Fault identification method and system for photovoltaic system

Abstract

The invention belongs to the technical field of fault monitoring of photovoltaic systems, and relates to a fault identification method and system of a photovoltaic system, and the method comprises the steps: calculating the performance degradation rate and the operation state characteristic quantity of the photovoltaic system according to an electrical parameter and an environmental parameter in historical operation parameters; performing feature fusion on the performance attenuation rate and the operation state feature quantity to form a comprehensive feature quantity; taking the comprehensive characteristic quantity as input and the fault label as output to train a fault identification model; obtaining new operation parameters in the photovoltaic system, and calculating a comprehensive characteristic quantity; and inputting the comprehensive characteristic quantity into a fault identification model to output a corresponding photovoltaic system fault. According to the method, the long-term attenuation trend and the short-term operation abnormity are combined, so that the model can analyze the fault mode more comprehensively, misjudgment and missed judgment are reduced, meanwhile, hidden faults which develop slowly can be found, sudden faults can be responded in time, and the operation and maintenance efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic system fault monitoring, and more specifically, to a photovoltaic system fault identification method and system. Background Art

[0002] Photovoltaic systems, as a clean energy generation method, have been widely used in various occasions. However, photovoltaic systems may encounter various faults during operation, such as component damage, loose wiring, shadowing, etc. These faults will affect the power generation efficiency of the system and even cause the system to shut down. Existing fault identification methods mostly rely on manual inspections or simple electrical parameter monitoring, which have problems such as low efficiency and poor accuracy. Therefore, it is of great significance to develop an efficient and accurate photovoltaic system fault identification method.

[0003] The Chinese invention patent with the authorization announcement number CN109525194B and the invention name "Photovoltaic panel fault light spot detection and identification method and system" discloses a method for detecting photovoltaic panel fault light spots, which includes obtaining first photovoltaic panel image data, preprocessing the first photovoltaic panel image data, obtaining second photovoltaic panel image data, wherein the image data of the second photovoltaic panel image data is in frames; identifying the QR code anchor point of the second photovoltaic panel image data, parsing the QR code anchor point, and obtaining the anchor point position information and the anchor point azimuth angle information; performing morphological operations on the second photovoltaic panel image data, eliminating interference areas, and identifying photovoltaic panel areas; locating the photovoltaic panel area by combining the anchor point position information and the anchor point azimuth angle information; performing Gaussian filtering on the photovoltaic panel area, eliminating interference points, and identifying faulty light spots; respectively calculating the angles between the QR code anchor point, the light spot connection line, and the photovoltaic panel area edge line, and locating the faulty light spot by combining the anchor point position information and the anchor point azimuth angle information.

[0004] However, this method can only detect when a large-area fault light spot has occurred, and cannot effectively identify other operating faults, resulting in low accuracy of the detection results and failure to fully and accurately reflect the current status of the photovoltaic system.

[0005] Therefore, how to solve the problem of single fault identification method and inability to accurately monitor faults in photovoltaic systems has always been the focus of research. Summary of the invention

[0006] In order to solve the above-mentioned technical problems of single existing fault identification method and inaccurate fault monitoring, the present invention provides solutions in the following aspects.

[0007] In a first aspect, the present invention provides a fault identification method for a photovoltaic system, comprising: calculating a performance decay rate and an operating state characteristic quantity of the photovoltaic system based on electrical parameters and environmental parameters in historical operating parameters, wherein the performance decay rate is positively correlated with the power change rate in the electrical parameters, and the operating state characteristic quantity is calculated based on the deviation rate of the electrical parameters and the deviation rate of the environmental parameters; fusing the performance decay rate and the operating state characteristic quantity to form a comprehensive characteristic quantity; training a fault identification model using the comprehensive characteristic quantity as input and the fault label as output; acquiring new operating parameters in the photovoltaic system and calculating the current comprehensive characteristic quantity; and inputting the current comprehensive characteristic quantity into the trained fault identification model to output the corresponding photovoltaic system fault.

