A photovoltaic panel surface dust detection method, device and storage medium

Abstract

The application provides a photovoltaic panel surface dust detection method, device and storage medium, and belongs to the technical field of photovoltaic panel dust detection. The method comprises the following steps: dividing a photovoltaic power station to be detected into a plurality of dust detection areas; marking the coordinates of the dust detection areas to obtain original photovoltaic panel coordinate information; obtaining an original physical photovoltaic panel image from an infrared imager; constructing a virtual photovoltaic power station by using dust deposition data, meteorological data and photovoltaic panel state data; and extracting an image of the virtual photovoltaic power station to obtain an original virtual photovoltaic panel image. The application can accurately detect the surface dust of the photovoltaic panel, effectively improves the detection efficiency of the surface dust of the photovoltaic panel, realizes fault diagnosis and health management of the photovoltaic power station to be detected, effectively prolongs the service life of the photovoltaic power station to be detected, saves a large amount of manpower, material resources and time cost, and reduces the labor intensity of power station employees.

Description

Technical Field

[0001] The present invention mainly relates to the technical field of photovoltaic panel dust accumulation detection, and specifically relates to a photovoltaic panel surface dust accumulation detection method, device and storage medium. Background Art

[0002] In recent years, solar photovoltaic power generation, as a widely used clean energy source, has played a vital role in environmental and economic sustainability. However, during the operation of solar photovoltaic power plants, due to prolonged exposure to complex external environments, large amounts of dust inevitably accumulate on the surfaces of photovoltaic panels. This accumulation of dust can cause shading and temperature effects on the panels, leading to abnormal heating and the appearance of noticeable hot spots. This in turn reduces the panels' power generation efficiency and the service life of the power plant. Therefore, timely, accurate, and efficient dust detection on photovoltaic panel surfaces is crucial.

[0003] The current existing detection method is to manually inspect the photovoltaic panels of the power station regularly using an infrared thermal imager and a lifting platform to determine whether there is a hot spot phenomenon, so as to take corresponding cleaning measures, or to use drones to collect images of the photovoltaic panel surface, use image recognition technology to obtain the amount of dust on the photovoltaic panel surface, and determine whether the photovoltaic panel needs to be cleaned. However, the above two detection methods have the following problems: (1) Manual regular inspection of the photovoltaic panel surface may fail to clean the abnormal photovoltaic panel surface in time, causing damage to the photovoltaic panel before cleaning. At the same time, the cost of manpower, material resources and time is too high; (2) Using drones to collect images of the photovoltaic panel surface and analyze the dust content, there is a problem of inaccurate identification of the dust content at non-hot spots on the photovoltaic panel surface, resulting in excessive cleaning and waste of resources; (3) The detection accuracy of the above two detection methods cannot accurately locate each photovoltaic panel, resulting in poor cleaning effect and low efficiency when cleaning the abnormal photovoltaic panel surface. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to address the deficiencies of the existing technology and provide a method, device and storage medium for detecting dust accumulation on the surface of a photovoltaic panel.

[0005] The present invention solves the above technical problems with the following technical solutions: A method for detecting dust accumulation on the surface of a photovoltaic panel, comprising the following steps:

[0006] S1: Divide the photovoltaic power station to be inspected into multiple dust detection areas;

[0007] S2: Marking the coordinates of each of the dust detection areas to obtain original photovoltaic panel coordinate information corresponding to each of the dust detection areas;

[0008] S3: obtaining an original physical photovoltaic panel image corresponding to each of the dust detection areas from an infrared imager;

[0009] S4: importing a plurality of dust deposition data, a plurality of meteorological data, and a plurality of photovoltaic panel status data, and constructing a virtual photovoltaic power station corresponding to the photovoltaic power station to be detected by using all of the dust deposition data, all of the meteorological data, and all of the photovoltaic panel status data;

[0010] S5: performing image extraction on the virtual photovoltaic power station to obtain original virtual photovoltaic panel images corresponding to the respective dust detection areas;

[0011] S6: constructing a training model, and performing model analysis on the training model according to all the original photovoltaic panel coordinate information, all the original virtual photovoltaic panel images, and all the original physical photovoltaic panel images to obtain a dust accumulation detection model;

[0012] S7: Using the dust accumulation detection model, the original photovoltaic panel coordinate information corresponding to each of the dust accumulation detection areas and the original virtual photovoltaic panel image corresponding to each of the dust accumulation detection areas are detected respectively to obtain detection results of each of the dust accumulation detection areas.

[0013] Another technical solution of the present invention to solve the above technical problem is as follows: a device for detecting dust accumulation on the surface of a photovoltaic panel, comprising:

[0014] A division module is used to divide the photovoltaic power station to be inspected into multiple dust detection areas;

[0015] A coordinate marking module is used to mark the coordinates of each of the dust accumulation detection areas respectively to obtain original photovoltaic panel coordinate information corresponding to each of the dust accumulation detection areas;

[0016] A physical image acquisition module, configured to obtain an original physical photovoltaic panel image corresponding to each of the dust accumulation detection areas from an infrared imager;

[0017] Import module, used to import multiple dust deposition data, multiple meteorological data and multiple photovoltaic panel status data;

[0018] a virtual power station construction module, configured to construct a virtual photovoltaic power station corresponding to the photovoltaic power station to be detected by using all the dust deposition data, all the meteorological data, and all the photovoltaic panel status data;

[0019] A virtual image extraction module is used to extract images of the virtual photovoltaic power station to obtain original virtual photovoltaic panel images corresponding to the respective dust detection areas;

[0020] a model analysis module, configured to construct a training model, and perform model analysis on the training model based on all the original photovoltaic panel coordinate information, all the original virtual photovoltaic panel images, and all the original physical photovoltaic panel images to obtain a dust accumulation detection model;

[0021] The detection result acquisition module is used to detect the original photovoltaic panel coordinate information corresponding to each dust detection area and the original virtual photovoltaic panel image corresponding to each dust detection area through the dust detection model to obtain the detection results of each dust detection area.

[0022] Based on the above-mentioned method for detecting dust accumulation on the surface of a photovoltaic panel, the present invention also provides a system for detecting dust accumulation on the surface of a photovoltaic panel.

[0023] Another technical solution of the present invention to solve the above-mentioned technical problem is as follows: a photovoltaic panel surface dust detection system includes a memory, a processor, and a computer program stored in the memory and runnable on the processor. When the processor executes the computer program, the photovoltaic panel surface dust detection method described above is implemented.

[0024] Based on the above-mentioned method for detecting dust accumulation on the surface of a photovoltaic panel, the present invention also provides a computer-readable storage medium.

[0025] Another technical solution of the present invention to solve the above technical problems is as follows: a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned method for detecting dust accumulation on the surface of a photovoltaic panel is implemented.

[0026] The beneficial effects of the present invention are as follows: by dividing the photovoltaic power station to be inspected into dust detection areas, marking the coordinates of the dust detection areas to obtain the original photovoltaic panel coordinate information, obtaining the original physical photovoltaic panel image from the infrared imager, constructing a virtual photovoltaic power station through dust deposition data, meteorological data and photovoltaic panel status data, extracting the image of the virtual photovoltaic power station to obtain the original virtual photovoltaic panel image, and analyzing the training model based on the original photovoltaic panel coordinate information, the original virtual photovoltaic panel image and the original physical photovoltaic panel image to obtain a dust detection model, and detecting the original photovoltaic panel coordinate information and the original virtual photovoltaic panel image through the dust detection model to obtain the detection result, which can accurately realize the detection of dust on the surface of the photovoltaic panel, effectively improve the detection efficiency of dust on the surface of the photovoltaic panel, realize fault diagnosis and health management of the photovoltaic power station to be inspected, effectively improve the service life of the photovoltaic power station to be inspected, and at the same time save a lot of manpower, material and time costs, and reduce the labor intensity of the power station employees. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1A schematic flow chart of a method for detecting dust accumulation on the surface of a photovoltaic panel provided by an embodiment of the present invention;

[0028] Figure 2 A schematic diagram of the coordinate division of each dust accumulation detection area in a photovoltaic power station to be detected in a method for detecting dust accumulation on the surface of a photovoltaic panel provided by an embodiment of the present invention;

[0029] Figure 3 A schematic diagram of force analysis of dust particles on the surface of a photovoltaic panel according to a method for detecting dust accumulation on the surface of a photovoltaic panel provided by an embodiment of the present invention;

[0030] Figure 4 A schematic diagram of a model structure of a method for detecting dust accumulation on the surface of a photovoltaic panel provided by an embodiment of the present invention;

[0031] Figure 5 A schematic diagram of a model for constructing a method for detecting dust accumulation on the surface of a photovoltaic panel provided by an embodiment of the present invention;

[0032] Figure 6 This is a module block diagram of a photovoltaic panel surface dust detection device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0033] The principles and features of the present invention are described below with reference to the accompanying drawings. The examples given are only used to explain the present invention and are not used to limit the scope of the present invention.

