A photovoltaic device detection method, system, apparatus, and medium

Abstract

The application provides a photovoltaic device detection method, system, device and medium, comprising: constructing a root node based on a photovoltaic device function set in response to a photovoltaic device detection request; recording a sub-device function set relied on by the photovoltaic device function set as a first function set, and constructing a first layer sub-node based on the first function set; recording a sub-device function set relied on by the first function set as a second function set, and constructing a second layer sub-node based on the second function set; determining a leaf node from the first layer sub-node and the second layer sub-node, and constructing a parent node of the leaf node; and finally performing parallel self-checking on the photovoltaic device based on the root node, the first layer sub-node, the second layer sub-node, the leaf node and the parent node, and generating a detection report of the photovoltaic device. The application can effectively improve the self-checking efficiency of the photovoltaic device and reduce the self-checking cost of the photovoltaic device by constructing a self-checking process of the photovoltaic device for the function set.

Description

Technical Field

[0001] This application relates to the field of photovoltaic equipment testing technology, and in particular to a photovoltaic equipment testing method, system, device and medium. Background Technology

[0002] Currently, the testing of integrated photovoltaic (PV) systems typically involves either individual self-tests or a full-scale self-test. However, full-scale self-tests are inefficient and costly. Individual self-tests, on the other hand, currently involve testing each category of function. This requires categorizing the equipment's functions, and the criteria for categorization must be designed based on the specific needs of each device, increasing self-test costs, such as the cost of writing and maintaining self-test codes. Summary of the Invention

[0003] In view of the shortcomings of the prior art described above, the purpose of this application is to provide a photovoltaic equipment testing method, system, device and medium to solve the problems of low equipment testing efficiency and high cost in the prior art.

[0004] To achieve the above and other related objectives, this application provides a photovoltaic equipment testing method, comprising the following steps:

[0005] In response to photovoltaic equipment testing requests, and based on a pre-determined or real-time set of photovoltaic equipment functions, a root node is constructed for the photovoltaic equipment to perform self-testing.

[0006] The set of sub-device functions on which the photovoltaic device function set depends is denoted as the first function set, and the first layer of sub-nodes for the photovoltaic device to perform self-test is constructed based on the first function set.

[0007] The sub-device function set on which the first function set depends is denoted as the second function set, and the second layer of sub-nodes is constructed based on the second function set when the photovoltaic device performs self-test.

[0008] The leaf node of the photovoltaic device during self-test is determined from the first layer child node and the second layer child node, and the parent node of the leaf node is constructed.

[0009] Based on the root node, the first layer child nodes, the second layer child nodes, the leaf nodes, and the parent node, the photovoltaic device is subjected to parallel self-testing, and a test report of the photovoltaic device is generated after each node completes the parallel self-testing of the photovoltaic device.

[0010] In one embodiment of this application, the process of designating the set of sub-device functions upon which the photovoltaic device function set depends as the first function set, and constructing the first layer of sub-nodes for self-testing of the photovoltaic device based on the first function set, includes:

[0011] Obtain the photovoltaic equipment to be tested;

[0012] The set of functions supported by the photovoltaic device to be tested is denoted as the photovoltaic device function set;

[0013] Based on the functions supported by the photovoltaic equipment function set, the sub-equipment function set on which the photovoltaic equipment function set depends is determined, and is denoted as the first sub-equipment function set;

[0014] The determined first sub-device function set is merged and deduplicated to obtain the first function set;

[0015] The first layer of child nodes in the initial state is generated based on the root node of the photovoltaic device during self-testing, and each function in the first function set is added as a branch node to the first layer of child nodes in the initial state; and test items and self-test tasks are added to the first layer of child nodes to construct and generate the first layer of child nodes when the photovoltaic device performs self-testing.

[0016] In one embodiment of this application, the process of designating the sub-device function set on which the first function set depends as the second function set, and constructing the second-layer sub-nodes for self-testing of the photovoltaic device based on the second function set, includes:

[0017] Based on each function in the first function set, determine the sub-device function set on which the first function set depends, denoted as the second sub-device function set;

[0018] The determined second sub-device function set is merged and deduplicated to obtain the second function set;

[0019] Based on the first layer of sub-nodes during the self-test of the photovoltaic equipment, a second layer of sub-nodes in the initial state is constructed, and each function in the second function set is added as a branch node to the second layer of sub-nodes in the initial state; and test items and self-test tasks are added to the second layer of sub-nodes to construct and generate the second layer of sub-nodes during the self-test of the photovoltaic equipment.

[0020] In one embodiment of this application, the process of determining the leaf node of the photovoltaic device during self-testing from the first layer of child nodes and the second layer of child nodes, and constructing the parent node of the leaf node, includes:

[0021] Traverse the first layer of child nodes, filter out the test items and self-check tasks from the first layer of child nodes, and use them as leaf nodes of the first layer of child nodes; and,

[0022] Traverse the second-level child nodes, filter out the test items and self-check tasks in the second-level child nodes, and use them as the leaf nodes of the second-level child nodes;

[0023] Based on the name and type of each leaf node, construct the corresponding parent node; and then connect each leaf node with its corresponding parent node and add it to the root node.

[0024] In one embodiment of this application, after generating the test report for the photovoltaic device, the method further includes:

[0025] Generate a digital image of the detection report;

[0026] The digital image is preprocessed, and the region containing text is extracted from the preprocessed image, which is denoted as the region of interest; wherein, the preprocessing includes: grayscale conversion, binarization, denoising, and enhancement;

[0027] Perform character recognition on the region of interest to obtain the corresponding character recognition results;

[0028] The character recognition results are corrected, and it is determined whether there are preset keywords in the corrected character recognition results; wherein, the preset keywords include photovoltaic module name keywords, fault type keywords, defect type keywords, and photovoltaic module location keywords;

[0029] If a preset keyword is found in the corrected character recognition result, it is determined that the photovoltaic equipment is faulty, and the component image corresponding to the preset keyword is obtained. The component image is then used to verify whether the corresponding component is faulty.

[0030] If the preset keyword is not found in the corrected character recognition result, it is determined that the photovoltaic equipment is not faulty.

[0031] In one embodiment of this application, the process of preprocessing the digital image includes:

[0032] The digital image is converted to grayscale using the formula: gray = 0.299 × R + 0.587 × G + 0.114 × B; where gray represents the color value of each pixel in the grayscale image; and R, G, and B represent the red, green, and blue color values ​​of each pixel in the digital image, respectively.

[0033] The grayscale image is binarized to convert it into a binary image; this includes converting pixel values ​​greater than a preset binarization threshold to white, and converting pixel values ​​less than or equal to the preset binarization threshold to black; [The following is a partial translation of the original text, which is not directly related to the initial statement about binarization.] In the formula, g(x, y) represents the pixel value in the grayscale image; f(x, y) represents the pixel value in the binary image, where f(x, y) = 255 represents white and f(x, y) = 0 represents black; T is a preset binarization threshold.

[0034] The binary image is denoised using opening and / or closing operations; wherein the formula for calculating the opening operation is: The formula for calculating the closing operation is: In the formula, B(x, y) represents the processed image, G represents the unprocessed image, and K represents the structuring element. ⊕ indicates an erosion operation, and ⊕ indicates an expansion operation;

[0035] To enhance the denoised binary image, we adjust its contrast and brightness as follows: In the formula, g(i) represents the enhanced image or the image after preprocessing; n i L represents the number of pixels with pixel value i in the denoised binary image; L represents the number of gray levels; N represents the total number of pixels in the denoised binary image.

[0036] In one embodiment of this application, the process of obtaining a component image corresponding to the preset keyword and verifying whether the corresponding component has a fault based on the component image includes:

[0037] The component image is input into a pre-generated or real-time photovoltaic equipment diagnostic model. The photovoltaic equipment diagnostic model is used to identify the component image, and the corresponding component is checked for faults based on the model identification results.

[0038] If the model identification result indicates that the component image has a fault, then the corresponding component is marked as faulty;

[0039] If the model identification result indicates that the component image does not have a fault, then the corresponding component is marked as not having a fault.

[0040] In one embodiment of this application, the process of generating the photovoltaic device diagnostic model includes:

[0041] Acquire infrared images of photovoltaic equipment and divide the infrared images into a sample training set and a sample verification set;

[0042] The sample training set is input into a neural network to train and generate an initial diagnostic model for photovoltaic equipment;

[0043] The sample validation set is input into the photovoltaic equipment initial diagnostic model to obtain the fault diagnosis accuracy of the photovoltaic equipment initial diagnostic model;

[0044] If the fault diagnosis accuracy is greater than or equal to the first preset value, then the initial diagnosis model of the photovoltaic equipment will be used as the diagnosis model of the photovoltaic equipment in actual application.

[0045] If the fault diagnosis accuracy is less than the first preset value, the initial diagnostic model of the photovoltaic equipment is iteratively trained using the sample training set until the fault diagnosis accuracy of the iterative diagnostic model of the photovoltaic equipment generated by the iterative training is greater than or equal to the first preset value. Then, the iterative diagnostic model of the photovoltaic equipment is used as the diagnostic model of the photovoltaic equipment in actual application.

