Photovoltaic equipment intelligent monitoring and fault diagnosis method and related device

Abstract

The invention provides a photovoltaic equipment intelligent monitoring and fault diagnosis method and a related device. The method comprises the following specific steps: inputting an actually measured I-V characteristic curve into an intelligent monitoring and fault diagnosis model to obtain a photovoltaic equipment fault diagnosis result; wherein the intelligent monitoring and fault diagnosis model comprises a data format conversion operator and a photovoltaic fault diagnosis model operator, and the photovoltaic fault diagnosis model operator comprises an offline training operator fit () and a judgment operator predict (); the data format conversion operator is used for converting original data stored in rows into data stored in columns; the off-line training operator fit () is used for preprocessing the actually measured I-V characteristic curve; and the judgment operator predict () is used for judging the environment state and performing fault diagnosis on the actually measured I-V characteristic curve and the corresponding environment measurement under the stable environment to obtain the fault type. According to the invention, through the intelligent monitoring and fault diagnosis model, real-time monitoring and fault diagnosis of the photovoltaic equipment are realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of photovoltaic equipment monitoring, and in particular to a photovoltaic equipment intelligent monitoring and fault diagnosis method and related devices. Background Art

[0002] With the increasing global awareness of environmental protection and the transformation of energy structure, the development of renewable energy has ushered in unprecedented opportunities. Photovoltaic power generation, as an important branch of renewable energy, has been widely used around the world due to its advantages such as cleanliness, renewability and wide distribution. However, photovoltaic equipment faces many challenges in actual operation.

[0003] Environmental factors are a major challenge for the operation of photovoltaic equipment. Changes in natural conditions such as solar irradiance, temperature, humidity, and wind speed will affect the performance of photovoltaic equipment. For example, high temperatures will cause the efficiency of photovoltaic cells to decrease, while changes in humidity and wind speed may affect the heat dissipation and insulation performance of photovoltaic equipment. In addition, the coverage of pollutants such as sand, dust, and bird droppings will also reduce the power generation efficiency of photovoltaic equipment. Equipment aging is another problem that cannot be ignored. As the operating time increases, the materials, components, and connecting parts of photovoltaic equipment will gradually age, resulting in performance degradation or even failure. These failures may manifest as broken cells, loose connection wires, inverter failures, etc., which seriously affect the power generation efficiency and stability of photovoltaic power stations.

[0004] Traditional photovoltaic equipment monitoring and fault diagnosis methods mainly rely on manual inspections and regular inspections. This method is not only inefficient, but also difficult to capture equipment status changes in real time. Since photovoltaic power stations are usually distributed in remote areas, manual inspections require a lot of time and manpower costs. At the same time, the frequency and accuracy of regular inspections are also limited, and potential faults cannot be discovered and handled in a timely manner. In order to improve the operating efficiency and reliability of photovoltaic equipment, it is particularly important to realize intelligent monitoring and fault diagnosis. However, the existing fault diagnosis methods based on mathematical models and data-driven still have many problems. For example, some models are not accurate and cannot accurately reflect the actual operating status of photovoltaic equipment; some methods are difficult to solve parameters, resulting in the inability to apply the model to actual scenarios; and some methods have limited fault diagnosis types and cannot cover all possible fault conditions. Therefore, the development of an efficient and accurate photovoltaic equipment intelligent monitoring and fault diagnosis method and related devices is of great significance to ensure the safe and stable operation of photovoltaic power stations. Summary of the invention

[0005] In order to solve the problems existing in the prior art, the present invention proposes a photovoltaic equipment intelligent monitoring and fault diagnosis method and related devices, aiming to achieve real-time monitoring and fault diagnosis of photovoltaic equipment through an intelligent monitoring and fault diagnosis model.

[0006] To achieve the above purpose, the present invention provides the following technical solution: a photovoltaic equipment intelligent monitoring and fault diagnosis method, the specific steps are as follows: Obtain the measured IV characteristic curve; The measured IV characteristic curve is input into the intelligent monitoring and fault diagnosis model to perform fault diagnosis and obtain the fault diagnosis result of the photovoltaic equipment; Among them, the intelligent monitoring and fault diagnosis model includes a data format conversion operator and a photovoltaic fault diagnosis model operator, wherein the photovoltaic fault diagnosis model operator includes an offline training operator fit() and a judgment operator predict(); the data format conversion operator is used to convert the original row-stored data into column-stored data; the offline training operator fit() is used to preprocess the measured IV characteristic curve; the judgment operator predict() is used to judge the environmental state, and perform fault diagnosis on the measured IV characteristic curve and the corresponding environmental measurement under stable environment to obtain the fault type.

