Photovoltaic energy storage inverter life test and evaluation system

Abstract

The present invention relates to the technical field of power electronic equipment testing and evaluation, and specifically to a photovoltaic energy storage inverter life test and evaluation system, including a multi-parameter real-time monitoring module, an electrical load simulation module, an environmental simulation module, a life prediction module, a comprehensive evaluation module, and a user interface module; wherein: the multi-parameter real-time monitoring module: is used to collect the performance data of the inverter in real time; the electrical load simulation module: is used to simulate different electrical load conditions; the environmental simulation module: is used to simulate a variety of environmental conditions; the life prediction module: is used to analyze the degradation trend of the inverter and predict its remaining life; the comprehensive evaluation module: is used to calculate the overall health status and performance indicators of the inverter. The present invention, by integrating advanced multi-parameter monitoring and environmental simulation technologies, significantly improves the accuracy and efficiency of inverter performance degradation analysis, and provides strong technical support for the long-term stable operation of photovoltaic energy storage inverters.

Description

Technical Field

[0001] The present invention relates to the technical field of power electronic equipment testing and evaluation, and in particular to a photovoltaic energy storage inverter life testing and evaluation system. Background Art

[0002] With the rapid development of renewable energy technology, photovoltaic power generation systems have been widely used around the world. As a key component in photovoltaic power generation systems, the performance and life of photovoltaic energy storage inverters directly affect the stability and economy of the entire system. However, during long-term operation, the inverter will be affected by various factors such as ambient temperature, humidity, and load fluctuations, resulting in gradual performance degradation. Therefore, how to effectively evaluate the performance changes and expected life of the inverter has become an important issue in the maintenance and optimization of photovoltaic power generation systems.

[0003] Existing inverter life testing and evaluation methods mainly rely on long-term operation data analysis and subsequent physical inspections, which are not only time-consuming and inefficient, but also difficult to accurately predict the performance changes of the inverter under complex environmental conditions. In addition, traditional evaluation methods lack the ability to comprehensively analyze multi-parameter data, making it difficult to fully reflect the health status of the inverter.

[0004] Therefore, it is necessary and of practical significance to develop an inverter life test and evaluation system that can collect multi-parameter data in real time, simulate various environmental and load conditions, and perform comprehensive evaluation through advanced algorithms. Summary of the invention

[0005] Based on the above objectives, the present invention provides a photovoltaic energy storage inverter life test and evaluation system.

[0006] The photovoltaic energy storage inverter life test and evaluation system includes a multi-parameter real-time monitoring module, an electrical load simulation module, an environmental simulation module, a life prediction module, a comprehensive evaluation module and a user interface module; among which:

[0007] Multi-parameter real-time monitoring module: equipped with a sensor network to collect real-time performance data of the inverter, including voltage, current, power, temperature and humidity;

[0008] Electrical load simulation module: Use the data collected by the multi-parameter real-time monitoring module to simulate different electrical load conditions and test the performance of the inverter under different working conditions;

[0009] Environmental simulation module: used to simulate various environmental conditions, including temperature, humidity, salt spray and UV radiation, to test the working performance and durability of the inverter under various extreme conditions;

[0010] Life prediction module: receives and processes data from the multi-parameter real-time monitoring module, the electrical load simulation module, and the environmental simulation module, uses graph neural network technology to extract relevant features, analyze the degradation trend of the inverter, and predict its remaining life;

[0011] Comprehensive evaluation module: Integrates the analysis results from the life prediction module and the test data from the environmental simulation module, calculates the overall health status and performance indicators of the inverter through a comprehensive evaluation algorithm, and generates a comprehensive evaluation report;

[0012] User interface module: It is used to provide an intuitive operation interface, through which users can set test parameters, start test procedures, and view various data and comprehensive evaluation reports in real time.

[0013] Optionally, the environmental simulation module includes a temperature gradient simulation unit, a sensor network unit and a data acquisition unit, wherein the temperature gradient simulation unit is configured with multiple temperature sensors arranged around the inverter, and is used to simulate and control different temperature conditions of various parts of the inverter during actual operation; the sensor network includes voltage sensors, current sensors, power sensors, temperature sensors and humidity sensors, which are used to collect performance data of the inverter in real time; each sensor is connected to the data acquisition unit, which is used to convert the data collected from the sensor into digital signals and send them to the life prediction module through the data bus.

