Defect processing method and device, electronic equipment, storage medium and program product

Abstract

The invention provides a defect processing method and device, electronic equipment, a storage medium and a program product. The method comprises the following steps: acquiring defect image data of the photovoltaic module, wherein the defect image data comprises thermal imaging image data; inputting the defect image data into the trained defect identification model, and enabling the defect identification model to output a defect type, a defect coordinate and a defect confidence coefficient of the photovoltaic module; determining the temperature of the defect position according to the defect coordinate and the thermal imaging image data for the target photovoltaic module of which the defect confidence is greater than a preset threshold value; and determining a processing priority of the target photovoltaic module according to the defect type, the defect coordinate and the temperature of the defect position based on a preset priority determination model. The method is used for achieving the effect of improving defect identification accuracy and processing efficiency.

Description

Technical Field

[0001] The present application relates to the field of electrical technology, and in particular to a defect handling method, device, electronic device, storage medium, and program product. Background Art

[0002] With the rapid development of photovoltaic power generation technology, the scale of large-scale ground-based photovoltaic power plants continues to expand, and the number of photovoltaic modules is growing exponentially. This has placed higher demands on the intelligent operation and maintenance of photovoltaic power plants. Photovoltaic modules are exposed to complex natural environments for a long time, and are prone to various defects such as hot spots, hidden cracks, and glass breakage. These defects not only reduce power generation efficiency but also pose safety hazards such as fires.

[0003] Currently, the industry generally uses drone inspections combined with image processing to address PV module defects. Specifically, after the drone completes aerial photography, the defect handling device identifies defects using traditional image processing algorithms (such as edge detection and threshold segmentation) or manual visual inspection. Defects are then classified according to pre-set rules. Finally, maintenance personnel manually assign processing tasks based on pre-set priorities to address the defects.

[0004] However, the inventors have found that the above method has low defect recognition accuracy and relies on manual processing, which is inefficient and may also lead to unreasonable allocation of defect processing tasks. Summary of the Invention

[0005] The embodiments of the present application provide a defect handling method, apparatus, electronic device, storage medium, and program product to achieve the effect of improving defect identification accuracy and handling efficiency.

[0006] In a first aspect, an embodiment of the present application provides a defect handling method, comprising:

[0007] Acquiring defect image data of a photovoltaic module, the defect image data including thermal imaging image data;

[0008] Input the defect image data into the trained defect recognition model, so that the defect recognition model outputs the defect type, defect coordinates and defect confidence of the photovoltaic module;

[0009] For target PV modules with a defect confidence level greater than a preset threshold, the temperature at the defect location is determined based on the defect coordinates and thermal imaging image data;

[0010] Based on a preset priority determination model, the processing priority of the target PV module is determined according to the defect type, defect coordinates and temperature of the defect location.

[0011] In one possible implementation, based on a preset priority determination model, determining the processing priority of a target photovoltaic module according to the defect type, defect coordinates, and temperature at the defect location includes:

[0012] Determine the defect area based on the defect coordinates;

[0013] Determine the severity of the defect of the target PV module based on the defect area, the total area of ​​the target PV module, the temperature of the defect location and the standard temperature;

[0014] Determine the urgency of the target PV module defect based on the time the defect is discovered and the planned processing cycle. The planned processing cycle is determined based on the defect type.

[0015] Based on the preset priority determination model, the processing priority of the target PV modules is determined according to the defect type, defect severity and defect urgency.

[0016] In one possible implementation, determining the urgency of the defect of the target photovoltaic module based on the defect discovery time and the planned processing period of the target photovoltaic module includes:

[0017] The urgency of the defect of the target PV module is calculated according to the following formula;

[0018] The urgency of the defect of the target PV module = (current time - defect discovery time) / planned processing cycle.

[0019] In one possible implementation, the method further includes:

[0020] Obtain weather information and power station load information for the target PV module;

[0021] Determine the urgency of the target PV module defect based on the time the defect is discovered and the planned processing cycle, including:

[0022] The urgency of the defect of the target PV module is determined based on the defect discovery time, planned processing cycle, defect type, weather information and power station load information of the target PV module.