[0007] Furthermore, the offline training operator fit() includes a data reading function, an IV data screening function, a parameter training function, a particle swarm parameter search function and an IV reconstruction function, wherein the data reading function is used to convert the offline historical IV data read in by column from a string type to a floating point type; the IV data screening function is used to screen out IV data with sudden irradiance changes in the read offline historical IV data, and eliminate the influence of the mismatch between irradiance and short-circuit points on subsequent analysis; the parameter training function is used to filter, interpolate and smooth the IV data to improve the quality of the IV data; the particle swarm parameter search function is used to solve the parameters of the mathematical model of the photovoltaic array; and the IV reconstruction function is used to solve the physical equations of the photovoltaic array.

[0008] Furthermore, the judgment operator predict() is composed of an environmental stability judgment function and a fault diagnosis function. The environmental stability judgment function performs environmental stability judgment based on online environmental measurement and outputs the environmental state to the fault diagnosis function; the fault diagnosis function performs fault diagnosis based on online IV data and corresponding environmental measurement and environmental state to obtain the fault type.

[0009] Furthermore, when the deviation between the theoretical output power of the photovoltaic array obtained by using the photovoltaic array mathematical model and the measured photovoltaic array output power is less than the fault detection threshold, it is considered that there is no fault, and the measured IV characteristic curve is stopped from being input into the intelligent monitoring and fault diagnosis model for fault diagnosis.

[0010] Furthermore, when the deviation between the theoretical output power of the photovoltaic array obtained by using the photovoltaic array mathematical model and the measured photovoltaic array output power is greater than the fault detection threshold, it is considered that a suspected fault has occurred. When the suspected fault is detected continuously for more than 3 times, the measured IV characteristic curve is obtained, and the measured IV characteristic curve is input into the intelligent monitoring and fault diagnosis model for fault diagnosis to obtain the fault diagnosis result of the photovoltaic equipment.

[0011] Furthermore, the photovoltaic array mathematical model is a single diode model, a particle swarm optimization algorithm is used to extract model parameters, a conventional iterative algorithm is used to reconstruct the IV characteristic curve, and the particle swarm optimization algorithm is used to adjust the hyperparameters of the photovoltaic array mathematical model.

[0012] The present invention also provides a photovoltaic equipment intelligent monitoring and fault diagnosis system, including a data acquisition module and a fault diagnosis module, wherein: The data acquisition module is used to obtain the measured IV characteristic curve; The fault diagnosis module is used to input the measured IV characteristic curve into the intelligent monitoring and fault diagnosis model to perform fault diagnosis and obtain the fault diagnosis result of the photovoltaic equipment; Among them, the intelligent monitoring and fault diagnosis model includes a data format conversion operator and a photovoltaic fault diagnosis model operator, wherein the photovoltaic fault diagnosis model operator includes an offline training operator fit() and a judgment operator predict(); the data format conversion operator is used to convert the original row-stored data into column-stored data; the offline training operator fit() is used to preprocess the measured IV characteristic curve; the judgment operator predict() is used to judge the environmental state, and perform fault diagnosis on the measured IV characteristic curve and the corresponding environmental measurement under stable environment to obtain the fault type.

[0013] The present invention provides a terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned method for intelligent monitoring and fault diagnosis of photovoltaic equipment are implemented.

[0014] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned photovoltaic equipment intelligent monitoring and fault diagnosis method are implemented.

[0015] The present invention also provides a computer program product, including a computer program, which implements the steps of the above-mentioned photovoltaic equipment intelligent monitoring and fault diagnosis method when executed by a processor.