[0034] Figure 1 A schematic flow chart of a method for detecting dust accumulation on the surface of a photovoltaic panel provided in an embodiment of the present invention.

[0035] like Figure 1 and 2 As shown, a method for detecting dust accumulation on the surface of a photovoltaic panel includes the following steps:

[0036] S1: Divide the photovoltaic power station to be inspected into multiple dust detection areas;

[0037] S2: Marking the coordinates of each of the dust detection areas to obtain original photovoltaic panel coordinate information corresponding to each of the dust detection areas;

[0038] S3: obtaining an original physical photovoltaic panel image corresponding to each of the dust detection areas from an infrared imager;

[0039] S4: importing a plurality of dust deposition data, a plurality of meteorological data, and a plurality of photovoltaic panel status data, and constructing a virtual photovoltaic power station corresponding to the photovoltaic power station to be detected by using all of the dust deposition data, all of the meteorological data, and all of the photovoltaic panel status data;

[0040] S5: performing image extraction on the virtual photovoltaic power station to obtain original virtual photovoltaic panel images corresponding to the respective dust detection areas;

[0041] S6: constructing a training model, and performing model analysis on the training model according to all the original photovoltaic panel coordinate information, all the original virtual photovoltaic panel images, and all the original physical photovoltaic panel images to obtain a dust accumulation detection model;

[0042] S7: Using the dust accumulation detection model, the original photovoltaic panel coordinate information corresponding to each of the dust accumulation detection areas and the original virtual photovoltaic panel image corresponding to each of the dust accumulation detection areas are detected respectively to obtain detection results of each of the dust accumulation detection areas.

[0043] It should be understood that a model is constructed for all the meteorological data and all the photovoltaic panel status data using the ANSYS Fluent tool to obtain a virtual photovoltaic power station.

[0044] It should be understood that the image of the virtual photovoltaic power station is extracted by using the infrared imaging technology principle.

[0045] It should be understood that the dust deposition data may be a dust deposition criterion.

[0046] Specifically, sensor technology is used to collect real-time status data of the photovoltaic power station, such as meteorological data such as light intensity, ambient temperature, relative humidity, and wind speed, as well as the current and voltage of the photovoltaic panels (i.e., photovoltaic panel status data). This data is then transmitted in real time to the virtual entity of the photovoltaic power station to be constructed using 5G technology combined with message queue data transmission. Secondly, based on the physical structure and operating principle of the photovoltaic power station itself and the collision-adhesion dynamic behavior criteria between the photovoltaic panel surface and dust particles, a virtual entity of the photovoltaic power station (i.e., a virtual photovoltaic power station) identical to the physical entity of the photovoltaic power station is constructed using platforms such as COMSOL Multiphysics, ANSYS Fluent, PVsyst, Twins, and SolarWinds.

[0047] It should be understood that the photovoltaic panels of the physical entity and virtual entity of the target power station (i.e. the photovoltaic power station to be detected) are divided into dust accumulation identification areas (i.e. dust accumulation detection areas) according to a plane grid format, and each dust accumulation identification area is a single photovoltaic panel. Figure 2 As shown, for example: the coordinates of photovoltaic panel No. 1 are (1, 1), the coordinates of photovoltaic panel No. 2 are (2, 1), and so on. Each photovoltaic panel in the power station is assigned the corresponding coordinates (i.e., the original photovoltaic panel coordinate information).

[0048] It should be understood that the infrared imager may be arranged above the photovoltaic power station to be inspected.

[0049] It should be understood that at each sampling moment, infrared image data (ie, original physical photovoltaic panel image) of each dust accumulation identification area is collected by infrared imaging technology.

[0050] Specifically, the coordinate information of each dust accumulation identification area corresponding to the physical entity and virtual entity at each sampling moment (i.e., the original photovoltaic panel coordinate information) and the infrared image data (i.e., the original physical photovoltaic panel image and the original virtual photovoltaic panel image) are respectively sent to their respective CCSAR-Net models (i.e., the training model).

[0051] In the above embodiment, the photovoltaic power station to be inspected is divided into dust detection areas, the coordinates of the dust detection areas are marked to obtain the original photovoltaic panel coordinate information, the original physical photovoltaic panel image is obtained from the infrared imager, the virtual photovoltaic power station is constructed by dust deposition data, meteorological data and photovoltaic panel status data, the image of the virtual photovoltaic power station is extracted to obtain the original virtual photovoltaic panel image, the dust detection model is obtained by model analysis of the training model based on the original photovoltaic panel coordinate information, the original virtual photovoltaic panel image and the original physical photovoltaic panel image, the dust detection model is used to detect the original photovoltaic panel coordinate information and the original virtual photovoltaic panel image to obtain the detection result, which can accurately realize the detection of dust on the surface of the photovoltaic panel, effectively improve the detection efficiency of dust on the surface of the photovoltaic panel, realize fault diagnosis and health management of the photovoltaic power station to be inspected, effectively improve the service life of the photovoltaic power station to be inspected, and at the same time save a lot of manpower, material and time costs, and reduce the labor intensity of the power station employees.

[0052] Optionally, as an embodiment of the present invention, the training model includes a backbone network and a head network.

[0053] The S6 process includes:

[0054] Performing feature extraction on each of the original photovoltaic panel coordinate information and the original physical photovoltaic panel image corresponding to each of the dust detection areas through the backbone network, thereby obtaining coordinate features of the physical photovoltaic panel to be processed corresponding to each of the dust detection areas and image features of the physical photovoltaic panel to be processed corresponding to each of the dust detection areas;

[0055] Performing feature extraction on each of the original photovoltaic panel coordinate information and the original virtual photovoltaic panel image corresponding to each of the dust detection areas through the backbone network, thereby obtaining a to-be-processed virtual photovoltaic panel coordinate feature corresponding to each of the dust detection areas and a to-be-processed virtual photovoltaic panel image feature corresponding to each of the dust detection areas;

[0056] mapping processing on each of the to-be-processed entity photovoltaic panel coordinate features and the to-be-processed entity photovoltaic panel image features corresponding to each of the dust accumulation detection areas by the head network to obtain an entity photovoltaic panel feature matrix corresponding to each of the dust accumulation detection areas and an entity photovoltaic panel predicted classification result corresponding to each of the dust accumulation detection areas;

[0057] mapping processing on each of the to-be-processed virtual photovoltaic panel coordinate features and the to-be-processed virtual photovoltaic panel image features corresponding to each of the dust accumulation detection areas by the head network to obtain a virtual photovoltaic panel feature matrix corresponding to each of the dust accumulation detection areas and a virtual photovoltaic panel predicted classification result corresponding to each of the dust accumulation detection areas;

[0058] importing the real classification results corresponding to each of the dust accumulation detection areas, and performing target loss value calculation on all the entity photovoltaic panel feature matrices, all the virtual photovoltaic panel feature matrices, all the entity photovoltaic panel predicted classification results, all the virtual photovoltaic panel predicted classification results, and all the real classification results to obtain a target loss value;

[0059] determining whether the target loss value is greater than or equal to a preset threshold value, and if not, returning to S2; if yes, performing parameter updating on the training model according to the target loss value to obtain a dust accumulation detection model.

[0060] It should be understood that the preset threshold value can be a threshold value of hot spot formation.

[0061] It should be understood that the data processing steps of feature extraction on each of the original photovoltaic panel coordinate information and the original virtual photovoltaic panel image corresponding to each of the dust accumulation detection areas by the backbone network are the same as the data processing steps of feature extraction on each of the original photovoltaic panel coordinate information and the original entity photovoltaic panel image corresponding to each of the dust accumulation detection areas by the backbone network, only the processed data is different.

[0062] It should be understood that the data processing steps of mapping processing on each of the to-be-processed virtual photovoltaic panel coordinate features and the to-be-processed virtual photovoltaic panel image features corresponding to each of the dust accumulation detection areas by the head network are the same as the data processing steps of mapping processing on each of the to-be-processed entity photovoltaic panel coordinate features and the to-be-processed entity photovoltaic panel image features corresponding to each of the dust accumulation detection areas by the head network, only the processed data is different.

