Photovoltaic fault diagnosis method, system and equipment based on big data analysis and medium

Abstract

The invention relates to the technical field of photovoltaic fault diagnosis, in particular to a photovoltaic fault diagnosis method, system, equipment and medium based on big data analysis, and the method comprises the steps: obtaining meteorological data, thermal image data, power generation data, sensor data and component video data based on a big data platform; performing big data analysis by adopting a deep learning algorithm according to the meteorological data, the thermal image data, the power generation data, the sensor data and the component video data to obtain a group of photovoltaic component data and a group of component data; inputting the photovoltaic module data and the component data into the trained fault diagnosis model, and performing fault diagnosis, fault prediction and fault early warning on the photovoltaic module and the key device to obtain fault diagnosis results of the photovoltaic module and the key device; and the fault diagnosis model adjusts the data feature weight according to the real-time data. The method can perform accurate fault diagnosis on the photovoltaic module and the device.

Description

Technical Field

[0001] This invention relates to the field of photovoltaic fault diagnosis technology, specifically to photovoltaic fault diagnosis methods, systems, equipment, and media based on big data analysis. Background Technology

[0002] In today's energy sector, photovoltaic (PV) power generation has been widely adopted and continues to develop due to its advantages such as cleanliness and sustainability. As the PV industry expands, the requirements for PV system operation and maintenance are also increasing. Data-driven analytics plays a crucial role in fault diagnosis and early warning. By collecting and analyzing large amounts of data during PV system operation, such as parameters like current, voltage, and temperature, it can accurately identify abnormal conditions in the system, providing a solution for precise PV operation and maintenance at this stage.

[0003] While data-driven analytics has made some progress in fault diagnosis and early warning, several technical challenges remain. In data collection, ensuring the accuracy, completeness, and representativeness of the collected data is a challenge. Different operating environments and equipment models can affect data quality, thus impacting the accuracy of fault diagnosis and early warning. Accurately simulating the aging and failure processes of components, auxiliary materials, and key power electronic components under complex operating environments is also a challenge when building failure physical models. Because factors such as temperature, humidity, and light intensity vary widely and interact in actual operating environments, accurately constructing physical models requires considering numerous factors. Furthermore, the accuracy and adaptability of data models need improvement when assessing losses and extrapolating expected lifespan. The significant quality differences between equipment and auxiliary materials from different manufacturers necessitate the development of universal and accurate assessment models. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a photovoltaic fault diagnosis method, system, equipment and medium based on big data analysis to address the shortcomings of the prior art, thereby solving the technical problem that the current failure physics model cannot accurately diagnose the faults of photovoltaic modules.

[0005] The objective of this invention is achieved through the following technical solutions: A photovoltaic fault diagnosis method based on big data analysis includes: Meteorological data, thermal imaging data, power generation data, sensor data, and component video data are acquired through a big data platform; Based on meteorological data, thermal imaging data, power generation data, sensor data, and component video data, deep learning algorithms are used for big data analysis to obtain a set of photovoltaic module data and a set of component data. The photovoltaic module data and component data are input into the trained fault diagnosis model to perform fault diagnosis, fault prediction and fault warning on the photovoltaic module and key components, and obtain the fault diagnosis results of the photovoltaic module and key components. The fault diagnosis model adjusts the weights of data features based on real-time data.

[0006] As a further improvement of the present invention, the photovoltaic module data includes module temperature data, module cumulative irradiance data, module stress data, and pressure resistance and humidity data; the module temperature data is obtained by analyzing thermal imaging data, meteorological data, and power generation data; the module cumulative irradiance data is obtained by analyzing meteorological data; the module stress data is obtained by analyzing video data; and the pressure resistance and humidity data are obtained by analyzing meteorological data and power generation data. The component data includes temperature data of key components, ambient temperature and humidity data, and cumulative load data. The temperature data of key components is obtained from sensor data analysis; the ambient temperature and humidity data is obtained from meteorological data; and the cumulative load data is obtained from power generation data.

[0007] As a further improvement of the present invention, the input data of the photovoltaic module loss factor model also includes historical photovoltaic module failure data and auxiliary material reliability data; The input data for the component loss factor model also includes fault data of key components and reliability data of auxiliary materials.