[0014] Optionally, the electrical load simulation module includes a load generation unit, a load adjustment unit, a data transmission unit and a test control unit; wherein:

[0015] Load generation unit: using the voltage, current and power data collected by the multi-parameter real-time monitoring module to generate various electrical load conditions, the load generation unit includes a programmed load controller and power electronics to generate electrical loads in various working states from light load to heavy load, constant load to fluctuating load;

[0016] Load regulation unit: used to dynamically adjust load conditions and simulate the working state of the inverter in different operating scenarios. The load regulation unit controls the inverter load by adjusting the amplitude, frequency and phase of current and voltage;

[0017] Data transmission unit: used to transmit data in the load generation and regulation process to the life prediction module and the comprehensive evaluation module. The data transmission unit includes a high-speed data transmission interface and a protocol converter, wherein the high-speed data transmission interface is used to transmit load condition data, and the protocol converter is used to convert the transmission data into a predetermined format.

[0018] Optionally, the environmental simulation module includes a temperature control unit, a humidity control unit, a salt spray simulation unit, a UV radiation simulation unit and a data acquisition unit; wherein:

[0019] Temperature control unit: used to simulate different temperature conditions. The temperature control unit includes a heater and a refrigerator to adjust the temperature range of the test environment from -40°C to 85°C.

[0020] Humidity control unit: used to simulate different humidity conditions. The humidity control unit includes a humidifier and a dehumidifier, which can adjust the humidity range of the test environment from 0% to 100%;

[0021] Salt spray simulation unit: used to simulate the salt spray environment to test the durability of the inverter in a corrosive environment. The salt spray simulation unit includes a salt spray generator and a control device, which can generate and maintain a salt spray environment of a predetermined concentration;

[0022] UV radiation simulation unit: used to simulate ultraviolet radiation environment. The UV radiation simulation unit includes a UV lamp and a radiation control device, which can simulate ultraviolet radiation conditions of different intensities and wavelengths;

[0023] Data acquisition unit: used to collect temperature, humidity, salt spray concentration and UV radiation intensity data in real time during the environmental simulation process. The collected data is transmitted to the life prediction module and comprehensive evaluation module through the data bus.

[0024] Optionally, the life prediction module includes a data receiving unit, a feature extraction unit, a degradation trend analysis unit, a life prediction unit and a data output unit; wherein:

[0025] Data receiving unit: used to receive data from the multi-parameter real-time monitoring module, the electrical load simulation module and the environmental simulation module; Feature extraction unit: uses graph neural network technology to process the received data and extract relevant features of inverter performance degradation;

[0026] Degradation trend analysis unit: Based on the features obtained from the feature extraction unit, the degradation rate and mode of the inverter under different test conditions are evaluated using time series analysis technology to obtain the performance degradation trend of the inverter;

[0027] Life prediction unit: Calculates the expected life of the inverter based on the degradation trend analysis results combined with historical degradation data;

[0028] Data output unit: outputs the life prediction results to the comprehensive evaluation module and the user interface module.

[0029] Optionally, the feature extraction unit includes:

[0030] Data preprocessing: preprocess the multi-source data from the data receiving unit, including normalization and standardization;

[0031] Constructing a graph structure: The preprocessed data is constructed into a graph structure, where nodes represent various performance indicators of the inverter and edges represent the relationship between the performance indicators;

[0032] Initialize node features: Initialize the feature vector of each node. The feature vector includes the performance indicator data corresponding to the node.

[0033] Graph convolution layer calculation: The graph convolution network is used to update the node features. The node features of each layer are aggregated and updated through the information of neighboring nodes. The update formula is: ,in, Is a node In the The feature vector of the layer, Is a node The set of neighbor nodes of and The nodes are and nodes The degree of , which indicates the number of connections of each node, It is The weight matrix of the layer represents the network parameters, is the activation function;

[0034] Node feature aggregation: Aggregate the outputs of the multi-layer graph convolutional layer to obtain the final feature representation of each node, which contains the information of neighboring nodes. The aggregation formula is:

[0035] ,in, Is a node The final feature representation, Aggregate is the feature aggregation function, which represents the aggregation of features at each layer. is the number of layers of the graph convolutional network;

[0036] Feature output: The final feature representation of each node is extracted as the relevant feature of the inverter performance degradation and transmitted to the degradation trend analysis unit.

[0037] Optionally, the degradation trend analysis unit includes:

[0038] Feature data preparation: receiving the final feature data from the feature extraction unit and arranging the data in chronological order to form a time series data set;

[0039] Time series decomposition: Decompose the time series data into trend part, seasonal part and random part;

[0040] Trend analysis: Use the sliding average analysis method to extract the long-term trend in the time series data and evaluate the performance degradation trend of the inverter: The trend calculation formula is:

[0041] ,in, It's time The trend value at the moment, is the size of the sliding window, Is a node In time Characteristic representation of moments;

[0042] Degradation rate calculation: Based on the extracted long-term trend, the degradation rate of the inverter is calculated; the degradation rate formula is: ,in, is the degradation rate, and The time and Trend value at the moment;

[0043] Pattern recognition: Use the dynamic time warping algorithm to identify typical degradation patterns in time series data and analyze the performance change characteristics of the inverter under different test conditions. The dynamic time warping algorithm formula is:

[0044] ,in, There are two time series and In Location and The cumulative distance of It's time point and The distance between

[0045] Degradation mode distinction: Based on the cumulative distance calculated by the dynamic time warping algorithm, the K-means clustering algorithm is used to classify the degradation modes and distinguish different types of degradation modes;

[0046] Result output: The evaluation results, including degradation trend and degradation rate, are output to the life prediction unit.