[0063] Specifically, the model is divided into a backbone network and a head network, the backbone network is used to extract high-level features in the input data, and the head network maps the high-level features extracted by the backbone network into the final output, so as to realize the recognition of the dust on the surface of the photovoltaic panel.

[0064] In the above embodiment, a dust accumulation detection model is obtained by analyzing the training model based on the original photovoltaic panel coordinate information, the original virtual photovoltaic panel image and the original physical photovoltaic panel image, thereby realizing the recognition of dust accumulation on the surface of the photovoltaic panel, effectively improving the detection efficiency of dust accumulation on the surface of the photovoltaic panel, realizing fault diagnosis and health management of the photovoltaic power station to be detected, and effectively improving the service life of the photovoltaic power station to be detected.

[0065] Optionally, as an embodiment of the present invention, the backbone network includes a plurality of sequentially arranged residual blocks,

[0066] The process of extracting features from the original photovoltaic panel coordinate information and the original physical photovoltaic panel image corresponding to each dust detection area through the backbone network to obtain the coordinate features of the physical photovoltaic panel to be processed corresponding to each dust detection area and the image features of the physical photovoltaic panel to be processed corresponding to each dust detection area includes:

[0067] The first residual block is used to extract features of the original photovoltaic panel coordinate information and the original physical photovoltaic panel image corresponding to each dust detection area, and the results of the feature extraction are input into the second residual block until the last residual block is passed, thereby obtaining the coordinate features of the physical photovoltaic panel to be processed corresponding to each dust detection area and the image features of the physical photovoltaic panel to be processed corresponding to each dust detection area.

[0068] It should be understood that the backbone network includes multiple residual blocks.

[0069] In the above embodiment, the backbone network is used to perform feature extraction on the original photovoltaic panel coordinate information and the original entity photovoltaic panel image to obtain the coordinate features of the entity photovoltaic panel to be processed and the image features of the entity photovoltaic panel to be processed, thereby realizing the recognition of dust on the surface of the photovoltaic panel, effectively improving the detection efficiency of dust on the surface of the photovoltaic panel, realizing fault diagnosis and health management of the photovoltaic power station to be detected, and effectively improving the service life of the photovoltaic power station to be detected.

[0070] Optionally, as an embodiment of the present invention, the residual block includes a convolution block, an attention mechanism layer and a residual connection layer.

[0071] The process of extracting features from the original photovoltaic panel coordinate information and the original physical photovoltaic panel image corresponding to each dust detection area using the first residual block includes:

[0072] Performing feature extraction on each of the original photovoltaic panel coordinate information and the original physical photovoltaic panel image corresponding to each of the dust accumulation detection areas through the convolution block, thereby obtaining a first physical photovoltaic panel coordinate feature corresponding to each of the dust accumulation detection areas and a first physical photovoltaic panel image feature corresponding to each of the dust accumulation detection areas;

[0073] Performing feature extraction on each of the first physical photovoltaic panel coordinate features and the first physical photovoltaic panel image features corresponding to each of the dust accumulation detection areas through the attention mechanism layer, thereby obtaining a second physical photovoltaic panel coordinate feature corresponding to each of the dust accumulation detection areas and a second physical photovoltaic panel image feature corresponding to each of the dust accumulation detection areas;

[0074] Performing feature extraction on each of the second physical photovoltaic panel coordinate features and the second physical photovoltaic panel image features corresponding to each of the dust accumulation detection areas through the residual connection layer, thereby obtaining third physical photovoltaic panel coordinate features corresponding to each of the dust accumulation detection areas and third physical photovoltaic panel image features corresponding to each of the dust accumulation detection areas;

[0075] respectively concatenating each of the second physical photovoltaic panel coordinate features with the corresponding physical third photovoltaic panel coordinate features to obtain a fourth physical photovoltaic panel coordinate feature corresponding to each of the dust accumulation detection areas;

[0076] Each of the second physical photovoltaic panel image features is spliced ​​with the corresponding third physical photovoltaic panel image feature to obtain a fourth physical photovoltaic panel image feature corresponding to each of the dust accumulation detection areas.

[0077] It should be understood that each residual block consists of a convolution block (Conv Block), an attention mechanism (Shuffle Attention) (i.e., an attention mechanism layer), a residual connection (i.e., a residual connection layer) and an addition operation (Addition).

[0078] Specifically, the present invention adopts Shuffle Attention (SA), which effectively combines the spatial attention mechanism and the channel attention mechanism. The specific operation is: SA first divides the channel dimension into multiple sub-features, and then processes them in parallel. For each sub-feature, SA uses Shuffle Unit (Shuffle Unit uses both the spatial attention mechanism and the channel attention mechanism for the sub-features) to extract the feature dependencies in the spatial and channel dimensions, and then aggregates all sub-features. Finally, Channel Shuffle is used to realize information communication between different sub-features. The application of SA uses two attention mechanisms at the same time, which improves the semantic expression ability of dust accumulation features, helps the CCSAR-Net model (i.e., the training model) extract attention areas, and focuses on dust accumulation features.

[0079] In the above embodiment, the first residual block is used to extract features of the original photovoltaic panel coordinate information and the original physical photovoltaic panel image, which effectively combines the spatial attention mechanism and the channel attention mechanism, improves the semantic expression ability of the dust accumulation feature, and can help the model extract the attention area and focus on the dust accumulation feature.

[0080] Optionally, as an embodiment of the present invention, the convolution block includes a first coordinate convolution layer, a first convolution layer, a batch normalization layer and an activation layer,

[0081] The process of performing feature extraction on each of the original photovoltaic panel coordinate information and the original physical photovoltaic panel image corresponding to each of the dust accumulation detection areas through the convolution block to obtain the first physical photovoltaic panel coordinate feature corresponding to each of the dust accumulation detection areas and the first physical photovoltaic panel image feature corresponding to each of the dust accumulation detection areas includes:

[0082] Performing coordinate information feature extraction on each of the original photovoltaic panel coordinate information through the first coordinate convolution layer to obtain fifth physical photovoltaic panel coordinate features corresponding to each of the dust detection areas;

[0083] Performing image feature extraction on each of the original physical photovoltaic panel images through the first convolutional layer to obtain fifth physical photovoltaic panel image features corresponding to each of the dust detection areas;

[0084] Normalizing each of the fifth physical photovoltaic panel coordinate features and the fifth physical photovoltaic panel image features corresponding to each of the dust accumulation detection areas through the batch normalization layer to obtain a sixth physical photovoltaic panel coordinate feature corresponding to each of the dust accumulation detection areas and a sixth physical photovoltaic panel image feature corresponding to each of the dust accumulation detection areas;

[0085] The activation layer is used to map the coordinate features of each of the sixth physical photovoltaic panels and the image features of the sixth physical photovoltaic panels corresponding to each of the dust detection areas to obtain the coordinate features of the first physical photovoltaic panel corresponding to each of the dust detection areas and the image features of the first physical photovoltaic panel corresponding to each of the dust detection areas.

[0086] It should be understood that in addition to the traditional convolution layer (Conv Layer) (i.e., the first convolution layer), batch normalization layer (Batchnorm Layer) and activation layer (Relu), the convolution block also introduces a coordinate convolution (CoordConv Layer) (i.e., the first coordinate convolution layer).

[0087] Specifically, coordinate convolution (i.e., the first coordinate convolution layer) adds coordinate information (i, j) to the input data (infrared images of each dust detection area), allowing the network to consider the spatial structure and positional relationships of the input data during the convolution process. The application of coordinate convolution better utilizes the positional information of the input data, thereby enhancing the CCSAR-Net model's (i.e., the training model's) ability to perceive dust accumulation locations.

[0088] In the above embodiment, the convolution block is used to perform feature extraction on the original photovoltaic panel coordinate information and the original physical photovoltaic panel image to obtain the first physical photovoltaic panel coordinate feature and the first physical photovoltaic panel image feature, thereby better utilizing the position information of the input data, thereby enhancing the model's perception of the dust accumulation location, effectively improving the detection efficiency of dust accumulation on the photovoltaic panel surface, realizing fault diagnosis and health management of the photovoltaic power station to be detected, and effectively improving the service life of the photovoltaic power station to be detected.

