A Photovoltaic Module PID Detection Method, Device and Electronic Equipment

Abstract

The present application provides a PID detection method, device and electronic device for photovoltaic modules, which relates to the field of data processing. In this method, detection data for a target photovoltaic module is obtained, and the detection data includes current, voltage, power output, ambient temperature, relative humidity and solar irradiance; according to the detection data, a target feature group is determined, and the target feature group includes time series features, relative performance features and environmental features; the time series features, relative performance features and environmental features are input into a support vector machine model to obtain a detection result; if it is determined that the detection result indicates an anomaly, it is determined that the target photovoltaic module has a PID effect. Implementing the technical solution provided by the present application facilitates improving the accuracy of PID detection for photovoltaic modules.

Description

Technical Field

[0001] This application relates to the technical field of data processing, and in particular, to a method, device, and electronic device for detecting PID of photovoltaic modules. Background Art

[0002] During long-term use, photovoltaic modules may be affected by various factors, resulting in a decline in their performance. Among them, the Potential Induced Degradation (PID) effect is a common fault phenomenon, which will significantly reduce the power generation efficiency of photovoltaic modules, thereby affecting the economy and reliability of the entire photovoltaic power generation system.

[0003] Currently, traditional PID detection technologies usually rely on empirical formulas and experience-based threshold judgments, and the accuracy and reliability of these methods are limited. However, due to the complex and changeable working environment of photovoltaic modules and numerous factors affecting their performance, a single empirical formula lacks adaptability to real-time data and may fail under new environmental conditions or operating states, resulting in low accuracy of PID detection for photovoltaic modules. Summary of the Invention

[0004] This application provides a method, device, and electronic device for detecting PID of photovoltaic modules, which is convenient for improving the accuracy of PID detection for photovoltaic modules.

[0005] In the first aspect of this application, a method for detecting PID of photovoltaic modules is provided. The method includes: obtaining detection data for a target photovoltaic module, where the detection data includes current, voltage, power output, ambient temperature, relative humidity, and solar irradiance; determining a target feature group according to the detection data, where the target feature group includes time-series features, relative performance features, and environmental features; inputting the time-series features, relative performance features, and environmental features into a support vector machine model to obtain a detection result; if it is determined that the detection result indicates an anomaly, it is determined that the target photovoltaic module has a PID effect.

[0006] By adopting the above technical solution, the method provides rich information for subsequent analysis by obtaining various detection data, namely current, voltage, power output, ambient temperature, relative humidity, and solar irradiance. This comprehensive data collection can more accurately reflect the actual working state of the photovoltaic module, making the subsequent analysis more reliable. By determining the target feature group, the method integrates time series features, relative performance features, and environmental features. This systematic feature extraction can fully capture the performance changes of the photovoltaic module under different environmental conditions, helping to improve the sensitivity and accuracy of detection and avoiding the one-sidedness common in traditional methods. Using the support vector machine model for detection gives full play to the advantages of machine learning in data pattern recognition and classification. SVM can effectively process high-dimensional data and maintain good performance in complex non-linear situations, improving the accuracy and robustness of PID detection. By directly judging the detection result, if the result indicates an anomaly, the PID effect of the photovoltaic module can be quickly determined. This clear feedback mechanism provides clear operation guidance for maintenance personnel, enabling them to take timely measures to reduce potential losses. Therefore, adopting the above method can improve the accuracy of PID detection for photovoltaic modules.

[0007] Optionally, the obtaining of the detection data for the target photovoltaic module specifically includes: receiving the original current data of the target photovoltaic module sent by the current sensor; receiving the original voltage data of the target photovoltaic module sent by the voltage sensor; receiving the original power data of the target photovoltaic module sent by the power sensor; receiving the original ambient temperature data of the target photovoltaic module sent by the ambient temperature sensor; receiving the original relative humidity data of the target photovoltaic module sent by the relative humidity sensor; receiving the original solar irradiance data of the target photovoltaic module sent by the solar irradiance sensor; and preprocessing the original current data, the original voltage data, the original power data, the original ambient temperature data, the original relative humidity data, and the original solar irradiance data to obtain the detection data, where the preprocessing includes denoising, filtering, and normalization processing.

[0008] By adopting the above technical solutions, by receiving the raw data from multiple sensors, this method can comprehensively capture the working state of the photovoltaic modules. This distributed multi-source data collection provides rich information for subsequent analysis, which helps to more accurately evaluate the performance of the modules and identify potential problems. Directly receiving the raw data sent by various sensors ensures the timeliness and accuracy of the data. The sensors can provide real-time measurement values, thus improving the timeliness of the data and enabling the detection results to better reflect the current working state of the photovoltaic modules. Denoising can significantly improve the reliability of the data and reduce the interference with subsequent analysis by removing the random noise in the measurement process. The filtering technology can smooth the data fluctuations and exclude the misleading information caused by instantaneous fluctuations, thereby enhancing the interpretability of the data. Normalizing the data can standardize the data with different dimensions and avoid the analysis errors caused by dimension differences. This is very important for subsequent feature extraction and model training. Through preprocessing, the consistency of data from different sources is ensured, making the comparability between various features stronger. This consistency is crucial for the training and feature analysis of machine learning models, which helps to improve the accuracy and stability of the models. The preprocessed data can usually significantly reduce the complexity in subsequent analysis. Reducing noise and outliers can help the model focus more on key features, thus improving the training efficiency and reducing the risk of overfitting. The preprocessing steps can lay a good foundation for subsequent data analysis and modeling. The cleaned and standardized data can be absorbed by the model faster, reducing the time invested by analysts in data cleaning and thus improving the overall work efficiency.

[0009] Optionally, determining the target feature group according to the detection data specifically includes: extracting the target time points in the current and voltage by using a sliding window, and the statistical features corresponding to the target time points, where the statistical features include mean, standard deviation, maximum value, minimum value, and time slope; generating the time series features according to the mean, the standard deviation, the maximum value, the minimum value, and the time slope; obtaining the reference power output of the target photovoltaic module; calculating the relative power according to the reference power output and the power output at the current moment; obtaining the power output corresponding to the target time point, where the target time point and the current moment are adjacent time points; calculating the power relative change rate according to the power output corresponding to the target time point and the power output at the current moment, and the relative performance features include the relative power and the power relative change rate.