[0023] In one possible implementation, determining the urgency of the defect of the target photovoltaic module based on the defect discovery time, planned processing cycle, defect type, weather information, and power station load information of the target photovoltaic module includes:

[0024] Determine the first urgency bonus value based on the defect type and weather information;

[0025] Determining a second emergency level bonus value based on power station load information;

[0026] The urgency of the defect of the target PV module is calculated according to the following formula;

[0027] The urgency of the defect of the target PV module = (current time - defect discovery time) / planned processing cycle + first urgency bonus value + second urgency bonus value.

[0028] In a possible implementation, before inputting the defect image data into the trained defect recognition model, the method further includes:

[0029] Preprocessing defect image data;

[0030] Input the defect image data into the trained defect recognition model, specifically:

[0031] The preprocessed defect image data is input into the trained defect recognition model.

[0032] In a second aspect, an embodiment of the present application provides a defect handling device, comprising:

[0033] An acquisition module is used to acquire defect image data of the photovoltaic module, wherein the defect image data includes thermal imaging image data;

[0034] An input module is used to input defect image data into a trained defect recognition model so that the defect recognition model outputs the defect type, defect coordinates, and defect confidence of the photovoltaic module;

[0035] a determination module for determining, for a target photovoltaic module having a defect confidence level greater than a preset threshold, a temperature at a defect location based on defect coordinates and thermal imaging image data;

[0036] The determination module is further used to determine the processing priority of the target photovoltaic module based on a preset priority determination model according to the defect type, defect coordinates and temperature of the defect location.

[0037] In a possible implementation, the determination module is specifically configured to determine the defect area based on the defect coordinates;

[0038] Determine the severity of the defect of the target PV module based on the defect area, the total area of ​​the target PV module, the temperature of the defect location and the standard temperature;

[0039] Determine the urgency of the target PV module defect based on the time the defect is discovered and the planned processing cycle. The planned processing cycle is determined based on the defect type.

[0040] Based on the preset priority determination model, the processing priority of the target PV modules is determined according to the defect type, defect severity and defect urgency.

[0041] In a possible implementation, the determining module is specifically configured to calculate the defect emergency degree of the target photovoltaic module according to the following formula:

[0042] Defect emergency degree of target photovoltaic module = (current time - defect discovery time) / planned processing period.

[0043] In a possible implementation, the obtaining module is further configured to obtain weather information and power station load information of the power station where the target photovoltaic module is located.

[0044] The determining module is further configured to determine the defect emergency degree of the target photovoltaic module according to the defect discovery time, the planned processing period, the defect type, the weather information and the power station load information of the target photovoltaic module.

[0045] In a possible implementation, the determining module is specifically configured to determine a first emergency degree addition value according to the defect type and the weather information.

[0046] A second emergency degree addition value is determined according to the power station load information.

[0047] The defect emergency degree of the target photovoltaic module is calculated according to the following formula:

[0048] Defect emergency degree of target photovoltaic module = (current time - defect discovery time) / planned processing period + first emergency degree addition value + second emergency degree addition value.

[0049] In a possible implementation, the inputting module is further configured to pre-process the defect image data.

[0050] The pre-processed defect image data is input into the trained defect recognition model.

[0051] In a third aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor.

[0052] The memory stores computer execution instructions.

[0053] The processor executes the computer execution instructions stored in the memory, so that the processor executes various possible implementations of the first aspect.

[0054] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, and the computer readable storage medium stores computer execution instructions. When the computer execution instructions are executed by a processor, the computer execution instructions are used to implement various possible implementations of the first aspect.

[0055] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, the computer program implements various possible implementations of the first aspect.