[0089] Optionally, as an embodiment of the present invention, the residual connection layer includes a second coordinate convolution layer and a second convolution layer,

[0090] The process of extracting features of each second physical photovoltaic panel coordinate feature and the second physical photovoltaic panel image feature corresponding to each dust accumulation detection area through the residual connection layer to obtain a third physical photovoltaic panel coordinate feature corresponding to each dust accumulation detection area and a third physical photovoltaic panel image feature corresponding to each dust accumulation detection area includes:

[0091] Extracting coordinate information from each of the second physical photovoltaic panel coordinate features through the second coordinate convolution layer to obtain third physical photovoltaic panel coordinate features corresponding to each of the dust detection areas;

[0092] The second convolutional layer is used to extract image features of each of the second physical photovoltaic panel images to obtain third physical photovoltaic panel image features corresponding to each of the dust detection areas.

[0093] It should be understood that the residual connection (i.e., the residual connection layer) is a pattern of coordinate convolution (i.e., the second coordinate convolution layer) plus a traditional convolution layer (i.e., the second convolution layer).

[0094] In the above embodiment, the third entity photovoltaic panel coordinate features and the third entity photovoltaic panel image features are obtained by extracting the second entity photovoltaic panel coordinate features and the second entity photovoltaic panel image features through the residual connection layer, which effectively improves the detection efficiency of dust on the surface of the photovoltaic panel, realizes the fault diagnosis and health management of the photovoltaic power station to be detected, and effectively improves the service life of the photovoltaic power station to be detected.

[0095] Optionally, as an embodiment of the present invention, the head network includes a maximum pooling layer, a dropout layer, a fully connected layer and a classification layer.

[0096] The process of mapping the coordinate features of each of the to-be-processed physical photovoltaic panels and the image features of the to-be-processed physical photovoltaic panels corresponding to each of the dust accumulation detection areas through the head network to obtain a physical photovoltaic panel feature matrix corresponding to each of the dust accumulation detection areas and a predicted classification result of the physical photovoltaic panels corresponding to each of the dust accumulation detection areas includes:

[0097] performing pooling processing on each of the to-be-processed physical photovoltaic panel coordinate features and the to-be-processed physical photovoltaic panel image features corresponding to each of the dust accumulation detection areas through the maximum pooling layer, thereby obtaining a seventh physical photovoltaic panel coordinate feature corresponding to each of the dust accumulation detection areas and a seventh physical photovoltaic panel image feature corresponding to each of the dust accumulation detection areas;

[0098] Performing feature optimization processing on each of the seventh physical photovoltaic panel coordinate features and the seventh physical photovoltaic panel image features corresponding to each of the dust accumulation detection areas through the discarded layer, thereby obtaining an eighth physical photovoltaic panel coordinate feature corresponding to each of the dust accumulation detection areas and an eighth physical photovoltaic panel image feature corresponding to each of the dust accumulation detection areas;

[0099] The eighth physical photovoltaic panel coordinate features corresponding to each of the dust accumulation detection areas and the eighth physical photovoltaic panel image features corresponding to each of the dust accumulation detection areas are respectively spliced ​​through the fully connected layer to obtain a physical photovoltaic panel feature matrix corresponding to each of the dust accumulation detection areas;

[0100] The classification layer is used to classify the feature matrices of each physical photovoltaic panel to obtain predicted classification results of the physical photovoltaic panels corresponding to each dust accumulation detection area.

[0101] It should be understood that the head network is composed of a Max-Pooling Layer, a Dropout Layer, a Fully Connected Layer, and a Softmax Layer.

[0102] In the above embodiment, the entity photovoltaic panel coordinate features and the entity photovoltaic panel image features are mapped by the head network to obtain the entity photovoltaic panel feature matrix and the entity photovoltaic panel prediction classification result, effectively improving the detection efficiency of the dust on the surface of the photovoltaic panel, realizing the fault diagnosis and health management of the photovoltaic power station to be detected, and effectively improving the service life of the photovoltaic power station to be detected.

[0103] Optionally, as an embodiment of the present application, the process of calculating the target loss value by the entity photovoltaic panel feature matrix, the virtual photovoltaic panel feature matrix, the entity photovoltaic panel prediction classification result, the virtual photovoltaic panel prediction classification result, and the true classification result comprises:

[0104] The field adaptive loss value corresponding to each dust accumulation detection area is calculated by the first formula on each entity photovoltaic panel feature matrix and the virtual photovoltaic panel feature matrix corresponding to each dust accumulation detection area, and the first formula is:

[0105]

[0106] Wherein, is the field adaptive loss value corresponding to the a-th dust accumulation detection area, C is the C-th dust category, m is the total number of dust categories, N is the total number of rows and columns of the entity photovoltaic panel feature matrix, W i a-s is the photovoltaic panel weight of the i-th row in the entity photovoltaic panel feature matrix corresponding to the a-th dust accumulation detection area, W j a-s is the photovoltaic panel weight of the j-th column in the entity photovoltaic panel feature matrix corresponding to the a-th dust accumulation detection area, K() is a Gaussian kernel function, is the entity photovoltaic panel feature of the i-th row in the entity photovoltaic panel feature matrix corresponding to the a-th dust accumulation detection area, is the entity photovoltaic panel feature of the j-th column in the entity photovoltaic panel feature matrix corresponding to the a-th dust accumulation detection area, W j a-t is the photovoltaic panel weight of the j-th column in the virtual photovoltaic panel feature matrix corresponding to the a-th dust accumulation detection area, is the virtual photovoltaic panel feature of the j-th column in the entity photovoltaic panel feature matrix corresponding to the a-th dust accumulation detection area, W ia-t is the photovoltaic panel weight of the i-th row in the virtual photovoltaic panel feature matrix corresponding to the a-th dust detection area, is the virtual photovoltaic panel feature of the i-th row in the physical photovoltaic panel feature matrix corresponding to the a-th dust detection area;

[0107] The target cross entropy loss value is obtained by calculating the cross entropy loss value for all the physical photovoltaic panel prediction classification results, all the virtual photovoltaic panel prediction classification results, and all the real classification results through the second formula, and the second formula is:

[0108] L MRCE =L MRCEs -L MRCEt ,

[0109] in,

[0110] in,

[0111] Among them, L MRCE is the target cross entropy loss value, L MRCEs is the entity cross entropy loss value, L MRCEt is the virtual cross entropy loss value, M is the total number of dust detection areas, is the predicted classification result of the physical photovoltaic panel corresponding to the a-th dust detection area, is the true classification result corresponding to the a-th dust detection area, E C is the regularization penalty coefficient of the Cth dust category, C is the Cth dust category, m is the total number of dust categories, Predict the classification results for the virtual photovoltaic panel corresponding to the a-th dust detection area;

[0112] All the domain adaptation loss values ​​are added to the cross entropy loss value to obtain a target loss value.

[0113] It should be understood that the domain adaptation loss (i.e., the domain adaptation loss value) is calculated from the features extracted from the source domain and the target domain (i.e., the predicted values ​​of the photovoltaic panels) and the corresponding true labels (i.e., the true values ​​of the photovoltaic panels). Both encourage the model to align the features of the source domain and the target domain and reduce the distribution difference between the source domain and the target domain. The boundary regularized cross entropy loss (i.e., the cross entropy loss value) is calculated from the classification results (i.e., the predicted classification results) output by the CCSAR-Net model (i.e., the training model) and the corresponding true labels (i.e., the true classification results). By continuously adjusting the parameters of the CCSAR-Net_1 model and the CCSAR-Net_2 model (i.e., the training model) based on the domain adaptation loss of the Gaussian kernel function and the boundary regularized cross entropy loss, the CCSAR-Net_2 model (i.e., the training model) can better adapt to the CCSAR-Net_1 model and reach the performance level of the CCSAR-Net_1 model.

[0114] Specifically, the present invention adopts a domain adaptation algorithm based on the Gaussian kernel function, which minimizes the difference between the means of the kernel matrices after dimensionality reduction between different domains, so as to make the source domain s (the feature information of the dust recognition area corresponding to the physical entity) and the target domain t (the feature information of the dust recognition area corresponding to the virtual entity) more consistent in the feature space. The specific process of the algorithm is: calculate the sample weight matrix and the Gaussian kernel matrix, extract the kernel matrices inside the source domain, inside the target domain, and between the source domain and the target domain from the Gaussian kernel matrix, perform dimensionality reduction operations on these matrices and calculate the means respectively, and calculate the final loss based on the sample weights and the kernel matrix after dimensionality reduction. The dust type defined in the present invention belongs to the binary classification (whether the threshold for hot spot formation is reached). Assuming X s is the sample of the source domain (i.e. the true value of the photovoltaic panel), X t is the sample of the target domain (i.e., the predicted value of the photovoltaic panel), and the weights of the two are W s and W t , H is the Hilbert feature mapping space, f(·) represents the data feature mapping process, and the domain adaptation loss L based on the Gaussian kernel function GKDA The definitions are as follows:

[0115]

[0116] Where C represents the number of dust categories (i.e. the Cth dust category), N s Indicates the number of samples in the source domain, N t represents the number of samples in the target domain, and K(·) represents the Gaussian kernel function used for data feature mapping.

