Integrated method, system, device, equipment and medium for operation and maintenance data acquisition and analysis and fault prediction and diagnosis of photovoltaic power station

Abstract

The invention provides a photovoltaic power station operation and maintenance data acquisition and analysis and fault prediction and diagnosis integration method, system, device and equipment and a medium, and the method comprises the following steps: 1, obtaining a damage evaluation characteristic value of each key part of a photovoltaic module in a target power station, and taking the damage evaluation characteristic value as a first characteristic value; acquiring a damage evaluation characteristic value of each key part of the photovoltaic bracket as a second characteristic value; acquiring an electric signal offset characteristic index of an inverter MPPT circuit in the target power station as a third characteristic value; 2, preprocessing the obtained first feature value, the second feature value and the third feature value to obtain corresponding feature vectors; 3, predicting a potential fault of the target photovoltaic power station by using the obtained feature vector; early warning can be carried out before the photovoltaic power station breaks down, operation and maintenance personnel are helped to take measures in time, and occurrence or expansion of the fault is avoided; and meanwhile, the downtime of the photovoltaic power station can be reduced, and the operation efficiency and the generating capacity of the power station can be improved.

Description

Technical Field

[0001] The present invention belongs to the field of photovoltaic power generation technology, and more specifically, particularly relates to an integrated method, system, device, equipment and medium for photovoltaic power station operation and maintenance data collection and analysis and fault prediction and diagnosis. Background Art

[0002] As an important part of renewable energy, photovoltaic power stations play an increasingly important role in the global energy transformation. The operation and maintenance management of photovoltaic power stations involves multiple links such as data collection, analysis and fault prediction and diagnosis, which is crucial to ensure the efficient operation and long-term reliability of photovoltaic power stations. Effective operation and maintenance management can improve the power generation efficiency of photovoltaics, extend the life of equipment, and reduce maintenance costs.

[0003] At present, the operation and maintenance management of photovoltaic power plants mainly relies on the traditional regular inspection and passive maintenance mode. This mode has many limitations, such as incomplete data collection, insufficient analysis depth, and low prediction accuracy. At the same time, due to the complexity and harshness of the offshore environment, traditional operation and maintenance methods often fail to detect and handle potential equipment failures in a timely manner, resulting in unnecessary downtime and economic losses. In addition, the existing operation and maintenance systems usually lack integrity and coordination, and the data sharing and linkage between the various subsystems are insufficient, making it difficult to achieve comprehensive status monitoring and intelligent decision-making.

[0004] Therefore, there is an urgent need for a comprehensive operation and maintenance method that can integrate multi-dimensional data collection, real-time analysis and processing, intelligent fault prediction, and collaborative decision-making. This method should be able to adapt to the special environment of photovoltaic power plants, achieve comprehensive data collection and secure transmission, provide accurate fault prediction and diagnosis, and support intelligent operation and maintenance decisions. At the same time, the method also needs to be scalable and adaptable to cope with the ever-changing technical environment and operational needs. Solving these technical problems will significantly improve the operation and maintenance efficiency and reliability of photovoltaic power plants, and make an important contribution to the sustainable development of renewable energy. Summary of the invention

[0005] The purpose of the present invention is to provide an integrated method, system, device, equipment and medium for photovoltaic power station operation and maintenance data collection and analysis and fault prediction and diagnosis, which solves the problems that existing operation and maintenance systems usually lack integrity and coordination, insufficient data sharing and linkage between subsystems, and difficulty in achieving comprehensive status monitoring and intelligent decision-making.

[0006] In order to achieve the above object, the technical solution adopted by the present invention is: The present invention provides an integrated method for photovoltaic power station operation and maintenance data collection and analysis and fault prediction and diagnosis, comprising the following steps: Step 1, obtaining a damage assessment characteristic value of each key part of a photovoltaic module in a target power station as a first characteristic value; Obtain the damage assessment characteristic value of each key part of the photovoltaic bracket as the second characteristic value; Obtaining an electrical signal offset characteristic index of an inverter MPPT circuit in a target power station as a third characteristic value; Step 2, preprocessing the first eigenvalue, the second eigenvalue and the third eigenvalue to obtain corresponding eigenvectors; Step 3: Use the obtained feature vector to predict the potential failure of the target photovoltaic power station.