[0010] By adopting the above technical solutions, the target time points of current and voltage and their corresponding statistical features are extracted using the sliding window technique, which can capture the dynamic changes of time series data, allow real-time analysis of data trends, and enhance the understanding of the state of photovoltaic modules. By extracting statistical features such as mean and standard deviation, the distribution characteristics and fluctuations of data can be comprehensively reflected, which helps to identify potential abnormal patterns. Obtaining the reference power output of the target photovoltaic module and comparing it with the current power output provides a reference for the calculation of relative power, which can more effectively evaluate the performance of the current power output and help identify changes in the performance of photovoltaic modules. This comparison method based on the reference value can reduce errors caused by environmental changes and make the evaluation results more objective and reliable. By calculating the relative power, a quantitative index can be provided, which can effectively track and compare the performance of photovoltaic modules at different time points, helping to identify trends and potential problems. Calculating the relative power change rate can provide a deeper understanding of the dynamic performance changes of photovoltaic modules. The calculation of the relative power change rate can capture small performance fluctuations, which is crucial for identifying early PID effects and helps to take maintenance measures early. By analyzing the relative change rate, the change trend of power output over time can be monitored, providing decision-making support for operation and maintenance personnel.

[0011] Optionally, determining the target feature group according to the detection data specifically further includes: calculating the average value, maximum value, and minimum value corresponding to the environmental data at each of the current moments according to the environmental temperature, the relative humidity, and the solar irradiance; obtaining the environmental data corresponding to the target time point; and calculating the environmental relative change rate according to the environmental data corresponding to the target time point and the environmental data at the current moment, where the environmental features include the average value, the maximum value, the minimum value, and the environmental relative change rate.

[0012] By adopting the above technical solutions, by calculating the average, maximum, and minimum values of the ambient temperature, relative humidity, and solar irradiance, comprehensively analyzing these environmental data helps to better understand the performance of components under different conditions. Conducting statistical analysis on the environmental data can more clearly reflect the potential impact of environmental factors on the output performance of photovoltaic modules, providing a basis for analyzing the reasons for performance fluctuations. The introduction of real-time environmental data makes feature extraction more in line with the actual situation, avoids using outdated data, and enhances the accuracy of the performance evaluation of photovoltaic modules. Based on the latest environmental data, the operation and maintenance strategies can be adjusted in a timely manner or maintenance measures can be taken to cope with sudden environmental changes. The relative change rate can capture minor environmental changes, which is particularly important for early identification of potential performance threats faced by photovoltaic modules, especially in the detection of the PID effect. By monitoring the environmental relative change rate, long-term trends or periodic fluctuations can be discovered, which helps to formulate more effective prediction models and operation and maintenance plans. This comprehensive feature group provides rich information for subsequent data analysis, helping to improve the recognition ability of machine learning models for the performance of photovoltaic modules. Multidimensional features can enable the model to better understand complex data relationships, enhancing its generalization ability and accuracy, especially when facing multiple environmental impacts. Environmental factors are often related to the PID effect. By monitoring changes in environmental features, the occurrence of the PID effect can be identified and diagnosed more accurately, improving the detection accuracy. Timely identification of the impact of the environment on component performance can help formulate a more effective early warning mechanism, reduce the risk of failures, and ensure the stable operation of the system. Through timely environmental monitoring and corresponding decision-making adjustments, the overall efficiency and sustainability of the photovoltaic power generation system can be improved.

[0013] Optionally, inputting the time series features, relative performance features, and environmental features into the support vector machine model to obtain a detection result specifically includes: using the mean filling method to process missing values of the time series features, the relative performance features, and the environmental features to obtain a framework feature group; calculating the framework feature group through the support vector machine model to obtain a feature space position; determining the positional relationship between the feature space position and the hyperplane corresponding to the support vector machine model; and generating the detection result according to the positional relationship.

[0014] By adopting the above technical solution, in actual detection, feature data may be missing due to sensor failures or other reasons. The mean filling method can effectively fill these missing values, avoiding incomplete model training caused by missing data. The mean filling method can preserve the overall characteristics of the data, thus having a relatively small impact on model training. Integrating multiple features enables the model to consider data from multiple dimensions, enhancing the model's sensitivity to changes in the performance of photovoltaic modules. The unified feature input framework helps simplify subsequent data processing and model training processes, improving efficiency. The SVM maps low-dimensional features to a high-dimensional space through a kernel function, enabling complex non-linear problems to be effectively classified in the high-dimensional space, which helps improve the detection accuracy of the PID effect. The SVM seeks to construct an optimal hyperplane to maximize the class spacing, and this characteristic makes it perform well in dealing with complex classification tasks, especially in the case of unbalanced samples. By judging the positional relationship in the feature space, it can be determined whether a sample lies on one side or the other side of the hyperplane, simplifying the logic of anomaly detection. This determination method based on spatial position makes the detection results more interpretable, and maintenance personnel can clearly understand the basis for the model's judgment. Automated processing reduces the need for manual intervention, improves the speed and efficiency of detection, and can promptly detect abnormal states of photovoltaic modules. By performing detection through a unified model, the consistency and reliability of the detection results can be ensured, reducing the possibility of human errors.

[0015] Optionally, the method further includes: calculating probability values based on the positional relationship, where the probability values include a first probability value and a second probability value. The first probability value is used to represent the probability value corresponding to the position in the feature space on the first side of the hyperplane, and the second probability value is used to identify the probability value corresponding to the position in the feature space on the second side of the hyperplane. The first side and the second side are two opposite sides of the hyperplane; if it is determined that the position in the feature space is on the first side and the first probability value is greater than or equal to a preset threshold, then it is determined that the detection result indicates normal, and it is determined that the target photovoltaic module does not have the PID effect; if it is determined that the position in the feature space is on the second side and the second probability value is greater than or equal to a preset threshold, then it is determined that the detection result indicates abnormal, and it is determined that the target photovoltaic module has the PID effect.

[0016] By adopting the above technical solution, the probability value can quantify the uncertainty of the classification result, thus making the decision-making more scientific. By setting a threshold to judge the component state, the decision-making process can be effectively optimized to ensure that decisions on maintenance or intervention are made only under high confidence, reducing the false alarm rate. This division provides a clear classification criterion, enabling the model to quickly and accurately identify the health status of photovoltaic components, facilitating the maintenance personnel to take corresponding measures. The division of the hyperplane makes the result easy to understand, and the maintenance personnel can intuitively know which category the current component state belongs to, thus making a quick decision and response. According to the operating environment and historical data of the photovoltaic components, the threshold can be adjusted to adapt to different scenarios and requirements, enhancing the adaptability and accuracy of the model. By adjusting the threshold, a balance can be achieved between sensitivity and specificity, improving the overall detection effect. The clear judgment result enables the maintenance personnel to take actions quickly, reducing the decision-making time and improving the maintenance efficiency. The clear judgment result provides a reliable basis for the maintenance decision-making, which can help the maintenance personnel formulate corresponding maintenance and repair strategies to ensure the stable operation of the system. The probability value higher than the preset threshold can ensure that the PID effect is reported only under a relatively high confidence, thus reducing unnecessary maintenance costs and resource waste. Through accurate detection and reporting, the overall reliability of the photovoltaic power generation system can be improved to ensure long-term stable power generation performance.

