate PV module is a dust module; otherwise, it is not a dust module.

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

[0048] Step A1: Obtain the second image of the photovoltaic panels in the target area and determine the hot spot defects in the second image; the second image is a thermal imaging image; the hot spot defects correspond to hot spot information, and the hot spot information includes temperature information and second position information.

[0049] Specifically, an image processing model can be used to identify hot spots in the second image to accurately determine the hot spot defects in the second image.

[0050] Step A2: Based on the second position information corresponding to the hot spot defects in the second image and the first position information of each dust component, determine the reference hot spot defects matched by each dust component.

[0051] Specifically, match the first position information with the second position information to find the second position information corresponding to the first position information of each dust component, so as to accurately determine the reference hot spot defects matched by each dust component.

[0052] Step A3: Based on the temperature information corresponding to the reference hot spot defects matched by the dust components, determine the dust accumulation level of the dust components; the dust accumulation level is used to reflect the severity of dust accumulation.

[0053] Specifically, the higher the temperature, the more serious the dust accumulation of the dust component; therefore, the dust accumulation level of the dust component can be determined according to the preset temperature range and the temperature information corresponding to the reference hot spot defects matched by the dust component. Among them, the preset temperature range can be understood as the temperature range corresponding to different dust accumulation levels.

[0054] Optionally, determining the dust accumulation level of the dust component based on the temperature information corresponding to the reference hot spot defects matched by the dust component includes: if the temperature information corresponding to the reference hot spot defects 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 defects matched by the dust component is greater than the first preset temperature and 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 defects 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 dust accumulation at the first level is less than that at the second level, and the severity of dust accumulation at the second level is less than that at the third level.

[0055] Exemplarily, the first preset temperature may be 40 degrees Celsius, and the second preset temperature may be 60 degrees Celsius. Then, 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 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] In the technical solution of this embodiment, by obtaining the second image of the photovoltaic panel in the target area, the hot spot defect in the second image is determined; 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. So as to determine the reference hot spot defect matched by 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; further, based on the temperature information corresponding to the reference hot spot defect matched by the dust component, the dust accumulation level of the dust component is determined, and the severity of the dust is graded by the hot spot temperature, so as to provide operation and maintenance guidance for the subsequent photovoltaic panel cleaning plan.

[0057] In the technical solution of the embodiment of the present invention, the first image of the photovoltaic panel in the target area is obtained. The photovoltaic panel includes a plurality of photovoltaic components, and the photovoltaic component images of each photovoltaic component in the first image are determined, so as to accurately locate each photovoltaic component subsequently for detecting the dust accumulation of each photovoltaic component; on the one hand, the dust in the photovoltaic component image is identified based on the image processing model to determine the first detection result of each photovoltaic component; the image processing model is a model based on an artificial neural network; on the other hand, the dust in the photovoltaic component image is identified based on the preset image processing method to determine the second detection result of each photovoltaic component; the preset image processing method is a method for processing images based on statistical principles and mathematical analysis principles; further, the first detection result and the second detection result are combined to determine whether the photovoltaic component is a dust component; a dust component is a photovoltaic component with dust accumulation; because due to the complex photovoltaic power station scenario and the limitation of data volume and data diversity, the dust detection using the model based on an artificial neural network cannot achieve a high generalization ability, and there are still cases of missed detection or false detection when the algorithm is actually applied to other power stations; while the preset image processing method, a traditional image processing method, can distinguish the dust area and the dust-free area 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 the traditional method on light and weather conditions, effectively reducing the problems of missed detection and false detection and improving the accuracy of photovoltaic panel dust detection.

[0058] Example Two

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

[0060] S210. Obtain a first image of a photovoltaic panel in a target area, and determine photovoltaic module images 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. Based on an image processing model, perform dust recognition on the photovoltaic module image, and 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 the probability value of dust accumulation on the photovoltaic module.

[0062] Among them, the first evaluation index may be a confidence value.

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

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

[0065] Among them, the first preset threshold can be obtained by analyzing experimental data. For example, the first preset threshold 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 with the first evaluation index less than the preset threshold as a reference photovoltaic module, and based on the second detection result, determine whether the reference photovoltaic module is a dust component.

