A method and system for detecting equipment failures in a photovoltaic power station

Abstract

The present invention belongs to the technical field of data processing, and particularly relates to a method and system for detecting faults in photovoltaic power station equipment. The method includes setting up a sensor subsystem for the photovoltaic power station, which can comprehensively monitor parameters such as the temperature, current, voltage, light, and vibration of the equipment; setting up a data processing subsystem, which includes a processor and a memory, and is used to process the sensor data output by the sensor subsystem, analyze and process the data of the sensor system accurately and reliably, and can monitor the working status of the photovoltaic power station equipment in real time; establishing a quality inspection subsystem for performing electric energy metering and power quality detection of the photovoltaic power station; performing data processing based on KPCA-Informer to achieve fault detection of the photovoltaic power station equipment, analyzing and processing the data of the sensor system accurately and reliably, and can monitor the working status of the photovoltaic power station equipment in real time.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing, and in particular relates to a photovoltaic power station equipment fault detection method and system. Background Art

[0002] With the rapid development of economy, problems such as energy shortage and environmental degradation have gradually become prominent around the world. In this context, the development of new energy represented by photovoltaics has ushered in a boom. With the rapid increase in the installed capacity of photovoltaics, fault detection of photovoltaic power station equipment has become increasingly important. Photovoltaic power station equipment includes solar panels, inverters, connectors and other components. These devices may have various faults during long-term operation and working under various environmental conditions, such as over-temperature, abnormal current, voltage fluctuation, insufficient light, vibration, etc.

[0003] The traditional method of detecting faults in photovoltaic power station equipment mainly relies on manual inspection and regular maintenance. This method has the following problems: First, the labor cost is high, and a large amount of human resources are required for equipment inspection and maintenance, which increases operating costs; second, the inspection efficiency is low. Manual inspection requires personnel to check the equipment one by one, which consumes time and energy, and cannot timely discover and solve equipment problems, resulting in the possibility of long-term existence of faults; third, for large-scale photovoltaic power stations, the coverage is wide and the equipment is numerous, making manual inspection difficult and difficult to achieve comprehensive coverage; fourth, manual inspection is easily affected by subjective factors, and the inspection results may have missed detections or false detections, and the accuracy and reliability of the detection results cannot be guaranteed; fifth, it is impossible to monitor and diagnose in real time. Manual regular inspections cannot monitor the working status and performance of the equipment in real time, and cannot timely discover equipment failures or abnormalities; sixth, there is a lack of data support. Traditional methods cannot provide detailed data on the operating status of the equipment, lack a comprehensive understanding of the equipment operation status, and it is difficult to diagnose and optimize faults.

[0004] Therefore, how to accurately, quickly and comprehensively perform fault detection is of great significance to maintaining the normal operation of photovoltaic power stations. Summary of the invention

[0005] In order to solve or improve the above problems, the present invention provides a photovoltaic power station equipment fault detection method and system, and the specific technical solution is as follows:

[0006] The present invention provides a photovoltaic power station equipment fault detection method, comprising: setting a sensor subsystem for the photovoltaic power station, the sensor subsystem comprising a temperature sensor, a current sensor, a voltage sensor, a light sensor and a vibration sensor; setting a data processing subsystem, the data processing subsystem comprising a processor and a memory, and being used to process sensor data output by the sensor subsystem; establishing a quality inspection subsystem for performing power metering and power quality detection of the photovoltaic power station; and performing data processing based on KPCA-Informer to realize fault detection of photovoltaic power station equipment.

[0007] Preferably, the temperature sensor is used to measure the temperature of the solar panel, the inverter and the environment; the current sensor is used to measure the output current of the battery pack and the inverter; the voltage sensor is used to measure the output voltage of the solar panel and the inverter; the light sensor is used to measure the light intensity around the photovoltaic power station to evaluate the power generation efficiency of the solar panel; the vibration sensor is used to detect whether the photovoltaic power station equipment is vibrating or vibrating to determine whether there is a risk of physical damage or collapse.

[0008] Preferably, the quality inspection subsystem is used to: obtain a photovoltaic inverter test signal collected by the photovoltaic inverter and the power analyzer, the photovoltaic inverter test signal including the voltage, current, electrical signal amplitude and power information at a preset collection time; determine whether the power parameters in the photovoltaic inverter test signal meet the preset parameters; when the power parameters in the photovoltaic inverter test signal meet the preset parameters, calculate the reactive current value of the photovoltaic inverter to determine the power state of the photovoltaic inverter.

