New energy inverter aging test method and system

Abstract

The invention provides a new energy inverter aging test method and system, and relates to the technical field of inverter testing, and the method comprises the steps: building an inverter aging test platform; performing test parameter analysis based on the attribute information of the inverter and the test application demand, and generating an aging test parameter table; performing test optimization and monitoring perception on the target inverter according to the aging test parameter table to obtain an inverter aging test multi-dimensional data stream; key feature extraction and attenuation degree evaluation are carried out on the aging test multi-dimensional data flow, and an inverter operation performance attenuation parameter set is obtained; and calling an aging performance analyzer to carry out aging performance evaluation on the operation performance attenuation parameter set, and determining an evaluation result. According to the aging test method and device, the technical problem that the test result is lack of pertinence and accuracy due to the fact that the test parameters are fixed and customized test analysis under different performance characteristics and application conditions is lacked in the prior art is solved, and the pertinence, adaptability and accuracy of the aging test are improved.

Description

Technical Field

[0001] This application relates to the technical field of inverter testing, and specifically relates to a new energy inverter aging test method and system. Background Art

[0002] Inverters will age during long-term operation, resulting in a decrease in output efficiency and even failures. Therefore, conducting aging tests on inverters has become an important means to ensure their long-term reliability.

[0003] Existing new energy inverter aging test methods usually adopt a set of fixed test parameters and evaluate the inverter through a standardized test process. These methods generally monitor basic parameters such as the working voltage, current, and temperature of the inverter, and conduct load tests under certain environmental conditions to evaluate the performance degradation of the inverter under specific conditions. However, due to the generality of the test parameters, these methods do not fully consider the specific performance characteristics of different models of inverters and the differences in application environments, resulting in a lack of sufficient pertinence in the test results and making it difficult to accurately reflect the aging conditions of different inverters in their respective application scenarios. Secondly, existing test methods usually only focus on single-dimensional performance indicators and fail to comprehensively analyze the multi-dimensional performance degradation of inverters in complex usage environments, resulting in insufficient accuracy and pertinence of the evaluation results. Summary of the Invention

[0004] This application provides a new energy inverter aging test method and system, which solves the technical problem that the existing technology lacks customized test analysis for different inverter performance characteristics and different application conditions due to fixed test parameters, resulting in a lack of pertinence and accuracy in the test results and being unable to comprehensively reflect the aging behavior of inverters under actual usage conditions, and achieves the technical effect of accurately evaluating the aging performance of inverters under different application conditions and improving the pertinence, adaptability, and accuracy of aging tests.

[0005] In view of the above problems, on the one hand, the present application provides a method for aging test of a new energy inverter, and the method includes: building an inverter aging test platform, where the inverter aging test platform includes a sensing test component, a data processor, and a performance evaluation component; connecting a target new energy inverter to the inverter aging test platform, and through the sensing test component, analyzing test parameters based on the attribute information of the target new energy inverter and the test application requirements to generate an inverter aging test parameter table; performing test optimization and monitoring sensing on the target new energy inverter according to the inverter aging test parameter table to obtain a multi-dimensional data stream of the inverter aging test; using the data processor to extract key features and evaluate the attenuation degree of the multi-dimensional data stream of the inverter aging test to obtain a set of inverter operation performance attenuation parameters; and based on the performance evaluation component, invoking an inverter aging performance analyzer, and through the inverter aging performance analyzer, performing an aging performance evaluation on the set of inverter operation performance attenuation parameters to determine the inverter aging performance evaluation result.

[0006] On the other hand, the present application further provides a new energy inverter aging test system, and the system includes: a test platform building module for building an inverter aging test platform, where the inverter aging test platform includes a sensing test component, a data processor, and a performance evaluation component; a test parameter analysis module for connecting a target new energy inverter to the inverter aging test platform, and through the sensing test component, analyzing test parameters based on the attribute information of the target new energy inverter and the test application requirements to generate an inverter aging test parameter table; an aging test module for performing test optimization and monitoring sensing on the target new energy inverter according to the inverter aging test parameter table to obtain a multi-dimensional data stream of the inverter aging test; a performance attenuation evaluation module for using the data processor to extract key features and evaluate the attenuation degree of the multi-dimensional data stream of the inverter aging test to obtain a set of inverter operation performance attenuation parameters; and an aging performance evaluation module for based on the performance evaluation component, invoking an inverter aging performance analyzer, and through the inverter aging performance analyzer, performing an aging performance evaluation on the set of inverter operation performance attenuation parameters to determine the inverter aging performance evaluation result.