[0047] Optionally, the life prediction unit includes:

[0048] Data integration: Integrate the degradation trend data from the degradation trend analysis unit and the historical degradation data to form a complete time series data set ;

[0049] Degradation model fitting: The exponential degradation model is used to fit the integrated time series data. The exponential degradation model formula is: ,in, It's time The trend value at the moment, is the initial trend value, is the degradation rate constant;

[0050] Parameter estimation: Estimate the parameters in the degradation model by the least squares method;

[0051] Life prediction: Based on the fitted degradation model, the performance of the inverter at a future moment is predicted. By determining the time required for it to reach the preset critical value, the expected life of the inverter is calculated. The expected life calculation formula is: ,in, is life expectancy, is the performance threshold, is the initial trend value, is the degradation rate constant;

[0052] Result verification: Verify the predicted expected life results by comparing with the actual degradation data and performing error analysis. The verification formula is:

[0053] ,in, is the prediction error, It's time The actual trend value at the moment, It's time The predicted trend value at the moment.

[0054] Optionally, the comprehensive evaluation module includes a data receiving unit, a data integration unit, a health status evaluation unit, a performance indicator calculation unit and a report generation unit; wherein:

[0055] Data receiving unit: used to receive expected life data and analysis results from the life prediction module, and test data from the environmental simulation module;

[0056] Data integration unit: used to integrate data from different sources to form a complete data set;

[0057] Health status assessment unit: Based on the integrated data, the overall health index of the inverter is calculated through the health status assessment algorithm. The health index calculation formula is: Health index calculation formula: ,in, Represents the health index, represents life expectancy, represents the environmental impact factor, and is the weight coefficient;

[0058] Performance index calculation unit: calculates the performance index of the inverter, including efficiency, power factor, and temperature rise, by analyzing the integrated data;

[0059] Report generation unit: used to generate a comprehensive assessment report based on the assessment results. The report content includes health index, various performance indicators, historical data comparison, predicted trends and recommended measures.

[0060] Optionally, the user interface module includes a parameter setting unit, a program starting unit, a real-time data display unit and a comprehensive evaluation report display unit; wherein:

[0061] Parameter setting unit: used for users to input and set test parameters, including temperature, humidity, voltage, and current parameters;

[0062] Program startup unit: used to start and control the test program;

[0063] Real-time data display unit: used to display various data collected during the test in real time;

[0064] Comprehensive evaluation report display unit: used to display the evaluation report generated by the comprehensive evaluation module.

[0065] Beneficial effects of the present invention:

[0066] The present invention collects data on multiple parameters such as voltage, current, power, temperature and humidity in real time and simulates various environmental influences, thereby accurately simulating and analyzing various complex situations that the inverter may encounter in the actual working environment. This comprehensive testing method significantly improves the accuracy and efficiency of inverter performance degradation analysis, and plays an important role in preventing and diagnosing early faults.

[0067] The present invention, through advanced graph neural network technology and time series analysis technology, can deeply analyze the data collected from the test module and effectively predict the performance degradation trend and expected life of the inverter. The comprehensive evaluation module of the system further compares the analysis results with historical data to provide a detailed report on the overall health status of the inverter, which not only helps operation and maintenance personnel make more accurate maintenance decisions, but also provides a scientific basis for the design improvement and technical upgrade of the inverter. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0069] Figure 1A schematic diagram of a life test and evaluation system according to an embodiment of the present invention;

[0070] Figure 2 Schematic diagram of a life prediction module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0071] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0072] It should be noted that the references to "one embodiment", "embodiment", "exemplary embodiments", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0073] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0074] like Figure 1-Figure 2 As shown, the photovoltaic energy storage inverter life test and evaluation system includes a multi-parameter real-time monitoring module, an electrical load simulation module, an environmental simulation module, a life prediction module, a comprehensive evaluation module and a user interface module; wherein:

[0075] Multi-parameter real-time monitoring module: equipped with a sensor network to collect real-time performance data of the inverter, including voltage, current, power, temperature and humidity;

[0076] Electrical load simulation module: Use the data collected by the multi-parameter real-time monitoring module to simulate different electrical load conditions, test the performance of the inverter under different working conditions, and transmit the test results to the life prediction module through the data bus to further enrich the performance data of the inverter;