[0046] This application also provides a photovoltaic equipment testing system, the system comprising:

[0047] The root node module is used to respond to photovoltaic equipment testing requests and construct the root node for photovoltaic equipment to perform self-tests based on the pre-determined or real-time determined set of photovoltaic equipment functions.

[0048] The first-layer sub-node module is used to record the sub-device function set on which the photovoltaic device function set depends as the first function set, and to construct the first-layer sub-node when the photovoltaic device performs self-test based on the first function set;

[0049] The second-layer sub-node module is used to record the sub-device function set on which the first function set depends as the second function set, and to construct the second-layer sub-node when the photovoltaic device performs self-test based on the second function set;

[0050] The leaf node module is used to determine the leaf node of the photovoltaic device when it performs self-test from the first layer of child nodes and the second layer of child nodes, and to construct the parent node of the leaf node.

[0051] The detection module is used to perform parallel self-tests on the photovoltaic device based on the root node, the first layer child nodes, the second layer child nodes, the leaf nodes, and the parent node, and generate a detection report for the photovoltaic device after each node completes the parallel self-test of the photovoltaic device.

[0052] In one embodiment of this application, the process of designating the set of sub-device functions upon which the photovoltaic device function set depends as the first function set, and constructing the first layer of sub-nodes for self-testing of the photovoltaic device based on the first function set, includes:

[0053] Obtain the photovoltaic equipment to be tested;

[0054] The set of functions supported by the photovoltaic device to be tested is denoted as the photovoltaic device function set;

[0055] Based on the functions supported by the photovoltaic equipment function set, the sub-equipment function set on which the photovoltaic equipment function set depends is determined, and is denoted as the first sub-equipment function set;

[0056] The determined first sub-device function set is merged and deduplicated to obtain the first function set;

[0057] The first layer of child nodes in the initial state is generated based on the root node of the photovoltaic device during self-testing, and each function in the first function set is added as a branch node to the first layer of child nodes in the initial state; and test items and self-test tasks are added to the first layer of child nodes to construct and generate the first layer of child nodes when the photovoltaic device performs self-testing.

[0058] In one embodiment of this application, the process of designating the sub-device function set on which the first function set depends as the second function set, and constructing the second-layer sub-nodes for self-testing of the photovoltaic device based on the second function set, includes:

[0059] Based on each function in the first function set, determine the sub-device function set on which the first function set depends, denoted as the second sub-device function set;

[0060] The determined second sub-device function set is merged and deduplicated to obtain the second function set;

[0061] Based on the first layer of sub-nodes during the self-test of the photovoltaic equipment, a second layer of sub-nodes in the initial state is constructed, and each function in the second function set is added as a branch node to the second layer of sub-nodes in the initial state; and test items and self-test tasks are added to the second layer of sub-nodes to construct and generate the second layer of sub-nodes during the self-test of the photovoltaic equipment.

[0062] In one embodiment of this application, the process of determining the leaf node of the photovoltaic device during self-testing from the first layer of child nodes and the second layer of child nodes, and constructing the parent node of the leaf node, includes:

[0063] Traverse the first layer of child nodes, filter out the test items and self-check tasks from the first layer of child nodes, and use them as leaf nodes of the first layer of child nodes; and,

[0064] Traverse the second-level child nodes, filter out the test items and self-check tasks in the second-level child nodes, and use them as the leaf nodes of the second-level child nodes;

[0065] Based on the name and type of each leaf node, construct the corresponding parent node; and then connect each leaf node with its corresponding parent node and add it to the root node.

[0066] This application also provides a photovoltaic equipment testing device, comprising:

[0067] processor; and,

[0068] A computer-readable medium storing instructions that, when executed by the processor, cause the apparatus to perform a photovoltaic device detection method as described above.

[0069] This application also provides a computer-readable medium having instructions stored thereon, the instructions being loaded by a processor and executed as described in any of the above-described photovoltaic device detection methods.

[0070] As described above, this application provides a photovoltaic equipment testing method, system, apparatus, and medium, which has the following beneficial effects: In response to a photovoltaic equipment testing request, and based on a pre-determined or real-time determined set of photovoltaic equipment functions, this application constructs a root node for self-testing of the photovoltaic equipment; then, the set of sub-equipment functions upon which the photovoltaic equipment function set depends is denoted as a first function set, and a first-layer sub-node for self-testing of the photovoltaic equipment is constructed based on the first function set; next, the set of sub-equipment functions upon which the first function set depends is denoted as a second function set, and a second-layer sub-node for self-testing of the photovoltaic equipment is constructed based on the second function set; then, leaf nodes for self-testing of the photovoltaic equipment are determined from the first-layer and second-layer sub-nodes, and parent nodes of the leaf nodes are constructed; finally, based on the root node, first-layer sub-nodes, second-layer sub-nodes, leaf nodes, and parent nodes, parallel self-testing of the photovoltaic equipment is performed, and a testing report for the photovoltaic equipment is generated after each node completes its parallel self-test. Therefore, this application, by defining the equipment capabilities required for the functions of photovoltaic equipment and the related capabilities of its dependent sub-equipment, can automatically construct a self-testing process for photovoltaic equipment during the self-testing of specific functions, thereby achieving self-testing of the photovoltaic equipment's functions. Simultaneously, by conducting self-testing for a set of functions, this application can effectively improve the self-testing efficiency and reduce the self-testing cost of photovoltaic equipment. Attached Figure Description

[0071] Figure 1 This is a schematic flowchart of a photovoltaic equipment testing method provided in one embodiment of this application;

[0072] Figure 2 This is a schematic diagram illustrating the construction of a self-testing link for a photovoltaic device according to an embodiment of this application;

[0073] Figure 3 This is a schematic flowchart of a photovoltaic equipment testing method provided in another embodiment of this application;

[0074] Figure 4 This is a schematic diagram of the hardware structure of a photovoltaic equipment testing system provided in one embodiment of this application;

[0075] Figure 5 This is a schematic diagram illustrating an exemplary system architecture that applies the technical solutions in one or more embodiments of this application;

[0076] Figure 6 This is a schematic diagram of the hardware structure of a photovoltaic equipment testing device suitable for implementing one or more embodiments of this application. Detailed Implementation

[0077] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, unless otherwise specified, the following embodiments and features in the embodiments can be combined with each other.

[0078] It should be noted that the illustrations provided in this embodiment are only schematic representations of the basic concept of this application. Therefore, the drawings only show the components related to this application and are not drawn according to the number, shape and size of the components in actual implementation. In actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0079] Figure 1 A schematic flowchart of a photovoltaic equipment testing method according to an embodiment of this application is shown. Specifically, in an exemplary embodiment, as follows... Figure 1 As shown, this embodiment provides a photovoltaic equipment testing method, which includes the following steps:

[0080] S110, responding to the photovoltaic equipment testing request, and based on the photovoltaic equipment function set determined in advance or in real time, constructs the root node for the photovoltaic equipment to perform self-test;

[0081] S120, the set of sub-device functions on which the photovoltaic device function set depends is denoted as the first function set, and the first layer of sub-nodes is constructed based on the first function set when the photovoltaic device performs self-test;

[0082] S130, denote the set of sub-device functions that the first set of functions depends on as the second set of functions, and construct the second layer of sub-nodes for self-testing of photovoltaic equipment based on the second set of functions;

[0083] S140, determine the leaf node of the photovoltaic device when it performs self-test from the first layer child node and the second layer child node, and construct the parent node of the leaf node;

[0084] S150 performs parallel self-tests on photovoltaic devices based on the root node, first-level child nodes, second-level child nodes, leaf nodes, and parent nodes. After each node completes the parallel self-test of the photovoltaic devices, a test report for the photovoltaic devices is generated.

[0085] Therefore, this embodiment defines the equipment capabilities required for the functions of photovoltaic equipment and the related capabilities of its dependent sub-equipment. During the self-testing of specific functions, a self-testing process for the photovoltaic equipment can be automatically constructed, thereby achieving self-testing of the photovoltaic equipment's functions. Furthermore, by conducting self-testing for a set of functions, this embodiment can effectively improve the self-testing efficiency and reduce the self-testing cost of photovoltaic equipment.