[0016] Compared with the prior art, the present invention has at least the following beneficial effects: The present invention provides a method for intelligent monitoring and fault diagnosis of photovoltaic equipment. The intelligent fault diagnosis algorithm combines an offline training operator and a judgment operator, can efficiently process and analyze the measured IV characteristic curve, accurately identify the fault type of the photovoltaic equipment, and realize accurate diagnosis of various photovoltaic array fault types; the fault diagnosis method of the present invention can monitor the operation status and fault information of the photovoltaic equipment in real time, and can timely discover and handle potential faults. This not only reduces the frequency of manual inspections and regular inspections, but also improves the monitoring efficiency, so that the operation and maintenance personnel can respond to and handle faults more quickly; the fault diagnosis method of the present invention can significantly reduce the downtime and maintenance costs caused by equipment failure. This helps to improve the operation efficiency and economic benefits of photovoltaic power stations, so that the operation and maintenance costs are effectively controlled; the fault diagnosis method of the present invention helps to timely discover and handle potential problems in photovoltaic equipment, thereby enhancing the stability and reliability of photovoltaic power stations. This helps to ensure that photovoltaic power stations can generate electricity continuously and stably, and provide reliable power supply for power grids. The fault diagnosis method of the present invention can enable operation and maintenance personnel to understand the operation status of photovoltaic equipment in a timely manner and quickly handle faults. This helps to improve the utilization rate of photovoltaic equipment, so that the equipment can be in normal working state for a longer time, thereby increasing the power generation.

[0017] The present invention provides an intelligent monitoring and fault diagnosis method to provide strong support for the intelligent development of the photovoltaic industry. By introducing intelligent algorithms and advanced technologies, the operation and maintenance of photovoltaic power stations are made more intelligent and automated, which helps promote the transformation and upgrading of the entire photovoltaic industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 Photovoltaic array modeling effect diagram (hyperparameter group 1); Figure 2 Photovoltaic array modeling effect diagram (hyperparameter group 2); Figure 3 Photovoltaic array modeling effect diagram (hyperparameter group 3); Figure 4 Schematic diagram of the photovoltaic array modeling method flow; Figure 5 Schematic diagram of intelligent monitoring and fault diagnosis algorithm of photovoltaic strings based on measured IV characteristics; Figure 6 Schematic diagram of the intelligent monitoring and fault diagnosis model framework; Figure 7 Schematic diagram of offline training operator fit(); Figure 8 Schematic diagram of the judgment operator predict(); Fig. 9 Comparison chart of series and parallel impedance characteristic values. DETAILED DESCRIPTION

[0019] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0020] The present invention provides a photovoltaic equipment intelligent monitoring and fault diagnosis method, comprising the following steps: Step 1: The realization of fault diagnosis of photovoltaic field equipment depends on the accurate establishment of the corresponding mathematical model. The main steps of establishing the mathematical model of photovoltaic array are as follows: 1. Based on the theoretical foundation and analysis of photovoltaic array electrical physics: In order to describe the nonlinear IV characteristics of the photovoltaic array, it is necessary to analyze the theoretical model of the photovoltaic array. At present, the single diode model is commonly used in the modeling of solar cells. The output current of the photovoltaic module is: (1) In the formula, I ph is the photogenerated current; I 0 is the reverse saturation current of the PN junction in the photovoltaic module; q is the charge constant; R s is the equivalent series resistance; R sh is the equivalent parallel resistance; a is the diode ideality coefficient; K is the Boltzmann constant; T is the temperature of the PV module; I , V are the output current and voltage of the PV module respectively; I ph The value of is: (2) In the formula, I SC,STC is the short-circuit current under standard test conditions (STC), α is the temperature coefficient of the short-circuit current point. G is the coplanar irradiance. T STC It is the reference temperature under STC, i.e. 25°C. G STC is the reference irradiance under STC, i.e. 1000W / m 2 . I 0 The value of is: (3) in, Eg is the bandgap width of the semiconductor material, I 0,STC is the equivalent reverse saturation current of the PN junction of the photovoltaic module under STC. Its value is: (4) In the formula V OC,STC It is the open circuit voltage under STC.