[0077] Environmental simulation module: used to simulate various environmental conditions, including temperature, humidity, salt spray and UV radiation, to test the working performance and durability of the inverter under various extreme conditions. The data generated during the test is also transmitted to the life prediction module;

[0078] Life prediction module: Receives and processes data from the multi-parameter real-time monitoring module, the electrical load simulation module, and the environmental simulation module, and uses graph neural network technology to extract relevant features, analyze the degradation trend of the inverter, and predict its remaining life; by capturing the complex interactive relationships and data dependencies in the inverter system, the graph neural network can effectively simulate and predict the behavior of the inverter under different environmental and load conditions, and the analysis results are fed back to the comprehensive evaluation module through the data bus;

[0079] Comprehensive evaluation module: Integrates the analysis results from the life prediction module and the test data from the environmental simulation module, calculates the overall health status and performance indicators of the inverter through a comprehensive evaluation algorithm, and generates a comprehensive evaluation report, which is transmitted to the user interface module for users to view and analyze;

[0080] User interface module: It is used to provide an intuitive operation interface, through which users can set test parameters, start test procedures, and view various data and comprehensive evaluation reports in real time.

[0081] The environmental simulation module includes a temperature gradient simulation unit, a sensor network unit and a data acquisition unit. The temperature gradient simulation unit is equipped with multiple temperature sensors, which are arranged around the inverter to simulate and control the different temperature conditions of various parts of the inverter in actual operation; the sensor network includes a voltage sensor, a current sensor, a power sensor, a temperature sensor and a humidity sensor, which are used to collect the performance data of the inverter in real time; each sensor is connected to the data acquisition unit, which is used to convert the data collected from the sensor into a digital signal and send it to the life prediction module through the data bus for further analysis;

[0082] The temperature gradient simulation unit contains a series of distributed temperature sensors that can accurately control and simulate the different temperature environments that various components of the inverter may be exposed to during operation, which helps to evaluate the performance stability and durability of the inverter under different temperature gradients; the sensor network is designed to comprehensively monitor the operating status of the inverter to ensure that all key parameters such as voltage, current, power, temperature and humidity are monitored in real time. The data collected by each sensor is the basis for the health status and performance evaluation of the inverter.

[0083] Sensors and their acquisition principles:

[0084] The voltage sensor is used to measure the voltage difference between the input and output of the inverter and output the voltage signal for subsequent analysis;

[0085] Current sensors are used to monitor the current flow of the inverter and obtain current data through induction or direct measurement;

[0086] Power sensors are used to calculate real-time power, which is derived from the product of voltage and current and is used to evaluate the efficiency of the inverter;

[0087] Temperature sensors are used in addition to the temperature gradient simulation unit. Independent temperature sensors are deployed in key inverter components to monitor overheating conditions that may cause performance degradation;

[0088] Humidity sensors are used to measure the relative humidity of the inverter environment. Humidity changes may affect the reliability and life of inverter components.

[0089] The electrical load simulation module includes a load generation unit, a load adjustment unit, a data transmission unit and a test control unit; wherein:

[0090] Load generation unit: using the voltage, current and power data collected by the multi-parameter real-time monitoring module to generate various electrical load conditions, the load generation unit includes a programmed load controller and power electronics to generate electrical loads in various working states from light load to heavy load, constant load to fluctuating load;

[0091] Load adjustment unit: used to dynamically adjust the load conditions and simulate the working state of the inverter in different operating scenarios. The load adjustment unit controls the inverter load by adjusting the amplitude, frequency and phase of the current and voltage. The load adjustment unit makes real-time adjustments based on the parameters provided by the load generation unit to ensure the diversity and accuracy of the test conditions.

[0092] Data transmission unit: used to transmit data in the process of load generation and regulation to the life prediction module and the comprehensive evaluation module. The data transmission unit includes a high-speed data transmission interface and a protocol converter, wherein the high-speed data transmission interface is used to transmit load condition data, and the protocol converter is used to convert the transmission data into a predetermined format. The electrical load simulation module generates a variety of electrical load conditions through the load generation unit, and dynamically adjusts these loads through the load regulation unit to accurately simulate the performance of the inverter under different working conditions. All data are transmitted to the life prediction module and the comprehensive evaluation module through the data transmission unit.

[0093] The environmental simulation module includes a temperature control unit, a humidity control unit, a salt spray simulation unit, a UV radiation simulation unit and a data acquisition unit; wherein:

[0094] Temperature control unit: used to simulate different temperature conditions. The temperature control unit includes a heater and a refrigerator to adjust the temperature range of the test environment from -40°C to 85°C. The temperature control unit monitors and adjusts the temperature in real time through sensors to ensure the accuracy and stability of temperature changes.