[0117] Specifically, the present invention introduces a boundary regularized cross entropy loss function, which improves the robustness of the decision boundary and enhances the discrimination between categories by applying a significant regularization penalty to the boundary of the dust type data. Assuming that the classification network is represented by S(·), the sample x i The boundary of is expressed as:

[0118]

[0119] In the formula Represents the category y in the classification network output i The output value of category c is expressed as:

[0120]

[0121] Where N c Represents the number of samples of category c, when When , the generalization error is minimum, that is, the larger the sample size of a category, the smaller the distance between the category and the decision boundary. Therefore, the cross entropy loss L based on the true label distribution is introduced to regularize the boundary. MRCE The definition is as follows:

[0122] L MRCE =L MRCEs -L MRCEt ,

[0123] L MRCEs or

[0124]

[0125] Where N represents the total number of samples, E c represents the regularization penalty coefficient of category c, Represents the category y in the classification network output i The output value of (i.e., the prediction classification result of the physical photovoltaic panel or the prediction classification result of the virtual photovoltaic panel).

[0126] In the above embodiment, the target loss value is calculated for the physical photovoltaic panel feature matrix, the virtual photovoltaic panel feature matrix, the physical photovoltaic panel prediction classification results, the virtual photovoltaic panel prediction classification results and the real classification results to obtain the target loss value, which can accurately realize the detection of dust on the surface of the photovoltaic panel, effectively improve the detection efficiency of dust on the surface of the photovoltaic panel, realize the fault diagnosis and health management of the photovoltaic power station to be detected, effectively improve the service life of the photovoltaic power station to be detected, and at the same time save a lot of manpower, material and time costs, and reduce the labor intensity of power station employees.

[0127] Optionally, as another embodiment of the present invention, after the construction of the virtual entity of the photovoltaic power station and the learning of the CCSAR-Net_2 model (i.e., the dust accumulation detection model) are completed, the dust accumulation on the surface of the physical entity photovoltaic panel can be cleaned through the digital twin of the photovoltaic power station. The overall framework is as follows: at each sampling moment, the coordinate information of each photovoltaic panel of the virtual entity photovoltaic power station (i.e., the original photovoltaic panel coordinate information) and its corresponding infrared image data (i.e., the original virtual photovoltaic panel image) are obtained, and transmitted to the CCSAR-Net_2 model (i.e., the dust accumulation detection model) in real time through 5G technology and message queue data transmission. The CCSAR-Net_2 model (i.e., the dust accumulation detection model) extracts its features and outputs the corresponding recognition result (i.e., the detection result) to determine whether the dust accumulation on the surface of the photovoltaic panel reaches the threshold for the formation of hot spots, thereby determining whether the photovoltaic panel needs to be cleaned. The specific contents are as follows: If the output result is "yes", the CCSAR-Net_2 model (i.e., the dust detection model) will also output the coordinate information corresponding to the photovoltaic panel. At the same time, the coordinate information will be transmitted to the photovoltaic panel surface dust cleaning system through 5G technology and message queues. After receiving the coordinate information, the system will execute the corresponding program to the location specified by the coordinates to complete the cleaning work. If the output result is "no", the CCSAR-Net_2 model (i.e., the dust detection model) will not output the coordinate information of the photovoltaic panel, which means that there is no need to clean the photovoltaic panel. Through the above method, the digital twin of the photovoltaic power station will complete the dust accumulation on the surface of each photovoltaic panel at each sampling moment, and at the same time, complete the corresponding cleaning tasks for the photovoltaic panels that need to be cleaned.

[0128] Optionally, as another embodiment of the present invention, the technical problem solved by the present invention is as follows:

[0129] 1. Accurately obtain the location information of abnormal photovoltaic panels. Currently, when detecting dust on the surface of photovoltaic panels, due to the high cost of manpower, material resources and time, the detection accuracy is often not accurate to each photovoltaic panel, which will lead to poor cleaning effect and low efficiency when cleaning abnormal photovoltaic panels. Therefore, the present invention is based on the residual network, introduces coordinate convolution, and combines domain adaptive loss and boundary regularized cross entropy loss to construct a CCSAR-Net model. The model can accurately detect dust on the surface of photovoltaic panels and output the location information of abnormal photovoltaic panels, effectively improving the cleaning effect and cleaning efficiency of dust on the surface of photovoltaic panels.

[0130] 2. Timely and efficient detection of abnormal photovoltaic panels. The existing method for detecting dust accumulation on the surface of photovoltaic panels cannot timely and efficiently complete the detection of dust accumulation on the surface of each photovoltaic panel. Based on digital twin technology, the present invention uses sensor technology and message queue data transmission in a 5G environment to obtain various data of the photovoltaic power station in real time and transmit it to the virtual entity of the photovoltaic power station. Combined with the collision-adhesion dynamic behavior criterion between the photovoltaic panel surface and dust particles and the CCSAR-Net model, a digital twin of the photovoltaic power station is built, and the real-time status of the physical entity of the photovoltaic power station is mapped through the digital twin of the photovoltaic power station. In the digital twin of the photovoltaic power station, the detection of dust accumulation on the surface of all photovoltaic panels can be completed in a timely and efficient manner, and abnormal photovoltaic panels can be screened out.

[0131] 3. Accurately and efficiently clean abnormal photovoltaic panels. The coordinate information of abnormal photovoltaic panels output by the digital twin of the photovoltaic power station is transmitted to the photovoltaic panel surface dust cleaning system in real time using 5G technology combined with message queue data transmission. Based on the photovoltaic panel coordinate division rules proposed by this invention, the system accurately locates the abnormal photovoltaic panel using the received coordinate information and completes the cleaning of the abnormal photovoltaic panel surface dust, effectively improving the cleaning efficiency of the photovoltaic panel surface dust cleaning system.

[0132] Optionally, as another embodiment of the present invention, the inventive point of the present invention is as follows:

[0133] 1. Based on the residual network, the present invention introduces coordinate convolution and integrates the domain adaptive loss based on Gaussian kernel function and the cross entropy loss with boundary regularization to construct a CCSAR-Net deep learning model. The model can accurately detect dust on the surface of photovoltaic panels and output the location information of abnormal photovoltaic panels, effectively improving the detection efficiency of dust on the surface of photovoltaic panels. At the same time, the detection accuracy is accurate to each photovoltaic panel, which greatly improves the cleaning effect and efficiency of dust on the surface of photovoltaic panels.

[0134] 2. Based on digital twin technology, the present invention realizes the integration of the virtual entity of the photovoltaic power station and the CCSAR-Net deep learning model to construct a digital twin of the photovoltaic power station. Through the digital twin of the photovoltaic power station, the dust accumulation detection work of all photovoltaic panels in the photovoltaic power station can be completed in a timely and efficient manner, abnormal photovoltaic panels can be screened out, and their coordinate information is transmitted to the photovoltaic panel surface dust cleaning system in real time through 5G technology combined with the data transmission method of the message queue, so as to complete the cleaning work of the abnormal photovoltaic panel surface dust in a timely, efficient and accurate manner. The digital twin of the photovoltaic power station realizes the fault diagnosis and health management of the photovoltaic power station, effectively improving the service life of the photovoltaic power station, while saving a lot of manpower, material and time costs, and reducing the labor intensity of the power station employees.

[0135] Optionally, as another embodiment of the present invention, the present invention is specifically:

[0136] First, sensor technology is used to collect real-time status data from the photovoltaic power station, including meteorological data such as light intensity, ambient temperature, relative humidity, and wind speed, as well as data on the photovoltaic panels themselves, such as current and voltage. This data is then transmitted in real time to the virtual photovoltaic power station to be constructed using 5G technology combined with message queues. Secondly, based on the physical structure and operating principles of the photovoltaic power station itself, as well as the collision-adhesion dynamics between the photovoltaic panel surface and dust particles, a virtual photovoltaic power station identical to the physical photovoltaic power station is constructed using platforms such as COMSOL Multiphysics, ANSYS Fluent, PVsyst, Twins, and SolarWinds.

