Photovoltaic power generation equipment diagnosis method, system, equipment and storage medium

Abstract

The invention relates to the technical field of photovoltaic power generation fault diagnosis. The invention provides a photovoltaic power generation equipment diagnosis method, system and equipment, and a storage medium. The method comprises the following steps: collecting related data information of photovoltaic power generation equipment and constructing a photovoltaic power generation equipment data set; preprocessing the photovoltaic power generation equipment data set and obtaining a power generation equipment data driving set; key characteristic parameters in the power generation equipment data drive set are extracted, and dimension reduction processing is carried out; constructing a fault classification model according to the key feature parameters after dimension reduction processing; according to the method, fault diagnosis is carried out on the photovoltaic power generation equipment through the fault classification model, a corresponding diagnosis result is obtained, and a corresponding execution measure is given, so that the problems that existing diagnosis methods mostly depend on manual inspection and traditional data analysis means, the efficiency is low, the cost is high, and faults are difficult to find in real time are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic power generation fault diagnosis, and in particular to a photovoltaic power generation equipment diagnosis method, system, equipment and storage medium. Background Art

[0002] As the global demand for renewable energy continues to grow, photovoltaic power generation, as a clean and renewable energy form, has received widespread attention and application. However, due to the complexity of photovoltaic power generation systems and the diversity of operating environments, various failures are inevitable in the long-term use of photovoltaic equipment, affecting the stability of the system and power generation efficiency.

[0003] At present, the diagnostic methods for photovoltaic power generation equipment mostly rely on manual inspections and traditional data analysis methods. These methods have problems such as low efficiency, high cost, and difficulty in real-time fault detection. Summary of the invention

[0004] The purpose of the present invention is to provide a photovoltaic power generation energy storage grid-connected optimization system and method, system, device and storage medium, aiming to solve the problems that most existing diagnostic methods rely on manual inspections and traditional data analysis methods, which have low efficiency, high cost and difficulty in real-time fault detection.

[0005] The embodiments of the present invention are implemented by the following technical solutions:

[0006] A photovoltaic power generation equipment diagnostic method comprises the following steps:

[0007] Collect relevant data information of photovoltaic power generation equipment and construct a photovoltaic power generation equipment data set;

[0008] Preprocess the photovoltaic power generation equipment data set and obtain the power generation equipment data driver set;

[0009] Extract key characteristic parameters from the data-driven set of power generation equipment and perform dimensionality reduction processing;

[0010] Construct a fault classification model based on the key characteristic parameters after dimensionality reduction;

[0011] The fault classification model is used to diagnose faults of photovoltaic power generation equipment, obtain corresponding diagnostic results and give corresponding implementation measures.

[0012] Optionally, the specific process of preprocessing the photovoltaic power generation equipment data set and obtaining the power generation equipment data drive set is:

[0013] The collected data is cleaned by setting a reasonable threshold range to identify and delete data points that exceed the threshold. Negative values ​​in power monitoring are regarded as missing values ​​and filled with the nearest neighbor algorithm. Invalid values ​​in temperature detection are corrected by taking the average value of the previous and next sampling records. The cleaned data is standardized to obtain the data driver set of the power generation equipment.

[0014] Optionally, the specific process of extracting key characteristic parameters from the power generation equipment data drive set and performing dimensionality reduction processing is:

[0015] According to the operation mechanism and fault characteristics of photovoltaic equipment, key characteristic parameters reflecting the status of photovoltaic equipment are selected from the photovoltaic power generation equipment data drive set;

[0016] For the key features of high latitude, principal component analysis or linear discriminant analysis is used to reduce their dimensionality.