[0009] Preferably, the data processing subsystem processes the sensor data output by the sensor subsystem based on a multi-sensor fusion algorithm; the power parameters include at least one of a power change value, a power fluctuation value, a reactive current response speed, a reactive current overshoot and a reactive current regulation time.

[0010] Preferably, the data processing based on KPCA-Informer to realize fault detection of photovoltaic power station equipment includes: using KPCA to reduce the dimension of original photovoltaic data while retaining the original data information, and then using the Informer model to make predictions, wherein the original photovoltaic data is the data output by at least one subsystem among the sensor subsystem, the data processing subsystem and the quality inspection subsystem.

[0011] The present invention provides a photovoltaic power station equipment fault detection system, comprising: a first module, used to set a sensor subsystem for the photovoltaic power station, the sensor subsystem comprising a temperature sensor, a current sensor, a voltage sensor, a light sensor and a vibration sensor; a second module, used to set a data processing subsystem, the data processing subsystem comprising a processor and a memory, and used to process sensor data output by the sensor subsystem; a third module, used to establish a quality inspection subsystem for performing power metering and power quality detection of the photovoltaic power station; and a fourth module, used to perform data processing based on KPCA-Informer to realize fault detection of photovoltaic power station equipment.

[0012] Preferably, the temperature sensor is used to measure the temperature of the solar panel and the inverter; the current sensor is used to measure the output current of the battery pack and the inverter; the voltage sensor is used to measure the output voltage of the solar panel and the inverter; the light sensor is used to measure the light intensity around the photovoltaic power station to evaluate the power generation efficiency of the solar panel; the vibration sensor is used to detect whether the photovoltaic power station equipment is vibrating or vibrating to determine whether there is a risk of physical damage or collapse.

[0013] Preferably, the quality inspection subsystem is used to: obtain a photovoltaic inverter test signal collected by the photovoltaic inverter and the power analyzer, the photovoltaic inverter test signal including the voltage, current, electrical signal amplitude and power information at a preset collection time; determine whether the power parameters in the photovoltaic inverter test signal meet the preset parameters; when the power parameters in the photovoltaic inverter test signal meet the preset parameters, calculate the reactive current value of the photovoltaic inverter to determine the power state of the photovoltaic inverter.

[0014] Preferably, the data processing subsystem processes the sensor data output by the sensor subsystem based on a multi-sensor fusion algorithm; the power parameters include at least one of a power change value, a power fluctuation value, a reactive current response speed, a reactive current overshoot and a reactive current regulation time.

[0015] Preferably, the data processing based on KPCA-Informer to realize fault detection of photovoltaic power station equipment includes: using KPCA to reduce the dimension of original photovoltaic data while retaining the original data information, and then using the Informer model to make predictions, wherein the original photovoltaic data is the data output by at least one subsystem among the sensor subsystem, the data processing subsystem and the quality inspection subsystem.

[0016] The beneficial effects of the present invention are as follows: a sensor system for a photovoltaic power station is established and equipped with multiple sensors, which can comprehensively monitor the temperature, current, voltage, light, vibration and other parameters of the equipment. A data processing subsystem for the photovoltaic power station is established to analyze and process the data of the sensor system accurately and reliably, and the working status of the photovoltaic power station equipment can be monitored in real time. A photovoltaic prediction model based on KPCA-Informer is established. The KPCA algorithm can reduce the information redundancy between photovoltaic features, and the Informer algorithm can effectively capture the information association between time series. The model effectively improves the accuracy of photovoltaic power prediction. A fault diagnosis model based on prediction accuracy and prediction volatility is established, which can be calculated through photovoltaic prediction values ​​and actual values, and can accurately determine whether the equipment has a fault. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a schematic diagram of a photovoltaic power station equipment fault detection method according to the present invention;

[0018] Figure 2 is a schematic diagram of a photovoltaic power station equipment fault detection system according to the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0021] It should also be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0022] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0023] To solve the technical problems mentioned in the background, the present invention provides Figure 1A photovoltaic power station equipment fault detection method shown includes: S1, setting a sensor subsystem for the photovoltaic power station, the sensor subsystem including a temperature sensor, a current sensor, a voltage sensor, a light sensor and a vibration sensor; S2, setting a data processing subsystem, the data processing subsystem including a processor and a memory, for processing sensor data output by the sensor subsystem; S3, establishing a quality inspection subsystem for power metering and power quality detection of the photovoltaic power station; S4, performing data processing based on KPCA-Informer to realize fault detection of photovoltaic power station equipment.