[0007] Preferably, in step 1, the damage assessment characteristic value of each key part of the photovoltaic module in the target power station is obtained as the first characteristic value, and the specific method is: Obtain the electromagnetic impedance spectrum of each key part of the photovoltaic module; Calculate the root mean square deviation of the electromagnetic impedance spectrum of each key part; A mapping relationship between the root mean square deviation and the degree of loss is established, and SVR is used for fitting to obtain the damage assessment eigenvalue of each key part of the PV module as the first eigenvalue.

[0008] Preferably, in step 1, the damage assessment characteristic value of each key part of the photovoltaic bracket is obtained as the second characteristic value, and the specific method is: Obtain the electromagnetic impedance spectrum of each key part of the photovoltaic bracket; Calculate the root mean square deviation of the electromagnetic impedance spectrum of each key part; A mapping relationship between the root mean square deviation and the degree of loss is established, and SVR is used for fitting to obtain the damage assessment eigenvalue of each key part of the photovoltaic bracket as the second eigenvalue.

[0009] Preferably, in step 1, the electrical signal offset characteristic index of the inverter MPPT circuit in the target power station is obtained as the third characteristic value, and the specific method is: The electric signal of the inverter MPPT circuit is processed by wavelet transform and singular value decomposition method to obtain the electric signal offset characteristic index as the third eigenvalue.

[0010] Preferably, in step 3, the potential failure of the target photovoltaic power station is predicted according to the obtained feature vector, and the specific method is: The obtained feature vector is used as the input of the deep learning model of the constructed LSTM-GRU hybrid architecture, and the predicted sub-faults corresponding to each key part of the photovoltaic module, each key part of the photovoltaic bracket and the inverter MPPT circuit are obtained respectively; All the predicted sub-faults obtained are used as the input of the constructed component correlation analysis model based on graph convolutional neural network to obtain the fault prediction results of the target photovoltaic power station.

[0011] The integrated system for photovoltaic power station operation and maintenance data collection and analysis and fault prediction and diagnosis includes the following steps: The characteristic value acquisition unit is used to acquire the damage assessment characteristic value of each key part of the photovoltaic component in the target power station as the first characteristic value; acquire the damage assessment characteristic value of each key part of the photovoltaic bracket as the second characteristic value; acquire the electrical signal offset characteristic index of the inverter MPPT circuit in the target power station as the third characteristic value; A preprocessing unit, used for preprocessing the first eigenvalue, the second eigenvalue and the third eigenvalue to obtain corresponding eigenvectors; The potential fault prediction unit is used to predict the potential fault of the target photovoltaic power station by using the obtained feature vector.

[0012] An integrated device for photovoltaic power station operation and maintenance data collection and analysis and fault prediction and diagnosis, including: The first data acquisition unit is used to collect the electromagnetic impedance spectrum of each key part of the photovoltaic module and the photovoltaic bracket; A second data acquisition unit, used for collecting electrical signals from the inverter MPPT circuit; The processor is used to predict potential faults of the target photovoltaic power station according to the received electromagnetic impedance spectrum and electrical signals.

[0013] A computer device comprising: a processor suitable for executing a computer program; A computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the method described is performed.

[0014] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described above is implemented.

[0015] A computer program product comprises a computer program, wherein the computer program implements the method when executed by a processor.