[0137] Alternatively, as another embodiment of the present invention, Figure 3 As shown, the specific content of the criterion for the collision-adhesion dynamic behavior between the floor panel surface and the dust particles of the present invention is as follows:

[0138] When dust particles move in gas-solid two-phase flow, the fluid drag force F d It is the main force affecting the movement of dust particles. If dust particles are to be deposited on the surface of the photovoltaic panel, they will be subjected to the collision force F of the photovoltaic panel surface. p In addition, dust particles are also affected by their own gravity F during movement. g and air buoyancy F b The effect is as follows:

[0139]

[0140] Where, ρ a and ρ are the density of dust particles and air respectively, in kg / m 3 ; d is the particle diameter, unit is m; m is the mass of the dust particle, unit is kg; u and v are the velocity of the dust particle and the velocity of the flow field, unit is m / s; τ p is the velocity response time of dust particles in the flow field, in s; μ is the aerodynamic viscosity, in P a ·s;C D is the resistance coefficient of the airflow around the particle; Re r is the Reynolds number; is the collision coefficient; L is the compression displacement, unit is μm; L av and L maxare the average and maximum values of L, respectively; x is the compression deformation period; r and R are the radii of the particle and the photovoltaic panel surface (R→∞ for the photovoltaic panel), respectively, in units of μm; α1, v1, and E1 are the elastic deformation coefficient, Poisson's ratio, and Young's modulus (in units of Pa) of the particle, respectively; α2, v2, and E2 are the elastic deformation coefficient, Poisson's ratio, and Young's modulus (in units of Pa) of the photovoltaic panel surface, respectively; m * and M are the equivalent mass and the mass of the photovoltaic panel surface, respectively (m * ≈m because M>>m).

[0141] When the dust particle collides with and adheres to the photovoltaic panel surface, it is subjected to the electrostatic force F e , the friction force F f , and the adhesion force F a , wherein the adhesion force F a is the sum of the van der Waals force F w and the capillary force F c . The calculation formulas of the forces are as follows:

[0142]

[0143] In the formulas, ρ a is the density of the dust particle, in units of kg / m 3 ; r is the radius of the dust particle, in units of μm; e is the relative dielectric constant of air, and e=1 in general cases; e0 is the absolute dielectric constant of air, and e0=8.85×10 -12 F / m in general cases; Q is the charge amount of the particle, in units of C; α is the distance between the surfaces of two contacting objects, in units of nm; ξ is the specific charge, and its value is generally -7×10 -6 C / g for microparticles; c RH is the relative humidity of air; h is the water film thickness, in units of nm; T is the indoor temperature, in units of K; R g is the molar gas constant, in units of J / (mol·K); V0 is the molar volume of water at room temperature, in units of m 3 / mol; H1 and H2 are the Hamaker constants of the two contacting objects in air and water, respectively; e m is the equivalent thickness of the single-layer water molecules when saturated adsorption occurs, in units of nm; C B is the water molecule adsorption coefficient.

[0144] When the dust particle collides with the photovoltaic panel surface, a space rectangular coordinate system xyz is established with the collision point as the origin and the z-axis as the normal direction of the photovoltaic panel surface, and the forces acting on the dust particle are as shown in FIG. 2. Figure 3 In the figure, θ is the included angle between the direction of the particle velocity and the normal z-axis; and v is the particle velocity. The angle between the projection on the xoy plane and the y-axis; δ is the installation inclination angle of the photovoltaic panel.

[0145] According to the kinetic energy theorem, if dust particles are deposited on the surface of a photovoltaic panel, the following conditions must be met simultaneously in the normal and tangential directions of the collision surface:

[0146] Normal:

[0147] F c L c +F w L w +γ+F e L e +F g L g cosδ+E p cos 2 θ-F p L p -F b L b cosδ-F d L d cosθ≥0,

[0148] Tangential:

[0149]

[0150] Where: L c 、L w 、L e 、L g 、L p 、L b 、L d and L f The capillary force F c 、Van der Waals force F w , electrostatic force F e Gravity F g , collision force F p 、Air buoyancy F b , fluid drag F d and friction force F f The effective distance is in meters; γ is the interfacial energy when dust particles come into contact with the photovoltaic panel surface, where γ1 and γ2 are the surface energies of dust particles and the glass cover of the photovoltaic panel, respectively. Their values ​​can be obtained by referring to relevant literature. The unit is J / m 2 ; A is the projected area of ​​dust particles on the photovoltaic panel surface, unit: m 2 ;E p is the kinetic energy of the particles before collision, in J.

[0151] The above conditions are the basis for judging whether dust particles adhere to the surface of photovoltaic panels when constructing a virtual entity of a photovoltaic power station.

[0152] Alternatively, as another embodiment of the present invention, Figures 2 to 5 As shown in Figure 2, the present invention establishes a CCSAR-Net (Coordinate Convolutional Shuffle Attention Residual Network) model to realize the recognition of dust accumulation on the surface of photovoltaic panels. The specific process is as follows: the photovoltaic panels of the target power station physical entity and virtual entity are divided into dust accumulation recognition areas according to the plane grid format. Each dust accumulation recognition area is a single photovoltaic panel, such as Figure 2 For example, the coordinates of photovoltaic panel 1 are (1,1), the coordinates of photovoltaic panel 2 are (2,1), and so on. Each photovoltaic panel in the power plant is assigned corresponding coordinates. Subsequently, infrared imaging technology is used to collect infrared image data for each dust identification area at each sampling time. Finally, the coordinate information and infrared image data of each dust identification area corresponding to the physical entity and virtual entity at each sampling time are fed into their respective CCSAR-Net models (CCSAR-Net_1 for the physical entity and CCSAR-Net_2 for the virtual entity). The CCSAR-Net model extracts and classifies dust features, and the parameters of both models are updated using a combination of domain adaptation loss and boundary-regularized cross-entropy loss. The domain adaptation loss is calculated from the features extracted from the source and target domains and the corresponding true labels. Both encourage the model to align the features of the source and target domains and reduce the distribution difference between the source and target domains. The boundary-regularized cross-entropy loss is calculated from the classification results output by the CCSAR-Net model and the corresponding true labels. The parameters of CCSAR-Net_1 and CCSAR-Net_2 models are continuously adjusted by domain adaptive loss based on Gaussian kernel function and cross entropy loss with boundary regularization, so that the CCSAR-Net_2 model can better adapt to the CCSAR-Net_1 model and reach the performance level of the CCSAR-Net_1 model.

[0153] Figure 6 This is a module block diagram of a photovoltaic panel surface dust detection device provided by an embodiment of the present invention.

[0154] Alternatively, as another embodiment of the present invention, Figure 6 As shown, a device for detecting dust accumulation on the surface of a photovoltaic panel comprises:

[0155] A division module is used to divide the photovoltaic power station to be inspected into multiple dust detection areas;

[0156] A coordinate marking module is used to mark the coordinates of each of the dust accumulation detection areas respectively to obtain original photovoltaic panel coordinate information corresponding to each of the dust accumulation detection areas;

[0157] A physical image acquisition module, configured to obtain an original physical photovoltaic panel image corresponding to each of the dust accumulation detection areas from an infrared imager;

[0158] Import module, used to import multiple dust deposition data, multiple meteorological data and multiple photovoltaic panel status data;

[0159] a virtual power station construction module, configured to construct a virtual photovoltaic power station corresponding to the photovoltaic power station to be detected by using all the dust deposition data, all the meteorological data, and all the photovoltaic panel status data;

[0160] A virtual image extraction module is used to extract images of the virtual photovoltaic power station to obtain original virtual photovoltaic panel images corresponding to the respective dust detection areas;

[0161] a model analysis module, configured to construct a training model, and perform model analysis on the training model based on all the original photovoltaic panel coordinate information, all the original virtual photovoltaic panel images, and all the original physical photovoltaic panel images to obtain a dust accumulation detection model;

[0162] The detection result acquisition module is used to detect the original photovoltaic panel coordinate information corresponding to each dust detection area and the original virtual photovoltaic panel image corresponding to each dust detection area through the dust detection model to obtain the detection results of each dust detection area.

[0163] Alternatively, another embodiment of the present invention provides a photovoltaic panel surface dust detection system, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the photovoltaic panel surface dust detection method described above is implemented. The system may be a computer or other system.