[0067] Among them, if the first evaluation index of the photovoltaic module is less than the first preset threshold, it means that the photovoltaic module may not have dust, and it is necessary to further determine whether the photovoltaic module 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 is used to indicate that the photovoltaic module indicated by the second detection result obtained by the preset image processing method for recognizing the first image must have dust accumulation. Then, determining whether the reference photovoltaic module is a dusty module based on the second detection result may include: if the reference photovoltaic module meets the third preset condition, determining that the reference photovoltaic module is a dusty module; otherwise, the reference photovoltaic module is not a dusty module.

[0069] In this embodiment, optionally, the second detection result includes a second evaluation index of the photovoltaic module, and the second evaluation index is a score for evaluating the dust accumulation situation on the photovoltaic module. Determining whether the reference photovoltaic module is a dusty module based on the second detection result includes: taking the reference photovoltaic module with the first evaluation index being zero as the first reference photovoltaic module, and taking the reference photovoltaic module with the first evaluation index not being zero as the second reference photovoltaic module; if the second evaluation index of the first reference photovoltaic module is greater than a second preset threshold, the first reference photovoltaic module is a dusty module; if the second evaluation index of the second reference photovoltaic module is greater than a third preset threshold, the second reference photovoltaic module is a dusty module; the second preset threshold is greater than the third preset threshold.

[0070] Among them, the second evaluation index can be understood as a score for the pollution degree of the photovoltaic module. The second preset threshold and the third preset threshold can be obtained through experimental data analysis.

[0071] In this embodiment, by combining the second evaluation index to further detect the photovoltaic modules with the first evaluation index less than the first preset threshold, more refined detection is achieved, effectively reducing the problems of missed detection and false detection.

[0072] The technical solution of the embodiment of the present invention is to obtain a first image of a photovoltaic panel in a target area and determine the photovoltaic module images 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. Based on an image processing model, dust identification is performed on the photovoltaic module images to determine the first detection result of each photovoltaic module; the image processing model is a model based on an artificial neural network; the first detection result includes the first evaluation index of the photovoltaic module, and the first evaluation index is used to describe the probability value of dust accumulation on the photovoltaic module. The present invention numerically displays the degree of dust accumulation on the photovoltaic module, realizing the quantification and comparability of data, and being more objective. Based on a preset image processing method, dust identification is performed on the photovoltaic module images to determine the 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. If the first evaluation index of a photovoltaic module is greater than a first preset threshold, it is determined that the photovoltaic module is a dust component. If the first evaluation index of a photovoltaic module is less than the first preset threshold, the photovoltaic module with the first evaluation index less than the preset threshold is used as a reference photovoltaic module, and based on the second detection result, it is determined whether the reference photovoltaic module is a dust component. The present invention combines the second detection result to further detect the photovoltaic module with the first evaluation index less than the first preset threshold, thereby realizing a more refined detection, effectively reducing the problems of missed detection and false detection, and improving the accuracy of photovoltaic panel dust detection.

[0073] Embodiment III

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

[0075] S310. Obtain a first image of a photovoltaic panel in a target area and determine the photovoltaic module images 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. Based on an image processing model, perform dust identification on the photovoltaic module images to determine the first detection result of each photovoltaic module; the image processing model is a model based on an artificial neural network.

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

[0078] Among them, grayscale conversion can be the process of converting a color image into a single-channel grayscale image, usually by calculating the grayscale value of each pixel through the weighted average method. The calculation formula of the grayscale value is as follows:

[0079] ;

[0080] where R, G, and B respectively represent the red, green, and blue channel values of the color image, 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 the image while retaining the main edge information of the image. The core of Gaussian filtering is to perform a convolution operation and use a Gaussian kernel function to perform weighted averaging on the image. 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 smoothing degree of the filtering. Through Gaussian filtering, the interference of noise on subsequent steps can be reduced.

[0084] Morphological operations can include erosion operations and dilation operations. After removing noise, morphological operations need to be used to further process the image. The specific processing process is as follows: First, use the erosion operation to remove small interference such as white strips on the surface of the photovoltaic panel. The erosion operation can shrink the bright areas in the image and eliminate small white strips or noise points. Then, use the dilation operation to enlarge the small dust areas in the image to make them more obvious. 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 operation and the dilation operation are as follows:

[0085]

[0086] where A is the input image, B is the structuring element, is the reflection of the structuring element.