[0008] As a further improvement of the present invention, the fault diagnosis model includes a photovoltaic module loss factor module and a component loss factor module; the photovoltaic module loss factor module is used to perform dispersion analysis based on the input photovoltaic module data to obtain the fault diagnosis result of the photovoltaic module; the component loss factor module is used to perform vibration and operation analysis based on the component data to obtain the fault diagnosis result of the component.

[0009] As a further improvement of the present invention, the component loss factor module is used to perform loss calculation based on component characteristics, load curve and photovoltaic characteristics to obtain loss curve results, perform temperature calculation based on the loss curve results and temperature characteristics to obtain temperature curve, determine the temperature difference of the component based on the temperature curve, and perform remaining lifetime calculation based on the temperature difference of the component to obtain the lifetime calculation result of the key component.

[0010] As a further improvement of the present invention, the fault diagnosis model adjusts the weights of data features based on real-time data, specifically including: The acquired real-time data features are statistically analyzed to calculate the variance and correlation coefficients of different data features. When the variance of a data feature is lower than a first threshold, the weight of the data feature is reduced accordingly; or when the correlation coefficient of different data features is lower than a second threshold, the weight of the data feature is reduced. When the variance of a data feature is greater than the third threshold, increase its weight; or when the correlation coefficient of different data features increases to the fourth threshold, increase the weight of one of the data features.

[0011] As a further improvement of the present invention, the fault diagnosis results of photovoltaic modules and key components are displayed visually.

[0012] Secondly, the present invention provides a photovoltaic fault diagnosis system based on big data analysis, used to implement the above-mentioned photovoltaic fault diagnosis method based on big data analysis, comprising: The data acquisition module is used to acquire meteorological data, thermal imaging data, power generation data, sensor data, and component video data based on the big data platform; The big data analysis module is used to perform big data analysis based on meteorological data, thermal imaging data, power generation data, sensor data, and component video data, using deep learning algorithms to obtain a set of photovoltaic module data and a set of component data. The fault diagnosis module is used to input photovoltaic module data and component data into the trained fault diagnosis model to perform fault diagnosis, fault prediction and fault warning on photovoltaic modules and key components, and obtain fault diagnosis results for photovoltaic modules and key components. The fault diagnosis model adjusts the weights of data features based on real-time data.

[0013] Thirdly, the present invention provides a computer-readable storage medium for storing one or more programs, the one or more programs including instructions that, when executed by a computing device, cause the computing device to perform the above-described photovoltaic fault diagnosis method based on big data analysis.

[0014] Fourthly, the present invention provides a computing device, comprising: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include steps for performing the above-described photovoltaic fault diagnosis method based on big data analysis.

[0015] The beneficial effects of this invention are as follows: The photovoltaic fault diagnosis method based on big data analysis provided by this invention acquires various types of data, including meteorological data, thermal imaging data, power generation data, sensor data, and component video data, through a big data platform. This provides a rich source of information for fault diagnosis, enabling analysis of photovoltaic modules and key components from multiple perspectives, thus improving the accuracy and comprehensiveness of the diagnosis. Employing deep learning algorithms for big data analysis allows for the automatic learning of complex patterns and features in the data, uncovering potential problems that are difficult to detect using traditional methods. It can adapt to different environmental and operating conditions, providing a more accurate assessment of the operating status of photovoltaic modules and key components. Inputting photovoltaic module data and component data into a trained fault diagnosis model enables fault diagnosis, prediction, and early warning for photovoltaic modules and key components, allowing for the early detection of potential faults, reducing equipment damage and downtime, and improving the reliability and stability of the photovoltaic system. The fault diagnosis model adjusts the weights of data features based on real-time data, dynamically adapting to changes in the photovoltaic system, improving the model's adaptability and robustness, and ensuring accurate fault diagnosis results under different operating conditions. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart of a photovoltaic fault diagnosis method based on big data analysis in an embodiment of the present invention; Figure 2 This is a schematic diagram of the photovoltaic fault diagnosis system based on big data analysis in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device in an embodiment of the present invention. Detailed Implementation

[0018] To make the objectives and technical solutions of this invention clearer and easier to understand, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. The specific embodiments described herein are for illustrative purposes only and are not intended to limit the invention.

[0019] The technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings and specific embodiments. The described embodiments are only some embodiments of the present invention, and not all embodiments.