[0056] The defect processing method and device, the electronic device, the storage medium and the program product provided by the embodiments of the present application improve the defect recognition accuracy by jointly analyzing the visible light and thermal imaging data through a deep learning model, recognizing the defect type and locating the defect coordinates, and quantifying the defect severity in combination with thermodynamic parameters; then, the dynamic priority evaluation model fused with the defect type features, spatial distribution features and temperature anomaly features is adopted, the intelligent sorting of the processing priority is realized through the adaptive weighted calculation of multi-dimensional parameters, and thus the reasonable allocation of defect processing resources and the defect processing efficiency are improved. BRIEF DESCRIPTION OF DRAWINGS

[0057] The accompanying drawings, which are incorporated herein and form part of the specification, illustrate embodiments consistent with the present application and, together with the description, further serve to explain the principles of the present application.

[0058] Figure 1 FIG. 1 is a structural schematic diagram of a defect processing system in the prior art;

[0059] Figure 2 FIG. 2 is a flow schematic diagram of a defect processing method provided by the present application;

[0060] Figure 3 FIG. 3 is a flow schematic diagram of another defect processing method provided by the present application;

[0061] Figure 4 FIG. 4 is a structural schematic diagram of a defect processing device provided by the present application;

[0062] Figure 5 FIG. 5 is a structural schematic diagram of an electronic device provided by the present application.

[0063] The above-described drawings have shown the specific embodiments of the present application, and more detailed descriptions will be given hereinafter. These drawings and textual descriptions are not intended to limit the scope of the concept of the present application by any means, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0064] The exemplary embodiments will be described in detail herein with reference to the attached drawings. The same or similar components are denoted by the same reference numerals throughout the different drawings. The embodiments described in the following exemplary embodiments do not represent all the embodiments consistent with the present application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the present application as detailed in the appended claims.

[0065] As the global energy structure continues to transition toward clean energy, the construction and operation of large-scale ground-mounted photovoltaic power plants continues to expand. As the core power generation unit of a photovoltaic power plant, photovoltaic modules are subject to environmental stress, material aging, and other factors during long-term operation, which can lead to various defects such as hot spots and hidden cracks. These defects not only reduce power generation efficiency but also pose potential safety hazards. Faced with the growing scale of power plants and the demand for operation and maintenance, traditional manual inspection methods have become significantly inefficient, inaccurate, and timely. There is an urgent need to develop intelligent operation and maintenance technologies to improve the operational management of photovoltaic power plants.

[0066] At present, the defects of photovoltaic modules are mainly dealt with through Figure 1 This is accomplished using the defect handling system 10 shown in the figure. Specifically, the drone inspection module 11 in the defect handling system 10 instructs drones to capture image data of photovoltaic modules. Surface defects of the photovoltaic modules are then identified manually or by the image processing module 12 using traditional image processing methods (such as edge detection and threshold segmentation). The defect management module 13 then determines the defect grade. For example, this can be done manually, or the defect management module 13 can determine the defect grade based on the defect type according to fixed rules. Finally, the task assignment module 14 manually creates a defect handling work order based on the defect grade and assigns a defect handler based on the defect grade.

[0067] However, using the aforementioned defect handling methods, traditional image processing methods have low accuracy in identifying defects such as hot spots and hidden cracks in photovoltaic modules, making them prone to misjudgment. Furthermore, manually assigning defect handling tasks relies on human experience and judgment, failing to respond to dynamic changes in photovoltaic power plants and environmental influences in real time, leading to irrational task allocation.

[0068] In response to the above problems, the present application proposes a defect processing method, device, electronic device, storage medium and program product. By acquiring defect image data and analyzing the defect image data through a deep learning model, the defect characteristics of photovoltaic modules can be accurately identified, and then a multi-dimensional evaluation model including defect characteristics is adopted to dynamically determine the processing priority of the defects, so that defect processing can adapt to the actual operating status and environmental changes of photovoltaic modules, thereby improving the rationality of defect processing task allocation and defect processing efficiency.