[0007] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0008] Build an inverter aging test platform, which provides an integrated hardware and software environment for the entire aging test, including sensing test components, data processors, and performance evaluation components. Through the construction of the platform, the organic combination of different test devices and functional modules is ensured, enabling comprehensive monitoring and evaluation of the inverter. By analyzing the performance characteristics and specific usage environment of the inverter through the sensing test components, a personalized test parameter table is generated, making the test more in line with the actual usage requirements of the inverter rather than relying on fixed general parameters. Conduct test optimization and monitoring perception according to the generated test parameter table to obtain multi-dimensional data streams. Test optimization ensures that the true performance of the inverter under various application conditions can be effectively captured, and monitoring perception provides real-time feedback on the performance status of the inverter, enabling comprehensive collection of various data during the aging test of the inverter, reflecting the status of the inverter from multiple dimensions, and obtaining comprehensive test data. Through the data processor, feature extraction and attenuation degree evaluation are carried out on the multi-dimensional data stream of the aging test, further exploring the key performance changes of the inverter during the aging process, enabling accurate quantitative analysis of the degree, mode, and influencing factors of the decline, and ensuring the accuracy of the test results. Through the inverter aging performance analyzer in the performance evaluation component, a comprehensive performance evaluation is carried out in combination with the decline parameter set, and the health status and decline trend of the inverter are judged based on the test results, finally obtaining accurate aging performance evaluation results, providing a scientific basis for subsequent decision-making.

[0009] In summary, this application constructs a systematic new energy inverter aging test system. Starting from building a dedicated test platform, to customized parameter analysis, multi-dimensional data stream collection, key feature extraction, and dedicated aging performance evaluation, it can accurately evaluate the aging performance of new energy inverters with different types and application requirements, achieving customization, high precision, and high adaptability of the inverter aging test, significantly improving the reliability and pertinence of the test results, and providing a reliable basis for the maintenance, optimization, and service life prediction of the inverter.

[0010] The above description is only an overview of the technical solution of this application. In order to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features, and advantages of this application more obvious and understandable, the following specifically illustrates the specific implementation manners of this application. Brief Description of the Drawings

[0011] Figure 1 It is a schematic flow chart of a new energy inverter aging test method provided by an embodiment of this application.

[0012] Figure 2 It is a schematic flow chart of generating an inverter aging test parameter table in a new energy inverter aging test method provided by an embodiment of this application.

[0013] Figure 3 It is a schematic flowchart for obtaining the inverter operation performance degradation parameter set in a new energy inverter aging test method provided by an embodiment of the present application.

[0014] Figure 4 It is a schematic structural diagram of a new energy inverter aging test system provided by an embodiment of the present application.

[0015] Explanation of reference numerals: Test platform construction module 10, test parameter analysis module 20, aging test module 30, performance degradation evaluation module 40, aging performance evaluation module 50. Specific implementation manner

[0016] By providing a new energy inverter aging test method and system in an embodiment of the present application, the technical problem in the prior art that due to fixed test parameters and lack of customized test analysis under different inverter performance characteristics and different application conditions, the test results lack pertinence and accuracy and cannot comprehensively reflect the aging behavior of the inverter under actual use conditions is solved, and the technical effects of accurately evaluating the aging performance of the inverter under different application conditions and improving the pertinence, adaptability and accuracy of the aging test are achieved.

[0017] Embodiment 1, as Figure 1 shown, an embodiment of the present application provides a new energy inverter aging test method, and the method includes:

[0018] Step S1: Build an inverter aging test platform, and the inverter aging test platform includes a sensing test component, a data processor and a performance evaluation component.

[0019] Specifically, before the aging test, first construct a platform architecture including a sensing test component, a data processor and a performance evaluation component. Among them, the sensing test component is mainly responsible for sensing and collecting various information related to the inverter (such as the working temperature, voltage, current, etc. of the inverter); the data processor is responsible for processing and analyzing the various data collected; the performance evaluation component is used to evaluate the performance of the inverter and judge the performance status of the inverter. Exemplarily, in terms of hardware, sensors can be used to construct the sensing test component for collecting the electrical parameters of the inverter; a microprocessor or a dedicated data processing chip can be used to construct the data processor; a software module with specific algorithms can be used to construct the performance evaluation component. This inverter aging test platform provides a complete test environment for the subsequent inverter aging test, enabling each link such as the collection, processing and performance evaluation of test data to proceed in an orderly manner.