[0020] Example 1 like Figure 1As shown in the figure, this embodiment provides a photovoltaic fault diagnosis method based on big data analysis, and the specific implementation method is as follows.

[0021] With the help of a big data platform, meteorological data, thermal imaging data, power generation data, sensor data, and component video data were successfully acquired; Based on meteorological data, thermal imaging data, power generation data, sensor data, and component video data, deep learning algorithms are used to conduct big data analysis, thereby obtaining a set of photovoltaic module data and a set of component data. The photovoltaic module data and component data are imported into a carefully trained fault diagnosis model to perform fault diagnosis, fault prediction and fault early warning operations on photovoltaic modules and key components, and finally obtain the fault diagnosis results of photovoltaic modules and key components. This fault diagnosis model can dynamically adjust the feature weights of the data based on real-time data.

[0022] The photovoltaic module data includes module temperature data, module cumulative irradiance data, module stress data, and withstand voltage and humidity data. The module temperature data is obtained by analyzing thermal imaging data, meteorological data, and power generation data. The module cumulative irradiance data is obtained by analyzing meteorological data. The module stress data is obtained by analyzing video data. The withstand voltage and humidity data are obtained by analyzing meteorological data and power generation data. The component data includes temperature data of key components, ambient temperature and humidity data, and cumulative load data. The temperature data of key components is obtained from sensor data analysis; the ambient temperature and humidity data is obtained from meteorological data; and the cumulative load data is obtained from power generation data.

[0023] Specifically, based on the acquired meteorological data, thermal imaging data, power generation data, sensor data, and component video data, we employ advanced deep learning algorithms to conduct comprehensive big data analysis. Through in-depth mining and refined processing of this multi-dimensional data, we can accurately obtain a set of photovoltaic module data and a set of component data.

[0024] Then, the carefully compiled photovoltaic module and component data are accurately input into a rigorously trained fault diagnosis model. During this process, the model performs comprehensive fault diagnosis, accurate fault prediction, and timely fault warnings for the photovoltaic modules and key components, ultimately yielding accurate and reliable fault diagnosis results for the photovoltaic modules and key components. It is worth mentioning that the fault diagnosis model possesses high flexibility and adaptability; it can dynamically adjust the data feature weights based on real-time data changes, thereby ensuring the accuracy and reliability of the diagnostic results.

[0025] Looking further, photovoltaic module data encompasses several important aspects. Module temperature data is obtained through comprehensive analysis of thermal imaging data, meteorological data, and power generation data. Thermal imaging data directly reflects the surface temperature distribution of the module, while environmental factors such as ambient temperature in meteorological data significantly influence module temperature. Power generation data indirectly reflects the module's operating temperature from an energy conversion perspective. Module cumulative irradiance data is primarily obtained through analysis of meteorological data; information such as solar radiation intensity and sunshine duration in meteorological data are key factors in calculating the module's cumulative irradiance. Module stress data is derived from the analysis of video data; by monitoring and analyzing the module's morphological changes under different operating conditions, module stress data can be accurately obtained. Furthermore, withstand voltage and humidity data are obtained through comprehensive analysis of meteorological and power generation data; humidity information in meteorological data and voltage changes during power generation jointly determine the module's withstand voltage and humidity data.

[0026] Meanwhile, the component data also includes important information such as key component temperature data, ambient temperature and humidity data, and cumulative load data. Key component temperature data is obtained through precise analysis of sensor data, which monitors real-time temperature changes in key components. Ambient temperature and humidity data are primarily obtained from meteorological data, which accurately reflects the temperature and humidity conditions of the environment in which the components are located. Cumulative load data is calculated based on power generation data; information such as power output and operating time from the power generation data is crucial for determining the cumulative load data.

[0027] In addition to the data mentioned above, the input data for the photovoltaic module loss factor model also includes historical photovoltaic module failure data and auxiliary material reliability data. Historical photovoltaic module failure data provides the model with past failure occurrences and patterns, helping to more accurately assess module loss. Auxiliary material reliability data affects the module's loss factor from the perspective of material quality. Similarly, the input data for the component loss factor model includes not only critical component failure data but also auxiliary material reliability data. Critical component failure data reflects the failure status of critical components during past operation, providing an important reference for assessing component loss, while auxiliary material reliability data has a significant impact on the overall performance and lifespan of components.