[0024] The temperature sensor is used to measure the temperature of the solar panel, inverter and environment; the current sensor is used to measure the output current of the battery pack and inverter; the voltage sensor is used to measure the output voltage of the solar panel and inverter; the light sensor is used to measure the light intensity around the photovoltaic power station to evaluate the power generation efficiency of the solar panel; the vibration sensor is used to detect whether the photovoltaic power station equipment is vibrating or vibrating to determine whether there is a risk of physical damage or collapse.

[0025] The quality inspection subsystem is used to: obtain a photovoltaic inverter test signal collected by a photovoltaic inverter and a power analyzer, wherein the photovoltaic inverter test signal includes voltage, current, electrical signal amplitude and power information at a preset collection time; determine whether the power parameters in the photovoltaic inverter test signal meet the preset parameters; when the power parameters in the photovoltaic inverter test signal meet the preset parameters, calculate the reactive current value of the photovoltaic inverter to determine the power state of the photovoltaic inverter.

[0026] The data processing subsystem processes the sensor data output by the sensor subsystem based on a multi-sensor fusion algorithm; the power parameters include at least one of a power change value, a power fluctuation value, a reactive current response speed, a reactive current overshoot and a reactive current adjustment time.

[0027] The KPCA-Informer-based data processing to achieve fault detection of photovoltaic power station equipment includes: using KPCA to reduce the dimension of original photovoltaic data while retaining the original data information, and then using the Informer model to make predictions, wherein the original photovoltaic data is data output by at least one of the sensor subsystem, the data processing subsystem, and the quality inspection subsystem.

[0028] The present invention provides Figure 2A photovoltaic power station equipment fault detection system shown includes: a first module 1, used to set a sensor subsystem for the photovoltaic power station, the sensor subsystem including a temperature sensor, a current sensor, a voltage sensor, a light sensor and a vibration sensor; a second module 2, used to set a data processing subsystem, the data processing subsystem including a processor and a memory, used to process sensor data output by the sensor subsystem; a third module 3, used to establish a quality inspection subsystem for power metering and power quality detection of the photovoltaic power station; a fourth module 4, used to perform data processing based on KPCA-Informer to realize fault detection of photovoltaic power station equipment.

[0029] The temperature sensor is used to measure the temperature of the solar panels and inverters; the current sensor is used to measure the output current of the battery pack and inverter; the voltage sensor is used to measure the output voltage of the solar panels and inverter; the light sensor is used to measure the light intensity around the photovoltaic power station to evaluate the power generation efficiency of the solar panels; the vibration sensor is used to detect whether the photovoltaic power station equipment is vibrating or vibrating to determine whether there is a risk of physical damage or collapse.

[0030] The quality inspection subsystem is used to: obtain a photovoltaic inverter test signal collected by a photovoltaic inverter and a power analyzer, wherein the photovoltaic inverter test signal includes voltage, current, electrical signal amplitude and power information at a preset collection time; determine whether the power parameters in the photovoltaic inverter test signal meet the preset parameters; when the power parameters in the photovoltaic inverter test signal meet the preset parameters, calculate the reactive current value of the photovoltaic inverter to determine the power state of the photovoltaic inverter.

[0031] The data processing subsystem processes the sensor data output by the sensor subsystem based on a multi-sensor fusion algorithm; the power parameters include at least one of a power change value, a power fluctuation value, a reactive current response speed, a reactive current overshoot and a reactive current adjustment time.

[0032] The KPCA-Informer-based data processing to achieve fault detection of photovoltaic power station equipment includes: using KPCA to reduce the dimension of original photovoltaic data while retaining the original data information, and then using the Informer model to make predictions, wherein the original photovoltaic data is data output by at least one of the sensor subsystem, the data processing subsystem, and the quality inspection subsystem.

[0033] Example

[0034] A portable photovoltaic power station equipment fault detection system based on KPCA-Informer power prediction adopts the following technical solutions:

[0035] Step 1: Establish the sensor system of the photovoltaic power station. The sensor system includes temperature sensor, current sensor, voltage sensor, light sensor and vibration sensor.