[0020] Step S2: Connect the target new energy inverter to the inverter aging test platform, and perform test parameter analysis based on the attribute information of the target new energy inverter and the test application requirements through the sensing test component to generate an inverter aging test parameter table.

[0021] Specifically, the target new energy inverter is a specific new energy inverter that needs to be subjected to aging tests, which can be a photovoltaic inverter or an energy storage system inverter of any model, etc. After connecting the target new energy inverter to the built inverter aging test platform, the sensing test component starts to work, reads the attribute information of the inverter, and obtains the test application requirements. Among them, the attribute information of the inverter can be obtained through the identifier or communication interface inside the inverter, including information related to the inverter itself such as the model, power, design parameters, and internal structure of the inverter; the test application requirements are preset by the tester according to the actual test purpose and usage scenario, such as test requirements under different environmental temperatures and load conditions. Then, perform test parameter analysis on this attribute information and test application requirements to generate an inverter aging test parameter table, and this inverter aging test parameter table stipulates the various parameters that need to be detected when performing aging tests on the inverter. For example, according to the power size and application scenario of the inverter, determine the load level and duration of the aging test.

[0022] By combining the self-attributes of the inverter and the actual test requirements to generate a test parameter table, the test parameters are no longer fixed, but are targeted, can better adapt to different inverters and different test purposes, and improve the accuracy and effectiveness of the test.

[0023] Step S3: Optimize the test and monitor the perception of the target new energy inverter according to the inverter aging test parameter table to obtain a multi-dimensional data stream of inverter aging tests.

[0024] Specifically, according to the inverter aging test parameter table generated in Step S2, use the sensing test component to optimize the test of the target new energy inverter, adjust and improve the test process to make it more in line with the test target, such as adjusting the data acquisition frequency or changing the load conditions, etc., and then monitor and perceive the state of the inverter, use various sensors (such as voltage sensors, current sensors, temperature sensors, etc.) to collect inverter test data, and then integrate the data collected from different sensors to form a multi-dimensional data stream of inverter aging tests. This multi-dimensional data stream of inverter aging tests contains continuous data collected from multiple aspects (such as different dimensions of voltage, current, temperature, frequency, etc.) during the aging test process. For example, a data stream may contain the voltage values, current values, and operating temperature values of the inverter at different times.

[0025] By performing test optimization and monitoring perception according to a customized parameter table, comprehensive and multi-dimensional inverter aging test data can be obtained. Compared with single-dimensional data, these data can more accurately reflect the aging state of the inverter.

[0026] Step S4: Use the data processor to extract key features and evaluate the attenuation degree of the multi-dimensional data stream of the inverter aging test, and obtain a set of inverter operating performance attenuation parameters.

[0027] Specifically, the data processor processes the multi-dimensional data stream of the inverter aging test obtained in step S3. Data mining techniques (such as principal component analysis, clustering analysis, etc.) are used to extract key features and find those features that have important indicative effects on the aging state of the inverter. For example, among a large number of temperature data, key features such as the highest temperature and the temperature fluctuation range are found. Then, according to a pre-set evaluation criterion (which can be based on a theoretical model or past empirical data), the attenuation degree of the inverter is evaluated, that is, the degree of decline in the inverter performance over time is evaluated, so as to obtain a set of inverter operating performance attenuation parameters. Among them, the set of inverter operating performance attenuation parameters is a data set of a group of parameters reflecting the attenuation degree of the inverter operating performance. Exemplarily, the attenuation parameter set can include parameters such as the power attenuation percentage and the efficiency decline value.

[0028] Through the processing of the multi-dimensional data stream by the data processor, key performance attenuation parameters are extracted from a large amount of complex data, providing more targeted data support for subsequent performance evaluation and improving the accuracy and scientific nature of the evaluation.

[0029] Step S5: Based on the performance evaluation component, call the inverter aging performance analyzer, and use the inverter aging performance analyzer to evaluate the aging performance of the set of inverter operating performance attenuation parameters to determine the inverter aging performance evaluation result.