[0017] Optionally, the method further includes: obtaining training data, where the training data includes a training set and a test set; training an initial model including a radial basis kernel and hyperparameters with the training set to obtain the corresponding relationship between the feature group and the label, where the label includes normal and abnormal; optimizing the parameters of the initial model by constructing a Lagrangian function, and through repeated iteration, obtaining the support vector machine model that meets the preset standard or converges.

[0018] By adopting the above technical solutions, dividing the data into a training set and a test set can effectively evaluate the generalization ability of the model, avoiding the situation where the model only memorizes the training data without the ability to process new data. The test set is used to independently evaluate the performance of the model, helping to understand the performance of the model on unknown data and ensuring that the model has good accuracy and reliability in practical applications. Through training, the model learns the correspondence between the input features and the output labels, laying a foundation for subsequent anomaly detection. The initial model can continuously learn and adapt to different operating states of the photovoltaic modules, thereby improving the detection accuracy. The radial basis kernel function can map the data from the original space to a higher-dimensional feature space, enabling the processing of complex non-linear relationships and helping to improve the classification ability of the model. Secondly, the radial basis kernel function has good adaptability and can be optimized for different data distributions, enhancing the performance of the model in various situations. Parameter optimization helps to find the optimal decision boundary, ensuring that the hyperplane of the model in the feature space can effectively distinguish normal and abnormal samples and improving the classification accuracy. Through parameter adjustment, the model can better adapt to the training data, reduce the misclassification rate, and thus enhance the reliability of the detection. Through iterative optimization, the model is fine-tuned at each step, gradually approaching the optimal model parameters and enhancing the overall performance. The iterative process can find a stable parameter combination through multiple attempts, ensuring that the model can exhibit good robustness in various data situations. The convergence criterion helps to determine when to stop training, avoiding unnecessary calculations and resource waste and improving the training efficiency. Setting the convergence criterion can ensure that the model stops training after reaching a certain performance level, avoiding the risk of overfitting.

[0019] In a second aspect of the present application, a PID detection device for photovoltaic modules is provided. The PID detection device for photovoltaic modules includes an acquisition module and a processing module. Among them, the acquisition module is used to acquire detection data for a target photovoltaic module, and the detection data includes current, voltage, power output, ambient temperature, relative humidity, and solar irradiance. The processing module is used to determine a target feature group according to the detection data, and the target feature group includes time series features, relative performance features, and environmental features. The processing module is further used to input the time series features, relative performance features, and environmental features into a support vector machine model to obtain a detection result. The processing module is further used to determine that the target photovoltaic module has a PID effect if it is determined that the detection result indicates an anomaly.

[0020] In a third aspect of the present application, an electronic device is provided. The electronic device includes a processor, a memory, a user interface, and a network interface. The memory is used to store instructions. The user interface and the network interface are both used to communicate with other devices. The processor is used to execute the instructions stored in the memory so that the electronic device executes the method described above.

[0021] In a fourth aspect of the present application, a computer-readable storage medium is provided. The computer-readable storage medium stores instructions, which, when executed, perform the method described above.

[0022] In summary, one or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0023] By obtaining various detection data, namely current, voltage, power output, ambient temperature, relative humidity, and solar irradiance, rich information is provided for subsequent analysis. Such comprehensive data collection can more accurately reflect the actual working state of the photovoltaic module, making subsequent analysis more reliable. By determining the target feature group, the method integrates time series features, relative performance features, and environmental features. This systematic feature extraction can fully capture the performance changes of the photovoltaic module under different environmental conditions, helping to improve the sensitivity and accuracy of detection and avoiding the one-sidedness commonly found in traditional methods. Using the support vector machine model for detection gives full play to the advantages of machine learning in data pattern recognition and classification. SVM can effectively process high-dimensional data and maintain good performance in complex non-linear situations, improving the accuracy and robustness of PID detection. Through the direct determination of the detection result, if the result indicates an anomaly, it can be quickly determined that the photovoltaic module has the PID effect. This clear feedback mechanism provides clear operation guidance for maintenance personnel, enabling timely measures to be taken to reduce potential losses. Therefore, the above method can improve the accuracy of PID detection for photovoltaic modules. Description of the Drawings

[0024] Figure 1 It is a schematic flowchart of a method for detecting PID of a photovoltaic module provided by an embodiment of the present application.

[0025] Figure 2 It is another schematic flowchart of a method for detecting PID of a photovoltaic module provided by an embodiment of the present application.

[0026] Figure 3 It is a schematic block diagram of a device for detecting PID of a photovoltaic module provided by an embodiment of the present application.

[0027] Figure 4 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

[0028] Description of the reference numerals: 31, acquisition module; 32, processing module; 41, processor; 42, communication bus; 43, user interface; 44, network interface; 45, memory. Detailed Embodiments

[0029] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all of the embodiments.

[0030] In the description of the embodiments of this application, words such as "for example" or "for illustration" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as "for example" or "for illustration" in the embodiments of this application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, the use of words such as "for example" or "for illustration" is intended to present relevant concepts in a specific manner.

[0031] In the description of the embodiments of this application, the meaning of the term "a plurality of" refers to two or more. For example, a plurality of systems refers to two or more systems, and a plurality of screen terminals refers to two or more screen terminals. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the technical features indicated. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. The terms "include", "comprise", "have" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0032] During the long-term use of photovoltaic modules, they may be affected by various external factors, resulting in a decline in their overall performance. The Potential Induced Degradation (PID) effect is one of the most common failure phenomena in the operation of photovoltaic modules. It will significantly reduce the power generation efficiency of the modules, thus directly affecting the economy and reliability of the entire photovoltaic power generation system. This phenomenon not only causes damage to the photovoltaic modules themselves, but may also bring serious negative impacts on the long-term operation of the power generation system.