[0036] Step 2: Establish a data processing system for the photovoltaic power station. The data processing system includes a processor and a memory, and the system analyzes and processes the data from the sensor system.

[0037] Step 3: Establish a photovoltaic power station power metering and power quality detection system. The system obtains the photovoltaic inverter test signal, determines the power parameters in the photovoltaic inverter test signal and compares them with the preset parameters to perform power quality detection.

[0038] Step 4: Establish the KPCA-Informer photovoltaic prediction model and fault detection method. The photovoltaic power prediction model based on KPCA-Informer first uses KPCA to reduce the dimension of the original photovoltaic data while retaining the original data information, and then uses the Informer model for prediction. The fault detection method detects faults through prediction accuracy and prediction volatility.

[0039] Among them, the sensor system includes: a temperature sensor for monitoring the temperature of photovoltaic power station equipment, including the temperature of solar panels, inverters and other components; a current sensor for measuring the current output of photovoltaic power station equipment, including the output current of battery packs, inverters and other components; a voltage sensor for monitoring the voltage output of photovoltaic power station equipment, including the output voltage of solar panels, inverters and other components; a light sensor for measuring the light intensity around the photovoltaic power station to evaluate the power generation efficiency of solar panels; a vibration sensor for detecting whether the photovoltaic power station equipment is vibrating or vibrating to determine whether there is a risk of physical damage or collapse.

[0040] The data processing system is used to receive the detection data of the sensor module and analyze and process it. The data processing module includes a processor and a memory. The processor is used to receive the temperature, sunshine intensity, output voltage of the photovoltaic module and other data detected by the sensor module and use the multi-sensor fusion algorithm (Multi-sensor Fusion, MSF) for analysis and processing, and the memory is used to store the processing results.

[0041] The specific steps of the power metering and power quality detection system are as follows:

[0042] First, obtain the photovoltaic inverter test signal. The photovoltaic inverter test signal is obtained through the test host. These signals are electrical signals collected by the photovoltaic inverter and the power analyzer. The photovoltaic inverter test signal includes the voltage, current, electrical signal amplitude and power information (including active and reactive information) at the preset collection time.

[0043] Then, it is determined whether the power parameters in the photovoltaic inverter test signal meet the preset parameters, and the power parameters include at least one of the power change value, power fluctuation value, reactive current response speed, reactive current overshoot and reactive current adjustment time. The test host extracts the power parameters from the photovoltaic inverter test signal and compares and determines with the preset parameters. These power parameters and preset parameters can be compared one to one or multiple to multiple.

[0044] Then, when the power parameters in the photovoltaic inverter test signal meet the preset parameters, the reactive current value of the photovoltaic inverter is calculated. The power state of the photovoltaic inverter is determined according to the reactive current value of the photovoltaic inverter. After the test host obtains the reactive current value of the photovoltaic inverter, it can correspond the reactive current value with the state table preset in the test host, and determine the power state of the photovoltaic inverter by looking up the state table. At the same time, the state table is also provided with a power adjustment value. After determining the power state of the photovoltaic inverter, the power adjustment value can also be output for manual adjustment by the user. In this embodiment, the power state of the photovoltaic inverter is inductive reactive power and capacitive reactive power.

[0045] The photovoltaic inverter test method analyzes the photovoltaic inverter test signal to determine whether the power parameters therein meet the preset requirements. When the power parameters meet the preset requirements, the reactive current value of the photovoltaic inverter can be calculated, and the power state of the photovoltaic inverter can be further determined. Therefore, by detecting whether the power parameters in the photovoltaic inverter test signal meet the preset requirements, the reactive power state can be detected.

[0046] The photovoltaic inverter test device includes the following components:

[0047] Acquisition module: used to obtain the photovoltaic inverter test signal.

[0048] Judgment module: used to judge whether the power parameters in the photovoltaic inverter test signal meet the preset conditions. These parameters include at least one of power change value, power fluctuation value, reactive current response speed, reactive current overshoot and reactive current adjustment time.

[0049] Calculation module: When the power parameters in the photovoltaic inverter test signal meet the preset conditions, it is used to calculate the reactive current value of the photovoltaic inverter.

[0050] Determination module: used to determine the power state of the photovoltaic inverter according to the reactive current value of the photovoltaic inverter.