[0086] As an example, a photovoltaic (PV) device might require the following self-test tasks: sensor testing, circuit testing, and battery testing. Sensor testing includes temperature sensor testing and light intensity sensor testing; circuit testing includes DC circuit testing and AC circuit testing; and battery testing includes charging and discharging testing. Each self-test task contains multiple self-test items. Taking sensor testing as an example, it includes two self-test items: temperature sensor testing and light intensity sensor testing. Based on the above steps, the specific implementation can be as follows: Respond to requests; listen for PV device testing requests and obtain the device information and function list that need to be self-tested. Determine the function set; based on the device information and the built-in function set, determine the self-tests and tests to be performed, which in this example include sensor testing, circuit testing, and battery testing. Construct the self-test root node; construct the self-test root node based on the determined function set. Taking sensor testing as an example, the sensor test node connects to two branch nodes: temperature sensor testing and light intensity sensor testing. Execute self-test tasks. After completing the construction of the self-test root node, execute the corresponding self-test tasks according to the definition of each branch node. Taking temperature sensor testing as an example, the test method can be determined based on the characteristics and specifications of the temperature sensor. If an AD converter is used to measure temperature, the temperature can be calculated based on the sampled value and the formula: T = (1.43 * Vref * V - 600) / 10, where Vref is the reference voltage, V is the output voltage of the AD converter, and T represents the temperature. This example is a simplified illustration of a self-test task. Actual self-test tasks can be designed and implemented according to specific equipment and testing requirements, which will not be elaborated upon in this embodiment.

[0087] In an exemplary embodiment, the process of designating the set of sub-device functions upon which the photovoltaic device's function set depends as a first function set, and constructing the first-layer sub-nodes for self-testing of the photovoltaic device based on the first function set, includes: acquiring the photovoltaic device to be tested; designating the set of functions supported by the photovoltaic device to be tested as the photovoltaic device function set; determining the set of sub-device functions upon which the photovoltaic device's function set depends based on the functions supported by the photovoltaic device function set, and designating it as the first sub-device function set; merging and deduplicating the determined first sub-device function sets to obtain the first function set; generating the initial state of the first-layer sub-nodes based on the root node for self-testing of the photovoltaic device, and adding each function in the first function set as a branch node to the initial state of the first-layer sub-nodes; and adding test items and self-test tasks to the first-layer sub-nodes to construct and generate the first-layer sub-nodes for self-testing of the photovoltaic device. Specifically, this embodiment can determine the photovoltaic device that needs to be self-tested and its supported function set; determine the function set of the sub-devices upon which the photovoltaic device depends, such as battery packs, controllers, etc.; merge the determined sub-device function sets and deduplicate them to obtain the first function set. Based on the root node during the self-test of the photovoltaic (PV) equipment, a first-level child node is constructed. Each function in the first function set is added as a branch node to the first-level child node, and corresponding test and self-test items are added as leaf nodes. During the self-test of the PV equipment, all test and self-test items on the first-level child node are executed. As an example, assume the PV equipment includes two sub-devices: a controller and a battery. The controller includes functions for detecting and controlling the grid voltage, while the battery includes functions for charging and discharging. Here, the function sets of the controller and battery are merged into the first function set. Through this embodiment, the first function set can be constructed based on the function set of the PV equipment and the function sets of its dependent sub-devices, thereby facilitating the self-test and testing management of the PV equipment.

[0088] In an exemplary embodiment, the process of designating the set of sub-device functions upon which the first set of functions depends as the second set of functions, and constructing the second-layer sub-nodes for self-testing of the photovoltaic device based on the second set of functions, includes: determining the set of sub-device functions upon which the first set of functions depends, based on each function in the first set of functions, and designating it as the second set of sub-device functions; merging and deduplicating the determined second set of sub-device functions to obtain the second set of functions; constructing the initial state of the second-layer sub-nodes based on the first-layer sub-nodes for self-testing of the photovoltaic device, and adding each function in the second set of functions as a branch node to the initial state of the second-layer sub-nodes; and adding test items and self-test tasks to the second-layer sub-nodes to construct and generate the second-layer sub-nodes for self-testing of the photovoltaic device. Specifically, this embodiment can determine the first set of functions of the photovoltaic device, i.e., the set of functions determined in the preceding steps. Based on the functions included in the first set of functions, the set of functions of the sub-devices upon which they depend is determined, such as the grid voltage detection and connection control functions of the controller depending on sensors, etc. The determined set of functions of the sub-devices is merged and deduplicated to obtain the second set of functions. Based on the first-layer child nodes, a second-layer child node is constructed, and each function in the second function set is added as a branch node to the second-layer child node, along with corresponding test and self-test items as leaf nodes. When the photovoltaic device performs a self-test, all tests and self-test items on the second-layer child node are executed. As an example, assume the photovoltaic device includes two sub-devices: a controller and a battery. The controller includes functions for detecting and controlling the grid voltage, while the battery includes charging and discharging functions. In the above embodiment, the first function set has been determined. Here, the functions of sensors and connectors, on which the controller depends, are used as the second function set to construct the second-layer child node. Through this embodiment, a second function set can be constructed based on the first function set and the function sets of its dependent sub-devices, thus facilitating self-testing and testing management of the photovoltaic device.

[0089] In an exemplary embodiment, the process of determining the leaf nodes of the photovoltaic device during self-testing from the first-layer and second-layer child nodes, and constructing the parent nodes of the leaf nodes, includes: traversing the first-layer child nodes, filtering out the test items and self-test tasks in the first-layer child nodes as leaf nodes; and traversing the second-layer child nodes, filtering out the test items and self-test tasks in the second-layer child nodes as leaf nodes; constructing the corresponding parent node according to the name and type of each leaf node; and connecting each leaf node with its corresponding parent node and adding it to the root node. Specifically, this embodiment can first determine the first-layer and second-layer child nodes of the photovoltaic device during self-testing, then traverse the first-layer and second-layer child nodes to find all leaf nodes, i.e., all self-test tasks and test items. The corresponding parent node is constructed according to the name and type of each leaf node. For example, if a leaf node corresponds to a temperature sensor test item, then a parent node named "Temperature Sensor Test" can be constructed for better self-test task management. Each leaf node is connected to its corresponding parent node to form a tree structure, which is then added to the root node of the tree for better self-test task management. As an example, suppose that when a photovoltaic device performs a self-test, the first layer of child nodes includes sensor testing, circuit testing, and battery testing, while the second layer includes connector testing and other tests. The leaf nodes can include temperature sensor testing, AC circuit testing, etc. Through this embodiment, the leaf nodes and their parent nodes during the photovoltaic device's self-test can be determined based on the first and second layer child nodes, facilitating better self-test task management.

[0090] In one exemplary embodiment, after generating the test report for the photovoltaic equipment, this embodiment may further include:

[0091] A digital image of the test report is generated. As an example, this embodiment can scan or photograph the self-inspection report of photovoltaic equipment to generate a corresponding digital image.

[0092] The digital image is preprocessed, and the region containing text is extracted from the preprocessed image, denoised as the region of interest. The preprocessing includes grayscale conversion, binarization, denoising, and enhancement. Specifically, the preprocessing of the digital image in this embodiment includes: grayscale conversion, converting the digital image to a grayscale image, with the formula: gray = 0.299 × R + 0.587 × G + 0.114 × B; where gray represents the color value of each pixel in the grayscale image; R, G, and B represent the red, green, and blue color values ​​of each pixel in the digital image, respectively; and binarization, converting the grayscale image to a binary image, including converting pixel values ​​greater than a preset binarization threshold to white and pixel values ​​less than or equal to the preset binarization threshold to black. In the formula, g(x, y) represents the pixel value in the grayscale image; f(x, y) represents the pixel value in the binary image, where f(x, y) = 255 represents white and f(x, y) = 0 represents black; T is the preset binarization threshold; denoising of the binary image is performed using opening and / or closing operations; the calculation formula for the opening operation is: The formula for calculating the closing operation is: In the formula, B(x, y) represents the processed image, G represents the unprocessed image, and K represents the structuring element. The symbol ⊕ represents the erosion operation, and ⊕ represents the dilation operation. To enhance the denoised binary image by adjusting contrast and brightness, we have: In the formula, g(i) represents the enhanced image or the image after preprocessing; n i The structuring element K represents the number of pixels with pixel value i in the denoised binary image; L represents the number of gray levels; and N represents the total number of pixels in the denoised binary image. In this embodiment, the structuring element K for the opening and closing operations can have different shapes and sizes, selected according to the specific application scenario. The effects of the opening and closing operations can complement each other, resulting in better image denoising. Specifically, the opening operation is used to remove small noise points, while the closing operation is used to fill small holes.

[0093] Furthermore, the process of extracting text-containing regions from a preprocessed image can be as follows: Edge detection algorithms, such as Sobel, Prewitt, and Canny, are used to detect boundary information in the image. Contour detection is then performed on the edge-detected image to determine the edge contours of the text regions. Based on the edge contours obtained from the contour detection, the image is segmented to extract the text regions. Specific implementation methods can be divided into threshold-based segmentation and edge detection-based methods. The threshold-based segmentation method involves the following steps: The image is converted to grayscale to obtain a grayscale image. Threshold segmentation is performed on the grayscale image, setting pixels with grayscale values ​​greater than a preset threshold to white and pixels with grayscale values ​​less than the threshold to black. Opening and closing operations are performed on the resulting binary image to fill in and remove small noise points and holes. Similarly, the edge detection-based method involves the following steps: The image is converted to grayscale to obtain a grayscale image. Edge detection is performed on the resulting grayscale image to obtain a binary image. Opening and closing operations are performed on the resulting binary image to fill in and remove small noise points and holes. Contour detection is performed on the image obtained after fill removal to extract the text region.