[0164] Optionally, another embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned method for detecting dust accumulation on the surface of a photovoltaic panel is implemented.

[0165] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0166] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0167] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is merely a logical functional division. In actual implementation, other division methods may be used, such as combining or integrating multiple units or components into another system, or ignoring or not implementing certain features.

[0168] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected based on actual needs to achieve the objectives of the embodiments of the present invention.

[0169] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0170] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program code.

[0171] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for detecting dust accumulation on the surface of a photovoltaic panel, characterized in that: The steps include: S1: Divide the photovoltaic power station to be inspected into multiple dust detection areas; S2: Marking the coordinates of each of the dust detection areas to obtain original photovoltaic panel coordinate information corresponding to each of the dust detection areas; S3: obtaining an original physical photovoltaic panel image corresponding to each of the dust detection areas from an infrared imager; S4: importing a plurality of dust deposition data, a plurality of meteorological data, and a plurality of photovoltaic panel status data, and constructing a virtual photovoltaic power station corresponding to the photovoltaic power station to be detected by using all of the dust deposition data, all of the meteorological data, and all of the photovoltaic panel status data; S5: performing image extraction on the virtual photovoltaic power station to obtain original virtual photovoltaic panel images corresponding to the respective dust detection areas; S6: constructing a training model, and performing model analysis on the training model according to all the original photovoltaic panel coordinate information, all the original virtual photovoltaic panel images, and all the original physical photovoltaic panel images to obtain a dust accumulation detection model; S7: Using the dust detection model, respectively detect the original photovoltaic panel coordinate information corresponding to each of the dust detection areas and the original virtual photovoltaic panel image corresponding to each of the dust detection areas to obtain a detection result for each of the dust detection areas; The training model includes a backbone network and a head network. The S6 process includes: Performing feature extraction on each of the original photovoltaic panel coordinate information and the original physical photovoltaic panel image corresponding to each of the dust detection areas through the backbone network, thereby obtaining coordinate features of the physical photovoltaic panel to be processed corresponding to each of the dust detection areas and image features of the physical photovoltaic panel to be processed corresponding to each of the dust detection areas; Performing feature extraction on each of the original photovoltaic panel coordinate information and the original virtual photovoltaic panel image corresponding to each of the dust detection areas through the backbone network, thereby obtaining a to-be-processed virtual photovoltaic panel coordinate feature corresponding to each of the dust detection areas and a to-be-processed virtual photovoltaic panel image feature corresponding to each of the dust detection areas; Mapping the coordinate features of each physical photovoltaic panel to be processed and the image features of the physical photovoltaic panel to be processed corresponding to each dust detection area is performed by the head network to obtain a physical photovoltaic panel feature matrix corresponding to each dust detection area and a prediction classification result of the physical photovoltaic panel corresponding to each dust detection area; Mapping the coordinate features of each virtual photovoltaic panel to be processed and the image features of the virtual photovoltaic panel to be processed corresponding to each dust detection area is performed by the head network to obtain a virtual photovoltaic panel feature matrix corresponding to each dust detection area and a virtual photovoltaic panel prediction classification result corresponding to each dust detection area; Importing the real classification results corresponding to each of the dust detection areas, calculating the target loss value for all the physical photovoltaic panel feature matrices, all the virtual photovoltaic panel feature matrices, all the physical photovoltaic panel predicted classification results, all the virtual photovoltaic panel predicted classification results, and all the real classification results to obtain the target loss value; Determine whether the target loss value is greater than or equal to a preset threshold. If not, return to S2; if so, update the parameters of the training model according to the target loss value to obtain a dust accumulation detection model.

2. The method for detecting dust accumulation on the surface of a photovoltaic panel according to claim 1, characterized in that: The backbone network includes a plurality of sequentially arranged residual blocks. The process of extracting features from the original photovoltaic panel coordinate information and the original physical photovoltaic panel image corresponding to each dust detection area through the backbone network to obtain the coordinate features of the physical photovoltaic panel to be processed corresponding to each dust detection area and the image features of the physical photovoltaic panel to be processed corresponding to each dust detection area includes: The first residual block is used to extract features of the original photovoltaic panel coordinate information and the original physical photovoltaic panel image corresponding to each dust detection area, and the results of the feature extraction are input into the second residual block until the last residual block is passed, thereby obtaining the coordinate features of the physical photovoltaic panel to be processed corresponding to each dust detection area and the image features of the physical photovoltaic panel to be processed corresponding to each dust detection area.

3. The method for detecting dust accumulation on the surface of photovoltaic panels according to claim 2, characterized in that: The residual block includes a convolution block, an attention mechanism layer, and a residual connection layer. The process of extracting features from the original photovoltaic panel coordinate information and the original physical photovoltaic panel image corresponding to each dust detection area using the first residual block includes: Performing feature extraction on each of the original photovoltaic panel coordinate information and the original physical photovoltaic panel image corresponding to each of the dust accumulation detection areas through the convolution block, thereby obtaining a first physical photovoltaic panel coordinate feature corresponding to each of the dust accumulation detection areas and a first physical photovoltaic panel image feature corresponding to each of the dust accumulation detection areas; Performing feature extraction on each of the first physical photovoltaic panel coordinate features and the first physical photovoltaic panel image features corresponding to each of the dust accumulation detection areas through the attention mechanism layer, thereby obtaining a second physical photovoltaic panel coordinate feature corresponding to each of the dust accumulation detection areas and a second physical photovoltaic panel image feature corresponding to each of the dust accumulation detection areas; Performing feature extraction on each of the second physical photovoltaic panel coordinate features and the second physical photovoltaic panel image features corresponding to each of the dust accumulation detection areas through the residual connection layer, thereby obtaining third physical photovoltaic panel coordinate features corresponding to each of the dust accumulation detection areas and third physical photovoltaic panel image features corresponding to each of the dust accumulation detection areas; respectively concatenating each of the second physical photovoltaic panel coordinate features with the corresponding physical third photovoltaic panel coordinate features to obtain a fourth physical photovoltaic panel coordinate feature corresponding to each of the dust accumulation detection areas; Each of the second physical photovoltaic panel image features is spliced ​​with the corresponding third physical photovoltaic panel image feature to obtain a fourth physical photovoltaic panel image feature corresponding to each of the dust accumulation detection areas.

4. The method for detecting dust accumulation on the surface of a photovoltaic panel according to claim 3, characterized in that: The convolution block includes a first coordinate convolution layer, a first convolution layer, a batch normalization layer, and an activation layer. The process of performing feature extraction on each of the original photovoltaic panel coordinate information and the original physical photovoltaic panel image corresponding to each of the dust accumulation detection areas through the convolution block to obtain the first physical photovoltaic panel coordinate feature corresponding to each of the dust accumulation detection areas and the first physical photovoltaic panel image feature corresponding to each of the dust accumulation detection areas includes: Performing coordinate information feature extraction on each of the original photovoltaic panel coordinate information through the first coordinate convolution layer to obtain fifth physical photovoltaic panel coordinate features corresponding to each of the dust detection areas; Performing image feature extraction on each of the original physical photovoltaic panel images through the first convolutional layer to obtain fifth physical photovoltaic panel image features corresponding to each of the dust detection areas; Normalizing each of the fifth physical photovoltaic panel coordinate features and the fifth physical photovoltaic panel image features corresponding to each of the dust accumulation detection areas through the batch normalization layer to obtain a sixth physical photovoltaic panel coordinate feature corresponding to each of the dust accumulation detection areas and a sixth physical photovoltaic panel image feature corresponding to each of the dust accumulation detection areas; The activation layer is used to map the coordinate features of each of the sixth physical photovoltaic panels and the image features of the sixth physical photovoltaic panels corresponding to each of the dust detection areas to obtain the coordinate features of the first physical photovoltaic panel corresponding to each of the dust detection areas and the image features of the first physical photovoltaic panel corresponding to each of the dust detection areas.

5. The method for detecting dust accumulation on the surface of photovoltaic panels according to claim 3, characterized in that: The residual connection layer includes a second coordinate convolution layer and a second convolution layer, The process of extracting features of each second physical photovoltaic panel coordinate feature and the second physical photovoltaic panel image feature corresponding to each dust accumulation detection area through the residual connection layer to obtain a third physical photovoltaic panel coordinate feature corresponding to each dust accumulation detection area and a third physical photovoltaic panel image feature corresponding to each dust accumulation detection area includes: Extracting coordinate information from each of the second physical photovoltaic panel coordinate features through the second coordinate convolution layer to obtain third physical photovoltaic panel coordinate features corresponding to each of the dust detection areas; The second convolutional layer is used to extract image features of each of the second physical photovoltaic panel images to obtain third physical photovoltaic panel image features corresponding to each of the dust detection areas.