[0008] According to the solution of the present invention, a comprehensive feature quantity can be constructed by combining the performance decay rate and the operating state feature quantity, and a fault identification model can be trained based on the feature quantity. The long-term degradation trend of the photovoltaic system can be realized through the performance decay rate, and the current operating state of the photovoltaic system can be monitored in real time through the operating state feature quantity to identify sudden faults. The combination of long-term decay trends and short-term operating anomalies enables the model to analyze fault modes more comprehensively and reduce misjudgments and missed judgments. At the same time, it can not only detect slowly developing hidden faults, but also respond to sudden faults in a timely manner, thereby improving operation and maintenance efficiency.

[0009] Preferably, the performance decay rate of the photovoltaic system is calculated based on the electrical parameters and environmental parameters in the historical operating parameters, including: calculating the measured power value based on the electrical parameters in the historical operating data, and calculating the power change rate based on the measured power value and the initial power; correcting the power change rate using the environmental parameters, and calculating the performance decay rate based on the correction result, and the performance decay rate is positively correlated with the correction result.

[0010] According to the solution of the present invention, the power change rate is corrected by using environmental parameters and the performance attenuation rate is calculated, so that natural aging and sudden failures can be distinguished and normal attenuation can be avoided from being misjudged as a failure.

[0011] Preferably, the power change rate is corrected using environmental parameters, including: correcting the power change rate using light intensity changes and temperature changes corresponding to the operating time to obtain a correction result, wherein the correction result is positively correlated with the light intensity changes and temperature changes.

[0012] According to the solution of the present invention, the power change rate is corrected by using the changes in light intensity and temperature, which can effectively distinguish between environmental fluctuations and real faults. Combining environmental parameters with electrical parameters can effectively filter environmental noise and improve the robustness of fault detection.

[0013] Preferably, the calculation formula for the performance attenuation rate is:

[0014] In the formula, represents the performance decay rate, represents the initial power, Indicates the measured power value, Indicates the measurement time, Indicates the light intensity under standard test conditions. Indicates the measured temperature. Represents the temperature coefficient of the photovoltaic module, Indicates the temperature under standard test conditions, Indicates the measured light intensity.

[0015] Preferably, the operating state characteristic quantities of the photovoltaic system are calculated based on the electrical parameters and environmental parameters in the historical operating parameters, including: calculating the electrical parameter characteristic quantities based on the electrical parameters in the historical operating parameters, wherein the electrical parameter characteristic quantities include voltage deviation rate, current deviation rate, power deviation rate and voltage-current correlation; calculating the environmental parameter characteristic quantities based on the environmental parameters, wherein the environmental parameter characteristic quantities include light intensity deviation rate, temperature deviation rate, humidity deviation rate and light-temperature correlation; combining the electrical parameter characteristic quantities and the environmental parameter characteristic quantities to form the operating state characteristic quantities.

[0016] In the technical solution of the present invention, by calculating the environmental parameter deviation rate (such as light intensity deviation rate, temperature deviation rate) and combining it with electrical parameters (voltage, current deviation rate), it is possible to effectively filter out environmental noise, improve the robustness of fault detection, and reflect the current operating status of the system in real time and identify sudden faults.

[0017] Preferably, the calculation formula of the electrical parameter characteristic quantity is:

[0018]

[0019]

[0020] In the formula, represents the corresponding deviation rate, hour, Respectively represent voltage, current, power, light intensity, temperature and humidity, Indicates the reference value, represents the voltage-current correlation, represents the covariance of voltage and current, and are the standard deviations of voltage and current, respectively, represents the light-temperature correlation, represents the covariance of light intensity and temperature, and are the standard deviations of light intensity and temperature, respectively.

[0021] Preferably, the electrical parameter characteristic quantity and the environmental parameter characteristic quantity are combined to form the operating state characteristic quantity, including: performing weighted summation on the electrical parameter characteristic quantity and the environmental parameter characteristic quantity to obtain the operating state characteristic quantity.

[0022] According to the technical solution of the present invention, the operating status characteristic quantity can capture abnormal signals (such as current drop, voltage fluctuation) in real time, realize rapid fault location, and combine the electrical parameter characteristic quantity and the environmental parameter characteristic quantity to effectively distinguish between environmental fluctuations and real faults.