[0095] Humidity control unit: used to simulate different humidity conditions. The humidity control unit includes a humidifier and a dehumidifier, which can adjust the humidity range of the test environment from 0% to 100%. The humidity control unit monitors and adjusts the humidity level in real time through a humidity sensor to achieve precise humidity control;

[0096] Salt spray simulation unit: used to simulate salt spray environment to test the durability of the inverter in a corrosive environment. The salt spray simulation unit includes a salt spray generator and a control device, which can generate and maintain a salt spray environment of a predetermined concentration. The salt spray simulation unit evenly distributes the salt spray through a spray device and monitors the salt spray concentration through a sensor;

[0097] UV radiation simulation unit: used to simulate ultraviolet radiation environment. The UV radiation simulation unit includes a UV lamp and a radiation control device, which can simulate ultraviolet radiation conditions of different intensities and wavelengths. The UV radiation simulation unit adjusts the radiation intensity through the control device and monitors the actual intensity and distribution of UV radiation through the radiation sensor;

[0098] Data acquisition unit: used to collect temperature, humidity, salt spray concentration and UV radiation intensity data in real time during the environmental simulation process. The collected data is transmitted to the life prediction module and the comprehensive evaluation module through the data bus; the environmental simulation module simulates various extreme environmental conditions through the temperature control unit, humidity control unit, salt spray simulation unit and UV radiation simulation unit. The data acquisition unit is responsible for real-time monitoring and recording of various environmental parameters. All data are transmitted to the life prediction module and the comprehensive evaluation module through the data bus for subsequent performance analysis and durability evaluation.

[0099] The life prediction module includes a data receiving unit, a feature extraction unit, a degradation trend analysis unit, a life prediction unit and a data output unit; wherein:

[0100] Data receiving unit: used to receive data from the multi-parameter real-time monitoring module, electrical load simulation module and environmental simulation module to ensure the integrity and real-time performance of the data received from each module;

[0101] Feature extraction unit: Graph neural network technology is used to process the received data and extract relevant features of inverter performance degradation. Specifically, a multi-layer graph neural network structure is used to capture the complex relationships and patterns of the inverter system through node and edge representation learning;

[0102] Degradation trend analysis unit: Based on the features obtained from the feature extraction unit, the degradation rate and mode of the inverter under different test conditions are evaluated using time series analysis technology to obtain the performance degradation trend of the inverter;

[0103] Life prediction unit: Calculates the expected life of the inverter based on the degradation trend analysis results combined with historical degradation data;

[0104] Data output unit: outputs the life prediction results to the comprehensive evaluation module and the user interface module. This unit includes data formatting and transmission mechanisms to ensure the accurate transmission and display of the prediction results. The life prediction module uses the powerful processing capabilities of the graph neural network to accurately extract features related to inverter performance degradation and uses advanced analysis technology to predict the remaining life of the inverter. This method effectively combines data from different test modules and improves the accuracy and reliability of the prediction.

[0105] The relevant features of inverter performance degradation extracted by the feature extraction unit specifically include:

[0106] Data preprocessing: preprocess the multi-source data from the data receiving unit, including normalization and standardization, to ensure that data of different dimensions are comparable;

[0107] Constructing a graph structure: The preprocessed data is constructed into a graph structure, where nodes represent various performance indicators of the inverter, such as voltage, current, temperature, etc., and edges represent the relationship between performance indicators;

[0108] Initialize node features: Initialize the feature vector of each node. The feature vector includes the performance indicator data corresponding to the node.

[0109] Graph convolution layer calculation: Graph Convolutional Network (GCN) is used to update node features. The node features of each layer are aggregated and updated through the information of neighboring nodes. The update formula is: ,in, Is a node In the The feature vector of the layer, Is a node The set of neighbor nodes of and The nodes are and nodes The degree of , which indicates the number of connections of each node, It is The weight matrix of the layer represents the network parameters, is the activation function;

[0110] Node feature aggregation: Aggregate the outputs of the multi-layer graph convolutional layer to obtain the final feature representation of each node, which contains the information of neighboring nodes. The aggregation formula is:

[0111] ,in, Is a node The final feature representation, Aggregate is the feature aggregation function, which represents the aggregation of features at each layer. is the number of layers of the graph convolutional network;

[0112] Feature output: Extract the final feature representation of each node as the relevant feature of inverter performance degradation , and transmit it to the degradation trend analysis unit; through the above steps, the feature extraction unit uses the graph neural network technology to process the received data, extracts the relevant features of the inverter performance degradation, and provides key data support for subsequent degradation trend analysis and life prediction.