[0094] Character recognition is performed on the region of interest to obtain the corresponding character recognition result. As an example, this embodiment uses OCR (Optical Character Recognition) technology for character recognition. Mainstream OCR technologies include template-matching-based OCR, feature extraction-based OCR, and deep learning-based OCR. Specifically, the process of character recognition in the region of interest in this embodiment can be as follows: For the extracted text region, character features need to be extracted to obtain its classification features in the digital environment. Mainstream feature extraction methods include DCT, wavelet transform, Fourier transform, and LBP. Character recognition is achieved by comparing the character to be recognized with one or more template characters. Template matching is mainly based on the shape and attributes of the characters. A method of first extracting character features and then using a classifier for classification and recognition is adopted. Commonly used classifiers include SVM and decision trees. Character recognition is achieved by building complex deep neural networks, eliminating the need for manual feature extraction and making it more suitable for training on large-scale data. Commonly used deep neural networks include CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), and LSTM (Long Short-Term Memory).

[0095] The character recognition results are corrected, and it is determined whether preset keywords exist in the corrected results. These preset keywords include photovoltaic module name keywords, fault type keywords, defect type keywords, and photovoltaic module location keywords. If the preset keywords are present in the corrected results, a fault is identified in the photovoltaic equipment. The component image corresponding to the preset keyword is then acquired, and the presence of a fault in the corresponding component is verified based on the image. If the preset keywords are not present in the corrected results, no fault is identified in the photovoltaic equipment. As an example, this embodiment may contain some errors or inaccuracies in the OCR recognition results, requiring post-processing and correction. Post-processing and correction methods include language models, dictionary models, and rule models.

[0096] Therefore, it can be seen that using OCR to analyze the self-inspection report of photovoltaic equipment in this embodiment can greatly improve the efficiency and accuracy of automated testing.

[0097] In an exemplary embodiment, the process of obtaining a component image corresponding to a preset keyword and verifying whether the corresponding component has a fault based on the component image includes: inputting the component image into a pre-generated or real-time photovoltaic equipment diagnostic model, using the photovoltaic equipment diagnostic model to identify the component image, and verifying whether the corresponding component has a fault based on the model identification result; if the model identification result indicates that the component image has a fault, then the corresponding component is marked as having a fault; if the model identification result indicates that the component image does not have a fault, then the corresponding component is marked as not having a fault. The generation process of the photovoltaic equipment diagnostic model includes: acquiring infrared images of the photovoltaic equipment and dividing the infrared images into a sample training set and a sample validation set; inputting the sample training set into a neural network to train and generate an initial diagnostic model for the photovoltaic equipment; inputting the sample validation set into the initial diagnostic model for the photovoltaic equipment to obtain the fault diagnosis accuracy of the initial diagnostic model; if the fault diagnosis accuracy is greater than or equal to a first preset value, the initial diagnostic model for the photovoltaic equipment is used as the diagnostic model for actual application; if the fault diagnosis accuracy is less than the first preset value, the initial diagnostic model for the photovoltaic equipment is iteratively trained using the sample training set until the fault diagnosis accuracy of the iteratively trained iterative diagnostic model for the photovoltaic equipment is greater than or equal to the first preset value, at which point the iterative diagnostic model is used as the diagnostic model for actual application. As an example, the first preset value in this embodiment can be set according to actual conditions, and no specific numerical limit is specified in this embodiment.

[0098] Specifically, in this embodiment, when acquiring infrared images of photovoltaic (PV) equipment, the PV equipment includes both fault-free and faulty PV equipment. Furthermore, this embodiment acquires infrared images not only when the PV equipment as a whole is fault-free, but also when each internal module of the PV equipment is fault-free; conversely, it also includes infrared images when the PV equipment as a whole is faulty, and infrared images when each internal module of the PV equipment is faulty. This ensures that the initial diagnostic model for PV equipment generated based on infrared image training can accurately identify not only whether the PV equipment under test is faulty overall, but also whether each internal module of the PV equipment under test is faulty.

[0099] The sample training set is input into the neural network to train and generate an initial diagnostic model for photovoltaic equipment. As an example, the neural network in this embodiment includes, but is not limited to: Convolutional Neural Network (CNN), Fully Convolutional Networks for Semantic Segmentation (FCN), Region-based CNN (or Regions with CNN features, R-CNN), Fast Region-based CNN (or Fast Regions with CNN features, Fast R-CNN), Faster Region-based CNN (or Faster Regions with CNN features, Faster R-CNN), Artificial Neural Network (ANN), and Deep Cross Network (DCN), etc.

[0100] The sample validation set is input into the initial diagnostic model of the photovoltaic equipment to obtain the fault diagnosis accuracy of the initial diagnostic model of the photovoltaic equipment. If the fault diagnosis accuracy is greater than or equal to the first preset value, the initial diagnostic model of the photovoltaic equipment is used as the diagnostic model of the photovoltaic equipment in actual application. If the fault diagnosis accuracy is less than the first preset value, the initial diagnostic model of the photovoltaic equipment is iteratively trained using the sample training set until the fault diagnosis accuracy of the iterative diagnostic model of the photovoltaic equipment generated by the iterative training is greater than or equal to the first preset value. Then, the iterative diagnostic model of the photovoltaic equipment is used as the diagnostic model of the photovoltaic equipment in actual application.

[0101] In another exemplary embodiment, such as Figure 3 As shown, this embodiment also provides a photovoltaic (PV) equipment testing method, including: constructing a PV equipment DAG (Directed Acyclic Graph); performing parallel PV equipment self-tests based on all nodes in the DAG; checking the health status of each completed PV equipment with its dependent devices; and outputting individual and overall PV equipment self-test reports to complete the PV equipment self-test. A schematic diagram of the self-test link construction principle of this method is shown below. Figure 2 As shown. Specifically, as Figure 2 As shown, when a user initiates a self-check request, a self-check process is first constructed based on the set of self-check functions. The self-check process includes the set of self-check functions, the set of functions of the sub-devices on which the self-check function set depends, and the set of functions of the sub-devices on which the self-check function set depends. The construction process of the self-check process is as follows:

[0102] Step 1: Based on the set of self-check functions, construct the root node of the self-check process.

[0103] Step 2: Based on the function set of the sub-devices that the self-test function set depends on, construct the first-level sub-node of the self-test process.

[0104] Step 3: Based on the function set of the sub-devices that the function set of the self-test depends on, construct the second-level sub-node of the self-test process.

[0105] Step 4: Repeat steps 2 and 3 until the leaf node of the self-check process is reached.

[0106] Step 5: Based on the leaf nodes of the self-inspection process, construct the parent node of the leaf nodes of the self-inspection process.

[0107] Step 6: Repeat step 5 until the root node of the self-test process.

[0108] In summary, this application provides a photovoltaic (PV) equipment testing method. Responding to a PV equipment testing request, and based on a pre-determined or real-time determined set of PV equipment functions, a root node is constructed for PV equipment self-testing. Then, the set of sub-device functions upon which the PV equipment function set depends is designated as a first function set, and a first-level sub-node is constructed based on this first function set. Next, the set of sub-device functions upon which the first function set depends is designated as a second function set, and a second-level sub-node is constructed based on this second function set. Leaf nodes for PV equipment self-testing are then determined from the first and second level sub-nodes, and their parent nodes are constructed. Finally, based on the root node, first-level sub-nodes, second-level sub-nodes, leaf nodes, and parent nodes, parallel self-testing of the PV equipment is performed. After each node completes its parallel self-test, a PV equipment testing report is generated. Therefore, this method, by defining the equipment capabilities required for PV equipment functions and the related capabilities of their dependent sub-devices, can automatically construct a PV equipment self-testing process during specific function self-testing, thereby achieving functional self-testing of the PV equipment. Meanwhile, this method can effectively improve the self-testing efficiency of photovoltaic equipment and reduce the self-testing cost of photovoltaic equipment by conducting self-testing on the functional set.

[0109] like Figure 4 As shown, this application also provides a photovoltaic equipment testing system, which includes:

[0110] The root node module 410 is used to respond to photovoltaic equipment testing requests and construct the root node for photovoltaic equipment to perform self-testing based on the photovoltaic equipment function set determined in advance or in real time.

[0111] The first-layer sub-node module 420 is used to record the sub-device function set on which the photovoltaic device function set depends as the first function set, and to construct the first-layer sub-node when the photovoltaic device performs self-test based on the first function set.

[0112] The second-layer sub-node module 430 is used to record the sub-device function set on which the first function set depends as the second function set, and to construct the second-layer sub-node when the photovoltaic device performs self-test based on the second function set;

[0113] Leaf node module 440 is used to determine the leaf node when the photovoltaic device performs self-test from the first layer child nodes and the second layer child nodes, and to construct the parent node of the leaf node.