6. The method for detecting dust accumulation on the surface of a photovoltaic panel according to claim 1, characterized in that: The head network includes a maximum pooling layer, a dropout layer, a fully connected layer, and a classification layer. The process of mapping the coordinate features of each of the to-be-processed physical photovoltaic panels and the image features of the to-be-processed physical photovoltaic panels corresponding to each of the dust accumulation detection areas through the head network to obtain a physical photovoltaic panel feature matrix corresponding to each of the dust accumulation detection areas and a predicted classification result of the physical photovoltaic panels corresponding to each of the dust accumulation detection areas includes: performing pooling processing on each of the to-be-processed physical photovoltaic panel coordinate features and the to-be-processed physical photovoltaic panel image features corresponding to each of the dust accumulation detection areas through the maximum pooling layer, thereby obtaining a seventh physical photovoltaic panel coordinate feature corresponding to each of the dust accumulation detection areas and a seventh physical photovoltaic panel image feature corresponding to each of the dust accumulation detection areas; Performing feature optimization processing on each of the seventh physical photovoltaic panel coordinate features and the seventh physical photovoltaic panel image features corresponding to each of the dust accumulation detection areas through the discarded layer, thereby obtaining an eighth physical photovoltaic panel coordinate feature corresponding to each of the dust accumulation detection areas and an eighth physical photovoltaic panel image feature corresponding to each of the dust accumulation detection areas; The eighth physical photovoltaic panel coordinate features corresponding to each of the dust accumulation detection areas and the eighth physical photovoltaic panel image features corresponding to each of the dust accumulation detection areas are respectively spliced ​​through the fully connected layer to obtain a physical photovoltaic panel feature matrix corresponding to each of the dust accumulation detection areas; The classification layer is used to classify the feature matrices of each physical photovoltaic panel to obtain predicted classification results of the physical photovoltaic panels corresponding to each dust accumulation detection area.

7. The method for detecting dust accumulation on the surface of a photovoltaic panel according to claim 1, characterized in that: The process of calculating the target loss value for all the physical photovoltaic panel feature matrices, all the virtual photovoltaic panel feature matrices, all the physical photovoltaic panel prediction classification results, all the virtual photovoltaic panel prediction classification results, and all the real classification results to obtain the target loss value includes: The domain adaptation loss value corresponding to each dust accumulation detection area is calculated by respectively calculating the domain adaptation loss value of each physical photovoltaic panel feature matrix and the virtual photovoltaic panel feature matrix corresponding to each dust accumulation detection area through the first formula, and the domain adaptation loss value corresponding to each dust accumulation detection area is obtained. The first formula is: in, is the domain adaptation loss value corresponding to the a-th dust detection area, C is the C-th dust category, m is the total number of dust categories, N is the total number of rows and columns of the physical photovoltaic panel feature matrix, W i a-s is the photovoltaic panel weight of the i-th row in the physical photovoltaic panel feature matrix corresponding to the a-th dust detection area, W j a-s is the photovoltaic panel weight of the jth column in the physical photovoltaic panel feature matrix corresponding to the ath dust detection area, K() is the Gaussian kernel function, is the physical photovoltaic panel feature of the i-th row in the physical photovoltaic panel feature matrix corresponding to the a-th dust detection area, is the physical photovoltaic panel feature in the jth column of the physical photovoltaic panel feature matrix corresponding to the ath dust detection area, W j a-t is the photovoltaic panel weight of the jth column in the virtual photovoltaic panel feature matrix corresponding to the ath dust detection area, is the jth column virtual photovoltaic panel feature in the physical photovoltaic panel feature matrix corresponding to the ath dust detection area, W i a-t is the photovoltaic panel weight of the i-th row in the virtual photovoltaic panel feature matrix corresponding to the a-th dust detection area, is the virtual photovoltaic panel feature of the i-th row in the physical photovoltaic panel feature matrix corresponding to the a-th dust detection area, and f(·) represents the data feature mapping process; The target cross entropy loss value is obtained by calculating the cross entropy loss value for all the physical photovoltaic panel prediction classification results, all the virtual photovoltaic panel prediction classification results, and all the real classification results through the second formula, and the second formula is: L MRCE =L MRCEs -L MRCEt , in, in, Among them, L MRCE is the target cross entropy loss value, L MRCEs is the entity cross entropy loss value, L MRCEt is the virtual cross entropy loss value, M is the total number of dust detection areas, is the predicted classification result of the physical photovoltaic panel corresponding to the a-th dust detection area, is the true classification result corresponding to the a-th dust detection area, E C is the regularization penalty coefficient of the Cth dust category, C is the Cth dust category, m is the total number of dust categories, Predict the classification results for the virtual photovoltaic panel corresponding to the a-th dust detection area; All the domain adaptation loss values ​​are added to the cross entropy loss value to obtain a target loss value.

8. A device for detecting dust accumulation on the surface of a photovoltaic panel, characterized in that: include: A division module is used to divide the photovoltaic power station to be inspected into multiple dust detection areas; A coordinate marking module is used to mark the coordinates of each of the dust accumulation detection areas respectively to obtain original photovoltaic panel coordinate information corresponding to each of the dust accumulation detection areas; A physical image acquisition module, configured to obtain an original physical photovoltaic panel image corresponding to each of the dust accumulation detection areas from an infrared imager; Import module, used to import multiple dust deposition data, multiple meteorological data and multiple photovoltaic panel status data; a virtual power station construction module, configured to construct a virtual photovoltaic power station corresponding to the photovoltaic power station to be detected by using all the dust deposition data, all the meteorological data, and all the photovoltaic panel status data; A virtual image extraction module is used to extract images of the virtual photovoltaic power station to obtain original virtual photovoltaic panel images corresponding to the respective dust detection areas; a model analysis module, configured to construct a training model, and perform model analysis on the training model based on all the original photovoltaic panel coordinate information, all the original virtual photovoltaic panel images, and all the original physical photovoltaic panel images to obtain a dust accumulation detection model; a detection result obtaining module, configured to detect the original photovoltaic panel coordinate information corresponding to each of the dust accumulation detection areas and the original virtual photovoltaic panel image corresponding to each of the dust accumulation detection areas using the dust accumulation detection model, to obtain a detection result for each of the dust accumulation detection areas; The training model includes a backbone network and a head network. The model analysis module is specifically used for: Performing feature extraction on each of the original photovoltaic panel coordinate information and the original physical photovoltaic panel image corresponding to each of the dust detection areas through the backbone network, thereby obtaining coordinate features of the physical photovoltaic panel to be processed corresponding to each of the dust detection areas and image features of the physical photovoltaic panel to be processed corresponding to each of the dust detection areas; Performing feature extraction on each of the original photovoltaic panel coordinate information and the original virtual photovoltaic panel image corresponding to each of the dust detection areas through the backbone network, thereby obtaining a to-be-processed virtual photovoltaic panel coordinate feature corresponding to each of the dust detection areas and a to-be-processed virtual photovoltaic panel image feature corresponding to each of the dust detection areas; Mapping the coordinate features of each physical photovoltaic panel to be processed and the image features of the physical photovoltaic panel to be processed corresponding to each dust detection area is performed by the head network to obtain a physical photovoltaic panel feature matrix corresponding to each dust detection area and a prediction classification result of the physical photovoltaic panel corresponding to each dust detection area; Mapping the coordinate features of each virtual photovoltaic panel to be processed and the image features of the virtual photovoltaic panel to be processed corresponding to each dust detection area is performed by the head network to obtain a virtual photovoltaic panel feature matrix corresponding to each dust detection area and a virtual photovoltaic panel prediction classification result corresponding to each dust detection area; Importing the real classification results corresponding to each of the dust detection areas, calculating the target loss value for all the physical photovoltaic panel feature matrices, all the virtual photovoltaic panel feature matrices, all the physical photovoltaic panel predicted classification results, all the virtual photovoltaic panel predicted classification results, and all the real classification results to obtain the target loss value; Determine whether the target loss value is greater than or equal to a preset threshold. If not, return to the coordinate marking module; if so, update the parameters of the training model according to the target loss value to obtain a dust accumulation detection model.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for detecting dust accumulation on the surface of a photovoltaic panel according to any one of claims 1 to 7 is implemented.

Images