[0069] The following specific embodiments describe in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0070] Figure 2 A flowchart of a defect handling method provided in this application is shown as follows: Figure 2 As shown in the method of the embodiment, the electronic device is the execution subject, and the method comprises the following steps:

[0071] S101, acquire defect image data of the photovoltaic module.

[0072] The defect image data comprises visible light image data and thermal imaging image data.

[0073] In this embodiment, the electronic device can fly according to a planned path by using a high-resolution (for example, 20 million pixels) optical camera and a thermal imager carried by a drone, and synchronously acquire dual-optical image data of the photovoltaic module. A Scale-Invariant Feature Transform (SIFT) feature point-based image registration algorithm is used to perform spatial alignment processing on the visible light image and the thermal imaging image, so as to ensure the consistency of the subsequent analysis region.

[0074] In view of the possible noise interference in the image acquisition process, the electronic device can use a non-local mean denoising algorithm for preprocessing, and at the same time, enhance the contrast of the image by histogram equalization, so as to provide high-quality input data for defect recognition.

[0075] S102, input the defect image data into the trained defect recognition model, so that the defect recognition model outputs the defect type, defect coordinates and defect confidence of the photovoltaic module.

[0076] In this embodiment, in the defect recognition stage, the electronic device can use a deep learning model (i.e., the defect recognition model) constructed based on an improved Residual Network (ResNet)-50 network for processing. The model is obtained by training and optimizing a photovoltaic defect sample library, and a multi-scale feature extraction module is specially designed for typical photovoltaic module defects such as hot spots and hidden cracks, which can simultaneously output defect type classification, accurate defect bounding box coordinates and confidence score of defect features.

[0077] For the recognition result with a confidence lower than a preset threshold (for example, 85%), the electronic device can mark it as a sample to be reviewed, and hand it over to the operation and maintenance personnel for secondary confirmation, so as to ensure the reliability of defect detection.

[0078] Optionally, the data confirmed by the operation and maintenance personnel can be used to periodically optimize the defect recognition model.

[0079] Optionally, the electronic device can configure an EfficientNet in the inside of the inspection drone, and complete the defect recognition process by the inspection drone.

[0080] S103, for the target photovoltaic module with a defect confidence greater than a preset threshold, determine the temperature of the defect position according to the defect coordinates and the thermal imaging image data.

[0081] Specifically, for the defect target with high confidence, the electronic device can start a thermodynamic feature analysis process. First, the corresponding region is located in the registered thermal image according to the defect coordinate information, and the adaptive threshold segmentation algorithm is used to accurately extract the defect region contour. Then, based on the calibration parameters of the thermal imaging sensor, the gray value is converted into actual temperature data to determine the temperature of the defect region.

[0082] S104, based on the preset priority determination model, the processing priority of the target photovoltaic module is determined according to the defect type, defect coordinate and temperature of the defect position.

[0083] In this embodiment, the electronic device can train the priority determination model according to historical defect data, and construct the defect processing priority as an optimization problem with constraints. Among them, the objective function can comprehensively consider the urgency of defect processing, maintenance resource consumption and expected power generation income recovery three dimensions. By training the priority determination model, the weight of each dimension in the objective function is determined, and finally the defect type, defect coordinate and defect position are quantified as each dimension in the objective function to determine the processing priority of the target photovoltaic module, so as to automatically allocate tasks according to the processing priority.

[0084] The defect processing method provided in this embodiment combines visible light and thermal imaging data for joint analysis through a deep learning model, identifies the defect type and locates the defect coordinate, and quantifies the defect severity by combining the thermodynamic parameters; Then, a dynamic priority evaluation model that integrates defect type features, spatial distribution features and temperature anomaly features is used, and the intelligent sorting of the processing priority is realized through adaptive weighting calculation of multi-dimensional parameters. The defect processing method of the embodiment effectively solves the problems of single defect evaluation dimension and rigid priority rule in traditional operation and maintenance, so that the task allocation can dynamically respond to the changes of the actual operation state of the photovoltaic module, thereby improving the rationality of operation and maintenance resource scheduling and the efficiency of emergency processing, and reducing the power generation loss and safety risk caused by the delay of defect processing.