[0017] Optionally, the specific process of constructing the fault classification model according to the key characteristic parameters after dimensionality reduction processing is:

[0018] Based on the key features after dimensionality reduction, a feature vector F is constructed, and a fault classification model is constructed based on the feature vector F. The expression of the fault classification model is shown in the following formula (1):

[0019]

[0020] Among them, Fault Type is the fault type diagnosed, K is the fault type set, k is the element in the fault type set, σ is the activation function, W is the weight matrix, b is the bias term, and n represents the value of the nth element in the feature vector F;

[0021] It represents the operation of finding the maximum value by traversing all fault types k in the fault type set K and returning n that maximizes the value of the nth element of σ(W·F+b).

[0022] Optionally, the activation function σ is a softmax function.

[0023] Optionally, the feature vector F is mapped to the target space through a linear transformation W·F+b, each dimension in the target space corresponds to a fault type, and the result of the linear transformation is converted into a probability distribution through an activation function σ. Each probability value represents the probability that the input data belongs to the corresponding fault type. The weight matrix W and the bias term b are obtained through machine learning training.

[0024] Optionally, the specific process of performing fault diagnosis on the photovoltaic power generation equipment through the fault classification model, obtaining corresponding diagnosis results and providing corresponding execution measures is:

[0025] By calculating the similarity between the feature vector and different fault types, the fault type with the highest similarity is selected as the diagnosis result, and the corresponding fault type, fault cause and corresponding execution measures are output according to the diagnosis result.

[0026] The present invention also provides a photovoltaic power generation energy storage grid-connected optimization system, comprising:

[0027] Data acquisition module, used to collect real-time operation data of photovoltaic power generation equipment and external meteorological data;

[0028] Data preprocessing module, used to clean, standardize and extract features from the collected data;

[0029] Fault detection and classification module, used to perform fault diagnosis on preprocessed data;

[0030] The result output module is used to display fault diagnosis results and maintenance suggestions.

[0031] The present invention also provides an electronic device, including a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the above-mentioned photovoltaic power generation equipment diagnosis method.

[0032] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned photovoltaic power generation equipment diagnosis method is implemented.

[0033] The technical solution of the embodiment of the present invention has at least the following advantages and beneficial effects:

[0034] The present invention provides a photovoltaic power generation equipment diagnosis method, system, equipment and storage medium, the method comprising the steps of: collecting relevant data information of photovoltaic power generation equipment and constructing a photovoltaic power generation equipment data set; preprocessing the photovoltaic power generation equipment data set and obtaining a power generation equipment data drive set; extracting key feature parameters in the power generation equipment data drive set and performing dimensionality reduction processing; constructing a fault classification model according to the key feature parameters after the dimensionality reduction processing; and performing fault diagnosis on the photovoltaic power generation equipment through the fault classification model, obtaining corresponding diagnosis results and providing corresponding execution measures.

[0035] Through automated data collection, preprocessing, feature extraction and fault classification processes, the efficiency and accuracy of fault diagnosis of photovoltaic power generation equipment can be significantly improved; compared with traditional manual inspections and manual analysis methods, equipment faults can be identified more quickly and accurately, reducing human errors and missed detections.

[0036] Automated diagnostic methods reduce reliance on manual inspections, lowering the workload and costs of operation and maintenance personnel; at the same time, timely fault diagnosis and maintenance recommendations help reduce downtime and power generation losses caused by equipment failures, further improving economic benefits.

[0037] By real-time monitoring and diagnosis of the operating status of photovoltaic power generation equipment, potential faults can be discovered in a timely manner and corresponding maintenance measures can be taken, thereby enhancing the reliability and stability of the system, helping to extend the service life of the equipment and reducing the impact of equipment failure on grid operation.

[0038] It integrates advanced technologies such as data preprocessing, feature extraction, and machine learning to realize intelligent fault diagnosis of photovoltaic power generation equipment, which not only improves the accuracy and efficiency of diagnosis, but also provides strong support for subsequent equipment management and optimization.

[0039] It can process various types of photovoltaic power generation equipment data, including operation data and external meteorological data; at the same time, through flexible selection of feature extraction and dimensionality reduction methods, and construction of classification models adapted to different fault types, it can adapt to photovoltaic power generation systems of different sizes and types, and has strong adaptability and scalability.