[0087] S340. Analyze the preprocessed photovoltaic module image based on the histogram analysis method to obtain a grayscale histogram.

[0088] Among them, the histogram analysis method can be the method of calculating the histogram of the preprocessed photovoltaic module image and then performing Gaussian smoothing on the histogram to obtain a grayscale histogram.

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

[0090] Among them, the preset threshold can be a threshold set or calculated in advance according to the requirements of image processing. Specifically, by performing binarization processing on the pixels in the grayscale histogram using the preset threshold, the pixels in the grayscale histogram are divided into two regions corresponding to two values, and a binary image of the photovoltaic module is obtained. By way of example, as Figure 5 The schematic diagram of the binary image shown.

[0091] In an embodiment of the present invention, optionally, the preset threshold includes a first grayscale threshold and a second grayscale threshold. Performing binarization processing on the grayscale histogram based on the preset threshold to obtain a binary image of the photovoltaic module includes steps B1 - B3:

[0092] Step B1: Determine the minimum grayscale value between the two largest peaks in the grayscale histogram based on the grayscale histogram, and use the minimum grayscale value as the first grayscale threshold; the first grayscale threshold is used to distinguish the normal region and the dust region 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: finding two peak points within a preset grayscale range; if there are two peaks within the preset grayscale range, calculate the minimum grayscale value between these two peaks; if not, find the minimum grayscale value between the two largest peaks within the global range. Among them, the preset grayscale range may be an interval with grayscale values in the range of 100 - 150.

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

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

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

[0097] Among them, the first grayscale value and the second grayscale value may be grayscale values of two significantly distinguishable color regions. 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 result, the reference dust region in the binary image is removed; among them, the reference dust region is the dust region in which the number of pixel rows and / or columns is less than 8% of the total region.

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

[0100] S360. Use 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 module.

[0101] S370. Based on the first detection result and the second detection result, determine whether the photovoltaic module is a dusty module; a dusty module is a photovoltaic module with dust accumulation.

[0102] The technical solution of the embodiment of the present invention acquires the first image of the photovoltaic panel in the target area and determines the photovoltaic module images of each photovoltaic module in the first image; the photovoltaic panel includes multiple photovoltaic modules; the first image is a visible light image. Based on the image processing model, dust recognition is performed on the photovoltaic module image to determine the first detection result of each photovoltaic module; the image processing model is a model based on an artificial neural network. Preprocess the photovoltaic module image to obtain the preprocessed photovoltaic module image; the preprocessing includes grayscale conversion, Gaussian filtering, and morphological operations, which effectively simplify the image while retaining the main structural information of the image. Analyze the preprocessed photovoltaic module image based on the histogram analysis method to obtain the grayscale histogram, which is convenient for subsequent determination of the preset thresholds for the dust area and the normal area. Perform binarization processing on the grayscale histogram based on the preset thresholds to obtain the binarized image of the photovoltaic module, effectively distinguishing the dust area and the normal area. Use 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 module to realize the quantification of the second detection result. Finally, based on the first detection result and the second detection result, determine whether the photovoltaic module is a dusty module, effectively overcoming the dependence of the traditional method on lighting and weather conditions, effectively reducing the problems of missed detection and false detection, and improving the accuracy of dust accumulation detection of the photovoltaic panel.

[0103] Embodiment 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 oriented bounding box algorithm; the image obtained by performing image processing using the YOLO11S-OBB algorithm has direction information.

[0105] Specifically, the direction information can be information described by a rotated box with a direction. The YOLO11S-OBB algorithm can output a rotated box with a direction through robust angle prediction. Since the photovoltaic panels are inclined to a certain degree in the image, by detecting the first image with the YOLO11S-OBB algorithm, the boundary information of each photovoltaic component can be well distinguished by the rotated box with a direction, and the position information of each photovoltaic component can be accurately located, so that the photovoltaic component images of each photovoltaic component in the first image can be accurately obtained.