[0085] Figure 3 Another flowchart of the defect processing method provided in this application is shown in Figure 3 Based on the embodiment of Figure 2 The embodiment is described in detail, and the method of the embodiment includes:

[0086] S201, acquiring defect image data of a photovoltaic module.

[0087] S202, pre-processing the defect image data.

[0088] Among them, the pre-processing includes distortion correction and defogging.

[0089] S203 , inputting the pre-processed defect image data into a trained defect recognition model, so that the defect recognition model outputs the defect type, defect coordinates, and defect confidence of the photovoltaic module.

[0090] S204 : For a target photovoltaic module with a defect confidence greater than a preset threshold, determine the temperature of the defect location according to the defect coordinates and the thermal imaging image data.

[0091] Steps S201-S204 and Figure 2 The implementation of steps S101-S103 in the embodiment is similar.

[0092] When preprocessing defect image data, distortion correction based on camera calibration parameters and dehazing using an improved dark channel prior algorithm can be used to effectively improve image data quality. This process can be understood by referring to existing technologies.

[0093] S205. Determine the defect area according to the defect coordinates.

[0094] Specifically, the electronic device can accurately extract the pixels of the defect area according to the defect coordinates based on the semantic segmentation network, and convert them into the defect area based on the actual physical size of the photovoltaic module.

[0095] S206 : Determine the severity of the defect of the target photovoltaic module according to the defect area, the total area of ​​the target photovoltaic module, the temperature at the defect location, and the standard temperature.

[0096] Optionally, the defect severity=a*(defect area / total area)+b*(|temperature at the defect location-standard temperature| / preset maximum allowable temperature difference).

[0097] Here, a+b=1, and the values ​​of a and b can be set as needed, for example, a=0.5, b=0.5.

[0098] The standard temperature is the temperature of the target PV module in the normal area, which can be the average of multiple points in the normal area. The normal area is the non-defective area.

[0099] For example, if the defect area accounts for 5%, |temperature at the defect location - standard temperature| = 10°C, the preset maximum allowable temperature difference is 15°C, a = 0.5, b = 0.5, then the defect severity = 0.5*(5% / 100%) + 0.5*(10°C / 15°C) = 0.025 + 0.333 = 0.358.

[0100] S207: Determine the urgency of the defect of the target photovoltaic module according to the defect discovery time and the planned processing cycle of the target photovoltaic module.

[0101] Among them, the planned processing cycle can be determined according to the defect type.

[0102] Optionally, there is a mapping relationship between the planned processing period and the defect type. When the defect type is identified, the electronic device can query the planned processing period in the mapping relationship table according to the defect type.

[0103] For example, if the defect type is leakage and the planned processing period is 12 hours, it means that the leakage problem needs to be processed within 12 hours.

[0104] Optionally, the urgency of the defect of the target photovoltaic module = (current time - defect discovery time) / planned processing cycle.

[0105] Optionally, the electronic device may also obtain weather information and power station load information of the power station where the target photovoltaic component is located.

[0106] On this basis, the specific implementation of step S207 may also be to determine the urgency of the defect of the target PV module according to the defect discovery time, planned processing cycle, defect type, weather information and power station load information of the target PV module.

[0107] Specifically, the electronic device can be implemented through the following steps:

[0108] S2071. Determine a first urgency bonus value based on the defect type and weather information.

[0109] For example, the weather information indicates that there will be heavy rain in the next 24 hours, and the defect types are electrical and structural defects. According to the preset rules, the first urgency bonus value is determined to be 0.3.

[0110] For another example, the weather information is a high temperature warning (such as greater than 40°C), and the defect type is a hot spot defect. According to the preset rules, the first urgency bonus value is determined to be 0.2.

[0111] S2072. Determine a second emergency level bonus value based on the power plant load information.

[0112] For example, if the power station load exceeds the preset maximum load, the second emergency level bonus value is determined to be 0.2 according to the preset rules.