[0028] By comprehensively collecting, deeply analyzing, and rationally applying this data, we can more accurately diagnose the fault conditions of photovoltaic modules and key components, predict potential fault risks, and issue timely warnings, thus providing strong support for the stable operation of photovoltaic systems.

[0029] The component loss factor module is used to calculate losses based on component characteristics, load curves, and photovoltaic characteristics to obtain loss curve results. Based on the loss curve results and temperature characteristics, temperature calculation is performed to obtain temperature curves. Based on the temperature curves, the temperature difference of the components is determined. Based on the temperature difference of the components, the remaining lifetime is calculated to obtain the lifetime calculation results of key components.

[0030] Specifically, this module calculates losses based on component characteristics, load curves, and photovoltaic characteristics. Component characteristics encompass various aspects such as material properties, structural parameters, and electrical performance. For example, resistors made of different materials exhibit different resistance variations with temperature; the capacitance of a capacitor is also affected by its dielectric material and structure. Load curves reflect the changes in current, voltage, and other loads experienced by the component under different operating conditions. Photovoltaic characteristics include parameters such as the output voltage, current, and power of the photovoltaic module, which change with environmental factors such as light intensity and temperature. Through comprehensive analysis of these factors, the module can accurately calculate the losses of the components under different operating conditions, thereby obtaining the loss curve results.

[0031] Next, based on the obtained loss curve results, the module performs temperature calculations in conjunction with the temperature characteristics. The temperature characteristics describe the temperature change pattern of the component under different loss levels. For example, when the loss of a component increases, the heat it generates also increases accordingly; if the heat dissipation conditions remain unchanged, the component's temperature will rise. By combining the loss curve results with the temperature characteristics, the module can calculate the temperature values ​​of the component at different operating times, thus obtaining the temperature curve.

[0032] Then, based on the temperature profile, the module can determine the temperature difference of the components. The temperature difference refers to the amount of temperature change of a component at different operating stages or under different operating conditions. This temperature difference is crucial for assessing the aging degree and lifespan loss of components. A larger temperature difference usually indicates that the component has experienced more drastic changes in thermal stress, which may accelerate its aging and damage.

[0033] Finally, based on the temperature difference between the components, the module calculates the remaining lifetime. This calculation is based on in-depth research into the aging mechanisms and lifetime models of the components. Different types of components may exhibit different aging patterns; for example, capacitors may fail due to electrolyte drying, and transistors may experience performance degradation due to hot carrier effects. By establishing corresponding lifetime models and incorporating key parameters such as temperature difference, the module can accurately calculate the lifetime of critical components.

[0034] The fault diagnosis model adjusts the weights of data features based on real-time data, specifically including: The acquired real-time data features are statistically analyzed to calculate the variance and correlation coefficients of different data features. When the variance of a data feature is lower than a first threshold, the weight of the data feature is reduced accordingly; or when the correlation coefficient of different data features is lower than a second threshold, the weight of the data feature is reduced. When the variance of a data feature is greater than the third threshold, increase its weight; or when the correlation coefficient of different data features increases to the fourth threshold, increase the weight of one of the data features.

[0035] Furthermore, the fault diagnosis results of photovoltaic modules and key components are visualized. Specifically, if in past fault cases, a data feature variance below a certain value often coincided with a fault, this value can be used as a threshold reference for that variance. The correlation coefficient threshold used in fault diagnosis of similar photovoltaic power plants can serve as an initial reference value, which can then be adjusted according to the characteristics of this system.

[0036] Example 2 like Figure 2 As shown, this embodiment provides a photovoltaic fault diagnosis system based on big data analysis, used to implement the photovoltaic fault diagnosis method based on big data analysis in Embodiment 1 above, including: The data acquisition module is used to acquire meteorological data, thermal imaging data, power generation data, sensor data, and component video data based on the big data platform; The big data analysis module is used to perform big data analysis based on meteorological data, thermal imaging data, power generation data, sensor data, and component video data, using deep learning algorithms to obtain a set of photovoltaic module data and a set of component data. The fault diagnosis module is used to input photovoltaic module data and component data into the trained fault diagnosis model to perform fault diagnosis, fault prediction and fault warning on photovoltaic modules and key components, and obtain fault diagnosis results for photovoltaic modules and key components. The fault diagnosis model adjusts the weights of data features based on real-time data.