[0106] In this embodiment, optionally, the YOLO11S-OBB algorithm further 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 a triple attention mechanism into the C3K2 module; the C2PSA-S module is formed by integrating a SEAM module into the PSA attention layer in the C2PSA module, and the rejection loss of the SEAM module includes classification loss, equivariant regularization loss, and equivariant cross-regularization loss.

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

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

[0109] Although the C3K2 module has certain advantages in the detection of photovoltaic panels, it has certain limitations when dealing with complex weather, especially in the capture of the detailed features of photovoltaic panels, which may not be accurate enough. To further improve the detection effect, the present invention integrates a triple attention mechanism into the C3K2 module to form a C3K2-T module. The C3K2-T module enhances the sensitivity of the image processing model to complex features by integrating multiple attentions of the channel attention mechanism, the spatial attention mechanism, and the context attention mechanism, thereby improving the accuracy and robustness of photovoltaic panel detection.

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

[0111]

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

[0113] The spatial attention mechanism focuses on the key regions in the image by weighting the weights at each pixel position, and its formula is as follows:

[0114]

[0115] where 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 context attention mechanism captures more long-range dependencies by integrating global information, and is usually calculated in the following way, and its formula is as follows:

[0117]

[0118] where S context is the parameter corresponding to the context attention mechanism, X is the input image, and W context is the weight of the context 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 object detection, when faced with light shadows and background interference, the model is prone to situations where the predicted bounding box overlaps or is misjudged with the true bounding box, resulting in missed detections and false detections. The SEAM module can enhance the correlation between different channels by optimizing the convolutional structure, combining the spatial attention and feature enhancement mechanisms, by focusing on the importance of unoccluded regions, and improving the overall feature representation, to enhance the detection effect in the case of object occlusion. This method not only improves the recognition accuracy in the case of light shadows, but also improves the ability to understand features in complex scenes. It helps the model to accurately locate and identify photovoltaic components. Therefore, the SEAM module is incorporated into the PSA attention layer in the C2PSA module of the YOLO11S algorithm to form the C2PSA-S module of the present invention.

[0122] The rejection loss of the SEAM module includes classification loss, equivariant regularization loss, and equivariant cross-regularization loss. Among them, the classification loss is used to roughly locate the object, and the ER loss is used to narrow the gap between pixel-level and image-level monitoring. The ECR loss is used to integrate the PCM with the network to make consistent predictions for various affine transformations.

[0123] The feature map of the classification loss is globally average pooled and then the loss is calculated with the classification label, Z 0 and Z t are two different sets of prediction results respectively, l is the true classification label, l cls is the basic classification loss function (such as cross-entropy loss, FocalLoss, etc.). The output is the classification error of a single sample or view. The classification loss L cls is expressed by the formula as follows:

[0124]

[0125] The equivariant regularization loss is an index of the similarity between the CAM of the original image and the CAM of the image after affine transformation. The predicted value is mapped to a certain space through the matrix A, and then the absolute value of the difference (L1 norm) from the target value is used as the error metric. The equivariant regularization loss L ER is expressed by the formula as follows:

[0126]

[0127] The equivariant cross-regularization loss calculates the L1 norm of the difference between the observed value y 0 mapped through the matrix A and the target value , and then calculates the L1 norm of the difference between the predicted value and another set of target values y t . Finally, the absolute value of the difference is taken and summed to measure the absolute error between the two vectors, that is, the equivariant cross-regularization loss. The formula for the absolute error between the two vectors, that is, the equivariant cross-regularization loss L ECR is expressed as follows:

[0128]

[0129] Finally, the formula for the total loss function 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 the light panel detection comparison experiment.

[0132] Table 1 shows the comparison experiments of the YOLO11S-OBB algorithm of the present invention and the popular algorithms in recent years on the same dataset. To reflect the model generalization ability, data under different weather conditions of different photovoltaic power stations are selected for testing to reflect the generalization of the model. The method of the present invention shows significant advantages in terms of detection accuracy, robustness and adaptability. Specifically, the YOLO11S-OBB algorithm can efficiently and accurately locate the photovoltaic panel components.