[0030] Specifically, the inverter aging performance analyzer is a tool or module in the performance evaluation component dedicated to analyzing the aging performance of the inverter. After obtaining the set of inverter operating performance attenuation parameters, the performance evaluation component calls the inverter aging performance analyzer and inputs this set of inverter operating performance attenuation parameters into this analyzer. This analyzer contains some specific algorithms (such as algorithms based on fuzzy logic, neural networks, etc.). According to these algorithms, the parameter set is analyzed to determine the inverter aging performance evaluation result. This result can provide an accurate basis for the maintenance, replacement or further optimization of the inverter. For example, analyze the relationship between the performance attenuation and aging degree of the inverter in historical data through a linear regression model. According to the prediction result of the model, output an inverter aging performance evaluation report.

[0031] Further, as Figure 2As shown, step S2 includes:

[0032] Step S21: Obtain the inverter attribute factor information, where the inverter attribute factor information includes model specifications, output waveform, number of output phases, conversion method, and power rating.

[0033] Step S22: Classify and label the attribute information of the target new energy inverter according to the inverter attribute factor information to obtain the inverter attribute factor parameters.

[0034] Step S23: Analyze the scenario parameters of the test application requirements of the target new energy inverter to obtain the inverter application scenario parameters.

[0035] Step S24: Build an inverter aging test parameter library, traverse and retrieve the inverter aging test parameter library based on the inverter attribute factor parameters and the inverter application scenario parameters, and generate an inverter aging test parameter table.

[0036] Specifically, extract the inverter attribute factor information pre-configured in the inverter aging test platform. These attribute factor information are the specific types of attribute information that need to be read from the target new energy inverter during the subsequent aging test process, including model specifications, output waveform, number of output phases, conversion method, and power rating. Among them, the model specification is the identification information such as the model number of the inverter. Inverters of different models have differences in performance, functions, etc.; the output waveform is the electrical signal waveform output by the inverter, and common ones include sine wave, square wave, etc.; the number of output phases refers to the number of phases output by the inverter, such as single-phase, three-phase, etc.; the conversion method is the power conversion method of the inverter, such as the DC-AC (direct current - alternating current) conversion method, etc., which determines the basic function and working principle of the inverter; the power rating indicates the rated power of the inverter, which determines the size of the load that the inverter can drive.

[0037] Obtain the specific attribute information such as the model specifications, output waveform, number of output phases, conversion method, and power rating of the target new energy inverter through the communication interface of the target new energy inverter according to the inverter attribute factor information, and conduct classification and labeling. For example, for a single-phase inverter used in a household photovoltaic system, the attribute information obtained through the communication interface is as follows: model A100, sine wave, single-phase, DC-AC conversion, rated power 3kW. Then, label "model A100" as the "model" category, "sine wave" as the "output waveform" category; "single-phase" as the "number of output phases" category; "DC-AC conversion" as the "conversion method" category; "rated power 3kW" as the "power rating" category, so as to organize the inverter attribute information into inverter attribute factor parameters, making the attribute information of the inverter more standardized and easy to process, facilitating integration with the inverter application scenario parameters in the subsequent steps and preparing for generating the test parameter table.

[0038] Analyze the scenario parameters in detail for the test application requirements of the target new energy inverter. If the test requirements are given in the form of a document, text analysis tools or manual analysis methods can be used to extract the parameters related to the scenario. For example, if the test requirements mention testing in an environment with an altitude above 2000 meters and a temperature between 30°C and 50°C, then the altitude above 2000 meters and the temperature range between 30°C and 50°C are the inverter application scenario parameters to be extracted. By analyzing the test application requirements to obtain the inverter application scenario parameters, the specific scenario requirements for the test are clarified, enabling the test to be closer to the actual requirements and providing a scenario-related basis for generating a test parameter table that conforms to the actual situation.

[0039] The inverter aging test parameter library is a pre-established database containing various test parameters that may be used for inverter aging tests. This test parameter library can be established by collecting past test experience data, referring to relevant industry standards, and theoretical calculation results. Exemplarily, the inverter aging test parameter library may contain information such as the value ranges of test parameters such as voltage, current, and frequency that may be used when testing different models of inverters in different environments. Based on the obtained inverter attribute factor parameters and inverter application scenario parameters, traverse and retrieve in the parameter library. For example, database query statements or specialized search algorithms can be used to search for test parameters in the parameter library that match the inverter attribute factor parameters and inverter application scenario parameters, and combine these parameters to generate an inverter aging test parameter table.