[0113] The degradation trend analysis unit includes:

[0114] Feature data preparation: receiving the final feature data from the feature extraction unit and arranging the data in chronological order to form a time series data set;

[0115] Time series decomposition: Decompose the time series data into trend, seasonal and random parts to better understand and analyze the changing patterns in the data; the data is represented as:

[0116] ,in, Representation Node In time The characteristic representation of the moment; the decomposition formula is: ,in, It's time The characteristic representation of the moment, Represents the trend part, Indicates the season part, represents the random part;

[0117] Trend analysis: Use the sliding average analysis method to extract the long-term trend in the time series data and evaluate the performance degradation trend of the inverter: The trend calculation formula (sliding average method) is:

[0118] ,in, It's time The trend value at the moment, is the size of the sliding window, Is a node In time Characteristic representation of moments;

[0119] Degradation rate calculation: Based on the extracted long-term trend, the degradation rate of the inverter is calculated to evaluate its performance change rate under different test conditions; the degradation rate formula is: ,in, is the degradation rate, and The time and Trend value at the moment;

[0120] Pattern recognition: Use the dynamic time warping algorithm to identify typical degradation patterns in time series data and analyze the performance change characteristics of the inverter under different test conditions. The dynamic time warping algorithm formula is:

[0121] ,in, There are two time series and In Location and The cumulative distance of It's time point and The distance between

[0122] Degradation mode distinction: Based on the cumulative distance calculated by the dynamic time warping algorithm, the K-means clustering algorithm is used to classify the degradation modes and distinguish different types of degradation modes. The K-means clustering formula is:

[0123] ,in, is the objective function, is the number of clusters, It is The number of points in a cluster, It is points in a cluster, It is The center of the cluster;

[0124] Result output: The evaluation results, including degradation trend and degradation rate, are output to the life prediction unit as basic data for further calculation of the expected life of the inverter. Through the above steps, the degradation trend analysis unit uses time series analysis technology to evaluate the degradation rate and mode of the inverter under different test conditions, obtain the performance degradation trend of the inverter, and distinguish different degradation modes, providing key data support for the life prediction unit.

[0125] The life expectancy calculation of the inverter in the life prediction unit includes:

[0126] Data integration: Integrate the degradation trend data from the degradation trend analysis unit and the historical degradation data to form a complete time series data set ;

[0127] Degradation model fitting: The exponential degradation model is used to fit the integrated time series data. The exponential degradation model formula is: ,in, It's time The trend value at the moment, is the initial trend value, is the degradation rate constant;

[0128] Parameter estimation: The parameters in the degradation model are estimated by the least squares method. The least squares formula is:

[0129] ,in, is the total number of data points, It's time The trend value at the moment, is the initial trend value, is the degradation rate constant;

[0130] Life prediction: Based on the fitted degradation model, the performance of the inverter at a future moment is predicted. By determining the time required for it to reach a preset critical value (such as the performance degrading to a certain threshold), the expected life of the inverter is calculated. The expected life calculation formula is: ,in, is life expectancy, is the performance threshold, is the initial trend value, is the degradation rate constant;

[0131] Result verification: Verify the predicted expected life results to ensure their rationality and accuracy, specifically by comparing with actual degradation data and error analysis. The verification formula is:

[0132] ,in, is the prediction error, It's time The actual trend value at the moment, It's time Through the above steps, the life prediction unit calculates the expected life of the inverter based on the degradation trend analysis results and the historical degradation data, providing a reliable reference for the maintenance and optimization of the inverter.

[0133] The comprehensive evaluation module includes a data receiving unit, a data integration unit, a health status evaluation unit, a performance indicator calculation unit and a report generation unit; wherein:

[0134] Data receiving unit: used to receive expected life data and analysis results from the life prediction module, and test data from the environmental simulation module;

[0135] Data integration unit: used to integrate data from different sources to form a complete data set for subsequent analysis;

[0136] Health status assessment unit: Based on the integrated data, the overall health index of the inverter is calculated through the health status assessment algorithm. The health index calculation formula is: Health index calculation formula: ,in, Represents the health index, represents life expectancy, represents the environmental impact factor, and is the weight coefficient;

[0137] Performance index calculation unit: By analyzing the integrated data, the performance index of the inverter is calculated, including efficiency, power factor, and temperature rise; the performance index calculation formula is (efficiency): ,in, Indicates efficiency, Indicates the output power, Indicates input power;

[0138] Report generation unit: used to generate a comprehensive evaluation report based on the evaluation results. The report content includes health index, various performance indicators (such as efficiency, power factor, etc.), historical data comparison, predicted trends and recommended measures. Through the above units, the comprehensive evaluation module integrates data from the life prediction module and the environmental simulation module, calculates the overall health status and performance indicators of the inverter through a comprehensive evaluation algorithm, and generates a detailed comprehensive evaluation report, providing comprehensive information support for the maintenance and optimization of the inverter.