[0133] Table 1 Comparative Experiments with Mainstream Algorithms

[0134]

[0135] Table 2 is the ablation experiment of the algorithm of the present invention. Analyzing Table 2, it can be seen that: (1) YOLO11s-OBB+C2PSA-S, (2) YOLO11s-OBB+C3K2-T, and (3) YOLO11s-OBB+C2PSA-s+C3K2-T have increased the mean average precision by 1.2%, 2.4%, and 7.3% respectively compared with YOLO11s-OBB. After comparison, the improved model in this paper has the highest improvement in accuracy up to 0.88, and improves the accuracy without adding too much computational cost, indicating that the YOLO11s-OBB algorithm of the present invention is more superior in the photovoltaic module detection task.

[0136] Table 2 Comparative Ablation Experiments

[0137]

[0138] Optionally, the superiority of the YOLO11S-OBB algorithm of the present invention can be demonstrated through the dust detection comparison experiment of the photovoltaic panel. Table 3 below is the dust detection comparison test between the method of the present invention and the mainstream algorithms. The results show that the algorithm proposed in this paper has significant advantages in terms of detection effect and accuracy.

[0139] Table 3 Dust Detection Comparative Experiments

[0140]

[0141] Due to the scarcity of photovoltaic panel dust data, it is difficult for traditional single-component dust detection methods to improve accuracy. To solve this problem, the present invention adopts the YOLO11s-OBB algorithm to first detect the photovoltaic strings of the photovoltaic panel and then divide the photovoltaic strings into photovoltaic modules to detect the dust of the photovoltaic modules, reducing the interference of background noise and providing high-quality data for dust detection. This method not only improves the detection accuracy but also further optimizes the detection effect, providing more reliable data support for the maintenance of the photovoltaic system.

[0142] In the technical solution of this embodiment, the YOLO11S-OBB algorithm formed by combining the YOLO11S algorithm and the OBB algorithm is used to detect the first image. The boundary information of each photovoltaic module can be well distinguished by the rotated bounding box with direction, and the position information of each photovoltaic module can be accurately located, so that the photovoltaic module images of each photovoltaic module in the first image can be accurately obtained. Further, by improving the C3K2 module and the C2PSA module in YOLO11S, the sensitivity of the image processing model to complex features is enhanced, thereby improving the accuracy and robustness of photovoltaic panel detection, eliminating the influence of complex weather on photovoltaic panel dust detection, effectively improving the recognition accuracy in the case of light shadows, and improving the understanding ability of features in complex scenes.

[0143] Embodiment 5

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

[0145] An image determination module 410, configured to obtain a first image of a photovoltaic panel in a target area and determine the photovoltaic module images 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;

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

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

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

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

[0150] Based on the above embodiments, optionally, the image processing model is a model for image processing based on the YOLO11S-OBB algorithm; wherein, the YOLO11S-OBB algorithm is an algorithm formed by combining the YOLO11S algorithm with the oriented bounding box algorithm. The image obtained by performing image processing using the YOLO11S-OBB algorithm has direction information.

[0151] Based on the above embodiments, optionally, the YOLO11S-OBB algorithm further 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 a triple attention mechanism into the C3K2 module; the C2PSA-S module is formed by integrating the SEAM module into the PSA attention layer in the C2PSA 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 embodiments, optionally, the first detection result includes a first evaluation index of the photovoltaic module, 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;

[0153] The first judgment unit is used to determine that the photovoltaic module is a dusty module if the first evaluation index of the photovoltaic module is greater than a first preset threshold;

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

[0155] The first detection unit is used to determine whether the reference photovoltaic module is a dusty module based on the second detection result.

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

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

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

[0159] The hot spot defect determination unit is configured to determine a reference hot spot defect matched by each dusty module based on the second position information corresponding to the hot spot defect in the second image and the first position information of each dusty module;

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

[0161] Based on the above embodiments, optionally, the dust accumulation level determination unit is configured to: if the temperature information corresponding to the reference hot spot defect matched by the dusty module is less than a first preset temperature, then the dust accumulation level of the dusty module is the first level; if the temperature information corresponding to the reference hot spot defect matched by the dusty module is greater than the first preset temperature and less than a second preset temperature, then the dust accumulation level of the dusty module is the second level; if the temperature information corresponding to the reference hot spot defect matched by the dusty module is greater than the second preset temperature, then the dust accumulation level of the dusty module is the third level; the severity of dust accumulation at the first level is less than the severity of dust accumulation at the second level, and the severity of dust accumulation at the second level is less than the severity of dust accumulation at the third level.