[0051] The photovoltaic inverter test method comprises the following steps:

[0052] Acquire a photovoltaic inverter test signal; determine whether the power parameter in the photovoltaic inverter test signal meets the preset conditions; when the power parameter meets the preset conditions, calculate the reactive current value of the photovoltaic inverter; and determine the power state of the photovoltaic inverter using the calculated reactive current value. Therefore, the test method realizes the detection of the reactive power state by calculating the reactive current value of the photovoltaic inverter after the power parameter in the photovoltaic inverter test signal meets the preset conditions, and determining the power state using the reactive current value.

[0053] The KPCA-Informer photovoltaic prediction model and fault detection method, the specific steps are as follows:

[0054] KPCA-Informer is an improved encoder-decoder structure deep neural network model based on the Transformer model. The photovoltaic power prediction model based on KPCA-Informer first uses KPCA to reduce the dimension of the original photovoltaic data while retaining the original data information, and then uses the Informer model for prediction. The Informer model is mainly composed of an encoder and a decoder. The encoder is used to extract the dependency relationship between variables, and the decoder is used to generate the photovoltaic power prediction result. Finally, fault detection is performed through the prediction accuracy and prediction volatility of the photovoltaic power prediction value and the actual value.

[0055] The basic principle of KPCA algorithm is to use nonlinear function to map the original data into high-dimensional space, and then perform PCA on the data in high-dimensional space. 1 |x 2 ,…,x k ,…,x n}Through the mapping function φ(x i ) maps n points to an N-dimensional space and solves the eigenvalue λ through the covariance matrix Cov i and the eigenvector

[0056] Further solve the eigenvector v and matrix Q(x i ,y i ):

[0057]

[0058] Q(x i ,y i )=Q(x i )Q(x j ) (3);

[0059]

[0060] Finally, we can get the kernel principal component y i ,

[0061] In this implementation case, the number of principal components extracted is 6. After obtaining the principal components of the data, Informer is used to predict the data. The Informer model encodes the photovoltaic power generation related variables through the multi-head probabilistic sparse self-attention mechanism module and the distillation module. The multi-head self-attention mechanism can independently train the variable feature information of different spaces in parallel, and prevent the overfitting problem to a certain extent through the integrated calculation mechanism. The calculation formulas of the probabilistic sparse self-attention mechanism, encoder, and decoder are as follows:

[0062]

[0063]

[0064]

[0065] Where: Q is the query vector; K is the key vector; V is the value vector; d is the input variable dimension; S is the activation function; is the query vector; are the basic variables of the attention module and sparse attention mechanism at time t; c(·) is the one-dimensional convolution function; E(·) is the activation function; M(·) is the maximum pooling function; is the input sequence at time t; is the photovoltaic historical sequence; Photovoltaic prediction target occupancy sequence; C(·) is the sequence connection function.

[0066] Then the predicted value p is obtained by t t and actual value By predicting the accuracy ε t and the predicted volatility θ t Determine the fault:

[0067] θ t =ε t -ε t-1 (10);

[0068] In this implementation case, the prediction accuracy ε t is 85%, and the predicted volatility θ t When the accuracy is less than the specified threshold and the predicted volatility is greater than the specified value, the system will issue a fault alarm.

[0069] Those of ordinary skill in the art will appreciate that the units of each example described in conjunction with the embodiments disclosed in this embodiment can be implemented with electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition of each example has been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0070] In the embodiments provided in the present application, it should be understood that the division of units is merely a logical function division, and there may be other division methods in actual implementation, for example, multiple units may be combined into one unit, one unit may be split into multiple units, or some features may be ignored.