[0033] Currently, traditional PID detection technologies often rely on empirical formulas and experience-based threshold judgments. Although these methods can provide certain guidance in some cases, their accuracy and reliability are greatly limited. This is mainly because the working environment of photovoltaic modules is usually very complex and changeable, and the factors affecting their performance are relatively numerous. A single empirical formula lacks adaptability to real-time data. Therefore, in new environmental conditions or specific operating states, it may fail, which leads to uncertainty in the accuracy of PID detection of photovoltaic modules.

[0034] To solve the above technical problems, this application provides a method for detecting PID of photovoltaic modules, referring to Figure 1, Figure 1 It is a schematic flowchart of a PID detection method provided by an embodiment of the present application. This detection method is applied to a server and includes steps S110 to S140, and the above steps are as follows:

[0035] S110. Obtain detection data for a target photovoltaic module, where the detection data includes current, voltage, power output, ambient temperature, relative humidity, and solar irradiance.

[0036] Specifically, the main role of the server in this process is to collect and process data. It can be a local server or a cloud server, responsible for storing, analyzing, and managing data related to photovoltaic modules. For example, in a large-scale photovoltaic power plant, multiple photovoltaic modules are connected to a central server, and the server regularly obtains real-time data from each photovoltaic module and performs centralized processing. The detection data is collected for a specific photovoltaic module, rather than the entire photovoltaic system. This targeting can help accurately diagnose performance problems of specific components. Suppose a certain photovoltaic module shows abnormal performance during power generation. The operation and maintenance personnel can obtain all the detection data of this specific module through the server for analysis, rather than viewing the data of all components in the entire power plant.

[0037] Among them, the current is the current value generated by the photovoltaic module during operation. Current is a key indicator reflecting the power generation capacity of the module. If a certain photovoltaic module should output a current of 5 amperes under ideal conditions, but the actual measured value is only 2 amperes, this may indicate a fault in the module. The voltage is the voltage value output by the photovoltaic module, which together with the current affects the power output of the module. A normal photovoltaic module may output a voltage of 40 volts under standard test conditions. If it is found that the output voltage is significantly lower than this value, it may indicate an electrical fault in the module. The power output is the electrical energy generated by the photovoltaic module within a certain period of time, usually measured in watts. When a photovoltaic module should output a power of 250 watts under good sunlight conditions, but the actual output is only 100 watts, this may mean that the module is affected by the PID effect or other faults. The ambient temperature is the temperature of the environment around the photovoltaic module, and the temperature will affect the power generation efficiency of the photovoltaic module. If the photovoltaic module operates in a high-temperature environment, it may lead to a decrease in efficiency. Therefore, the server needs to monitor the ambient temperature to analyze its impact on the module performance. The relative humidity is the humidity level of the surrounding environment, which may affect the long-term performance and reliability of the module. In a high-humidity environment, the photovoltaic module is more likely to experience electrical short circuits or corrosion. Therefore, monitoring the relative humidity is crucial for evaluating the health status of the module. The solar irradiance is the intensity of sunlight received by the photovoltaic module, usually expressed in watts per square meter, and is an important indicator for evaluating the performance of the photovoltaic module. Under different times and weather conditions, the change in solar irradiance will directly affect the power output of the photovoltaic module. The server needs to monitor this parameter in real time for a comprehensive performance analysis.

[0038] In a possible implementation manner, obtaining the detection data for the target photovoltaic module specifically includes: receiving the original current data of the target photovoltaic module sent by the current sensor; receiving the original voltage data of the target photovoltaic module sent by the voltage sensor; receiving the original power data of the target photovoltaic module sent by the power sensor; receiving the original ambient temperature data of the target photovoltaic module sent by the ambient temperature sensor; receiving the original relative humidity data of the target photovoltaic module sent by the relative humidity sensor; receiving the original solar irradiance data of the target photovoltaic module sent by the solar irradiance sensor; performing preprocessing on the original current data, original voltage data, original power data, original ambient temperature data, original relative humidity data, and original solar irradiance data to obtain the detection data, and the preprocessing includes denoising, filtering, and normalization processing.

[0039] Specifically, first, the server needs to obtain various detection data related to specific photovoltaic components. These data are collected distributively through different types of sensors, ensuring comprehensive monitoring of the working status of the photovoltaic components. The current sensor is responsible for measuring the output current of the photovoltaic components. This is an important indicator for evaluating the power generation capacity of the components. The voltage sensor is used to measure the output voltage of the photovoltaic components. When combined with the current, the power output can be calculated. The power sensor directly measures the power output of the photovoltaic components. For example, if the power sensor shows that the actual power output of the components is 105 watts, this is crucial for evaluating its efficiency. The ambient temperature sensor measures the ambient temperature around the photovoltaic components. The ambient temperature directly affects the power generation efficiency of the components. The relative humidity sensor monitors the humidity level of the environment, which may affect the long-term performance of the components. The solar irradiance sensor measures the sunlight intensity received by the photovoltaic components, usually expressed in watts per square meter (W / m²). Among them, the above-mentioned multiple sensor devices are pre-installed at the corresponding measurement positions of the photovoltaic components and maintain a communication connection with the server.

[0040] Among them, after the data collection is completed, the server needs to preprocess the original data to improve the data quality and the accuracy of analysis. The preprocessing includes the following aspects: eliminating the random noise that may be introduced during the data collection process. For example, the current sensor may generate instantaneous current fluctuations due to electromagnetic interference. Through denoising processing, these untrue fluctuations can be eliminated, making the data more stable. Applying filtering techniques to smooth the original data to reduce the volatility and error of the data. This can help highlight the main trends of the data. For example, using a low-pass filter to eliminate high-frequency noise and retain the main signal changes. Converting data with different dimensions to the same standard range, usually between 0 and 1. This step is particularly important for comparing different types of data, such as current, voltage, power, etc., because the dimensions and ranges of these data may vary greatly. If the range of current is 0 to 10 amperes, the range of voltage is 0 to 60 volts, and the range of power is 0 to 300 watts, through normalization processing, they can be converted to the same scale, making it easier to compare in subsequent analysis.

[0041] S120. Determine the target feature group according to the detection data. The target feature group includes time series features, relative performance features, and environmental features.