[0114] The detection module 450 is used to perform parallel self-tests on the photovoltaic equipment based on the root node, first-level child nodes, second-level child nodes, leaf nodes, and parent nodes, and generate a detection report for the photovoltaic equipment after each node completes the parallel self-test.

[0115] Therefore, this embodiment defines the equipment capabilities required for the functions of photovoltaic equipment and the related capabilities of its dependent sub-equipment. During the self-testing of specific functions, a self-testing process for the photovoltaic equipment can be automatically constructed, thereby achieving self-testing of the photovoltaic equipment's functions. Furthermore, by conducting self-testing for a set of functions, this embodiment can effectively improve the self-testing efficiency and reduce the self-testing cost of photovoltaic equipment.

[0116] As an example, a photovoltaic (PV) device might require the following self-test tasks: sensor testing, circuit testing, and battery testing. Sensor testing includes temperature sensor testing and light intensity sensor testing; circuit testing includes DC circuit testing and AC circuit testing; and battery testing includes charging and discharging testing. Each self-test task contains multiple self-test items. Taking sensor testing as an example, it includes two self-test items: temperature sensor testing and light intensity sensor testing. Based on the above steps, the specific implementation can be as follows: Respond to requests; listen for PV device testing requests and obtain the device information and function list that need to be self-tested. Determine the function set; based on the device information and the built-in function set, determine the self-tests and tests to be performed, which in this example include sensor testing, circuit testing, and battery testing. Construct the self-test root node; construct the self-test root node based on the determined function set. Taking sensor testing as an example, the sensor test node connects to two branch nodes: temperature sensor testing and light intensity sensor testing. Execute self-test tasks. After completing the construction of the self-test root node, execute the corresponding self-test tasks according to the definition of each branch node. Taking temperature sensor testing as an example, the test method can be determined based on the characteristics and specifications of the temperature sensor. If an AD converter is used to measure temperature, the temperature can be calculated based on the sampled value and the formula: T = (1.43 * Vref * V - 600) / 10, where Vref is the reference voltage, V is the output voltage of the AD converter, and T represents the temperature. This example is a simplified illustration of a self-test task. Actual self-test tasks can be designed and implemented according to specific equipment and testing requirements, which will not be elaborated upon in this embodiment.

[0117] In an exemplary embodiment, the process of designating the set of sub-device functions upon which the photovoltaic device's function set depends as a first function set, and constructing the first-layer sub-nodes for self-testing of the photovoltaic device based on the first function set, includes: acquiring the photovoltaic device to be tested; designating the set of functions supported by the photovoltaic device to be tested as the photovoltaic device function set; determining the set of sub-device functions upon which the photovoltaic device's function set depends based on the functions supported by the photovoltaic device function set, and designating it as the first sub-device function set; merging and deduplicating the determined first sub-device function sets to obtain the first function set; generating the initial state of the first-layer sub-nodes based on the root node for self-testing of the photovoltaic device, and adding each function in the first function set as a branch node to the initial state of the first-layer sub-nodes; and adding test items and self-test tasks to the first-layer sub-nodes to construct and generate the first-layer sub-nodes for self-testing of the photovoltaic device. Specifically, this embodiment can determine the photovoltaic device that needs to be self-tested and its supported function set; determine the function set of the sub-devices upon which the photovoltaic device depends, such as battery packs, controllers, etc.; merge the determined sub-device function sets and deduplicate them to obtain the first function set. Based on the root node during the self-test of the photovoltaic (PV) equipment, a first-level child node is constructed. Each function in the first function set is added as a branch node to the first-level child node, and corresponding test and self-test items are added as leaf nodes. During the self-test of the PV equipment, all test and self-test items on the first-level child node are executed. As an example, assume the PV equipment includes two sub-devices: a controller and a battery. The controller includes functions for detecting and controlling the grid voltage, while the battery includes functions for charging and discharging. Here, the function sets of the controller and battery are merged into the first function set. Through this embodiment, the first function set can be constructed based on the function set of the PV equipment and the function sets of its dependent sub-devices, thereby facilitating the self-test and testing management of the PV equipment.

[0118] In an exemplary embodiment, the process of designating the set of sub-device functions upon which the first set of functions depends as the second set of functions, and constructing the second-layer sub-nodes for self-testing of the photovoltaic device based on the second set of functions, includes: determining the set of sub-device functions upon which the first set of functions depends, based on each function in the first set of functions, and designating it as the second set of sub-device functions; merging and deduplicating the determined second set of sub-device functions to obtain the second set of functions; constructing the initial state of the second-layer sub-nodes based on the first-layer sub-nodes for self-testing of the photovoltaic device, and adding each function in the second set of functions as a branch node to the initial state of the second-layer sub-nodes; and adding test items and self-test tasks to the second-layer sub-nodes to construct and generate the second-layer sub-nodes for self-testing of the photovoltaic device. Specifically, this embodiment can determine the first set of functions of the photovoltaic device, i.e., the set of functions determined in the preceding steps. Based on the functions included in the first set of functions, the set of functions of the sub-devices upon which they depend is determined, such as the grid voltage detection and connection control functions of the controller depending on sensors, etc. The determined set of functions of the sub-devices is merged and deduplicated to obtain the second set of functions. Based on the first-layer child nodes, a second-layer child node is constructed, and each function in the second function set is added as a branch node to the second-layer child node, along with corresponding test and self-test items as leaf nodes. When the photovoltaic device performs a self-test, all tests and self-test items on the second-layer child node are executed. As an example, assume the photovoltaic device includes two sub-devices: a controller and a battery. The controller includes functions for detecting and controlling the grid voltage, while the battery includes charging and discharging functions. In the above embodiment, the first function set has been determined. Here, the functions of sensors and connectors, on which the controller depends, are used as the second function set to construct the second-layer child node. Through this embodiment, a second function set can be constructed based on the first function set and the function sets of its dependent sub-devices, thus facilitating self-testing and testing management of the photovoltaic device.

[0119] In an exemplary embodiment, the process of determining the leaf nodes of the photovoltaic device during self-testing from the first-layer and second-layer child nodes, and constructing the parent nodes of the leaf nodes, includes: traversing the first-layer child nodes, filtering out the test items and self-test tasks in the first-layer child nodes as leaf nodes; and traversing the second-layer child nodes, filtering out the test items and self-test tasks in the second-layer child nodes as leaf nodes; constructing the corresponding parent node according to the name and type of each leaf node; and connecting each leaf node with its corresponding parent node and adding it to the root node. Specifically, this embodiment can first determine the first-layer and second-layer child nodes of the photovoltaic device during self-testing, then traverse the first-layer and second-layer child nodes to find all leaf nodes, i.e., all self-test tasks and test items. The corresponding parent node is constructed according to the name and type of each leaf node. For example, if a leaf node corresponds to a temperature sensor test item, then a parent node named "Temperature Sensor Test" can be constructed for better self-test task management. Each leaf node is connected to its corresponding parent node to form a tree structure, which is then added to the root node of the tree for better self-test task management. As an example, suppose that when a photovoltaic device performs a self-test, the first layer of child nodes includes sensor testing, circuit testing, and battery testing, while the second layer includes connector testing and other tests. The leaf nodes can include temperature sensor testing, AC circuit testing, etc. Through this embodiment, the leaf nodes and their parent nodes during the photovoltaic device's self-test can be determined based on the first and second layer child nodes, facilitating better self-test task management.

[0120] In one exemplary embodiment, after generating the test report for the photovoltaic equipment, this embodiment may further include:

[0121] A digital image of the test report is generated. As an example, this embodiment can scan or photograph the self-inspection report of photovoltaic equipment to generate a corresponding digital image.

[0122] The digital image is preprocessed, and the region containing text is extracted from the preprocessed image, denoised as the region of interest. The preprocessing includes grayscale conversion, binarization, denoising, and enhancement. Specifically, the preprocessing of the digital image in this embodiment includes: grayscale conversion, converting the digital image to a grayscale image, with the formula: gray = 0.299 × R + 0.587 × G + 0.114 × B; where gray represents the color value of each pixel in the grayscale image; R, G, and B represent the red, green, and blue color values ​​of each pixel in the digital image, respectively; and binarization, converting the grayscale image to a binary image, including converting pixel values ​​greater than a preset binarization threshold to white and pixel values ​​less than or equal to the preset binarization threshold to black. In the formula, g(x, y) represents the pixel value in the grayscale image; f(x, y) represents the pixel value in the binary image, where f(x, y) = 255 represents white and f(x, y) = 0 represents black; T is the preset binarization threshold; denoising of the binary image is performed using opening and / or closing operations; the calculation formula for the opening operation is: The formula for calculating the closing operation is: In the formula, B(x, y) represents the processed image, G represents the unprocessed image, and K represents the structuring element. The symbol ⊕ represents the erosion operation, and ⊕ represents the dilation operation. To enhance the denoised binary image by adjusting contrast and brightness, we have: In the formula, g(i) represents the enhanced image or the image after preprocessing; n i The structuring element K represents the number of pixels with pixel value i in the denoised binary image; L represents the number of gray levels; and N represents the total number of pixels in the denoised binary image. In this embodiment, the structuring element K for the opening and closing operations can have different shapes and sizes, selected according to the specific application scenario. The effects of the opening and closing operations can complement each other, resulting in better image denoising. Specifically, the opening operation is used to remove small noise points, while the closing operation is used to fill small holes.