[0040] By traversing and retrieving the inverter aging test parameter library and combining the inverter attribute factor parameters and inverter application scenario parameters to generate a test parameter table, the generated test parameter table takes into account both the characteristics of the inverter itself and the application scenario requirements of the test, improving the accuracy and pertinence of the test parameters.

[0041] Further, step S24 includes:

[0042] Step S241: Use the inverter attribute factor information and application scenario information to perform data coding and classification on the inverter aging test parameter library to obtain an inverter aging test coding parameter library.

[0043] Step S242: Based on the inverter attribute factor parameters and the inverter application scenario parameters, calculate the similarity with each test parameter in the inverter aging test coding parameter library to obtain a set of Jaccard similarity coefficients for the test parameters.

[0044] Step S243: Sort the inverter aging test coding parameter library in descending order according to the test parameter Jaccard similarity coefficient set, and determine the inverter aging test parameter sequence.

[0045] Step S244: Set a similarity threshold according to the aging test accuracy requirement, and perform division and optimization on the inverter aging test parameter sequence based on the similarity threshold to generate the inverter aging test parameter table.

[0046] Specifically, before traversing and retrieving the inverter aging test parameter library, it is necessary to perform data coding and classification on the inverter aging test parameter library, that is, the inverter attribute factor information and application scenario information in the inverter aging test parameter library are converted into a coding form according to certain rules, so as to classify and manage the inverter aging test parameter library. First, determine the coding rules, which can be formulated according to the characteristics of the inverter attribute factor information (such as model specifications, output waveforms, etc.) and application scenario information (such as test environment temperature, humidity, etc.). For example, for model specifications, specific coding can be performed according to their letter and number combinations; for temperature ranges, coding can be performed according to a certain interval. Then, use programming or database management tools (such as SQL statements to operate in the database) to code and classify the data in the inverter aging test parameter library according to this coding rule, so as to obtain the inverter aging test coding parameter library. Exemplarily, a new energy inverter has a model of "A100", a power of "3kW", an output waveform of "sinusoidal wave", an application scenario of "household photovoltaic system", and environmental conditions of "room temperature indoors". These information can be encoded as: model coding: 001 (A100); power coding: 010 (3kW); output waveform coding: 011 (sinusoidal wave); application scenario coding: 100 (household photovoltaic system); environmental condition coding: 101 (room temperature indoors), and these codes will be stored in the inverter aging test coding parameter library. Similarly, the inverter attribute factor parameters of the target new energy inverter obtained in the aforementioned step S22 and the inverter application scenario parameters of the target new energy inverter obtained in step S23 are also encoded in the same way to facilitate subsequent similarity calculation and retrieval.

[0047] After obtaining the inverter aging test coding parameter library, the inverter attribute factor parameters and inverter application scenario parameters of the target new energy inverter are regarded as a set, and the Jaccard similarity coefficients are calculated respectively with the inverter attribute factor parameters and inverter application scenario parameters (also regarded as sets) corresponding to each group of test parameters in the inverter aging test coding parameter library, and finally the test parameter Jaccard similarity coefficient set is obtained. By calculating the Jaccard similarity coefficient set, the similarity degree between the inverter attribute factor parameters and inverter application scenario parameters of the target new energy inverter and the test parameters corresponding to each group of test parameters in the inverter aging test coding parameter library can be quantified, providing a basis for screening appropriate test parameters subsequently.

[0048] Using sorting algorithms (such as variants of bubble sort, quick sort, etc.), the data in the inverter aging test coding parameter library is sorted in descending order according to the values in the test parameter Jaccard similarity coefficient set, so that the test parameters most similar to the inverter attribute factor parameters and inverter application scenario parameters of the target new energy inverter are ranked in the front, thereby determining the inverter aging test parameter sequence, which is convenient for subsequent screening according to the aging test accuracy requirements.