[0042] Specifically, a feature group refers to the key indicators extracted from the detection data, which are used to reflect the operating status and performance of photovoltaic modules. The selection of features is crucial for the accuracy and effectiveness of the model. In this example, the target feature group includes three types of features: Time series features refer to the changing trends of the detection data of photovoltaic modules over a period of time. These features can reveal the performance changes of photovoltaic modules at different time points. Example: Suppose during the monitoring process, the current data is recorded as [3A, 3.2A, 3.5A, 2.8A, 3.1A] at different time periods. Through these data, the mean, standard deviation, maximum value, minimum value, and time slope can be calculated. For example, a negative slope indicates a downward trend in current, thus obtaining time series features. These features help to detect early signs of performance degradation. Relative performance features are indicators obtained by comparing the current performance with the benchmark performance, usually the performance under ideal conditions. These features can help to determine whether the actual power generation capacity of the module meets the standard. Environmental features refer to the external environmental factors that affect the performance of photovoltaic modules at a specific time, including temperature, humidity, and solar irradiance, etc. Example: Suppose during the recording period, the environmental temperature is 25°C, the relative humidity is 60%, and the solar irradiance is 800 W / m². These data can be used to analyze the difference between the actual performance and the expected performance of the photovoltaic module under the current environmental conditions, thereby helping to evaluate the health status of the module. For example, high temperature and high humidity may lead to a decrease in module performance and require special attention.

[0043] In a possible implementation manner, according to the detection data, the target feature group is determined, specifically including: using a sliding window to extract the target time points in the current and voltage, and the statistical features corresponding to the target time points, where the statistical features include the mean, standard deviation, maximum value, minimum value, and time slope; generating time series features according to the mean, standard deviation, maximum value, minimum value, and time slope; obtaining the benchmark power output of the target photovoltaic module; calculating the relative power according to the benchmark power output and the power output at the current moment; obtaining the power output corresponding to the target time point, where the target time point and the current moment are adjacent time points; calculating the power relative change rate according to the power output corresponding to the target time point and the power output at the current moment, and the relative performance features include the relative power and the power relative change rate.

[0044] Specifically, the sliding window is a method for time series data analysis. It extracts data segments within the window step by step by setting a window with a fixed length and moving it over the data. In the detection data of photovoltaic modules, the current and voltage signals can be analyzed using the sliding window to obtain their time-varying features.

[0045] For example, assume the following current data: [2.5A, 2.6A, 2.4A, 2.7A, 2.9A, 2.5A]. If a window size of 3 is set, the server can extract the following data segments:

[0046] Window 1: [2.5A, 2.6A, 2.4A]; Window 2: [2.6A, 2.4A, 2.7A];

[0047] Window 3: [2.4A, 2.7A, 2.9A]; Window 4: [2.7A, 2.9A, 2.5A];

[0048] For each extracted window, a series of statistical features are calculated, such as the mean, standard deviation, maximum value, minimum value, and time slope, to capture the change trend and volatility of the data. The mean is the average value of the data within the window. The standard deviation is the degree of dispersion of the data. The maximum value is the maximum value of the data within the window. The minimum value is the minimum value of the data within the window. The time slope can be calculated by linear regression to obtain the slope of the data within the window, reflecting the change trend of the data over time. For example, for Window 1 [2.5A, 2.6A, 2.4A], the mean can be calculated as 2.5A, the standard deviation as 0.0816A, the maximum value as 2.6A, the minimum value as 2.4A, and the time slope as 0.1. Time series features are generated using the above statistical features, and these features are used to describe the performance changes of the photovoltaic module over a period of time. The reference power output refers to the output power that the photovoltaic module should have under ideal conditions. This indicator is usually based on the design parameters or historical performance data of the module. The relative power is generated by comparing the current power output with the reference power output, and it can reflect the actual power generation capacity of the photovoltaic module. The relative power change rate is used to reflect the degree of change in the power output, and it is calculated based on the power output at the current moment and the power output at adjacent time points. The relative performance features combine the relative power and the relative power change rate to provide a performance evaluation of the photovoltaic module under specific conditions. In summary, this passage details how to extract features from the detection data of photovoltaic modules for subsequent performance analysis and fault diagnosis. This feature extraction process can improve the monitoring and evaluation capabilities of the health status of photovoltaic modules, thereby providing data support for maintenance decisions.

[0049] In a possible implementation manner, according to the detection data, a target feature group is determined, which specifically further includes: calculating the average value, maximum value, and minimum value corresponding to the environmental data at each current moment according to the environmental temperature, relative humidity, and solar irradiance; obtaining the environmental data corresponding to the target time point; calculating the environmental relative change rate according to the environmental data corresponding to the target time point and the environmental data at the current moment, and the environmental features include the average value, maximum value, minimum value, and environmental relative change rate.

[0050] Specifically, for the environmental data (such as temperature, humidity, and irradiance) collected within a certain time period, the overall characteristics of the environmental conditions can be obtained by calculating the average value, maximum value, and minimum value of these data. These statistical characteristics can reflect the trend and amplitude of environmental changes and help analyze the impact of the environment on the performance of photovoltaic modules. During the analysis process, environmental data at specific time points are required for comparison with the data at the current moment. The target time point usually refers to the time point related to the power output or other performance indicators of the photovoltaic module. Suppose the environmental data recorded at a specific time point, such as 10:00 AM, are: Temperature: 26°C, Humidity: 48%, Irradiance: 800 W / m 2 . The environmental relative change rate is used to represent the degree of change in environmental conditions between a specific time point and the current moment. This change rate can reflect the possible impact of environmental conditions on the performance of photovoltaic modules. Example: Suppose the environmental data recorded at the current moment, such as 11:00 AM, are: Temperature: 27°C, Humidity: 50%, Irradiance: 900 W / m 2 . Then the calculated environmental temperature relative change rate is 3.85%, the environmental humidity relative change rate is 4.17%, and the environmental irradiance relative change rate is 125.%.

[0051] S130. Input the time series features, relative performance features, and environmental features into the support vector machine model to obtain the detection result.

[0052] Specifically, when performing PID detection, first, the features extracted from the operation data of the photovoltaic module, including time series features, relative performance features, and environmental features, need to be input into the trained support vector machine model. The SVM model is a powerful classification and regression tool that can make predictions by learning the relationship between features and labels. After receiving the input features, the support vector machine model will perform calculations in its feature space, judge the positional relationship corresponding to these features, and output a detection result. This result is usually a classification result (such as "normal" or "abnormal") to indicate whether the photovoltaic module has PID effect.