[0113] S2073. Calculate the urgency of the defect of the target photovoltaic module according to the following formula.

[0114] The urgency of the defect of the target PV module = (current time - defect discovery time) / planned processing cycle + first urgency bonus value + second urgency bonus value.

[0115] S208 : Based on a preset priority determination model, determine the processing priority of the target photovoltaic module according to the defect type, defect severity, and defect urgency.

[0116] Optionally, the electronic device may calculate the processing priority of the target photovoltaic assembly according to the following formula.

[0117] Processing priority = α*T+β*S+γ*E.

[0118] T represents the defect type, and is assigned a value based on the defect category. For example, if the defect type is electrical safety (such as leakage or short circuit), T is assigned a value of 1; if the defect type is functional loss (such as hot spots or hidden cracks), T is assigned a value of 0.7; if the defect type is cosmetic damage (such as glass cracks or stains), T is assigned a value of 0.4. The value of T ranges from 0.1 to 1.

[0119] S represents the severity of the defect, which can be calculated according to the method described in step S206. The value of S ranges from 0.1 to 1.

[0120] E represents the urgency of the defect, which can be calculated according to the method described in step S207. The value range of E is 0.1-1.

[0121] α, β, and γ represent the weights of each factor, which can be determined through regression analysis of historical operation and maintenance data and can be flexibly configured based on the scale of the power plant and the operation and maintenance strategy. α + β + γ = 1.

[0122] The weight distribution can be set as needed. For example, when the defect type is an electrical defect, α can be set to 0.4, β to 0.3, and γ to 0.3, with α being the largest value to ensure safety priority.

[0123] Combining the above, the following examples are provided:

[0124] The defect type is leakage, the defect area accounts for 5%, |temperature at the defect location - standard temperature| = 10°C, the preset maximum allowable temperature difference is 15°C, a = 0.5, b = 0.5, α = 0.4, β = 0.3, γ = 0.3, and there will be heavy rain in 6 hours. The power station load exceeds the preset maximum load.

[0125] The defect type is leakage, and the corresponding planned maintenance period is 12 hours. The current time - the time when the defect is discovered = 6 hours.

[0126] Based on the above information, we can get: T=1;

[0127] S=0.5*(5% / 100%)+0.5*(10℃ / 15℃)=0.025+0.333=0.358;

[0128] E=6 / 12+0.3+0.2=0.5+0.3+0.2=1;

[0129] Processing priority = 0.4*1+0.3*0.358+0.3*1=0.8074.

[0130] It can be understood that the larger the calculated value is, the higher the processing priority is.

[0131] Based on the determined processing priority, the electronic equipment can assign operation and maintenance personnel according to the processing priority and allocate operation and maintenance resources, such as rainstorm protection resources.

[0132] The defect handling method provided in this embodiment reduces the error rate of defect identification by using a deep learning model to identify defect characteristics; by integrating defect characteristics, environmental factors, etc., it dynamically determines the defect handling priority, avoids the problem of rigid defect handling task scheduling caused by reliance on manual experience, and improves defect handling efficiency.

[0133] Figure 4 A schematic diagram of the structure of the defect handling device provided in this application, such as Figure 4 As shown, the defect handling device 20 of this embodiment is used to implement the operation corresponding to the electronic device in any of the above method embodiments. The defect handling device 20 provided in this embodiment includes:

[0134] An acquisition module 21 is used to acquire defect image data of a photovoltaic module, where the defect image data includes visible light image data and thermal imaging image data;

[0135] An input module 22 is used to input defect image data into a trained defect recognition model so that the defect recognition model outputs the defect type, defect coordinates, and defect confidence of the photovoltaic module;

[0136] A determination module 23 is configured to determine, for a target photovoltaic module having a defect confidence level greater than a preset threshold, the temperature at the defect location based on the defect coordinates and the thermal imaging image data;

[0137] The determination module 23 is further configured to determine the processing priority of the target photovoltaic module based on a preset priority determination model and according to the defect type, defect coordinates and temperature of the defect location.