[0123] Furthermore, the process of extracting text-containing regions from a preprocessed image can be as follows: Edge detection algorithms, such as Sobel, Prewitt, and Canny, are used to detect boundary information in the image. Contour detection is then performed on the edge-detected image to determine the edge contours of the text regions. Based on the edge contours obtained from the contour detection, the image is segmented to extract the text regions. Specific implementation methods can be divided into threshold-based segmentation and edge detection-based methods. The threshold-based segmentation method involves the following steps: The image is converted to grayscale to obtain a grayscale image. Threshold segmentation is performed on the grayscale image, setting pixels with grayscale values ​​greater than a preset threshold to white and pixels with grayscale values ​​less than the threshold to black. Opening and closing operations are performed on the resulting binary image to fill in and remove small noise points and holes. Similarly, the edge detection-based method involves the following steps: The image is converted to grayscale to obtain a grayscale image. Edge detection is performed on the resulting grayscale image to obtain a binary image. Opening and closing operations are performed on the resulting binary image to fill in and remove small noise points and holes. Contour detection is performed on the image obtained after fill removal to extract the text region.

[0124] Character recognition is performed on the region of interest to obtain the corresponding character recognition result. As an example, this embodiment uses OCR (Optical Character Recognition) technology for character recognition. Mainstream OCR technologies include template-matching-based OCR, feature extraction-based OCR, and deep learning-based OCR. Specifically, the process of character recognition in the region of interest in this embodiment can be as follows: For the extracted text region, character features need to be extracted to obtain its classification features in the digital environment. Mainstream feature extraction methods include DCT, wavelet transform, Fourier transform, and LBP. Character recognition is achieved by comparing the character to be recognized with one or more template characters. Template matching is mainly based on the shape and attributes of the characters. A method of first extracting character features and then using a classifier for classification and recognition is adopted. Commonly used classifiers include SVM and decision trees. Character recognition is achieved by building complex deep neural networks, eliminating the need for manual feature extraction and making it more suitable for training on large-scale data. Commonly used deep neural networks include CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), and LSTM (Long Short-Term Memory).

[0125] The character recognition results are corrected, and it is determined whether preset keywords exist in the corrected results. These preset keywords include photovoltaic module name keywords, fault type keywords, defect type keywords, and photovoltaic module location keywords. If the preset keywords are present in the corrected results, a fault is identified in the photovoltaic equipment. The component image corresponding to the preset keyword is then acquired, and the presence of a fault in the corresponding component is verified based on the image. If the preset keywords are not present in the corrected results, no fault is identified in the photovoltaic equipment. As an example, this embodiment may contain some errors or inaccuracies in the OCR recognition results, requiring post-processing and correction. Post-processing and correction methods include language models, dictionary models, and rule models.

[0126] Therefore, it can be seen that using OCR to analyze the self-inspection report of photovoltaic equipment in this embodiment can greatly improve the efficiency and accuracy of automated testing.

[0127] In an exemplary embodiment, the process of obtaining a component image corresponding to a preset keyword and verifying whether the corresponding component has a fault based on the component image includes: inputting the component image into a pre-generated or real-time photovoltaic equipment diagnostic model, using the photovoltaic equipment diagnostic model to identify the component image, and verifying whether the corresponding component has a fault based on the model identification result; if the model identification result indicates that the component image has a fault, then the corresponding component is marked as having a fault; if the model identification result indicates that the component image does not have a fault, then the corresponding component is marked as not having a fault. The generation process of the photovoltaic equipment diagnostic model includes: acquiring infrared images of the photovoltaic equipment and dividing the infrared images into a sample training set and a sample validation set; inputting the sample training set into a neural network to train and generate an initial diagnostic model for the photovoltaic equipment; inputting the sample validation set into the initial diagnostic model for the photovoltaic equipment to obtain the fault diagnosis accuracy of the initial diagnostic model; if the fault diagnosis accuracy is greater than or equal to a first preset value, the initial diagnostic model for the photovoltaic equipment is used as the diagnostic model for actual application; if the fault diagnosis accuracy is less than the first preset value, the initial diagnostic model for the photovoltaic equipment is iteratively trained using the sample training set until the fault diagnosis accuracy of the iteratively trained iterative diagnostic model for the photovoltaic equipment is greater than or equal to the first preset value, at which point the iterative diagnostic model is used as the diagnostic model for actual application. As an example, the first preset value in this embodiment can be set according to actual conditions, and no specific numerical limit is specified in this embodiment.

[0128] Specifically, in this embodiment, when acquiring infrared images of photovoltaic (PV) equipment, the PV equipment includes both fault-free and faulty PV equipment. Furthermore, this embodiment acquires infrared images not only when the PV equipment as a whole is fault-free, but also when each internal module of the PV equipment is fault-free; conversely, it also includes infrared images when the PV equipment as a whole is faulty, and infrared images when each internal module of the PV equipment is faulty. This ensures that the initial diagnostic model for PV equipment generated based on infrared image training can accurately identify not only whether the PV equipment under test is faulty overall, but also whether each internal module of the PV equipment under test is faulty.

[0129] The sample training set is input into the neural network to train and generate an initial diagnostic model for photovoltaic equipment. As an example, the neural network in this embodiment includes, but is not limited to: Convolutional Neural Network (CNN), Fully Convolutional Networks for Semantic Segmentation (FCN), Region-based CNN (or Regions with CNN features, R-CNN), Fast Region-based CNN (or Fast Regions with CNN features, Fast R-CNN), Faster Region-based CNN (or Faster Regions with CNN features, Faster R-CNN), Artificial Neural Network (ANN), and Deep Cross Network (DCN), etc.

[0130] The sample validation set is input into the initial diagnostic model of the photovoltaic equipment to obtain the fault diagnosis accuracy of the initial diagnostic model of the photovoltaic equipment. If the fault diagnosis accuracy is greater than or equal to the first preset value, the initial diagnostic model of the photovoltaic equipment is used as the diagnostic model of the photovoltaic equipment in actual application. If the fault diagnosis accuracy is less than the first preset value, the initial diagnostic model of the photovoltaic equipment is iteratively trained using the sample training set until the fault diagnosis accuracy of the iterative diagnostic model of the photovoltaic equipment generated by the iterative training is greater than or equal to the first preset value. Then, the iterative diagnostic model of the photovoltaic equipment is used as the diagnostic model of the photovoltaic equipment in actual application.

[0131] In summary, this application provides a photovoltaic (PV) equipment testing system. Responding to a PV equipment testing request, and based on a pre-determined or real-time determined set of PV equipment functions, it constructs a root node for PV equipment self-testing. Then, it denotes the set of sub-device functions upon which the PV equipment function set depends as a first function set, and constructs a first-level sub-node for PV equipment self-testing based on this first function set. Next, it denotes the set of sub-device functions upon which the first function set depends as a second function set, and constructs a second-level sub-node for PV equipment self-testing based on this second function set. Then, it determines the leaf nodes for PV equipment self-testing from the first and second level sub-nodes and constructs the parent nodes of these leaf nodes. Finally, based on the root node, first-level sub-nodes, second-level sub-nodes, leaf nodes, and parent nodes, it performs parallel self-testing of the PV equipment. After each node completes its parallel self-test, it generates a PV equipment testing report. Therefore, this system, by defining the equipment capabilities required for PV equipment functions and the related capabilities of their dependent sub-devices, can automatically construct a self-testing process for PV equipment functions during specific function self-testing, thereby achieving self-testing of PV equipment functions. Meanwhile, this system can effectively improve the self-testing efficiency of photovoltaic equipment and reduce the self-testing cost of photovoltaic equipment by performing self-tests on the functional set.

[0132] It should be noted that the photovoltaic equipment testing system and the photovoltaic equipment testing method provided in the above embodiments belong to the same concept. The specific operation methods of each module have been described in detail in the method embodiments and will not be repeated here. In practical applications, the photovoltaic equipment testing system provided in the above embodiments can be assigned to different functional modules as needed, that is, the internal structure of the system can be divided into different functional modules to complete all or part of the functions described above. This is not a limitation here. Therefore, this application effectively overcomes the various shortcomings of the prior art and has high industrial application value.

[0133] Figure 5 A schematic diagram of an exemplary system architecture that can apply the technical solutions of one or more embodiments of this application is shown. Figure 5 As shown, the system architecture 100 may include terminal device 110, network 120, and server 130. Terminal device 110 may include various electronic devices such as smartphones, tablets, laptops, and desktop computers. Server 130 may be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. Network 120 may be a communication medium of various connection types capable of providing a communication link between terminal device 110 and server 130, such as a wired communication link or a wireless communication link.