[0037] Example 3 In another embodiment of the present invention, a terminal device is provided, comprising a processor and a memory. The memory stores a computer program, which includes program instructions. The processor executes 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 (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions to achieve a corresponding method flow or corresponding function. The processor described in this embodiment of the present invention can be used for the operation of a photovoltaic fault diagnosis method based on big data analysis, including: Meteorological data, thermal imaging data, power generation data, sensor data, and component video data are acquired through a big data platform; Based on meteorological data, thermal imaging data, power generation data, sensor data, and component video data, deep learning algorithms are used for big data analysis to obtain a set of photovoltaic module data and a set of component data. The photovoltaic module data and component data are input into the trained fault diagnosis model to perform fault diagnosis, fault prediction and fault warning on the photovoltaic module and key components, and obtain the fault diagnosis results of the photovoltaic module and key components. The fault diagnosis model adjusts the weights of data features based on real-time data.

[0038] Example 4 In another embodiment of the present invention, a storage medium is provided, specifically a computer-readable storage medium (Memory), which is a memory device in a terminal device for storing programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the terminal device and extended storage media supported by the terminal device; it can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, the storage space also stores one or more instructions suitable for loading and execution by a processor, which can be one or more computer programs (including program code). It should be noted that more specific examples (a non-exhaustive list) of the computer-readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0039] Computer-readable storage media also include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable storage medium can also be any readable medium other than a readable storage medium that can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium can be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0040] Program code for performing the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0041] One or more instructions stored in a computer-readable storage medium can be loaded and executed by a processor to implement the corresponding steps of the photovoltaic fault diagnosis method based on big data analysis in the above embodiments; one or more instructions in the computer-readable storage medium are loaded and executed by the processor in the following steps: Meteorological data, thermal imaging data, power generation data, sensor data, and component video data are acquired through a big data platform; Based on meteorological data, thermal imaging data, power generation data, sensor data, and component video data, deep learning algorithms are used for big data analysis to obtain a set of photovoltaic module data and a set of component data. The photovoltaic module data and component data are input into the trained fault diagnosis model to perform fault diagnosis, fault prediction and fault warning on the photovoltaic module and key components, and obtain the fault diagnosis results of the photovoltaic module and key components. The fault diagnosis model adjusts the weights of data features based on real-time data.

[0042] Figure 3 This is a schematic diagram of a computer device provided according to an embodiment of the present invention.

[0043] Please see Figure 3 The terminal device is a computer device. In this embodiment, the computer device 60 includes a processor 61, a memory 62, and a computer program 63 stored in the memory 62 and executable on the processor 61. When executed by the processor 61, the computer program 63 implements the photovoltaic fault diagnosis method based on big data analysis in this embodiment. To avoid repetition, details are omitted here. Alternatively, when executed by the processor 61, the computer program 63 implements the functions of each model / unit in the computational system constituting the photovoltaic fault diagnosis method based on big data analysis in this embodiment. To avoid repetition, details are omitted here.

[0044] Computer device 60 can be a desktop computer, laptop, handheld computer, cloud server, or other computing device. Computer device 60 may include, but is not limited to, a processor 61 and a memory 62. Those skilled in the art will understand that... Figure 3 This is merely an example of computer device 60 and does not constitute a limitation on computer device 60. It may include more or fewer components than shown, or combine certain components, or different components. For example, computer device may also include input / output devices, network access devices, buses, etc.

[0045] The processor 61 may be a central processing unit (CPU), or other general-purpose processors, CPUs, graphics processing units (GPUs), digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, quantum computing-based data processing logic units, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0046] The memory 62 can be an internal storage unit of the computer device 60, such as a hard disk or RAM of the computer device 60. The memory 62 can also be an external storage device of the computer device 60, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc., equipped on the computer device 60.

[0047] Furthermore, the memory 62 may include both internal storage units of the computer device 60 and external storage devices. The memory 62 is used to store computer programs and other programs and data required by the computer device. The memory 62 can also be used to temporarily store data that has been output or will be output.