[0040] After diagnosing the fault type and cause, it can give corresponding implementation measures and maintenance suggestions, providing strong decision-making support for operation and maintenance personnel, helping them to quickly formulate and implement effective maintenance plans to ensure the normal operation of the photovoltaic power generation system. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a schematic flow chart of the photovoltaic power generation equipment diagnosis method in Embodiment 1 of the present invention;

[0042] Figure 2 It is a schematic diagram of the structure of the photovoltaic power generation equipment diagnostic system in Example 2 of the present invention. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0044] Example 1

[0045] Reference Figure 1 , a photovoltaic power generation equipment diagnosis method, comprising the following steps:

[0046] Step 1: Collect relevant data information of photovoltaic power generation equipment and construct a photovoltaic power generation equipment data set;

[0047] Determine the scope and target of data collection. The scope and target of data collection usually include various key components in the photovoltaic power generation system, such as photovoltaic components, inverters, transformers, cables, energy storage systems, and monitoring systems. In addition, it is also necessary to determine what types of data to collect, such as voltage, current, power, temperature, humidity, light intensity, wind speed, wind direction, etc. These data can reflect the operating status and performance of the equipment. According to the target and scope of data collection, select appropriate data collection methods and technologies. In this embodiment, the operating parameters of the equipment can be measured in real time by installing corresponding sensors such as temperature sensors, current sensors, voltage sensors, and light sensors, or data can be obtained through the existing monitoring system; at the same time, the frequency and accuracy of data collection need to be considered to ensure the validity and accuracy of the data. After determining the data collection methods and technologies, it is necessary to deploy corresponding data acquisition equipment in the actual photovoltaic power generation system. In this embodiment, the data acquisition equipment is deployed by installing sensors, configuring data acquisition units, and setting up data transmission networks; the data acquisition units can be data acquisition devices such as data acquisition cards and PLCs, and the data transmission network can use wireless transmission, wired networks, and other communication networks. During the deployment process, attention should be paid to the stability and reliability of the equipment to ensure that data can be collected continuously and accurately. After the data acquisition equipment is deployed and starts working, it starts to collect and record data. The data collected by the sensor is transmitted to the central control system or data storage device, and real-time data recording and processing are performed. During the data collection process, it is necessary to ensure the integrity and accuracy of the data to avoid data loss or errors. The collected data needs to be integrated and verified to ensure the consistency and reliability of the data. The collected data will be integrated into a complete photovoltaic power generation equipment data set. This data set contains the operating parameters and status information of each key component of the photovoltaic power generation system, which can be used for subsequent data analysis, fault diagnosis and optimization adjustment. The data set exists in the form of a database, data file or data stream, and can be further processed and processed as needed.

[0048] Step 2: preprocess the photovoltaic power generation equipment data set and obtain the power generation equipment data drive set;

[0049] The collected data is cleaned by setting a reasonable threshold range to identify and delete data points that exceed the threshold. Negative values ​​in power monitoring are regarded as missing values ​​and filled with the nearest neighbor algorithm. Invalid values ​​in temperature detection are corrected by taking the average value of the previous and next sampling records. The cleaned data is standardized to obtain the data driver set of power generation equipment. The expression of standardized processing is shown in the following formula (2):

[0050]

[0051] Among them, x norm is the standardized data, x is the observed value in the original data, μ is the mean of the original data, and ω is the standard deviation of the original data;

[0052] The expression of the original data mean μ is shown in the following formula (3):

[0053]

[0054] Where N is the number of observations, x i is the i-th observation value;

[0055] The expression of the standard deviation of the original data is shown in the following formula (4):

[0056]

[0057] After the above data cleaning and standardization processing, the resulting data set is the power generation equipment data drive set. The power generation equipment data drive set contains the key characteristic parameters of photovoltaic power generation equipment in normal operation and possible fault conditions, which is the basis for subsequent feature extraction, model construction and fault diagnosis.