[0162] Based on the above embodiments, 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] The first image processing unit is configured to preprocess the photovoltaic module image to obtain a preprocessed photovoltaic module image; the preprocessing includes at least one of grayscale conversion, Gaussian filtering, and morphological operations;

[0164] The image analysis unit is configured to analyze the preprocessed photovoltaic module image based on the histogram analysis method to obtain a grayscale histogram;

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

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

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

[0168] Determine the minimum grayscale value between the two largest peaks in the grayscale histogram based on the grayscale histogram, and use the minimum grayscale value as the first grayscale threshold; the first grayscale threshold is used to distinguish the normal area and the dust area in the photovoltaic module image;

[0169] Set the pixels greater than the second grayscale threshold in the grayscale histogram to the first grayscale value; the second grayscale threshold is greater than the first grayscale threshold;

[0170] Set the pixels less than the first grayscale threshold in the grayscale histogram to the first grayscale value;

[0171] Set the pixels greater than the first grayscale threshold in the grayscale histogram to the second grayscale value;

[0172] 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.

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

[0174] Embodiment Six

[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 FIG. shows a schematic structural 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, for example, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, for example, a personal digital processor, a cellular phone, a smart phone, a wearable device (such as a helmet, glasses, a watch, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present invention described and / or claimed herein.

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

[0178] A plurality of 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 disc, 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] The processor 11 may be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The 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 may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the photovoltaic panel dust accumulation detection method described above may be executed. Alternatively, in other embodiments, the processor 11 may be configured to execute the photovoltaic panel dust accumulation detection method by any other suitable means (e.g., by means of firmware).

[0181] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuitry, integrated circuit systems, field-programmable gate arrays (FPGA), application specific integrated circuits (ASIC), application specific standard products (ASSP), systems on a chip (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including 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 the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0182] The computer program for implementing the method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to the 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 flowchart and / or block diagram are implemented. The computer program can 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 can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0184] To provide for interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: 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 a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can also be used to provide for interaction with the user; for example, 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 backend 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 frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend 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 a client and a server. The client and the server are generally far from each other and usually interact through a communication network. The relationship between the client and the server is created by computer programs running on respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, and solves the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0187] It should be understood that various forms of the processes shown above can be used, steps can be reordered, added or deleted. For example, the steps recited in the present invention can be executed 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, and no limitation is made herein.

[0188] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for detecting dust accumulation on a photovoltaic panel, characterized in that, The method includes: Obtaining a first image of a photovoltaic panel in a target area and determining photovoltaic module images 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; Performing dust recognition on the photovoltaic module images 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 recognition on the photovoltaic module images 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 module is a dust module; the dust module is a photovoltaic module with dust accumulation.

2. The method according to claim 1, characterized in that, The determining the photovoltaic module images of each photovoltaic module in the first image includes: Processing the first image based on the image processing model to obtain the photovoltaic module images of each photovoltaic module 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 an oriented bounding box algorithm; the image obtained by performing image processing using the YOLO11S-OBB algorithm has direction information.

4. The method according to claim 3, characterized in that, The YOLO11S-OBB algorithm further includes a C3K2-T module and a C2PSA-S module; the C3K2-T module has the ability to capture 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 a triple attention mechanism into the C3K2 module; the C2PSA-S module is formed by integrating the SEAM module into the PSA attention layer in the C2PSA 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 a first evaluation index of the photovoltaic module, and the first evaluation index is used to describe the probability value of dust accumulation on the photovoltaic module; the determining whether the photovoltaic module is a dust module based on the first detection result and the second detection result includes: If the first evaluation index of the photovoltaic module is greater than a first preset threshold, determining that the photovoltaic module is a dust module; If the first evaluation index of the photovoltaic module is less than the first preset threshold, using the photovoltaic module with the first evaluation index less than the preset threshold as a reference photovoltaic module; Based on the second detection result, determining whether the reference photovoltaic module is a dust module.