[0134] Depending on the implementation requirements, the system architecture in this application embodiment can have any number of terminal devices, networks, and servers. For example, server 130 can be a server group composed of multiple server devices. In addition, the technical solutions provided in this application embodiment can be applied to terminal device 110, or to server 130, or can be implemented jointly by terminal device 110 and server 130. This application does not impose any special limitations on this.

[0135] In one embodiment of this application, the terminal device 110 or server 130 can respond to a photovoltaic device testing request and construct a root node for the photovoltaic device to perform self-testing based on a pre-determined or real-time determined set of photovoltaic device functions; then, the set of sub-device functions on which the photovoltaic device function set depends is denoted as a first function set, and a first-level sub-node for the photovoltaic device to perform self-testing is constructed based on the first function set; then, the set of sub-device functions on which the first function set depends is denoted as a second function set, and a second-level sub-node for the photovoltaic device to perform self-testing is constructed based on the second function set; then, leaf nodes for the photovoltaic device to perform self-testing are determined from the first-level and second-level sub-nodes, and parent nodes of the leaf nodes are constructed; finally, the photovoltaic device is subjected to parallel self-testing based on the root node, the first-level sub-nodes, the second-level sub-nodes, the leaf nodes, and the parent nodes, and a testing report for the photovoltaic device is generated after each node completes the parallel self-testing of the photovoltaic device. The photovoltaic equipment testing method is executed using terminal device 110 or server 130. By defining the equipment capabilities required for the photovoltaic equipment's functions and the related capabilities of its dependent sub-devices, a self-testing process for the photovoltaic equipment can be automatically constructed during the self-testing of specific functions, thereby achieving self-testing of the photovoltaic equipment's functions. Simultaneously, by conducting self-tests on a set of functions, the self-testing efficiency of the photovoltaic equipment can be effectively improved, and the self-testing cost can be reduced. The above section describes an exemplary system architecture applying the technical solution of this application.

[0136] This application also provides a photovoltaic equipment testing device, which may include: one or more processors; and one or more machine-readable media storing instructions thereon, which, when executed by the one or more processors, cause the device to perform... Figure 1 The aforementioned photovoltaic equipment testing method. Figure 6 A schematic diagram of a photovoltaic equipment testing device 1000 is shown. (See also...) Figure 6 As shown, the photovoltaic equipment testing device 1000 includes: a processor 1010, a memory 1020, a power supply 1030, a display unit 1040, and an input unit 1060.

[0137] The processor 1010 is the control center of the photovoltaic equipment testing device 1000. It connects to various components via various interfaces and lines, and executes various functions of the photovoltaic equipment testing device 1000 by running or executing software programs and / or data stored in the memory 1020, thereby performing overall monitoring of the photovoltaic equipment testing device 1000. In this embodiment, when the processor 1010 calls the computer program stored in the memory 1020, it executes, for example... Figure 1 The photovoltaic equipment testing method is described above. Optionally, the processor 1010 may include one or more processing units; preferably, the processor 1010 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. In some embodiments, the processor and memory can be implemented on a single chip; in some embodiments, they can also be implemented separately on independent chips.

[0138] The memory 1020 may primarily include a program storage area and a data storage area. The program storage area may store the operating system, various applications, etc.; the data storage area may store data created based on the use of the photovoltaic equipment detection device 1000, etc. In addition, the memory 1020 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0139] The photovoltaic equipment testing device 1000 also includes a power supply 1030 (such as a battery) that supplies power to various components. The power supply can be logically connected to the processor 1010 through a power management system, thereby enabling the power management system to manage functions such as charging, discharging, and power consumption.

[0140] The display unit 1040 can be used to display information input by the user or information provided to the user, as well as various menus of the photovoltaic equipment testing device 1000. In this embodiment, it is mainly used to display the display interfaces of various applications in the photovoltaic equipment testing device 1000, as well as text, images, and other objects displayed on the display interfaces. The display unit 1040 may include a display panel 1050. The display panel 1050 may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like.

[0141] The input unit 1060 can be used to receive information such as numbers or characters input by the user. The input unit 1060 may include a touch panel 1070 and other input devices 1080. The touch panel 1070, also known as a touch screen, can collect touch operations on or near the touch panel 1070 by the user (such as operations performed by the user using a finger, stylus, or any suitable object or accessory on or near the touch panel 1070).

[0142] Specifically, the touch panel 1070 can detect user touch operations and the signals generated by these operations, convert them into touch point coordinates, send them to the processor 1010, and receive and execute commands from the processor 1010. Furthermore, the touch panel 1070 can be implemented using various types of touch technologies, including resistive, capacitive, infrared, and surface acoustic wave. Other input devices 1080 can include, but are not limited to, one or more of the following: physical keyboard, function keys (such as volume control buttons, power buttons, etc.), trackball, mouse, joystick, etc.

[0143] Of course, the touch panel 1070 can cover the display panel 1050. When the touch panel 1070 detects a touch operation on or near it, it transmits the information to the processor 1010 to determine the type of touch event. Subsequently, the processor 1010 provides corresponding visual output on the display panel 1050 based on the type of touch event. Although in Figure 6 In this embodiment, the touch panel 1070 and the display panel 1050 are two independent components to realize the input and output functions of the photovoltaic equipment testing device 1000. However, in some embodiments, the touch panel 1070 and the display panel 1050 can be integrated to realize the input and output functions of the photovoltaic equipment testing device 1000.

[0144] The photovoltaic equipment testing device 1000 may also include one or more sensors, such as pressure sensors, gravity acceleration sensors, proximity sensors, etc. Of course, depending on the specific application requirements, the photovoltaic equipment testing device 1000 may also include other components such as cameras.

[0145] This application also provides a computer-readable storage medium storing instructions that, when executed by one or more processors, enable the device to perform the functions described in this application. Figure 1 The aforementioned photovoltaic equipment testing method.

[0146] It will be understood by those skilled in the art that Figure 6This is merely an example of a photovoltaic equipment testing device and does not constitute a limitation on the device. The device may include more or fewer components than illustrated, or a combination of certain components, or different components. For ease of description, the above parts are divided into modules (or units) according to their functions and described separately. Of course, in implementing this application, the functions of each module (or unit) can be implemented in one or more software or hardware components.

[0147] Those skilled in the art will understand that this application may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application, and should be understood to be achievable by computer program instructions for each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams. These computer program instructions may be applied to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 The computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The functions specified in one or more boxes. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable apparatus for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0148] It should be understood that although terms such as first, second, third, etc., may be used to describe preset ranges in the embodiments of this application, these preset ranges should not be limited to these terms. These terms are only used to distinguish preset ranges from one another. For example, without departing from the scope of the embodiments of this application, the first preset range may also be referred to as the second preset range, and similarly, the second preset range may also be referred to as the first preset range.

[0149] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. A method for testing photovoltaic equipment, characterized in that, The method includes the following steps: In response to photovoltaic equipment testing requests, and based on a pre-determined or real-time set of photovoltaic equipment functions, a root node is constructed for the photovoltaic equipment to perform self-testing. The set of sub-device functions on which the photovoltaic device function set depends is denoted as the first function set, and the first layer of sub-nodes for the photovoltaic device to perform self-test is constructed based on the first function set. The sub-device function set on which the first function set depends is denoted as the second function set, and the second layer of sub-nodes is constructed based on the second function set when the photovoltaic device performs self-test. The leaf node of the photovoltaic device during self-test is determined from the first layer child node and the second layer child node, and the parent node of the leaf node is constructed. Based on the root node, the first layer child nodes, the second layer child nodes, the leaf nodes, and the parent node, the photovoltaic device is subjected to parallel self-testing, and a test report of the photovoltaic device is generated after each node completes the parallel self-testing of the photovoltaic device. The process of designating the set of sub-device functions upon which the photovoltaic device function set depends as the first function set, and constructing the first-layer sub-nodes for self-testing of the photovoltaic device based on the first function set, includes: Obtain the photovoltaic equipment to be tested; The set of functions supported by the photovoltaic equipment to be tested is denoted as the photovoltaic equipment function set; Based on the functions supported by the photovoltaic equipment function set, the sub-equipment function set on which the photovoltaic equipment function set depends is determined, and is denoted as the first sub-equipment function set; The determined first sub-device function set is merged and deduplicated to obtain the first function set; The first layer of child nodes in the initial state is generated based on the root node of the photovoltaic device during self-testing, and each function in the first function set is added as a branch node to the first layer of child nodes in the initial state; and test items and self-test tasks are added to the first layer of child nodes to construct and generate the first layer of child nodes when the photovoltaic device performs self-testing.