[0016] Compared with the prior art, the present invention has the following beneficial effects: The integrated method for photovoltaic power station operation and maintenance data collection and analysis and fault prediction and diagnosis provided by the present invention can comprehensively reflect the operation status and potential faults of the photovoltaic power station from multiple dimensions by obtaining the damage assessment characteristic values ​​of each key part of the photovoltaic components and photovoltaic brackets, and the electrical signal offset characteristic indicators of the inverter MPPT circuit; preprocessing the obtained first characteristic value, second characteristic value and third characteristic value to obtain corresponding characteristic vectors, which can remove redundant information and improve data quality; using the obtained characteristic vectors to predict the potential faults of the target photovoltaic power station, advanced algorithms such as deep learning can be used to improve the accuracy and precision of the prediction; the deep learning model can automatically learn the rules and characteristics in the data, has strong adaptability, and can cope with complex and changeable fault conditions; through the above method, early warning can be carried out before the photovoltaic power station fails, helping the operation and maintenance personnel to take measures in time to avoid the occurrence or expansion of the fault; at the same time, it helps to reduce the downtime of the photovoltaic power station and improve the operation efficiency and power generation of the power station. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0018] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0019] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0020] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0021] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0022] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0023] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0024] Example 1 This embodiment provides an integrated method for photovoltaic power station operation and maintenance data collection and analysis and fault prediction and diagnosis, including the following steps: Step 1: Obtain the damage assessment characteristic value of each key part of the photovoltaic module in the target power station as the first characteristic value, specifically: Obtain the electromagnetic impedance spectrum of each key part of the photovoltaic module; Calculate the root mean square deviation of the electromagnetic impedance spectrum of each key part; A mapping relationship between the root mean square deviation and the degree of loss is established, and SVR is used for fitting to obtain the damage assessment eigenvalue of each key part of the PV module as the first eigenvalue.

[0025] Obtain the damage assessment eigenvalue of each key part of the photovoltaic bracket as the second eigenvalue, specifically: Obtain the electromagnetic impedance spectrum of each key part of the photovoltaic bracket; Calculate the root mean square deviation of the electromagnetic impedance spectrum of each key part; A mapping relationship between the root mean square deviation and the degree of loss is established, and SVR is used for fitting to obtain the damage assessment eigenvalue of each key part of the photovoltaic bracket as the second eigenvalue.

[0026] The electrical signal offset characteristic index of the inverter MPPT circuit in the target power station is obtained as the third eigenvalue. Specifically, the electrical signal of the inverter MPPT circuit is processed using wavelet transform and singular value decomposition method to obtain the electrical signal offset characteristic index as the third eigenvalue.

[0027] Step 2, preprocessing the first eigenvalue, the second eigenvalue and the third eigenvalue to obtain corresponding eigenvectors; Step 3: Use the obtained feature vector to predict the potential failure of the target photovoltaic power station. Specifically: The obtained feature vector is used as the input of the deep learning model of the constructed LSTM-GRU hybrid architecture, and the predicted sub-faults corresponding to each key part of the photovoltaic module, each key part of the photovoltaic bracket and the inverter MPPT circuit are obtained respectively; All the predicted sub-faults obtained are used as the input of the constructed component correlation analysis model based on graph convolutional neural network to obtain the fault prediction results of the target photovoltaic power station.

[0028] Example 2 This embodiment provides an integrated method for photovoltaic power station operation and maintenance data collection and analysis and fault prediction and diagnosis, see Figure 1 , including the following main steps: Step 1: deploy the structural health monitoring system; This step uses MFC (Macro Fiber Composite) piezoelectric sensors, which are integrated into each key part of the photovoltaic module and photovoltaic bracket to achieve strain self-sensing and energy collection. The damage detection algorithm based on electromagnetic impedance spectroscopy can detect micron-level structural damage. The specific steps of the damage detection algorithm based on electromagnetic impedance spectroscopy are as follows: 1) Use an impedance analyzer to measure the electromagnetic impedance spectrum of the piezoelectric sensor in the frequency range of 1-1000 kHz; 2) The root mean square deviation (RMSD) is used as the damage indicator, and the calculation formula is as follows:

[0029] in, and are the real part of the impedance at the i-th frequency point in the current state and the initial healthy state, respectively, N is the total number of sampling frequency points, and RMSD is the damage index; 3) By comparing the RMSD values ​​of multiple piezoelectric sensors, the damage location is determined using the triangulation method; the positioning formula is as follows:

[0030]

[0031]

[0032] Where (x, y) is the coordinate of the damage location to be determined, ( , ) is the coordinate of the i-th sensor, is the RMSD value measured by the i-th sensor, is the maximum RMSD value, R is the detection range radius; 4) The mapping relationship between RMSD value and damage degree is established, and the support vector regression (SVR) model is used for fitting to evaluate the damage degree and obtain the damage assessment eigenvalues, which are used as the first eigenvalue and the second eigenvalue respectively.