[0021] 2. Establishment of mathematical model of photovoltaic array: In order to establish a mathematical model of a photovoltaic array, the calculation speed and accuracy of the modeling should be guaranteed first. Since equation (1) is an implicit equation, iterative calculation is required to obtain an approximate solution. Commonly used iterative algorithms include Newton iteration method, parabola method, Stephenson method, etc. However, different iterative methods have different convergence speeds when solving the above equations. Usually, the photovoltaic module is the smallest unit analyzed in the photovoltaic array. Considering that the photovoltaic array may be affected by local shading, the equivalent absorbed irradiance of each photovoltaic module may be different. Therefore, it is necessary to calculate the output characteristics of the photovoltaic module under different environmental conditions, and finally obtain the IV curve of the entire photovoltaic array by superimposing the IV curves of each photovoltaic module. By analyzing the IV curve of the photovoltaic array, for example, when a photovoltaic module is partially shaded, the short-circuit current of the abnormal photovoltaic module is less than the short-circuit current of other normal photovoltaic modules. Because the photovoltaic modules in the string are connected in series, when the current of the normal photovoltaic module in the string is greater than the short-circuit current of the locally shaded photovoltaic module, the shaded photovoltaic module will become a load, causing a negative bias voltage. At this time, the bypass diode of the photovoltaic module with local shadow is turned on. The above-mentioned photovoltaic module mathematical model and photovoltaic array modeling method can be combined to use the Stephenson iteration method to quickly calculate the theoretical IV curve of the photovoltaic array under different environmental conditions. The specific process is as follows: Figure 4 As shown; 3. Through equations (1)-(4), the series resistance of the photovoltaic array mathematical model parameters can be extracted R s , Parallel resistance R sh and ideality factor a The model parameters are further estimated by the above three parameters and environmental radiation and temperature I ph and I 0 However, these model parameters will change with the degradation of the photovoltaic array, so the above parameters need to be calibrated and preprocessed before analysis. The output IV curve of the photovoltaic array is also affected by the ambient irradiance and temperature, so it is also necessary to calibrate the parameters under different environmental conditions, and finally obtain the corrected parameters relative to the environmental parameters. After establishing the above photovoltaic array mathematical model, the photovoltaic equipment monitoring data can be compared with the above theoretical model estimation results to preliminarily perform photovoltaic equipment fault diagnosis, such as Figure 5 shown.

[0022] The present invention is based on a single diode model to determine the three parameters of the photovoltaic array mathematical model (series resistance R s , parallel resistance R sh and ideal factor a), and further estimate the model parameter I according to the ambient irradiance and temperature ph and I 0 In order to solve the problem of difficulty in parameter solution, the particle swarm optimization algorithm is used to extract model parameters, and the conventional iterative algorithm is used to reconstruct IV data. By adjusting the hyperparameters of the particle swarm optimization algorithm, the accuracy of model parameter extraction is improved. The photovoltaic array modeling effect diagram is shown in the figure. Figure 1~Figure 3 , it can be seen that the reconstructed curve gradually approaches and fits the original curve.

[0023] Step 2: Build an intelligent monitoring and fault diagnosis model: like Figure 6 As shown, the photovoltaic equipment intelligent monitoring and fault diagnosis model includes a data format conversion operator and a photovoltaic fault diagnosis model operator, wherein the photovoltaic fault diagnosis model operator includes an offline training operator fit() and a judgment operator predict(), specifically: The data format conversion operator is used to convert the original row-based data into column-based data. The offline training operator fit() includes data reading function, IV data screening function, parameter training function, particle swarm parameter search function and IV reconstruction function. The data reading function is used to convert the offline historical IV data read in by column from string type to floating point type; the IV data screening function is used to filter out the IV data with sudden irradiance changes in the read offline historical IV data, and eliminate the influence of the mismatch between irradiance and short-circuit point on subsequent analysis; the parameter training function is used to filter, interpolate and smooth the IV data to improve the quality of IV data; the particle swarm parameter search function is used to solve the parameters of the mathematical model of the photovoltaic array; the IV reconstruction function is used to solve the physical equations of the photovoltaic array.

[0024] like Figure 7 As shown, the offline training operator fit() of the present invention realizes parameter training and can output the model API file of the corresponding photovoltaic power station according to the historical IV data and the ring test. In addition, the offline training operator fit() of the present invention preprocesses the historical IV data and matches the corresponding ring test to further realize parameter optimization and correction. fit() eliminates the influence of the ring test error and takes into account the changes in the photovoltaic model parameters in different seasons, which is the basis for subsequent fault diagnosis.

[0025] like Figure 8 As shown, the judgment operator predict() is composed of an environmental stability judgment function and a fault diagnosis function. It performs fault diagnosis under environmental stability and outputs the environmental state and fault type.