[0138] In a possible implementation, the determination module 23 is specifically configured to determine the defect area according to the defect coordinates;

[0139] Determine the severity of the defect of the target PV module based on the defect area, the total area of ​​the target PV module, the temperature of the defect location and the standard temperature;

[0140] Determine the urgency of the target PV module defect based on the time the defect is discovered and the planned processing cycle. The planned processing cycle is determined based on the defect type.

[0141] Based on the preset priority determination model, the processing priority of the target PV modules is determined according to the defect type, defect severity and defect urgency.

[0142] In a possible implementation, the determination module 23 is specifically configured to calculate the urgency of the defect of the target photovoltaic module according to the following formula:

[0143] The urgency of the defect of the target PV module = (current time - defect discovery time) / planned processing cycle.

[0144] In a possible implementation, the acquisition module 21 is further configured to acquire weather information and power station load information of the power station where the target photovoltaic module is located;

[0145] The determination module 23 is further configured to determine the urgency of the defect of the target photovoltaic module according to the defect discovery time, planned processing cycle, defect type, weather information and power station load information of the target photovoltaic module.

[0146] In a possible implementation, the determination module 23 is specifically configured to determine a first urgency bonus value based on the defect type and weather information;

[0147] Determining a second emergency level bonus value based on power station load information;

[0148] The urgency of the defect of the target PV module is calculated according to the following formula;

[0149] The urgency of the defect of the target PV module = (current time - defect discovery time) / planned processing cycle + first urgency bonus value + second urgency bonus value.

[0150] In a possible implementation, the input module 22 is further configured to pre-process the defect image data;

[0151] The preprocessed defect image data is input into the trained defect recognition model.

[0152] The defect handling device 20 provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effects are similar, and are not described in detail in this embodiment.

[0153] Figure 5 This is a schematic diagram of the structure of an electronic device provided by this application. Figure 5As shown, the electronic device 30 provided by the embodiment includes a memory 31 and at least one processor 32. Optionally, the device 30 further includes a communication component 33. The memory 31, the processor 32 and the communication component 33 are connected through a bus 34.

[0154] In the implementation process, the at least one processor 32 executes the computer execution instructions stored in the memory 31, so that the at least one processor 32 executes the above-mentioned method.

[0155] The specific implementation process of the processor 32 can refer to the method embodiments described above, which have similar implementation principles and technical effects, and will not be described here in detail.

[0156] In the above embodiments, it should be understood that the processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the application can be directly embodied as the execution of the hardware processor, or executed by the combination of hardware and software modules in the processor.

[0157] The memory can include a random access memory (RAM), and can also include a non-volatile memory (NVM), for example, at least one disk memory.

[0158] The bus can be an industry standard architecture (ISA) bus, a peripheral component (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, the bus in the drawings of the present application does not limit to only one bus or one type of bus.

[0159] The present application also provides a computer program product, including a computer program, which is executed by the processor to realize the above-mentioned method.

[0160] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0161] The readable storage medium may be implemented by any type of volatile or non-volatile memory device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium may be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0162] An exemplary readable storage medium is coupled to a processor, such that the processor can read information from and write information to the readable storage medium. Alternatively, the readable storage medium may be an integral part of the processor. The processor and the readable storage medium may reside in an application-specific integrated circuit (ASIC). Alternatively, the processor and the readable storage medium may reside in a device as discrete components.

[0163] The division of units is merely a logical functional division; actual implementations may employ alternative divisions, such as combining or integrating multiple units or components into another system, or omitting or disabling certain features. Furthermore, any direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between devices or units, either through an interface, electrical, mechanical, or other means.