[0033] Through the above steps, this embodiment can monitor the structural health status of photovoltaic modules and brackets in real time, detect micron-level damage in time, and provide evaluation results of the damage location and degree, providing an important basis for preventive maintenance; Step 2: deploy the inverter monitoring system; This embodiment uses an optical fiber electrical signal sensor and a demodulator to collect and process the inverter MPPT circuit signal, achieves a sampling frequency of 1kHz, and extracts electrical signal features with small deviations based on a signal processing method of wavelet transform and singular value decomposition. The specific method is as follows; 1) Perform wavelet decomposition on the original signal, select db4 wavelet, and the decomposition level is 5, which can effectively separate the different frequency components in the signal and help identify the high-frequency harmonic characteristics; 2) Perform singular value decomposition on the high-frequency coefficient matrix after wavelet decomposition. By analyzing the changes in singular values, tiny anomalies in the electrical signal can be detected; 3) Select the first three largest singular values ​​as the electrical signal offset characteristic indicators and as the third eigenvalue.

[0034] Step 3: Build edge computing platform and quantum encryption communication system; The edge computing platform is deployed on the inverter side of the photovoltaic power station. Specifically, it is a PowerEdge R740 edge server equipped with Intel Xeon processors and Tesla T4 GPUs to accelerate AI reasoning, implement a microservice architecture based on Docker containers, and facilitate rapid deployment and updating of algorithms; develop a data stream processing pipeline based on Apache Kafka to achieve real-time data processing of eigenvalue data in steps 1 and 2; The real-time data processing method of the characteristic value data obtained in step 1 and step 2 is to adopt the following steps: Quantum encryption communication uses the Cerberis QKD system, implements quantum key distribution based on the BB84 protocol, uses SMF-28 ULL optical fiber for long-distance transmission, and uses AES-256 and Kyber post-quantum cryptographic algorithms to build a hybrid encryption solution to further enhance communication security; Step 4: Establish a cloud-based big data and artificial intelligence analysis platform The analysis platform uses the Apache Hadoop ecosystem to build a distributed storage and processing architecture, uses HDFS to store massive data, and sets data redundancy; uses Apache Spark for large-scale cloud data processing, configures SparkSQL for structured data analysis; and deploys an Elasticsearch cluster to achieve efficient time series data indexing and querying; In terms of the AI-driven fault prediction model, this embodiment uses the TensorFlow framework to implement a deep learning model of the LSTM-GRU hybrid architecture for time series data analysis and fault prediction. The core formula of the model is as follows:

[0035] in, For the predicted state, is the output gate factor, is the eigenvalue vector obtained in step 3; h is the LSTM-GRU hybrid architecture operator, which predicts potential faults through real-time monitoring status; When predicting potential faults, the PyTorch Geometric library is used to implement component correlation analysis based on graph convolutional neural network (GCN) to model the mutual influence between photovoltaic power generation components; the XGBoost library is used to build an integrated learning model to integrate the prediction results of multiple sub-models to improve prediction accuracy.

[0036] Through the integrated implementation of the above technical solutions, the present invention realizes comprehensive monitoring, accurate diagnosis and intelligent prediction of photovoltaic power stations, significantly improves the efficiency and reliability of operation and maintenance, and solves the problems of incomplete data collection, in-depth analysis, inaccurate prediction, etc. in the prior art. At the same time, the innovation of this method is reflected in the comprehensive application of the overall architecture design of multi-dimensional data collection, multi-level data processing and multi-model fusion analysis.

[0037] Example 3 The integrated system for photovoltaic power station operation and maintenance data collection and analysis and fault prediction and diagnosis provided in this embodiment includes the following steps: The characteristic value acquisition unit is used to acquire the damage assessment characteristic value of each key part of the photovoltaic component in the target power station as the first characteristic value; acquire the damage assessment characteristic value of each key part of the photovoltaic bracket as the second characteristic value; acquire the electrical signal offset characteristic index of the inverter MPPT circuit in the target power station as the third characteristic value; A preprocessing unit, used for preprocessing the first eigenvalue, the second eigenvalue and the third eigenvalue to obtain corresponding eigenvectors; The potential fault prediction unit is used to predict the potential fault of the target photovoltaic power station by using the obtained feature vector.