[0049] According to the aging test accuracy requirements, the similarity threshold is preset by the tester or based on past experience to judge whether the test parameters meet the aging test accuracy requirements. For example, if the similarity threshold is set to 0.8, then only the test parameters with a Jaccard similarity coefficient greater than 0.8 will be considered to meet the accuracy requirements. Then, in the obtained inverter aging test parameter sequence, the test parameters with a Jaccard similarity coefficient lower than the similarity threshold are discarded, and only the test parameters higher than the threshold are retained. The conditional judgment statements in programming (such as if statements) can be used to achieve this division and optimization, and finally the inverter aging test parameter table is generated. By setting the similarity threshold for division and optimization, it can be ensured that the parameters in the generated inverter aging test parameter table meet the aging test accuracy requirements, thereby improving the accuracy and reliability of the test results.

[0050] The above steps achieve the precise selection of inverter aging test parameters through data coding and classification, similarity calculation, descending order arrangement, and division and optimization, not only improving the efficiency and accuracy of parameter selection, but also ensuring that the test parameters highly match the characteristics and application scenarios of the target inverter. The finally generated test parameter table provides scientific and precise guidance for the aging test, significantly enhancing the pertinence and reliability of the aging test.

[0051] Further, step S3 includes:

[0052] Step S31: Conduct an aging test on the target new energy inverter according to the inverter aging test parameter table to obtain the initial inverter aging test data stream.

[0053] Step S32: Collect the inverter abnormal operation database, and use a deep neural network to perform identification training on the inverter abnormal operation database to construct an inverter operation anomaly recognizer.

[0054] Step S33: Based on the inverter operation anomaly recognizer, perform anomaly identification on the initial inverter aging test data stream to determine the inverter abnormal operation parameters.

[0055] Step S34: Based on the inverter abnormal operation parameters, supplement and optimize the inverter aging test parameter table to obtain an optimized aging test parameter table.

[0056] Step S35: Use the optimized aging test parameter table to perform test monitoring and perception on the target new energy inverter to obtain the multi-dimensional data stream of the inverter aging test.

[0057] Specifically, according to the test parameters (such as test time interval, test voltage range, etc.) set in the inverter aging test parameter table, use test instruments (such as voltmeters, ammeters, temperature sensors, etc.) to conduct an aging test on the target new energy inverter, collect the test data of these tests and combine them in a certain time sequence and format to obtain the initial inverter aging test data stream. For example, use a high-precision voltage sensor to perform tests at a frequency of collecting voltage values every 5 minutes, and arrange these voltage values in order to become part of the data stream. The initial inverter aging test data stream provides basic data for subsequent state analysis (such as anomaly identification, etc.) of the inverter.

[0058] The inverter abnormal operation database is a database that stores data related to the abnormal operation of the inverter. These data related to abnormal operation can come from previous fault records, simulated fault experiments, etc., including records of parameters such as voltage, current, and temperature of the inverter under different abnormal conditions (such as short circuit, overload, overheat, etc.). For example, data such as the current of the inverter suddenly increasing to a certain value and the temperature rising sharply under a certain short circuit condition. Using a deep neural network framework (such as TensorFlow or PyTorch), divide the data in the inverter abnormal operation database into input features (such as various electrical parameters) and output labels (whether it is abnormal) for identification training. After multiple iterative trainings, adjust parameters such as the weights of the neural network until a better recognition effect is achieved, thereby constructing an inverter operation anomaly recognizer. Constructing an inverter operation anomaly recognizer can effectively identify the abnormal operation state of the inverter during the aging test, improve the detection ability of inverter abnormal conditions, and help to discover potential problems in a timely manner.

[0059] Input the initial inverter aging test data stream into the already constructed inverter abnormal operation recognizer. The inverter abnormal operation recognizer analyzes and judges each data point in the data stream according to the training model inside it. If it is judged as abnormal, record the corresponding relevant parameters at this time, and collate all the abnormal parameters to generate the inverter abnormal operation parameters.

[0060] Analyze the inverter abnormal operation parameters, find out the possible deficiencies in the original inverter aging test parameter table, and supplement and optimize the aging test parameter table. For example, if it is found that some parameters are not tested or the test frequency is insufficient during abnormal operation, supplement these parameters or adjust the test frequency. For example, when the inverter abnormal operation recognizer finds that the inverter has abnormal fluctuations under the overload state, then increase the test time under the overload state in the aging test parameter table, from the original 2 hours to 4 hours. By adding and modifying relevant parameters in the original parameter table, obtain the optimized aging test parameter table to more comprehensively simulate the actual operation state of the inverter, and improve the pertinence and accuracy of the aging test.