[0058] Step 3: extract key characteristic parameters from the data driver set of power generation equipment and perform dimensionality reduction processing;

[0059] According to the operation mechanism and fault characteristics of photovoltaic equipment, key characteristic parameters reflecting the status of photovoltaic equipment are selected from the photovoltaic power generation equipment data drive set. These key characteristic parameters include but are not limited to the following key characteristic parameters:

[0060] Current and voltage data, such as the output voltage and current of solar panels, the input / output voltage and current of inverters, etc., which directly reflect the electrical performance of photovoltaic systems;

[0061] Power data, including total power output and power output of each component, is an important indicator for evaluating system performance and detecting potential failures;

[0062] Temperature data, such as the temperature of key components such as solar panels, inverters, and cables. Abnormal temperatures often indicate equipment failure or performance degradation.

[0063] Environmental data, such as light intensity, ambient temperature, wind speed, etc. These external factors will directly affect the power generation efficiency and equipment operating status of the photovoltaic system.

[0064] After identifying all possible feature parameters, it is necessary to further perform feature selection through statistical methods to remove redundant or irrelevant features and retain the features that are most helpful for fault diagnosis. Feature selection can reduce data dimensions and improve the generalization ability of the model.

[0065] In this embodiment, for the key features of high dimensions, principal component analysis or linear discriminant analysis is used to reduce their dimensionality; after the dimensionality reduction process, the dimensionality reduction effect needs to be evaluated to ensure that key information is retained while reducing the data dimension. This can be achieved by comparing the variance, information gain and other indicators of the data before and after dimensionality reduction, or it can be indirectly evaluated by testing the performance of the fault diagnosis model on the training set and the validation set.

[0066] Step 4: Construct a fault classification model based on the key feature parameters after dimensionality reduction processing;

[0067] Based on the key features after dimensionality reduction, a feature vector F is constructed, and a fault classification model is constructed based on the feature vector F. The expression of the fault classification model is shown in the following formula (1):

[0068]

[0069] Among them, Fault Type is the fault type diagnosed, K is the fault type set, k is the element in the fault type set, σ is the activation function, W is the weight matrix, b is the bias term, and n represents the value of the nth element in the feature vector F;

[0070] represents the operation of finding the maximum value, by traversing all fault types k in the fault type set K and returning n that maximizes the value of the nth element of σ(W·F+b);

[0071] The feature vector contains all the information useful for fault diagnosis, and has removed redundancy and noise through dimensionality reduction technology, retaining the most important features; in this embodiment, a neural network model architecture is selected to build a fault classification model, and the fault classification model is trained through corresponding training data. Initialize the weight matrix W and the bias term b; input the feature vector F into the model, and obtain the predicted probability of each fault type through the calculation of the model; calculate the loss between the probability distribution predicted by the model and the actual fault type; according to the gradient of the loss function, use optimization algorithms such as gradient descent, Adam and other methods to update the parameters of the model to minimize the loss; iterate the training until the performance of the model on the validation set is satisfactory; after the training is completed, the model needs to be evaluated to verify its performance. The evaluation usually includes calculating indicators such as accuracy, recall, F1 score on the test set, and displaying the classification effect of the model through visualization tools such as confusion matrix.

[0072] In this embodiment, the activation function σ is a softmax function. The feature vector F is mapped to the target space through the linear transformation W·F+b. Each dimension in the target space corresponds to a fault type. The result of the linear transformation is converted into a probability distribution through the activation function σ. Each probability value represents the probability that the input data belongs to the corresponding fault type. The weight matrix W and the bias term b are obtained through machine learning training.