[0038] Example 4 The integrated device for photovoltaic power station operation and maintenance data collection and analysis and fault prediction and diagnosis provided in this embodiment is characterized by comprising: The first data acquisition unit is used to collect the electromagnetic impedance spectrum of each key part of the photovoltaic module and the photovoltaic bracket; A second data acquisition unit, used for collecting electrical signals from the inverter MPPT circuit; The processor is used to predict potential faults of the target photovoltaic power station according to the received electromagnetic impedance spectrum and electrical signals.

[0039] Example 5 This embodiment 5 provides a computer device, including: a memory for storing a computer program; and a processor for implementing the steps of a computer method when executing the computer program.

[0040] When the processor executes the computer program, the steps of the above-mentioned computer method are implemented, for example: Obtaining the damage assessment characteristic value of each key part of the photovoltaic module in the target power station as the first characteristic value; Obtain the damage assessment characteristic value of each key part of the photovoltaic bracket as the second characteristic value; Obtaining an electrical signal offset characteristic index of an inverter MPPT circuit in a target power station as a third characteristic value; Preprocessing the first eigenvalue, the second eigenvalue and the third eigenvalue to obtain corresponding eigenvectors; The obtained feature vector is used to predict the potential faults of the target photovoltaic power station.

[0041] Alternatively, when the processor executes the computer program, the functions of each module in the above system are realized, for example: The characteristic value acquisition unit is used to acquire the damage assessment characteristic value of each key part of the photovoltaic component in the target power station as the first characteristic value; acquire the damage assessment characteristic value of each key part of the photovoltaic bracket as the second characteristic value; acquire the electrical signal offset characteristic index of the inverter MPPT circuit in the target power station as the third characteristic value; A preprocessing unit, used for preprocessing the first eigenvalue, the second eigenvalue and the third eigenvalue to obtain corresponding eigenvectors; The potential fault prediction unit is used to predict the potential fault of the target photovoltaic power station by using the obtained feature vector.

[0042] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing preset functions, and the instruction segments are used to describe the execution process of the computer program in the computer device.

[0043] For example, the computer program may be divided into: a feature value acquisition unit, a preprocessing unit, and a potential fault prediction unit, and the specific functions of each module are as follows: The characteristic value acquisition unit is used to acquire the damage assessment characteristic value of each key part of the photovoltaic component in the target power station as the first characteristic value; acquire the damage assessment characteristic value of each key part of the photovoltaic bracket as the second characteristic value; acquire the electrical signal offset characteristic index of the inverter MPPT circuit in the target power station as the third characteristic value; A preprocessing unit, used for preprocessing the first eigenvalue, the second eigenvalue and the third eigenvalue to obtain corresponding eigenvectors; The potential fault prediction unit is used to predict the potential fault of the target photovoltaic power station by using the obtained feature vector.

[0044] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The computer device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the above are examples of computer devices and do not constitute a limitation on computer devices. The computer device may include more components than the above, or a combination of certain components, or different components. For example, the computer device may also include input and output devices, network access devices, buses, etc.

[0045] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the computer device, and uses various interfaces and lines to connect various parts of the entire computer device.

[0046] The memory may be used to store the computer programs and / or modules, and the processor implements various functions of the computer device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory.

[0047] The memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (SmartMediaCard, SMC), a secure digital (SecureDigital, SD) card, a flash card (FlashCard), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0048] Example 6 This embodiment 6 also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of the method described are implemented.

[0049] If the module / unit integrated in the computer system is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0050] Based on such understanding, the present invention implements all or part of the processes in the above method, and can also be completed by instructing related hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the above computer method can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or preset intermediate form, etc.

[0051] The computer-readable storage medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0052] It should be noted that the content contained in the computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable storage media do not include electrical carrier signals and telecommunication signals.

[0053] Example 7 This embodiment 7 provides a computer product, which includes a computer program, and the computer program is stored in a computer-readable storage medium; the processor of the computer device reads the computer program from the computer-readable storage medium, and the processor executes the computer program, so that the computer device can execute the method in embodiment 1, which will not be repeated here.

[0054] It should be noted that a person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods.