[0053] In a possible implementation manner, inputting the time series features, relative performance features, and environmental features into the support vector machine model to obtain the detection result specifically includes: using the mean filling method to process the missing values of the time series features, relative performance features, and environmental features to obtain a frame feature group; calculating the frame feature group through the support vector machine model to obtain the position in the feature space; judging the positional relationship between the position in the feature space and the hyperplane corresponding to the support vector machine model; and generating the detection result according to the positional relationship.

[0054] Specifically, when performing data analysis, there may be missing values in the feature data, that is, data that has not been collected. The mean filling method is a commonly used missing value processing technique. It replaces the missing values with the mean of the feature to ensure the integrity and usability of the data. This can prevent calculation errors caused by missing values during model training. Suppose in the time series feature, the current data at a certain time point is missing, and the mean of other current data is known to be 5.0A. Then, the missing current value will be filled with 5.0A. After the missing value processing, all the time series features, relative performance features, and environmental features will be combined into a complete feature group, called the frame feature group. This group of features will be used for subsequent model calculations. The frame feature group is input into the trained support vector machine model, and the model will calculate the position of this feature group in the feature space according to the input features. The feature space is a multi-dimensional space, where each dimension corresponds to a feature. Once the position in the feature space is obtained, the model will judge the relationship between this position and the defined hyperplane. The hyperplane is used to divide data points of different categories (such as normal and abnormal). If the position is on one side of the hyperplane, it usually represents one category (such as normal), and on the other side represents another category (such as abnormal). Finally, according to the relationship between the feature space position and the hyperplane, the final detection result is generated, indicating whether the photovoltaic module has the PID effect.

[0055] S140. If it is determined that the detection result indicates an anomaly, it is determined that the target photovoltaic module has the PID effect.

[0056] Specifically, after the input features are processed by the support vector machine model, the model will generate a detection result. This result is divided into two categories: normal and abnormal. If the detection result is judged as "abnormal", it means that the performance of the photovoltaic module is abnormal and there may be some kind of fault. Once the detection result indicates an anomaly, the system can infer that the photovoltaic module may be affected by the PID effect. This is because the PID effect will cause the current, voltage, and power output of the module to decrease, resulting in the detection result deviating from the normal range. Through the above process, the abnormal indication of the detection result is an important judgment basis, which can effectively identify the risk of the photovoltaic module having the PID effect. This timely feedback can not only help maintenance personnel respond quickly but also effectively maintain the overall performance and economy of the photovoltaic power generation system.

[0057] In a possible implementation, based on the positional relationship, probability values are calculated. The probability values include a first probability value and a second probability value. The first probability value is used to represent the probability value corresponding to the position in the feature space on the first side of the hyperplane, and the second probability value is used to identify the probability value corresponding to the position in the feature space on the second side of the hyperplane. The first side and the second side are two opposite sides of the hyperplane. If it is determined that the position in the feature space is on the first side and the first probability value is greater than or equal to a preset threshold, then it is determined that the detection result indicates normal, and it is determined that the target photovoltaic module does not have the PID effect. If it is determined that the position in the feature space is on the second side and the second probability value is greater than or equal to a preset threshold, then it is determined that the detection result indicates abnormal, and it is determined that the target photovoltaic module has the PID effect.

[0058] Specifically, the hyperplane is a key structure for classification by the support vector machine, which divides the feature space into two parts. The data points in the feature space, that is, the feature positions, will be classified as normal or abnormal according to their relationship with the hyperplane. The support vector machine model calculates two probability values. The first probability value represents the probability that the position in the feature space is on the first side of the hyperplane, corresponding to the normal state. The second probability value represents the probability that the position in the feature space is on the second side of the hyperplane, corresponding to the abnormal state. If the position in the feature space is on the first side of the hyperplane and the first probability value is greater than or equal to the set preset threshold, such as 0.7, the server determines it as normal and believes that the photovoltaic module does not have the PID effect. If the position in the feature space is on the second side of the hyperplane and the second probability value is greater than or equal to the set 0.7, the server determines it as abnormal and believes that the photovoltaic module has the PID effect. The server systematically judges the operating state of the photovoltaic module by analyzing the relationship between the position in the feature space and the hyperplane and the relevant probability values. Through the judgment of the set threshold, the normal and abnormal states can be effectively distinguished, so as to timely discover potential PID effects, providing a basis for maintenance and repair. This method improves the accuracy and reliability of photovoltaic module detection.

[0059] In a possible implementation, referring to Figure 2 , Figure 2 FIG. 10 is another flowchart of a method for detecting PID of a photovoltaic module provided by an embodiment of the present application, including steps S210 to S230. The above steps are as follows: S210, obtaining training data, where the training data includes a training set and a test set; S220, training an initial model including a radial basis kernel and hyperparameters using the training set to obtain the corresponding relationship between the feature group and the label, where the label includes normal and abnormal; S230, optimizing the parameters of the initial model by constructing a Lagrangian function, and through repeated iteration, obtaining a support vector machine model that meets the preset criteria or converges.

[0060] Specifically, in machine learning, training data is used to train a model to help the model learn the relationship between input features and output labels. The test set is usually used after the model is trained to verify the generalization ability of the model. The radial basis kernel function is a kernel function that can map input data into a high-dimensional space, making it easier to perform classification in this space. Through this mapping, the support vector machine can handle non-linearly separable data. During the model training process, hyperparameters are parameters that need to be manually set, such as the parameters of the kernel function and the penalty parameter. Hyperparameters have an important impact on the performance of the model. The input data of the model is a feature group, that is, the detection data of photovoltaic modules, such as features like current and voltage. The label is the output result of the model, which is the classification result in the embodiments of this application, such as "normal" or "abnormal". Through training, the model learns how to predict the corresponding label based on the input features. In an optimization problem, the Lagrangian function is a mathematical tool used to solve constrained optimization problems. In a support vector machine, the Lagrangian function is used to construct the objective function so that the model can find the optimal classification boundary. By constructing the Lagrangian function, the model parameters are adjusted through repeated iterations during the model training process to optimize the classification boundary. This process can be achieved through algorithms such as the gradient descent method. During the training process, the algorithm continuously adjusts the parameters through iteration until the performance of the model no longer changes significantly and reaches a convergence state, such as the loss function. The results of the training need to meet certain preset criteria, such as the classification accuracy or error rate, to consider the model to be effective.