[0026] The predict() part of the judgment operator has completed functions such as data reading, data preprocessing, and IV curve data analysis. Data reading and data preprocessing are the same as fit(), and are directly called from the packaged library. IV curve data analysis mainly realizes the derivation of current data, which is convenient for subsequent fault analysis.

[0027] The environmental stability judgment function makes stability judgments on the online ring test to avoid misjudgments caused by sudden changes in irradiance. If the judgment result is a fluctuation, the fault diagnosis is terminated. In a stable environment, fault diagnosis is performed based on online IV data and ring test. Considering that there may be errors in the measured irradiance and temperature, the environmental irradiance and temperature are corrected to improve the accuracy of the mathematical model of the photovoltaic array. At the same time, based on the modeling results of the trained power generation model, the characteristic value differences between fault types such as series impedance anomaly and parallel impedance anomaly and fault-free data are compared and analyzed to realize the diagnosis of various photovoltaic array fault types. There are 14 types of photovoltaic array faults that can be diagnosed, as follows:

[0028] Taking a photovoltaic power station as an example, the present invention establishes a photovoltaic array mathematical model and develops an intelligent monitoring and fault diagnosis model for the existing data types of the big data platform. In addition, considering that the measured irradiance and temperature may have errors, the ambient irradiance and temperature are corrected through the model to improve the accuracy of the photovoltaic array mathematical model. The irradiance and temperature trends of the corrected photovoltaic array mathematical model are basically consistent with the measured values. A comparative analysis was conducted on the fault data and fault-free data of the series impedance abnormality and parallel impedance abnormality fault types, such as Fig. 9 shown.

[0029] The following are device embodiments of the present invention, which can be used to perform method embodiments of the present invention. For details not disclosed in the device embodiments, please refer to the method embodiments of the present invention.

[0030] In one embodiment of the present invention, a photovoltaic equipment intelligent monitoring and fault diagnosis system is provided, including a data acquisition module and a fault diagnosis module, wherein: the data acquisition module is used to obtain a measured IV characteristic curve; the fault diagnosis module is used to input the measured IV characteristic curve into an intelligent monitoring and fault diagnosis model for fault diagnosis, and obtain a photovoltaic equipment fault diagnosis result; Among them, the intelligent monitoring and fault diagnosis model includes a data format conversion operator and a photovoltaic fault diagnosis model operator, wherein the photovoltaic fault diagnosis model operator includes an offline training operator fit() and a judgment operator predict(); the data format conversion operator is used to convert the original row-stored data into column-stored data; the offline training operator fit() is used to preprocess the measured IV characteristic curve; the judgment operator predict() is used to judge the environmental state, and perform fault diagnosis on the measured IV characteristic curve and the corresponding environmental measurement under stable environment to obtain the fault type.

[0031] In another embodiment of the present invention, a terminal device is provided, the terminal device includes a processor and a memory, the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc., which are the computing core and control core of the terminal, which are suitable for implementing one or more instructions, and are specifically suitable for loading and executing one or more instructions to implement the corresponding method flow or corresponding functions; the processor described in the embodiment of the present invention can be used for the operation of the Internet advertising false traffic identification method.

[0032] In another embodiment of the present invention, the present invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a terminal device for storing programs and data. It is understandable that the computer-readable storage medium here can include both the built-in storage medium in the terminal device and the extended storage medium supported by the terminal device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the method for identifying false traffic of Internet advertisements in the above embodiment.

[0033] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0034] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0035] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1A function specified in one or more boxes.

[0036] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0037] By implementing the present invention, the photovoltaic power station successfully realizes intelligent monitoring and fault diagnosis of photovoltaic equipment, improves the operating efficiency and reliability of the equipment, and reduces the operation and maintenance costs. At the same time, the method and related devices of the present invention are also applicable to other types of photovoltaic power stations and photovoltaic equipment, and have broad application prospects and promotion value.

[0038] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A photovoltaic equipment intelligent monitoring and fault diagnosis method, characterized in that: The specific steps are as follows: Obtain the measured IV characteristic curve; The measured IV characteristic curve is input into the intelligent monitoring and fault diagnosis model to perform fault diagnosis and obtain the fault diagnosis result of the photovoltaic equipment; Among them, the intelligent monitoring and fault diagnosis model includes a data format conversion operator and a photovoltaic fault diagnosis model operator, wherein the photovoltaic fault diagnosis model operator includes an offline training operator fit() and a judgment operator predict(); the data format conversion operator is used to convert the original row-stored data into column-stored data; the offline training operator fit() is used to preprocess the measured IV characteristic curve; the judgment operator predict() is used to judge the environmental state, and perform fault diagnosis on the measured IV characteristic curve and the corresponding environmental measurement under stable environment to obtain the fault type.