[0023] Preferably, the calculation formula of the running state characteristic quantity is:

[0024] In the formula, Indicates the characteristic quantity of the operating state, represents the corresponding deviation rate, represents the weight coefficient of each feature quantity, The weight coefficient representing the voltage-current correlation, A weight coefficient representing the light-temperature correlation.

[0025] Preferably, the performance decay rate and the operating state characteristic quantity are feature-fused to form a comprehensive characteristic quantity, including: combining the operating state characteristic quantity and the performance decay rate to form a comprehensive characteristic quantity.

[0026] According to the solution of the present invention, the performance decay rate can be used to monitor the long-term health status of the photovoltaic system. When the decay rate is abnormally accelerated, potential faults can be warned in advance, and the operating status characteristic quantity can capture abnormal signals in real time to achieve rapid fault location. The combination of the two can not only detect slowly developing hidden faults, but also respond to sudden faults in a timely manner, thereby improving operation and maintenance efficiency.

[0027] In a second aspect, the present invention further provides a photovoltaic system fault identification system, comprising: a processor; a memory storing computer program instructions for identifying photovoltaic system faults, wherein when the computer program instructions are executed by the processor, a photovoltaic system fault identification method as described in the first aspect is implemented.

[0028] The beneficial effects of the present invention are as follows: the fault identification method of the present invention obtains a comprehensive characteristic quantity by combining the performance attenuation rate with the operating state characteristic quantity, and uses the comprehensive characteristic quantity to train the fault identification model process, thereby achieving more accurate fault classification and having stronger anti-interference ability. At the same time, it can realize early fault warning and realize intelligent operation and maintenance. It is suitable for various photovoltaic power stations, rooftop photovoltaic systems and other scenarios, and can significantly improve the reliability and power generation efficiency of photovoltaic systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 is a flow chart showing a fault identification method for a photovoltaic system according to an embodiment of the present invention; Figure 2 is a schematic diagram showing a fault identification system for a photovoltaic system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0031] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0032] Figure 1 is a flow chart showing a fault identification method 100 for a photovoltaic system according to an embodiment of the present invention.

[0033] like Figure 1 As shown, at step S101, the performance attenuation rate and the operating state characteristic quantity of the photovoltaic system are calculated according to the electrical parameters and environmental parameters in the historical operating parameters. The performance attenuation rate is positively correlated with the power change rate in the electrical parameters, and the operating state characteristic quantity is calculated according to the deviation rate of the electrical parameters and the deviation rate of the environmental parameters. The performance attenuation rate and the operating state characteristic quantity of the photovoltaic system are calculated according to the electrical parameters and environmental parameters in the historical operating parameters.

[0034] In actual application scenarios, historical data is collected, including electrical parameters, environmental parameters, and corresponding fault labels (such as normal, component damage, loose wiring, shadow occlusion, etc.). By introducing the performance decay rate, it is possible to distinguish between natural aging and sudden failures, and avoid misjudging normal decay as a fault. For example, if the power of a photovoltaic component continues to decrease slowly (high performance decay rate), the model can determine that it is an aging problem rather than a short circuit fault; if the power suddenly drops (abnormal operating status characteristic quantity), it is determined to be shadow occlusion or component damage.

[0035] In some embodiments, the performance degradation rate is positively correlated with the power change rate in the electrical parameters, and the operating state characteristic quantity is calculated based on the deviation rate of the electrical parameters and the deviation rate of the environmental parameters.

[0036] The performance degradation of photovoltaic systems refers to the phenomenon that the power generation efficiency of photovoltaic modules or systems gradually decreases during long-term operation. Performance degradation may be caused by a variety of factors, such as material aging, environmental corrosion, hot spot effects, etc. In order to accurately evaluate the performance degradation of photovoltaic systems, in addition to considering the status information of photovoltaic modules or systems during operation, it is also necessary to consider the impact of environmental factors.