[0061] This application also provides a PID detection device for photovoltaic modules. Referring to Figure 3 , Figure 3 is a schematic diagram of the modules of a PID detection device for photovoltaic modules provided by an embodiment of this application. The detection device is a server, and the server includes an acquisition module 31 and a processing module 32. Among them, the acquisition module 31 acquires the detection data for the target photovoltaic module, and the detection data includes current, voltage, power output, ambient temperature, relative humidity, and solar irradiance; the processing module 32 determines the target feature group according to the detection data, and the target feature group includes time series features, relative performance features, and environmental features; the processing module 32 inputs the time series features, relative performance features, and environmental features into the support vector machine model to obtain the detection result; if the processing module 32 determines that the detection result indicates an abnormality, it determines that the target photovoltaic module has a PID effect.

[0062] In a possible implementation, the acquisition module 31 acquires detection data for a target photovoltaic module, which specifically includes: the acquisition module 31 receives the original current data of the target photovoltaic module sent by a current sensor; the acquisition module 31 receives the original voltage data of the target photovoltaic module sent by a voltage sensor; the acquisition module 31 receives the original power data of the target photovoltaic module sent by a power sensor; the acquisition module 31 receives the original ambient temperature data of the target photovoltaic module sent by an ambient temperature sensor; the acquisition module 31 receives the original relative humidity data of the target photovoltaic module sent by a relative humidity sensor; the acquisition module 31 receives the original solar irradiance data of the target photovoltaic module sent by a solar irradiance sensor; the processing module 32 preprocesses the original current data, original voltage data, original power data, original ambient temperature data, original relative humidity data, and original solar irradiance data to obtain detection data, and the preprocessing includes denoising, filtering, and normalization processing.

[0063] In a possible implementation, the processing module 32 determines a target feature group according to the detection data, which specifically includes: the processing module 32 uses a sliding window to extract the target time points in the current and voltage, and the statistical features corresponding to the target time points, and the statistical features include mean, standard deviation, maximum value, minimum value, and time slope; the processing module 32 generates time series features according to the mean, standard deviation, maximum value, minimum value, and time slope; the acquisition module 31 acquires the reference power output of the target photovoltaic module; the processing module 32 calculates the relative power according to the reference power output and the power output at the current moment; the acquisition module 31 acquires the power output corresponding to the target time point, and the target time point and the current moment are adjacent time points; the processing module 32 calculates the power relative change rate according to the power output corresponding to the target time point and the power output at the current moment, and the relative performance features include relative power and power relative change rate.

[0064] In a possible implementation, the processing module 32 determining the target feature group according to the detection data specifically further includes: the processing module 32 calculates the average value, maximum value, and minimum value corresponding to the environmental data at each current moment according to the ambient temperature, relative humidity, and solar irradiance; the acquisition module 31 acquires the environmental data corresponding to the target time point; the processing module 32 calculates the environmental relative change rate according to the environmental data corresponding to the target time point and the environmental data at the current moment, and the environmental features include average value, maximum value, minimum value, and environmental relative change rate.

[0065] In a possible implementation manner, the processing module 32 inputs the time series features, relative performance features, and environmental features into the support vector machine model to obtain a detection result, which specifically includes: the processing module 32 uses the mean filling method to process the missing values of the time series features, relative performance features, and environmental features to obtain a frame feature group; the processing module 32 calculates the frame feature group through the support vector machine model to obtain the position in the feature space; the processing module 32 determines the positional relationship between the position in the feature space and the hyperplane corresponding to the support vector machine model; the processing module 32 generates a detection result according to the positional relationship.

[0066] In a possible implementation manner, the processing module 32 calculates a probability value based on the positional relationship. The probability value includes a first probability value and a second probability value. The first probability value is used to represent the probability value corresponding to the position in the feature space on the first side of the hyperplane, and the second probability value is used to identify the probability value corresponding to the position in the feature space on the second side of the hyperplane. The first side and the second side are two opposite sides of the hyperplane; if the processing module 32 determines that the position in the feature space is located on the first side and the first probability value is greater than or equal to a preset threshold, it is determined that the detection result indicates normal, and it is determined that the target photovoltaic module does not have the PID effect; if the processing module 32 determines that the position in the feature space is located on the second side and the second probability value is greater than or equal to a preset threshold, it is determined that the detection result indicates abnormal, and it is determined that the target photovoltaic module has the PID effect.

[0067] In a possible implementation manner, the acquisition module 31 acquires training data, and the training data includes a training set and a test set; the processing module 32 uses the training set to train an initial model including a radial basis kernel and hyperparameters to obtain the corresponding relationship between the feature group and the label. The label includes normal and abnormal; the processing module 32 uses the constructed Lagrangian function to optimize the parameters of the initial model, and through repeated iteration, obtains a support vector machine model that meets the preset criteria or converges.

[0068] It should be noted that: when the device provided in the above embodiment realizes its functions, only the above-mentioned division of each functional module is used for illustration. In practical applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0069] This application also provides an electronic device. Refer to Figure 4 , Figure 4 which is a schematic structural diagram of an electronic device provided in an embodiment of this application. The electronic device may include: at least one processor 41, at least one network interface 44, a user interface 43, a memory 45, and at least one communication bus 42.

[0070] Among them, the communication bus 42 is used to implement the connection and communication between these components.

[0071] Among them, the user interface 43 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 43 may further include a standard wired interface and a wireless interface.

[0072] Among them, the network interface 44 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0073] Among them, the processor 41 may include one or more processing cores. The processor 41 uses various interfaces and circuits to connect various parts within the entire server. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 45, and by calling the data stored in the memory 45, the processor 41 executes various functions of the server and processes data. Optionally, the processor 41 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 41 may integrate a combination of one or more of a central processing unit (CPU), a graphics processing unit (GPU), and a modem, etc. Among them, the CPU mainly processes the operating system, user interface, and application programs, etc.; the GPU is responsible for the rendering and drawing of the content to be displayed on the display screen; the modem is used to process wireless communication. It can be understood that the above-mentioned modem may not be integrated into the processor 41 and may be implemented separately through a single chip.

[0074] Among them, the memory 45 may include a Random Access Memory (RAM), or may include a Read-Only Memory. Optionally, the memory 45 includes a non-transitory computer-readable storage medium. The memory 45 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 45 may include a program storage area and a data storage area. Among them, the program storage area can store instructions for implementing the operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area can store the data involved in the above-mentioned method embodiments. Optionally, the memory 45 may also be at least one storage device located far from the aforementioned processor 41. As Figure 4 shown, in the memory 45 as a computer storage medium, there may be included an operating system, a network communication module, a user interface module, and an application program of a photovoltaic module PID detection method.