[0048] Any references to memory, databases, or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0049] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

Claims

1. A photovoltaic fault diagnosis method based on big data analysis, characterized in that, include: Meteorological data, thermal imaging data, power generation data, sensor data, and component video data are acquired through a big data platform; Based on meteorological data, thermal imaging data, power generation data, sensor data, and component video data, deep learning algorithms are used for big data analysis to obtain a set of photovoltaic module data and a set of component data. The photovoltaic module data and component data are input into the trained fault diagnosis model to perform fault diagnosis, fault prediction and fault warning on the photovoltaic module and key components, and obtain the fault diagnosis results of the photovoltaic module and key components. The fault diagnosis model adjusts the weights of data features based on real-time data.

2. The photovoltaic fault diagnosis method based on big data analysis according to claim 1, characterized in that, The photovoltaic module data includes module temperature data, module cumulative irradiance data, module stress data, and pressure resistance and humidity data; the module temperature data is obtained by analyzing thermal imaging data, meteorological data, and power generation data; the module cumulative irradiance data is obtained by analyzing meteorological data. The component stress data is obtained from video data; the pressure resistance and humidity data are obtained from meteorological data and power generation data analysis. The component data includes temperature data of key components, ambient temperature and humidity data, and cumulative load data. The temperature data of key components is obtained by analyzing sensor data; the ambient temperature and humidity data is obtained by analyzing meteorological data. The cumulative load data is obtained from the power generation data.

3. The photovoltaic fault diagnosis method based on big data analysis according to claim 1, characterized in that, The input data for the photovoltaic module loss factor model also includes historical photovoltaic module failure data and auxiliary material reliability data; The input data for the component loss factor model also includes fault data of key components and reliability data of auxiliary materials.

4. The photovoltaic fault diagnosis method based on big data analysis according to claim 3, characterized in that, The fault diagnosis model includes a photovoltaic module loss factor module and a component loss factor module. The photovoltaic module loss factor module is used to perform dispersion analysis based on the input photovoltaic module data to obtain the fault diagnosis results of the photovoltaic module. The component loss factor module is used to perform vibration and operation analysis based on the component data to obtain the fault diagnosis results of the component.

5. The photovoltaic fault diagnosis method based on big data analysis according to claim 1, characterized in that, The component loss factor module is used to calculate the loss based on the component characteristics, load curve and photovoltaic characteristics to obtain the loss curve result. Based on the loss curve result and temperature characteristics, the temperature is calculated to obtain the temperature curve. Based on the temperature curve, the temperature difference of the component is determined. Based on the temperature difference of the component, the remaining lifetime is calculated to obtain the lifetime calculation result of the key component.

6. The photovoltaic fault diagnosis method based on big data analysis according to claim 1, characterized in that, The fault diagnosis model adjusts the weights of data features based on real-time data, specifically including: The acquired real-time data features are statistically analyzed to calculate the variance and correlation coefficients of different data features. When the variance of a data feature is lower than a first threshold, the weight of the data feature is reduced accordingly; or when the correlation coefficient of different data features is lower than a second threshold, the weight of the data feature is reduced. When the variance of a data feature is greater than the third threshold, increase its weight; or when the correlation coefficient of different data features increases to the fourth threshold, increase the weight of one of the data features.

7. The photovoltaic fault diagnosis method based on big data analysis according to claim 3, characterized in that, The fault diagnosis results of photovoltaic modules and key components are displayed visually.

8. A photovoltaic fault diagnosis system based on big data analysis, used to implement the photovoltaic fault diagnosis method based on big data analysis as described in any one of claims 1-7, characterized in that, include: The data acquisition module is used to acquire meteorological data, thermal imaging data, power generation data, sensor data, and component video data based on the big data platform; The big data analysis module is used to perform big data analysis based on meteorological data, thermal imaging data, power generation data, sensor data, and component video data, using deep learning algorithms to obtain a set of photovoltaic module data and a set of component data. The fault diagnosis module is used to input photovoltaic module data and component data into the trained fault diagnosis model to perform fault diagnosis, fault prediction and fault warning on photovoltaic modules and key components, and obtain fault diagnosis results for photovoltaic modules and key components. The fault diagnosis model adjusts the weights of data features based on real-time data.

9. A computer-readable storage medium for storing one or more programs, characterized in that, The one or more programs include instructions that, when executed by a computing device, cause the computing device to perform the photovoltaic fault diagnosis method based on big data analysis as described in any one of claims 1 to 7.

10. A computing device, characterized in that, include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including steps for performing the photovoltaic fault diagnosis method based on big data analysis according to any one of claims 1 to 7.

Images