6. The method according to claim 5, wherein The second detection result includes a second evaluation index of the photovoltaic module, and the second evaluation index is a score for evaluating the dust accumulation condition on the photovoltaic module; The determining whether the reference photovoltaic module is a dust module based on the second detection result includes: Take the reference photovoltaic module with the first evaluation index being zero as the first reference photovoltaic module, and take the reference photovoltaic module with the first evaluation index not being zero as the second reference photovoltaic module; If the second evaluation index of the first reference photovoltaic module is greater than the second preset threshold, then the first reference photovoltaic module is a dusty module; If the second evaluation index of the second reference photovoltaic module is greater than the third preset threshold, then the second reference photovoltaic module is a dusty module; the second preset threshold is greater than the third preset threshold.

7. The method according to claim 1, characterized in that, The first detection result includes the first position information of the photovoltaic module. After determining whether the photovoltaic module is a dusty module based on the first detection result and the second detection result, the method further includes: Obtain a second image of the photovoltaic panel in the target area and determine the 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; Based on the second position information corresponding to the hot spot defect in the second image and the first position information of each dusty module, determine the reference hot spot defect matched by each dusty module; Based on the temperature information corresponding to the reference hot spot defect matched by the dusty module, determine the dust accumulation level of the dusty module; the dust accumulation level is used to reflect the severity of dust accumulation.

8. The method according to claim 7, wherein The determining the dust accumulation level of the dusty module based on the temperature information corresponding to the reference hot spot defect matched by the dusty module includes: If the temperature information corresponding to the reference hot spot defect matched by the dusty module is less than the first preset temperature, then the dust accumulation level of the dusty module is the first level; If the temperature information corresponding to the reference hot spot defect matched by the dusty module is greater than the first preset temperature and the temperature information corresponding to the reference hot spot defect matched by the dusty module is less than the second preset temperature, then the dust accumulation level of the dusty module is the second level; If the temperature information corresponding to the reference hot spot defect matched by the dusty module is greater than the second preset temperature, then the dust accumulation level of the dusty module is the third level; the severity of dust accumulation at the first level is less than the severity of dust accumulation at the second level, and the severity of dust accumulation at the second level is less than the severity of dust accumulation at the third level.

9. The method according to claim 1, characterized in that, The preset image processing method is the histogram analysis method. The determining the second detection result of each photovoltaic module by performing dust identification on the photovoltaic module image based on the preset image processing method includes: Perform preprocessing on the photovoltaic module image to obtain the preprocessed photovoltaic module image; the preprocessing includes at least one of grayscale conversion, Gaussian filtering, and morphological operations; Analyze the preprocessed photovoltaic module image based on the histogram analysis method to obtain a grayscale histogram; Perform binarization processing on the grayscale histogram based on a preset threshold to obtain the binarized image of the photovoltaic module; Take 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 module.

10. The method according to claim 9, wherein The preset threshold includes a first grayscale threshold and a second grayscale threshold. Binarizing the grayscale histogram based on the preset threshold to obtain a binary image of the photovoltaic module, which includes: 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 the first grayscale threshold; the first grayscale threshold is used to distinguish the normal area and the dust area in the photovoltaic module image; Setting the pixels greater than the second grayscale threshold in the grayscale histogram to the first grayscale value; the second grayscale threshold is greater than the first grayscale threshold; Setting the pixels less than the first grayscale threshold in the grayscale histogram to the first grayscale value; Setting the pixels greater than the first grayscale threshold in the grayscale histogram to the second grayscale value; Wherein, 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.

11. A photovoltaic panel dust accumulation detection device, characterized in that, The device includes: An image determination module, configured to obtain 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; 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 of each photovoltaic module; the image processing model is 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 to determine a second detection result of each photovoltaic module; the preset image processing method is a method for processing an image based on statistical principles and mathematical analysis principles; A third detection module, configured to determine whether the photovoltaic module is a dust component based on the first detection result and the second detection result; the dust component is a photovoltaic module with dust accumulation.

12. An electronic device, characterized in that, The electronic device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the photovoltaic panel dust detection method according to any one of claims 1-10.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a processor to implement the photovoltaic panel dust detection method according to any one of claims 1-10 when executed.

Images