[0071] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A photovoltaic power station equipment fault detection method, characterized in that: include: A sensor subsystem is provided for the photovoltaic power station, wherein the sensor subsystem includes a temperature sensor, a current sensor, a voltage sensor, a light sensor and a vibration sensor; The temperature sensor is used to measure the temperature of the solar panel, inverter and environment; the current sensor is used to measure the output current of the battery pack and inverter; the voltage sensor is used to measure the output voltage of the solar panel and inverter; the light sensor is used to measure the light intensity around the photovoltaic power station to evaluate the power generation efficiency of the solar panel; the vibration sensor is used to detect whether the photovoltaic power station equipment is vibrating or vibrating to determine whether there is a risk of physical damage or collapse; A data processing subsystem is provided, wherein the data processing subsystem includes a processor and a memory, and is used to process the sensor data output by the sensor subsystem; the data processing subsystem processes the sensor data output by the sensor subsystem based on a multi-sensor fusion algorithm; A quality inspection subsystem for power metering and power quality detection of a photovoltaic power station is established; the quality inspection subsystem is used to: obtain a photovoltaic inverter test signal collected by a photovoltaic inverter and a power analyzer, the photovoltaic inverter test signal including voltage, current, electrical signal amplitude and power information at a preset collection time; determine whether the power parameters in the photovoltaic inverter test signal meet the preset parameters, and perform power quality detection; the power parameters include at least one of a power change value, a power fluctuation value, a reactive current response speed, a reactive current overshoot and a reactive current adjustment time; when the power parameters in the photovoltaic inverter test signal meet the preset parameters, calculate the reactive current value of the photovoltaic inverter to determine the power state of the photovoltaic inverter; after obtaining the reactive current value of the photovoltaic inverter, correspond the reactive current value to a preset state table, determine the power state of the photovoltaic inverter by searching the state table, and a power adjustment value is also set in the state table. After determining the power state of the photovoltaic inverter, the power adjustment value is also output; the power state of the photovoltaic inverter is inductive reactive power and capacitive reactive power; Data processing is performed based on KPCA-Informer to realize fault detection of photovoltaic power station equipment; including: using KPCA to reduce the dimension of original photovoltaic data while retaining the original data information, and then using the Informer model to make predictions, wherein the original photovoltaic data is the data output by at least one subsystem of the sensor subsystem, the data processing subsystem and the quality inspection subsystem; the Informer model uses a decoder to generate a photovoltaic power prediction result, and the photovoltaic power prediction value at time t is used and actual value The prediction accuracy and predicted volatility Perform fault detection; , ; When the accuracy is less than the specified threshold and the predicted volatility is greater than the specified value, the system will issue a fault alarm.

2. A photovoltaic power station equipment fault detection system, characterized in that: The method of claim 1 comprises: The first module is used to set a sensor subsystem for the photovoltaic power station, wherein the sensor subsystem includes a temperature sensor, a current sensor, a voltage sensor, a light sensor and a vibration sensor; A second module is used to set up a data processing subsystem, wherein the data processing subsystem includes a processor and a memory, and is used to process the sensor data output by the sensor subsystem; The third module is used to establish a quality inspection subsystem for power metering and power quality inspection of photovoltaic power stations; The fourth module is used for data processing based on KPCA-Informer to realize fault detection of photovoltaic power station equipment.

3. The photovoltaic power station equipment fault detection system according to claim 2, characterized in that: The temperature sensor is used to measure the temperature of the solar panel, the inverter and the environment; The current sensor is used to measure the output current of the battery pack and the inverter; The voltage sensor is used to measure the output voltage of the solar panel and the inverter; The light sensor is used to measure the light intensity around the photovoltaic power station to evaluate the power generation efficiency of the solar panel; The vibration sensor is used to detect whether the photovoltaic power station equipment is vibrating or shaking, so as to determine whether there is a risk of physical damage or collapse.

4. The photovoltaic power station equipment fault detection system according to claim 3, characterized in that: The quality inspection subsystem is used to: Acquire a photovoltaic inverter test signal collected by the photovoltaic inverter and the power analyzer, wherein the photovoltaic inverter test signal includes voltage, current, electrical signal amplitude and power information at a preset collection time; Determining whether the power parameters in the photovoltaic inverter test signal meet the preset parameters; When the power parameter in the photovoltaic inverter test signal meets the preset parameter, the reactive current value of the photovoltaic inverter is calculated to determine the power state of the photovoltaic inverter.

5. The photovoltaic power station equipment fault detection system according to claim 4, characterized in that: The data processing subsystem processes the sensor data output by the sensor subsystem based on a multi-sensor fusion algorithm; The power parameter includes at least one of a power variation value, a power fluctuation value, a reactive current response speed, a reactive current overshoot and a reactive current regulation time.

6. The photovoltaic power station equipment fault detection system according to claim 5, characterized in that: The data processing based on KPCA-Informer to realize fault detection of photovoltaic power station equipment includes: KPCA is used to reduce the dimension of the original photovoltaic data while retaining the original data information, and then the Informer model is used for prediction, wherein the original photovoltaic data is the data output by at least one of the sensor subsystem, the data processing subsystem and the quality inspection subsystem.

Images