[0037] In order to effectively identify faults in photovoltaic systems, it is necessary to extract characteristic quantities that can reflect the operating status of the system from electrical parameters and environmental parameters. In some embodiments, electrical parameters may include voltage, current, power, etc. Environmental parameters include light intensity, temperature, and humidity, etc. The output of the photovoltaic system is greatly affected by environmental parameters (light, temperature, humidity), and traditional methods are difficult to distinguish between environmental fluctuations and real faults. The present invention can effectively filter environmental noise and improve the robustness of fault detection by calculating the environmental parameter deviation rate (such as light intensity deviation rate, temperature deviation rate) and combining electrical parameters (voltage, current deviation rate). Based on this, by combining electrical parameters and environmental parameters to form operating status characteristic quantities, it can effectively reflect the current operating status of the photovoltaic system and help to judge sudden faults.

[0038] In some embodiments, the measured power value can be calculated based on the electrical parameters in the historical operation data, and the power change rate can be calculated based on the measured power value and the initial power. The power change rate is corrected using the environmental parameters, and the performance attenuation rate is calculated based on the correction result, and the performance attenuation rate is positively correlated with the correction result.

[0039] Specifically, when the power change rate is corrected using environmental parameters, the power change rate can be corrected using the light intensity change and temperature change corresponding to the operating time to obtain a correction result, wherein the correction result is positively correlated with the light intensity change and the temperature change.

[0040] In an application scenario, the performance degradation rate is calculated as follows:

[0041] In the formula, Indicates the performance attenuation rate in % / year. Indicates the initial power, which can be the initial rated power or the initial measured power of the photovoltaic system. For example, the initial power of the photovoltaic system is measured under standard test conditions (STC: light intensity 1000 W / m², temperature 25°C, AM1.5 spectrum). represents the operating time (usually in years), Indicates the measured power value, that is, the photovoltaic system during operation time The measured power after. Indicates the light intensity under standard test conditions (1000 W / m²), Indicates the measured temperature. represents the temperature coefficient of the PV module (usually -0.3% to -0.5% / °C), Indicates the temperature under standard test conditions, Indicates the measured light intensity.

[0042] In another application scenario, the temperature distribution of photovoltaic modules can be detected by using infrared thermal imagers to identify hot spot effects or local aging areas, and the performance degradation rate can be determined by the area of ​​hot spot effects or local aging areas. In addition, the IV characteristic curve of photovoltaic modules can be measured regularly to analyze the changes in its fill factor (FF) and maximum power point (MPP). Changes in the IV characteristic curve can reflect the performance degradation inside the module.

[0043] In the above-mentioned method of calculating the operating state characteristic quantity of the photovoltaic system based on the electrical parameters and environmental parameters in the historical operating parameters, the electrical parameter characteristic quantity can be calculated based on the electrical parameters in the historical operating parameters, wherein the electrical parameter characteristic quantity includes the voltage deviation rate, the current deviation rate, the power deviation rate and the voltage-current correlation. The environmental parameter characteristic quantity is calculated based on the environmental parameters, wherein the environmental parameter characteristic quantity includes the light intensity deviation rate, the temperature deviation rate, the humidity deviation rate and the light-temperature correlation. The electrical parameter characteristic quantity and the environmental parameter characteristic quantity are combined to form the operating state characteristic quantity. The operating state characteristic quantity can capture abnormal signals (such as current sudden drop, voltage fluctuation) in real time to achieve rapid fault location.

[0044] In some embodiments, the calculation formula of the electrical parameter characteristic quantity is:

[0045]

[0046]

[0047] In the formula, represents the corresponding deviation rate, hour, Respectively represent voltage, current, power, light intensity, temperature and humidity, Indicates the reference value, represents the voltage-current correlation, represents the covariance of voltage and current, and are the standard deviations of voltage and current, respectively, represents the light-temperature correlation, represents the covariance of light intensity and temperature, and are the standard deviations of light intensity and temperature, respectively.

[0048] When the electrical parameter characteristic quantity and the environmental parameter characteristic quantity are combined to form the operating state characteristic quantity, the operating state characteristic quantity can be obtained by performing a weighted summation on the electrical parameter characteristic quantity and the environmental parameter characteristic quantity.