[0075] In Figure 4 the electronic device shown, the user interface 43 is mainly used to provide an input interface for the user to obtain the data input by the user; and the processor 41 can be used to call the application program of a photovoltaic module PID detection method stored in the memory 45. When executed by one or more processors, the electronic device is caused to execute the method as described in one or more of the above embodiments.

[0076] It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that this application is not limited by the described action sequence, because according to this application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0077] This application also provides a computer-readable storage medium storing instructions. When executed by one or more processors, the electronic device is caused to execute the method as described in one or more of the above embodiments.

[0078] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0079] In several embodiments provided by this application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some service interfaces. The indirect coupling or communication connection of the device or unit can be in electrical or other forms.

[0080] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0081] In addition, in each embodiment of this application, each functional unit can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0082] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in each embodiment of this application. And the aforementioned memory includes: various media such as USB flash drives, mobile hard disks, magnetic disks, or optical discs that can store program codes.

[0083] The above are only exemplary embodiments of the present disclosure and should not be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made in accordance with the teachings of the present disclosure still fall within the scope covered by the present disclosure. Those skilled in the art will easily think of other implementation schemes of the present disclosure after considering the specification and the disclosure of the practical truth. This application aims to cover any variations, uses, or adaptive changes of the present disclosure, and these variations, uses, or adaptive changes follow the general principles of the present disclosure and include common general knowledge or conventional technical means in the technical field not recorded in the present disclosure. The specification and the embodiments are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A method for detecting PID of a photovoltaic module, characterized in that, The method includes: Obtaining detection data for a target photovoltaic module, where the detection data includes current, voltage, power output, ambient temperature, relative humidity, and solar irradiance; Determining a target feature group according to the detection data, where the target feature group includes time series features, relative performance features, and environmental features; Inputting the time series features, relative performance features, and environmental features into a support vector machine model to obtain a detection result; If it is determined that the detection result indicates an anomaly, it is determined that the target photovoltaic module has a PID effect; The determining the target feature group according to the detection data specifically includes: Using a sliding window to extract target time points in the current and voltage, and statistical features corresponding to the target time points, where the statistical features include mean, standard deviation, maximum value, minimum value, and time slope; Generating the time series features according to the mean, the standard deviation, the maximum value, the minimum value, and the time slope; Obtaining the reference power output of the target photovoltaic module; Calculating a relative power according to the reference power output and the power output at the current moment; Obtaining the power output corresponding to the target time point, where the target time point and the current moment are adjacent time points; Calculating a power relative change rate according to the power output corresponding to the target time point and the power output at the current moment, where the relative performance features include the relative power and the power relative change rate; The determining the target feature group according to the detection data specifically further includes: Calculating the average value, maximum value, and minimum value corresponding to the environmental data at each current moment according to the ambient temperature, the relative humidity, and the solar irradiance; Obtaining the environmental data corresponding to the target time point; Calculating an environmental relative change rate according to the environmental data corresponding to the target time point and the environmental data at the current moment, where the environmental features include the average value, the maximum value, the minimum value, and the environmental relative change rate; The inputting the time series features, relative performance features, and environmental features into a support vector machine model to obtain a detection result specifically includes: Performing missing value processing on the time series features, the relative performance features, and the environmental features by using a mean filling method to obtain a framework feature group; Calculating the feature space position of the framework feature group through the support vector machine model; Judging the positional relationship between the feature space position and the hyperplane corresponding to the support vector machine model; Generating the detection result according to the positional relationship; Calculating a probability value based on the positional relationship, where the probability value includes a first probability value and a second probability value, the first probability value is used to represent the probability value corresponding to the feature space position on the first side of the hyperplane, the second probability value is used to identify the probability value corresponding to the feature space position on the second side of the hyperplane, and the first side and the second side are two opposite sides of the hyperplane; If it is determined that the characteristic space position is located on the first side and the first probability value is greater than or equal to a preset threshold, it is determined that the detection result indicates normal, and it is determined that the target photovoltaic module has no PID effect; If it is determined that the characteristic space position is located on the second side and the second probability value is greater than or equal to a preset threshold, it is determined that the detection result indicates abnormal, and it is determined that the target photovoltaic module has a PID effect.

2. The PID detection method for a photovoltaic module according to claim 1, wherein The obtaining of the detection data for the target photovoltaic module specifically includes: Receiving the original current data of the target photovoltaic module sent by a current sensor; Receiving the original voltage data of the target photovoltaic module sent by a voltage sensor; Receiving the original power data of the target photovoltaic module sent by a power sensor; Receiving the original ambient temperature data of the target photovoltaic module sent by an ambient temperature sensor; Receiving the original relative humidity data of the target photovoltaic module sent by a relative humidity sensor; Receiving the original solar irradiance data of the target photovoltaic module sent by a solar irradiance sensor; Preprocessing the original current data, the original voltage data, the original power data, the original ambient temperature data, the original relative humidity data, and the original solar irradiance data to obtain the detection data, and the preprocessing includes denoising, filtering, and normalization processing.

3. The PID detection method for a photovoltaic module according to claim 1, wherein The method further includes: Obtaining training data, where the training data includes a training set and a test set; Training an initial model including a radial basis kernel and hyperparameters with the training set to obtain the corresponding relationship between the feature group and the label, and the label includes normal and abnormal; Optimizing the parameters of the initial model by constructing a Lagrangian function, and through repeated iteration, obtaining the support vector machine model that meets the preset criteria or converges.

4. A PID detection device for a photovoltaic module, characterized in that, The photovoltaic module PID detection device is used to execute the method according to any one of claims 1 to 3. The photovoltaic module PID detection device includes an obtaining module (31) and a processing module (32), where The obtaining module (31) is used to obtain the detection data for the target photovoltaic module, and the detection data includes current, voltage, power output, ambient temperature, relative humidity, and solar irradiance; The processing module (32) is used to determine a target feature group according to the detection data, and the target feature group includes time series features, relative performance features, and environmental features; The processing module (32) is further used to input the time series features, relative performance features, and environmental features into a support vector machine model to obtain a detection result; The processing module (32) is further used to determine that the target photovoltaic module has a PID effect if it is determined that the detection result indicates abnormal.

5. An electronic device, characterized in that, The electronic device includes a processor (41), a memory (45), a user interface (43), and a network interface (44). The memory (45) is used to store instructions. Both the user interface (43) and the network interface (44) are used to communicate with other devices. The processor (41) is used to execute the instructions stored in the memory (45) so that the electronic device executes the method according to any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions which, when executed, execute the method according to any one of claims 1 to 3.

Images