Claims

1. Photovoltaic energy storage inverter life test and evaluation system, characterized in that: It includes multi-parameter real-time monitoring module, electrical load simulation module, environmental simulation module, life prediction module, comprehensive evaluation module and user interface module; among which: Multi-parameter real-time monitoring module: equipped with a sensor network to collect real-time performance data of the inverter, including voltage, current, power, temperature and humidity; Electrical load simulation module: Use the data collected by the multi-parameter real-time monitoring module to simulate different electrical load conditions and test the performance of the inverter under different working conditions; Environmental simulation module: used to simulate various environmental conditions, including temperature, humidity, salt spray and UV radiation, to test the working performance and durability of the inverter under various extreme conditions; Life prediction module: receives and processes data from the multi-parameter real-time monitoring module, the electrical load simulation module and the environment simulation module, uses graph neural network technology to extract relevant features, analyzes the degradation trend of the inverter, and predicts its remaining life. The life prediction module includes a data receiving unit, a feature extraction unit, a degradation trend analysis unit, a life prediction unit and a data output unit; wherein: Data receiving unit: used to receive data from the multi-parameter real-time monitoring module, the electrical load simulation module and the environment simulation module; Feature extraction unit: uses graph neural network technology to process the received data and extract relevant features of inverter performance degradation; Degradation trend analysis unit: Based on the features obtained from the feature extraction unit, the degradation rate and mode of the inverter under different test conditions are evaluated using time series analysis technology to obtain the performance degradation trend of the inverter; Life prediction unit: Calculates the expected life of the inverter based on the degradation trend analysis results combined with historical degradation data; Data output unit: outputs the life prediction results to the comprehensive evaluation module and the user interface module; The feature extraction unit comprises: Data preprocessing: preprocess the multi-source data from the data receiving unit, including normalization and standardization; Constructing a graph structure: The preprocessed data is constructed into a graph structure, where nodes represent various performance indicators of the inverter and edges represent the relationship between the performance indicators; Initialize node features: Initialize the feature vector of each node. The feature vector includes the performance indicator data corresponding to the node. Graph convolution layer calculation: The graph convolution network is used to update the node features. The node features of each layer are aggregated and updated through the information of neighboring nodes. The update formula is: ,in, Is a node In the The feature vector of the layer, Is a node The set of neighbor nodes of and The nodes are and nodes The degree of , which indicates the number of connections of each node, It is The weight matrix of the layer represents the network parameters, is the activation function; Node feature aggregation: Aggregate the outputs of the multi-layer graph convolutional layer to obtain the final feature representation of each node, which contains the information of neighboring nodes. The aggregation formula is: ,in, Is a node The final feature representation, Aggregate is the feature aggregation function, which represents the aggregation of features at each layer. is the number of layers of the graph convolutional network; Feature output: extract the final feature representation of each node as the relevant feature of inverter performance degradation and transmit it to the degradation trend analysis unit; The degradation trend analysis unit comprises: Feature data preparation: receiving the final feature data from the feature extraction unit and arranging the data in chronological order to form a time series data set; Time series decomposition: Decompose the time series data into trend part, seasonal part and random part; Trend analysis: Use the sliding average analysis method to extract the long-term trend in the time series data and evaluate the performance degradation trend of the inverter: The trend calculation formula is: ,in, It's time The trend value at the moment, is the size of the sliding window, Is a node In time Characteristic representation of moments; Degradation rate calculation: Based on the extracted long-term trend, the degradation rate of the inverter is calculated; the degradation rate formula is: ,in, is the degradation rate, and The time and Trend value at the moment; Pattern recognition: Use the dynamic time warping algorithm to identify typical degradation patterns in time series data and analyze the performance change characteristics of the inverter under different test conditions. The dynamic time warping algorithm formula is: ,in, There are two time series and In Location and The cumulative distance of It's time point and The distance between Degradation mode distinction: Based on the cumulative distance calculated by the dynamic time warping algorithm, the K-means clustering algorithm is used to classify the degradation modes and distinguish different types of degradation modes; Result output: The evaluation results, including degradation trend and degradation rate, are output to the life prediction unit; Comprehensive evaluation module: Integrates the analysis results from the life prediction module and the test data from the environmental simulation module, calculates the overall health status and performance indicators of the inverter through a comprehensive evaluation algorithm, and generates a comprehensive evaluation report; User interface module: It is used to provide an intuitive operation interface, through which users can set test parameters, start test procedures, and view various data and comprehensive evaluation reports in real time.

2. The photovoltaic energy storage inverter life test and evaluation system according to claim 1 is characterized in that: The environmental simulation module includes a temperature gradient simulation unit, a sensor network unit and a data acquisition unit. The temperature gradient simulation unit is configured with multiple temperature sensors, which are arranged around the inverter to simulate and control different temperature conditions of various parts of the inverter during actual operation; the sensor network includes a voltage sensor, a current sensor, a power sensor, a temperature sensor and a humidity sensor, which are used to collect performance data of the inverter in real time; each sensor is connected to the data acquisition unit, which is used to convert the data collected from the sensor into a digital signal and send it to the life prediction module through a data bus.