2. The photovoltaic equipment testing method according to claim 1, characterized in that, The process of designating the sub-device function set upon which the first function set depends as the second function set, and constructing the second-layer sub-node for self-testing of the photovoltaic device based on the second function set, includes: Based on each function in the first function set, determine the sub-device function set on which the first function set depends, denoted as the second sub-device function set; The determined second sub-device function set is merged and deduplicated to obtain the second function set; Based on the first layer of sub-nodes during the self-test of the photovoltaic equipment, a second layer of sub-nodes in the initial state is constructed, and each function in the second function set is added as a branch node to the second layer of sub-nodes in the initial state; and test items and self-test tasks are added to the second layer of sub-nodes to construct and generate the second layer of sub-nodes during the self-test of the photovoltaic equipment.

3. The photovoltaic equipment testing method according to claim 2, characterized in that, The process of determining the leaf node of the photovoltaic device during self-testing from the first layer of child nodes and the second layer of child nodes, and constructing the parent node of the leaf node, includes: Traverse the first layer of child nodes, filter out the test items and self-check tasks from the first layer of child nodes, and use them as leaf nodes of the first layer of child nodes; and, Traverse the second-level child nodes, filter out the test items and self-check tasks in the second-level child nodes, and use them as the leaf nodes of the second-level child nodes; Based on the name and type of each leaf node, construct the corresponding parent node; and then connect each leaf node with its corresponding parent node and add it to the root node.

4. The photovoltaic equipment testing method according to any one of claims 1 to 3, characterized in that, After generating the test report for the photovoltaic equipment, the method further includes: Generate a digital image of the detection report; The digital image is preprocessed, and the region containing text is extracted from the preprocessed image, which is denoted as the region of interest; wherein, the preprocessing includes: grayscale conversion, binarization, denoising, and enhancement; Perform character recognition on the region of interest to obtain the corresponding character recognition results; The character recognition results are corrected, and it is determined whether there are preset keywords in the corrected character recognition results; wherein, the preset keywords include photovoltaic module name keywords, fault type keywords, defect type keywords, and photovoltaic module location keywords; If a preset keyword is found in the corrected character recognition result, it is determined that the photovoltaic equipment is faulty, and the component image corresponding to the preset keyword is obtained. The component image is then used to verify whether the corresponding component is faulty. If the preset keyword is not found in the corrected character recognition result, it is determined that the photovoltaic equipment is not faulty.

5. The photovoltaic equipment testing method according to claim 4, characterized in that, The preprocessing process for the digital image includes: The digital image is converted to grayscale using the formula: gray = 0.299 × R + 0.587 × G + 0.114 × B; where gray represents the color value of each pixel in the grayscale image; and R, G, and B represent the red, green, and blue color values ​​of each pixel in the digital image, respectively. The grayscale image is binarized to convert it into a binary image; this includes converting pixel values ​​greater than a preset binarization threshold to white, and converting pixel values ​​less than or equal to the preset binarization threshold to black; [The following is a partial translation of the original text, which is not directly related to the initial statement about binarization.] In the formula, g(x, y) represents the pixel value in the grayscale image; f(x, y) represents the pixel value in the binary image, where f(x, y) = 255 represents white and f(x, y) = 0 represents black; T is a preset binarization threshold. The binary image is denoised using opening and / or closing operations; wherein the formula for calculating the opening operation is: The formula for calculating the closing operation is: In the formula, B(x, y) represents the processed image, G represents the unprocessed image, and K represents the structuring element. Indicates corrosion operation. Indicates an expansion operation; To enhance the denoised binary image, we adjust its contrast and brightness as follows: In the formula, g(i) represents the enhanced image or the image after preprocessing; n i L represents the number of pixels with pixel value i in the denoised binary image; L represents the number of gray levels; N represents the total number of pixels in the denoised binary image.

6. The photovoltaic equipment testing method according to claim 4, characterized in that, The process of obtaining the component image corresponding to the preset keyword and verifying whether the corresponding component has a fault based on the component image includes: The component image is input into a pre-generated or real-time photovoltaic equipment diagnostic model. The photovoltaic equipment diagnostic model is used to identify the component image, and the corresponding component is checked for faults based on the model identification results. If the model identification result indicates that the component image has a fault, then the corresponding component is marked as faulty; If the model identification result indicates that the component image does not have a fault, then the corresponding component is marked as not having a fault.

7. The photovoltaic equipment testing method according to claim 6, characterized in that, The generation process of the photovoltaic equipment diagnostic model includes: Acquire infrared images of photovoltaic equipment and divide the infrared images into a sample training set and a sample verification set; The sample training set is input into a neural network to train and generate an initial diagnostic model for photovoltaic equipment; The sample validation set is input into the photovoltaic equipment initial diagnostic model to obtain the fault diagnosis accuracy of the photovoltaic equipment initial diagnostic model; If the fault diagnosis accuracy is greater than or equal to the first preset value, then the initial diagnosis model of the photovoltaic equipment will be used as the diagnosis model of the photovoltaic equipment in actual application. If the fault diagnosis accuracy is less than the first preset value, the initial diagnostic model of the photovoltaic equipment is iteratively trained using the sample training set until the fault diagnosis accuracy of the iterative diagnostic model of the photovoltaic equipment generated by the iterative training is greater than or equal to the first preset value. Then, the iterative diagnostic model of the photovoltaic equipment is used as the diagnostic model of the photovoltaic equipment in actual application.

8. A photovoltaic equipment testing system, characterized in that, The system includes: The root node module is used to respond to photovoltaic equipment testing requests and construct the root node for photovoltaic equipment to perform self-tests based on the pre-determined or real-time determined set of photovoltaic equipment functions. The first-layer sub-node module is used to record the sub-device function set on which the photovoltaic device function set depends as the first function set, and to construct the first-layer sub-node when the photovoltaic device performs self-test based on the first function set; The second-layer sub-node module is used to record the sub-device function set on which the first function set depends as the second function set, and to construct the second-layer sub-node when the photovoltaic device performs self-test based on the second function set; The leaf node module is used to determine the leaf node of the photovoltaic device when it performs self-test from the first layer of child nodes and the second layer of child nodes, and to construct the parent node of the leaf node. The detection module is used to perform parallel self-tests on the photovoltaic device based on the root node, the first layer child nodes, the second layer child nodes, the leaf nodes, and the parent node, and generate a detection report for the photovoltaic device after each node completes the parallel self-test of the photovoltaic device. The process of designating the set of sub-device functions upon which the photovoltaic device function set depends as the first function set, and constructing the first-layer sub-nodes for self-testing of the photovoltaic device based on the first function set, includes: Obtain the photovoltaic equipment to be tested; The set of functions supported by the photovoltaic equipment to be tested is denoted as the photovoltaic equipment function set; Based on the functions supported by the photovoltaic equipment function set, the sub-equipment function set on which the photovoltaic equipment function set depends is determined, and is denoted as the first sub-equipment function set; The determined first sub-device function set is merged and deduplicated to obtain the first function set; The first layer of child nodes in the initial state is generated based on the root node of the photovoltaic device during self-testing, and each function in the first function set is added as a branch node to the first layer of child nodes in the initial state; and test items and self-test tasks are added to the first layer of child nodes to construct and generate the first layer of child nodes when the photovoltaic device performs self-testing.

9. The photovoltaic equipment testing system according to claim 8, characterized in that, The process of designating the sub-device function set upon which the first function set depends as the second function set, and constructing the second-layer sub-node for self-testing of the photovoltaic device based on the second function set, includes: Based on each function in the first function set, determine the sub-device function set on which the first function set depends, denoted as the second sub-device function set; The determined second sub-device function set is merged and deduplicated to obtain the second function set; Based on the first layer of sub-nodes during the self-test of the photovoltaic equipment, a second layer of sub-nodes in the initial state is constructed, and each function in the second function set is added as a branch node to the second layer of sub-nodes in the initial state; and test items and self-test tasks are added to the second layer of sub-nodes to construct and generate the second layer of sub-nodes during the self-test of the photovoltaic equipment.

10. The photovoltaic equipment testing system according to claim 9, characterized in that, The process of determining the leaf node of the photovoltaic device during self-testing from the first layer of child nodes and the second layer of child nodes, and constructing the parent node of the leaf node, includes: Traverse the first layer of child nodes, filter out the test items and self-check tasks from the first layer of child nodes, and use them as leaf nodes of the first layer of child nodes; and, Traverse the second-level child nodes, filter out the test items and self-check tasks in the second-level child nodes, and use them as the leaf nodes of the second-level child nodes; Based on the name and type of each leaf node, construct the corresponding parent node; and then connect each leaf node with its corresponding parent node and add it to the root node.

11. A photovoltaic equipment testing device, characterized in that, include: processor; and, A computer-readable medium storing instructions that, when executed by the processor, cause the apparatus to perform the photovoltaic device testing method as described in any one of claims 1 to 7.

12. A computer-readable medium, characterized in that, It stores instructions that are loaded by a processor and executed as described in any one of claims 1 to 7 for the photovoltaic equipment testing method.

Images