[0164] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0165] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0166] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the method of the present invention. The aforementioned storage medium includes various media that can store program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0167] Those skilled in the art will appreciate that all or part of the steps in the above-described method embodiments can be implemented using hardware associated with program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0168] Finally, it should be noted that those skilled in the art will readily identify other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art not disclosed herein. The present invention is not limited to the precise structure described above and illustrated in the accompanying drawings, and various modifications and variations may be made without departing from the scope thereof. The scope of the present invention is limited solely by the appended claims.

Claims

1. A defect handling method, characterized in that: The method comprises: Acquiring defect image data of a photovoltaic module, wherein the defect image data includes thermal imaging image data; Inputting the defect image data into a trained defect recognition model, so that the defect recognition model outputs the defect type, defect coordinates and defect confidence of the photovoltaic module; For the target photovoltaic module whose defect confidence is greater than a preset threshold, determining the temperature of the defect location according to the defect coordinates and the thermal imaging image data; Based on a preset priority determination model, the processing priority of the target photovoltaic component is determined according to the defect type, the defect coordinates, and the temperature of the defect position.

2. The method according to claim 1, characterized in that The determining, based on a preset priority determination model and according to the defect type, the defect coordinates, and the temperature of the defect location, of the processing priority of the target photovoltaic assembly includes: determining the defect area according to the defect coordinates; determining a severity of a defect of the target photovoltaic module according to the defect area, the total area of ​​the target photovoltaic module, the temperature of the defect location, and a standard temperature; determining an urgency level of the defect of the target photovoltaic module according to a time when the defect of the target photovoltaic module is discovered and a planned processing period, wherein the planned processing period is determined according to the defect type; Based on the preset priority determination model, the processing priority of the target photovoltaic assembly is determined according to the defect type, the defect severity and the defect urgency.

3. The method according to claim 2, characterized in that The determining the urgency of the defect of the target photovoltaic module according to the defect discovery time of the target photovoltaic module and the planned processing period includes: Calculate the urgency of the defect of the target photovoltaic module according to the following formula; The urgency of the defect of the target photovoltaic module = (current time - the time when the defect is discovered) / the planned processing period.

4. The method according to claim 2, characterized in that The method further comprises: Obtaining weather information and power station load information of the power station where the target photovoltaic module is located; The determining the urgency of the defect of the target photovoltaic module according to the defect discovery time of the target photovoltaic module and the planned processing period includes: The urgency of the defect of the target photovoltaic module is determined according to the defect discovery time of the target photovoltaic module, the planned processing cycle, the defect type, the weather information and the power station load information.

5. The method according to claim 4, characterized in that The determining the urgency of the defect of the target photovoltaic module according to the defect discovery time of the target photovoltaic module, the planned processing cycle, the defect type, the weather information, and the power station load information includes: determining a first urgency bonus value according to the defect type and the weather information; determining a second emergency level bonus value based on the power station load information; Calculate the urgency of the defect of the target photovoltaic module according to the following formula; The urgency level of the defect of the target photovoltaic module = (current time - defect discovery time) / the planned processing period + the first urgency level bonus value + the second urgency level bonus value.

6. The method according to any one of claims 1 to 5, characterized in that Before inputting the defect image data into the trained defect recognition model, the method further includes: Preprocessing the defect image data; The step of inputting the defect image data into the trained defect recognition model is as follows: The preprocessed defect image data is input into a trained defect recognition model.

7. A defect handling device, characterized in that: include: An acquisition module, configured to acquire defect image data of a photovoltaic module, wherein the defect image data includes thermal imaging image data; An input module, configured to input the defect image data into a trained defect recognition model, so that the defect recognition model outputs the defect type, defect coordinates, and defect confidence of the photovoltaic module; a determination module, configured to determine, for the target photovoltaic module having a defect confidence greater than a preset threshold, a temperature at a defect location based on the defect coordinates and the thermal imaging image data; The determination module is further configured to determine the processing priority of the target photovoltaic assembly based on a preset priority determination model and according to the defect type, the defect coordinates, and the temperature of the defect location.

8. An electronic device, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 6 when executed by a processor.

10. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 6 when the computer program is executed by a processor.

Images