3. The photovoltaic energy storage inverter life test and evaluation system according to claim 1, characterized in that: The electrical load simulation module includes a load generation unit, a load adjustment unit, a data transmission unit and a test control unit; wherein: Load generation unit: using the voltage, current and power data collected by the multi-parameter real-time monitoring module to generate various electrical load conditions, the load generation unit includes a programmed load controller and power electronics to generate electrical loads in various working states from light load to heavy load, constant load to fluctuating load; Load regulation unit: used to dynamically adjust load conditions and simulate the working state of the inverter in different operating scenarios. The load regulation unit controls the inverter load by adjusting the amplitude, frequency and phase of current and voltage; Data transmission unit: used to transmit data in the load generation and regulation process to the life prediction module and the comprehensive evaluation module. The data transmission unit includes a high-speed data transmission interface and a protocol converter, wherein the high-speed data transmission interface is used to transmit load condition data, and the protocol converter is used to convert the transmission data into a predetermined format.

4. The photovoltaic energy storage inverter life test and evaluation system according to claim 1, characterized in that: The environmental simulation module includes a temperature control unit, a humidity control unit, a salt spray simulation unit, a UV radiation simulation unit and a data acquisition unit; wherein: Temperature control unit: used to simulate different temperature conditions. The temperature control unit includes a heater and a refrigerator to adjust the temperature range of the test environment from -40°C to 85°C. Humidity control unit: used to simulate different humidity conditions. The humidity control unit includes a humidifier and a dehumidifier, which can adjust the humidity range of the test environment from 0% to 100%; Salt spray simulation unit: used to simulate the salt spray environment to test the durability of the inverter in a corrosive environment. The salt spray simulation unit includes a salt spray generator and a control device, which can generate and maintain a salt spray environment of a predetermined concentration; UV radiation simulation unit: used to simulate ultraviolet radiation environment. The UV radiation simulation unit includes a UV lamp and a radiation control device, which can simulate ultraviolet radiation conditions of different intensities and wavelengths; Data acquisition unit: used to collect temperature, humidity, salt spray concentration and UV radiation intensity data in real time during the environmental simulation process. The collected data is transmitted to the life prediction module and comprehensive evaluation module through the data bus.

5. The photovoltaic energy storage inverter life test and evaluation system according to claim 1, characterized in that: The life prediction unit includes: Data integration: Integrate the degradation trend data from the degradation trend analysis unit and the historical degradation data to form a complete time series data set ; Degradation model fitting: The exponential degradation model is used to fit the integrated time series data. The exponential degradation model formula is: ,in, It's time The trend value at the moment, is the initial trend value, is the degradation rate constant; Parameter estimation: Estimate the parameters in the degradation model by the least squares method; Life prediction: Based on the fitted degradation model, the performance of the inverter at a future moment is predicted. By determining the time required for it to reach the preset critical value, the expected life of the inverter is calculated. The expected life calculation formula is: ,in, is life expectancy, is the performance threshold, is the initial trend value, is the degradation rate constant; Result verification: verify the predicted expected life results by comparing with the actual degradation data and error analysis. The verification formula is: ,in, is the prediction error, It's time The actual trend value at the moment, It's time The predicted trend value at the moment.

6. The photovoltaic energy storage inverter life test and evaluation system according to claim 1, characterized in that: The comprehensive evaluation module includes a data receiving unit, a data integration unit, a health status evaluation unit, a performance indicator calculation unit and a report generation unit; wherein: Data receiving unit: used to receive expected life data and analysis results from the life prediction module, and test data from the environmental simulation module; Data integration unit: used to integrate data from different sources to form a complete data set; Health status assessment unit: Based on the integrated data, the overall health index of the inverter is calculated through the health status assessment algorithm. The health index calculation formula is: Health index calculation formula: ,in, Represents the health index, represents life expectancy, represents the environmental impact factor, and is the weight coefficient; Performance index calculation unit: calculates the performance index of the inverter, including efficiency, power factor, and temperature rise, by analyzing the integrated data; Report generation unit: used to generate a comprehensive assessment report based on the assessment results. The report content includes health index, various performance indicators, historical data comparison, predicted trends and recommended measures.

7. The photovoltaic energy storage inverter life test and evaluation system according to claim 1, characterized in that: The user interface module includes a parameter setting unit, a program starting unit, a real-time data display unit and a comprehensive evaluation report display unit; wherein: Parameter setting unit: used for users to input and set test parameters, including temperature, humidity, voltage, and current parameters; Program startup unit: used to start and control the test program; Real-time data display unit: used to display various data collected during the test in real time; Comprehensive evaluation report display unit: used to display the evaluation report generated by the comprehensive evaluation module.

Images