[0049] Furthermore, when combining, corresponding weights may be set for the motion state characteristic quantity and the performance attenuation rate, respectively, to perform weighted processing. Specifically, the calculation formula for the motion state characteristic quantity is:

[0050] In the formula, Indicates the characteristic quantity of the operating state, represents the corresponding deviation rate, represents the weight coefficient of each feature quantity, The weight coefficient representing the voltage-current correlation, The weight coefficient represents the light-temperature correlation. By adjusting the weight coefficient, the characteristics of different photovoltaic systems can be adapted. In one embodiment, the weight coefficient , and , the set value can be selected according to the experience of those skilled in the art. In another embodiment, it can also be determined by optimizing the training data. For example, the model trained in this embodiment can be evaluated by using a test data set to evaluate the accuracy, recall rate, F1 score and other indicators of the fault recognition model, and the feature weight can be adjusted according to the evaluation result.

[0051] At step S102, the performance decay rate and the operating state characteristic quantity are feature fused to form a comprehensive characteristic quantity. In some embodiments, the comprehensive characteristic quantity of each sample can be calculated by combining the vectors corresponding to the performance decay rate and the operating state characteristic quantity into a higher-dimensional vector as a comprehensive characteristic quantity. The fault identification model is trained using the comprehensive characteristic quantity. In some embodiments, when the performance decay rate and the operating state characteristic quantity are feature fused to form a comprehensive characteristic quantity, the operating state characteristic quantity and the performance decay rate can be combined to form a comprehensive characteristic quantity.

[0052] At step S103, the comprehensive feature quantity is used as input and the fault label is used as output to train the fault recognition model. The fault recognition model is constructed using machine learning algorithms (such as support vector machines, neural networks, etc.). By training the fault recognition model, different faults in the photovoltaic system can be recognized. The fault recognition model is trained with historical data and can recognize various fault modes, such as component damage, loose wiring, shadow occlusion, etc. The fault recognition model performs fault diagnosis based on the input data and outputs the fault type and location. According to the identified fault type, the system alarms or automatically processes according to the diagnosis results.

[0053] At step S104, new operating parameters in the photovoltaic system are obtained, and the current comprehensive characteristic quantity is calculated. In some embodiments, the electrical parameters of the photovoltaic system, including voltage, current, power, etc., can be collected in real time by sensors. Environmental parameters, including light intensity, temperature, humidity, etc., are collected by environmental monitoring equipment. Furthermore, the collected electrical parameters and environmental parameters can also be preprocessed, including filtering, normalization, etc. Since this part belongs to the prior art, it will not be repeated here.

[0054] In step S105, the current comprehensive feature quantity is input into the trained fault identification model to output the corresponding photovoltaic system fault. Model training and fault judgment based on the comprehensive feature quantity have high efficiency and accuracy.

[0055] The photovoltaic system fault identification method of the present invention integrates electrical parameters and environmental parameters, constructs a comprehensive feature quantity by combining the performance attenuation rate and the operating state feature quantity, and trains a fault identification model based on the feature quantity, which can more comprehensively reflect the system status. Model training and fault judgment based on the comprehensive feature quantity have high efficiency and accuracy. It is also suitable for various photovoltaic power stations, rooftop photovoltaic systems and other scenarios, and can significantly improve the reliability and power generation efficiency of photovoltaic systems.

[0056] Figure 2 is a schematic diagram showing a fault identification system for a photovoltaic system according to an embodiment of the present invention.

[0057] like Figure 2 As shown, the present invention also provides a photovoltaic system fault identification system, including a processor and a memory, the memory storing computer program instructions for identifying photovoltaic system faults, and when the computer program instructions are executed by the processor, a photovoltaic system fault identification method as described above is implemented.

[0058] The system also includes other components familiar to those skilled in the art, such as a communication bus and a communication interface, whose configuration and functions are known in the art and thus will not be described in detail here.

[0059] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device. Any application or module described in the present invention may be implemented using computer-readable / executable instructions that may be stored or otherwise maintained by such a computer-readable medium.