[0055] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. An integrated method for photovoltaic power station operation and maintenance data collection and analysis and fault prediction and diagnosis, characterized in that: The following steps are involved: Step 1, obtaining a damage assessment characteristic value of each key part of a photovoltaic module in a target power station as a first characteristic value; Obtain the damage assessment characteristic value of each key part of the photovoltaic bracket as the second characteristic value; Obtaining an electrical signal offset characteristic index of an inverter MPPT circuit in a target power station as a third characteristic value; Step 2, preprocessing the first eigenvalue, the second eigenvalue and the third eigenvalue to obtain corresponding eigenvectors; Step 3: Use the obtained feature vector to predict the potential failure of the target photovoltaic power station.

2. The integrated method for photovoltaic power station operation and maintenance data collection and analysis and fault prediction and diagnosis according to claim 1 is characterized in that: In step 1, the damage assessment characteristic value of each key part of the photovoltaic module in the target power station is obtained as the first characteristic value. The specific method is: Obtain the electromagnetic impedance spectrum of each key part of the photovoltaic module; Calculate the root mean square deviation of the electromagnetic impedance spectrum of each key part; A mapping relationship between the root mean square deviation and the degree of loss is established, and SVR is used for fitting to obtain the damage assessment eigenvalue of each key part of the PV module as the first eigenvalue.

3. The integrated method for photovoltaic power station operation and maintenance data collection and analysis and fault prediction and diagnosis according to claim 1 is characterized in that: In step 1, the damage assessment characteristic value of each key part of the photovoltaic bracket is obtained as the second characteristic value. The specific method is: Obtain the electromagnetic impedance spectrum of each key part of the photovoltaic bracket; Calculate the root mean square deviation of the electromagnetic impedance spectrum of each key part; A mapping relationship between the root mean square deviation and the degree of loss is established, and SVR is used for fitting to obtain the damage assessment eigenvalue of each key part of the photovoltaic bracket as the second eigenvalue.

4. The integrated method for photovoltaic power station operation and maintenance data collection and analysis and fault prediction and diagnosis according to claim 1 is characterized in that: In step 1, the electrical signal offset characteristic index of the inverter MPPT circuit in the target power station is obtained as the third characteristic value. The specific method is: The electric signal of the inverter MPPT circuit is processed by wavelet transform and singular value decomposition method to obtain the electric signal offset characteristic index as the third eigenvalue.

5. The integrated method for photovoltaic power station operation and maintenance data collection and analysis and fault prediction and diagnosis according to claim 1 is characterized in that: In step 3, the potential faults of the target photovoltaic power station are predicted based on the obtained feature vector. The specific method is: The obtained feature vector is used as the input of the deep learning model of the constructed LSTM-GRU hybrid architecture, and the predicted sub-faults corresponding to each key part of the photovoltaic module, each key part of the photovoltaic bracket and the inverter MPPT circuit are obtained respectively; All the predicted sub-faults obtained are used as the input of the constructed component correlation analysis model based on graph convolutional neural network to obtain the fault prediction results of the target photovoltaic power station.

6. An integrated system for photovoltaic power station operation and maintenance data collection and analysis and fault prediction and diagnosis, characterized in that: The following steps are involved: A characteristic value acquisition unit, used to acquire a damage assessment characteristic value of each key part of a photovoltaic module in a target power station as a first characteristic value; Obtain the damage assessment characteristic value of each key part of the photovoltaic bracket as the second characteristic value; Obtaining an electrical signal offset characteristic index of an inverter MPPT circuit in a target power station as a third characteristic value; A preprocessing unit, used for preprocessing the first eigenvalue, the second eigenvalue and the third eigenvalue to obtain corresponding eigenvectors; The potential fault prediction unit is used to predict the potential fault of the target photovoltaic power station by using the obtained feature vector.

7. An integrated device for photovoltaic power station operation and maintenance data collection and analysis and fault prediction and diagnosis, characterized in that: include: The first data acquisition unit is used to collect the electromagnetic impedance spectrum of each key part of the photovoltaic module and the photovoltaic bracket; A second data acquisition unit, used for collecting electrical signals from the inverter MPPT circuit; The processor is used to predict potential faults of the target photovoltaic power station according to the received electromagnetic impedance spectrum and electrical signals.

8. A computer device, characterized in that: include: a processor suitable for executing a computer program; A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by the processor, the method according to any one of claims 1 to 6 is performed.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

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

Images