2. A photovoltaic equipment intelligent monitoring and fault diagnosis method according to claim 1, characterized in that: The offline training operator fit() includes a data reading function, an IV data screening function, a parameter training function, a particle swarm parameter search function and an IV reconstruction function, wherein the data reading function is used to convert the offline historical IV data read in by column from a string type to a floating point type; the IV data screening function is used to screen out IV data with sudden changes in irradiance in the read offline historical IV data, and eliminate the influence of the mismatch between irradiance and short-circuit point on subsequent analysis; the parameter training function is used to filter, interpolate and smooth the IV data to improve the quality of the IV data; the particle swarm parameter search function is used to solve the parameters of the mathematical model of the photovoltaic array; and the IV reconstruction function is used to solve the physical equations of the photovoltaic array.

3. A photovoltaic equipment intelligent monitoring and fault diagnosis method according to claim 1, characterized in that: The judgment operator predict() is composed of an environmental stability judgment function and a fault diagnosis function. The environmental stability judgment function performs environmental stability judgment based on online environmental measurement and outputs the environmental status to the fault diagnosis function. The fault diagnosis function performs fault diagnosis based on online IV data and corresponding environmental measurement and environmental status to obtain the fault type.

4. A photovoltaic equipment intelligent monitoring and fault diagnosis method according to claim 1, characterized in that: When the deviation between the theoretical output power of the photovoltaic array obtained by using the photovoltaic array mathematical model and the measured photovoltaic array output power is less than the fault detection threshold, it is considered that there is no fault, and the measured IV characteristic curve is stopped from being input into the intelligent monitoring and fault diagnosis model for fault diagnosis.

5. A photovoltaic equipment intelligent monitoring and fault diagnosis method according to claim 1, characterized in that: When the deviation between the theoretical output power of the photovoltaic array obtained by using the photovoltaic array mathematical model and the measured photovoltaic array output power is greater than the fault detection threshold, it is considered that a suspected fault has occurred. When the suspected fault is detected continuously for more than 3 times, the measured IV characteristic curve is obtained and input into the intelligent monitoring and fault diagnosis model for fault diagnosis to obtain the fault diagnosis result of the photovoltaic equipment.

6. A photovoltaic equipment intelligent monitoring and fault diagnosis method according to claim 4 or 5, characterized in that: The photovoltaic array mathematical model is a single diode model, a particle swarm optimization algorithm is used to extract model parameters, a conventional iterative algorithm is used to reconstruct the IV characteristic curve, and the particle swarm optimization algorithm is used to adjust the hyperparameters of the photovoltaic array mathematical model.

7. A photovoltaic equipment intelligent monitoring and fault diagnosis system, characterized in that: It includes data acquisition module and fault diagnosis module, among which: The data acquisition module is used to obtain the measured IV characteristic curve; The fault diagnosis module is used to input the measured IV characteristic curve into the intelligent monitoring and fault diagnosis model to perform fault diagnosis and obtain the fault diagnosis result of the photovoltaic equipment; Among them, the intelligent monitoring and fault diagnosis model includes a data format conversion operator and a photovoltaic fault diagnosis model operator, wherein the photovoltaic fault diagnosis model operator includes an offline training operator fit() and a judgment operator predict(); the data format conversion operator is used to convert the original row-stored data into column-stored data; the offline training operator fit() is used to preprocess the measured IV characteristic curve; the judgment operator predict() is used to judge the environmental state, and perform fault diagnosis on the measured IV characteristic curve and the corresponding environmental measurement under stable environment to obtain the fault type.

8. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of a photovoltaic equipment intelligent monitoring and fault diagnosis method as described in any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by the processor, the steps of the photovoltaic equipment intelligent monitoring and fault diagnosis method as described in any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of a photovoltaic equipment intelligent monitoring and fault diagnosis method as described in any one of claims 1 to 6 are implemented.

Images