[0060] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0061] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. A photovoltaic system fault identification method, characterized in that: include: The performance attenuation rate and the operating state characteristic quantity of the photovoltaic system are calculated according to the electrical parameters and the environmental parameters in the historical operating parameters, wherein the performance attenuation rate is positively correlated with the power change rate in the electrical parameters, and the operating state characteristic quantity is calculated according to the deviation rate of the electrical parameters and the deviation rate of the environmental parameters; The performance attenuation rate and the operating status characteristic quantity are fused to form a comprehensive characteristic quantity; Take the comprehensive feature quantity as input and the fault label as output to train the fault recognition model; Obtain new operating parameters in the photovoltaic system and calculate the current comprehensive characteristic quantities; The current comprehensive feature quantity is input into the trained fault identification model to output the corresponding photovoltaic system fault.

2. The photovoltaic system fault identification method according to claim 1, characterized in that: The performance degradation rate of the photovoltaic system is calculated based on the electrical parameters and environmental parameters in the historical operating parameters, including: Calculate the measured power value based on the electrical parameters in the historical operation data, and calculate the power change rate based on the measured power value and the initial power; The power change rate is corrected using environmental parameters, and the performance attenuation rate is calculated based on the correction result, wherein the performance attenuation rate is positively correlated with the correction result.

3. The photovoltaic system fault identification method according to claim 2, characterized in that: The power change rate is corrected using environmental parameters, including: The power change rate is corrected using the light intensity change and the temperature change corresponding to the operating time to obtain a correction result, wherein the correction result is positively correlated with the light intensity change and the temperature change.

4. The photovoltaic system fault identification method according to claim 3, characterized in that: The calculation formula for performance attenuation rate is: In the formula, represents the performance decay rate, represents the initial power, Indicates the measured power value, Indicates the running time, Indicates the light intensity under standard test conditions. Indicates the measured temperature. Represents the temperature coefficient of the photovoltaic module, Indicates the temperature under standard test conditions, Indicates the measured light intensity.

5. The photovoltaic system fault identification method according to claim 1, characterized in that: The operating state characteristic quantities of the photovoltaic system are calculated based on the electrical parameters and environmental parameters in the historical operating parameters, including: Calculating electrical parameter characteristic quantities according to electrical parameters in historical operating parameters, wherein the electrical parameter characteristic quantities include voltage deviation rate, current deviation rate, power deviation rate and voltage-current correlation; Calculating environmental parameter characteristic quantities according to the environmental parameters, wherein the environmental parameter characteristic quantities include a light intensity deviation rate, a temperature deviation rate, a humidity deviation rate, and a light-temperature correlation; The electrical parameter characteristic quantity and the environmental parameter characteristic quantity are combined to form the operating state characteristic quantity.

6. The photovoltaic system fault identification method according to claim 5, characterized in that: The calculation formula of electrical parameter characteristic quantity is: In the formula, represents the corresponding deviation rate, hour, Respectively represent voltage, current, power, light intensity, temperature and humidity, Indicates the reference value, represents the voltage-current correlation, represents the covariance of voltage and current, and are the standard deviations of voltage and current, respectively, represents the light-temperature correlation, represents the covariance of light intensity and temperature, and are the standard deviations of light intensity and temperature, respectively.

7. The photovoltaic system fault identification method according to claim 1, characterized in that: The electrical parameter characteristic quantity and the environmental parameter characteristic quantity are combined to form the operating state characteristic quantity, including: The electrical parameter characteristic quantity and the environmental parameter characteristic quantity are weightedly summed to obtain the operating state characteristic quantity.

8. The photovoltaic system fault identification method according to claim 7, characterized in that: The calculation formula of the operating status characteristic quantity is: In the formula, Indicates the characteristic quantity of the operating state, represents the corresponding deviation rate, represents the weight coefficient of each feature quantity, The weight coefficient representing the voltage-current correlation, A weight coefficient representing the light-temperature correlation.

9. The photovoltaic system fault identification method according to claim 1, characterized in that: The performance attenuation rate and the operating status feature quantity are fused to form a comprehensive feature quantity, including: The operating status characteristic quantity and the performance decay rate are combined to form a comprehensive characteristic quantity.

10. A photovoltaic system fault identification system, characterized in that: include: processor; A memory storing computer program instructions for identifying photovoltaic system faults, wherein when the computer program instructions are executed by the processor, a photovoltaic system fault identification method as described in any one of claims 1 to 9 is implemented.

Images