[0073] Step 5: Perform fault diagnosis on photovoltaic power generation equipment through the fault classification model, obtain corresponding diagnosis results and give corresponding implementation measures;

[0074] After preprocessing and dimension reduction, the real-time or historical data of the photovoltaic power generation equipment to be diagnosed is processed to form a feature vector F. This feature vector F contains key information that can reflect the status of the photovoltaic equipment; the feature vector F is input into the trained fault classification model. In the model, the feature vector F will undergo a series of calculations, including linear transformation and activation function processing; by traversing all elements k in the fault type set K, the value of σ(W·F+b) is calculated, and the k that maximizes the value is found. This k is the most likely fault type predicted by the model, that is, Fault Type This step is done by The operation is implemented, which ensures that the fault type that best matches the current feature vector F is selected from all possible fault types; the identified fault type Fault Type Output as a diagnostic result. This result clearly shows the current problems of the photovoltaic equipment so that maintenance personnel can quickly understand and take appropriate measures; in addition to outputting the fault type, the system can also provide corresponding execution measures or maintenance suggestions based on the fault type. These measures include but are not limited to: checking specific equipment parts, adjusting equipment parameters, replacing damaged components, performing cleaning and maintenance, etc. The provision of execution measures can be based on a pre-defined fault handling rule base, or it can be dynamically generated in combination with the advice of the expert system or real-time data analysis.

[0075] In practical applications, the effectiveness of diagnostic results and implementation measures can be evaluated through subsequent feedback mechanisms. If a certain fault type occurs frequently or a certain implementation measure is ineffective, you can consider retraining or adjusting the fault classification model to improve its accuracy and practicality.

[0076] Example 2

[0077] In order to execute the method corresponding to the above embodiment 1 to achieve the corresponding functions and technical effects, refer to Figure 2 In this embodiment, a photovoltaic power generation equipment diagnostic system is provided, including:

[0078] The data acquisition module 101 is used to collect the operation data of the photovoltaic power generation equipment and the external meteorological data in real time; the operation data includes the voltage, current, power output, temperature, etc. of the photovoltaic module, and the external meteorological data includes the light intensity, temperature, humidity, wind speed, etc.; the data acquisition module 101 can be implemented through a sensor network, Internet of Things (IoT) technology or a dedicated data acquisition device to transmit the real-time data to the system's data center or cloud storage platform for subsequent processing and analysis;

[0079] The data preprocessing module 102 is used to clean, standardize and extract features from the collected data; data cleaning includes identifying and processing abnormal values, missing values, etc.; standardization is to convert data into a unified format and range for subsequent processing; feature extraction is to extract key feature parameters useful for fault detection and performance analysis from the original data;

[0080] The fault detection and classification module 103 is used to perform fault diagnosis on the preprocessed data; the fault detection and classification module builds a fault classification model based on the neural network model architecture. The fault classification model learns the normal and abnormal operation characteristics of the photovoltaic equipment by training a large amount of historical data, so that it can accurately judge the health status of the equipment when new data is input;

[0081] The result output module 104 is used to display the fault diagnosis results and maintenance suggestions; the output results of the fault detection and classification module are presented to the user in an easy-to-understand manner so that the user can take appropriate measures to solve the problem; in this embodiment, the result output module can use a graphical user interface, a report generation tool or an API interface to display the diagnosis results. The user can view information such as the fault type, fault cause, occurrence time, and impact range through these methods, and obtain targeted maintenance suggestions or operation guides.

[0082] Example 3

[0083] This embodiment provides an electronic device, including a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the photovoltaic power generation equipment diagnosis method of Embodiment 1.

[0084] Optionally, the above-mentioned electronic device may be a server.

[0085] In addition, this embodiment further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the photovoltaic power generation equipment diagnosis method of embodiment 1 is implemented.

[0086] It is understandable that the processor in the embodiments of the present invention 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, transistor logic devices, hardware components or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0087] The method steps in the embodiments of the present invention can be implemented by hardware or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, and the software modules can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, mobile hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC.

[0088] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a storage medium or transmitted through the storage medium. The computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state disk (SSD)), etc.

[0089] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A photovoltaic power generation equipment diagnostic method, characterized in that: The following steps are involved: Collect relevant data information of photovoltaic power generation equipment and construct a photovoltaic power generation equipment data set; Preprocess the photovoltaic power generation equipment data set and obtain the power generation equipment data driver set; Extract key characteristic parameters from the data-driven set of power generation equipment and perform dimensionality reduction processing; Construct a fault classification model based on the key characteristic parameters after dimensionality reduction; The fault classification model is used to diagnose faults of photovoltaic power generation equipment, obtain corresponding diagnostic results and give corresponding implementation measures.

2. The photovoltaic power generation equipment diagnostic method according to claim 1, characterized in that: The specific process of preprocessing the photovoltaic power generation equipment data set and obtaining the power generation equipment data drive set is as follows: The collected data is cleaned by setting a reasonable threshold range to identify and delete data points that exceed the threshold. Negative values ​​in power monitoring are regarded as missing values ​​and filled with the nearest neighbor algorithm. Invalid values ​​in temperature detection are corrected by taking the average value of the previous and next sampling records. The cleaned data is standardized to obtain the data driver set of the power generation equipment.

3. The photovoltaic power generation equipment diagnostic method according to claim 1, characterized in that: The specific process of extracting the key characteristic parameters from the power generation equipment data drive set and performing dimensionality reduction processing is as follows: According to the operation mechanism and fault characteristics of photovoltaic equipment, key characteristic parameters reflecting the status of photovoltaic equipment are selected from the photovoltaic power generation equipment data drive set; For the key features of high latitude, principal component analysis or linear discriminant analysis is used to reduce their dimensionality.

4. The photovoltaic power generation equipment diagnostic method according to claim 1, characterized in that: The specific process of constructing the fault classification model according to the key characteristic parameters after dimensionality reduction processing is as follows: Based on the key features after dimensionality reduction, a feature vector F is constructed, and a fault classification model is constructed based on the feature vector F. The expression of the fault classification model is shown in the following formula (1): Among them, Fault Type is the fault type diagnosed, K is the fault type set, k is the element in the fault type set, σ is the activation function, W is the weight matrix, b is the bias term, and n represents the value of the nth element in the feature vector F; It represents the operation of finding the maximum value by traversing all fault types k in the fault type set K and returning n that maximizes the value of the nth element of σ(W·F+b).

5. The photovoltaic power generation equipment diagnostic method according to claim 4, characterized in that: The activation function σ is a softmax function.

6. The photovoltaic power generation equipment diagnostic method according to claim 5, characterized in that: The feature vector F is mapped to the target space through the linear transformation W·F+b. Each dimension in the target space corresponds to a fault type. The result of the linear transformation is converted into a probability distribution through the activation function σ. Each probability value represents the probability that the input data belongs to the corresponding fault type. The weight matrix W and the bias term b are obtained through machine learning training.

7. The photovoltaic power generation equipment diagnostic method according to claim 1, characterized in that: The specific process of diagnosing the faults of photovoltaic power generation equipment through the fault classification model, obtaining the corresponding diagnosis results and giving the corresponding execution measures is as follows: By calculating the similarity between the feature vector and different fault types, the fault type with the highest similarity is selected as the diagnosis result, and the corresponding fault type, fault cause and corresponding execution measures are output according to the diagnosis result.

8. A photovoltaic power generation energy storage grid-connected optimization system, characterized in that: include: Data acquisition module, used to collect real-time operation data of photovoltaic power generation equipment and external meteorological data; Data preprocessing module, used to clean, standardize and extract features from the collected data; Fault detection and classification module, used to perform fault diagnosis on preprocessed data; The result output module is used to display fault diagnosis results and maintenance suggestions.

9. An electronic device, characterized in that: The device comprises a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the photovoltaic power generation equipment diagnosis method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the photovoltaic power generation equipment diagnostic method according to any one of claims 1 to 7 is implemented.

Images