[0061] Use the test parameters set by the optimized aging test parameter table to retest and monitor the target new energy inverter, integrate the newly collected test data with the original test data, obtain more comprehensive operation data, form the inverter aging test multi-dimensional data stream, and provide richer data resources for the subsequent analysis of the inverter operation performance decay parameter set.

[0062] The above steps can automatically identify the abnormal operation of the inverter by combining a deep neural network, dynamically optimize the test parameter table, can adjust the test conditions in real time, accurately identify the abnormal operation state, improve the adaptability and accuracy of the test, ensure that the inverter aging test can better fit the actual working environment, and obtain more comprehensive aging test data.

[0063] Further, as Figure 3 shown, step S4 includes:

[0064] Step S41: Obtain the data preprocessing program according to the data processor, and the data preprocessing program includes abnormal data identification, abnormal data cleaning, and data standardization.

[0065] Step S42: Preprocess the inverter aging test multi-dimensional data stream based on the data preprocessing program to obtain the standard inverter aging test multi-dimensional data stream.

[0066] Step S43: Determine the inverter aging associated performance set according to the inverter aging test target, and the inverter aging associated performance set includes conversion efficiency, output power stability, output waveform quality, protection mechanism trigger frequency, and internal component reliability.

[0067] Step S44: Based on the inverter aging-related performance set, extract key features and evaluate the attenuation degree of the multi-dimensional data stream of the standard inverter aging test to obtain an inverter operation performance attenuation parameter set.

[0068] Specifically, algorithms or rules for data preprocessing, that is, data preprocessing programs, are pre-stored in the data processor, including abnormal data identification, abnormal data cleaning, and data standardization. Among them, abnormal data identification is used to find data points that do not conform to normal rules or expected ranges in the data; abnormal data cleaning is used to remove or correct these data from the data set after identifying abnormal data. For example, replace the identified incorrect voltage value with a reasonable estimated value or directly delete it; data standardization is to convert data with different dimensions and different value ranges into a unified standard data form. For example, convert numerical values in different ranges such as current values and voltage values into the range of 0 to 1 to facilitate subsequent data analysis.

[0069] Input the multi-dimensional data stream of the inverter aging test into the data preprocessing program, and process the multi-dimensional data stream according to the processes of abnormal data identification, abnormal data cleaning, and data standardization. First, run the abnormal data identification program to find abnormal data points in the data stream, then perform abnormal data cleaning operations, and finally perform standardization processing on the cleaned data to obtain the multi-dimensional data stream of the standard inverter aging test. Exemplarily, for abnormal data identification, the method of setting thresholds can be used. For example, set upper and lower limits according to the ranges of parameters such as voltage and current when the inverter is working normally, and data outside this range is identified as abnormal data; abnormal data cleaning can be implemented by writing program logic. For example, after identifying abnormal data, replace the abnormal data with the average value of adjacent normal data or directly delete it; data standardization can use the maximum-minimum normalization formula. After data preprocessing, the data quality of the multi-dimensional data stream of the standard inverter aging test is higher, and the data form is more standardized and unified, providing a high-quality and standardized data basis for key feature extraction and attenuation degree evaluation based on the inverter aging-related performance set, which helps to improve the accuracy of the analysis results.

[0070] According to the objectives of the inverter aging test (such as evaluating the performance changes of the inverter after long-term use, etc.), determine the set of inverter aging-related performance. This set of inverter aging-related performance is a collection of performance indicators related to inverter aging (including indicator types and indicator value ranges), and these performance indicators can be determined through the principle analysis of the inverter, past test experience, and relevant technical documents. Usually, these performance indicators include conversion efficiency, output power stability, output waveform quality, protection mechanism trigger frequency, and internal component reliability. Among them, the conversion efficiency refers to the efficiency of the inverter in converting input power into output power, reflecting the performance of the inverter during the energy conversion process. As the inverter ages, the conversion efficiency may decrease; the output power stability indicates the degree of stability of the inverter's output power over a period of time, and aging will affect its stability; the output waveform quality refers to the degree of approximation of the inverter's output waveform to the ideal waveform, which can be measured by indicators such as waveform distortion. As the inverter ages, waveform distortion and other situations may occur; the protection mechanism trigger frequency is the frequency at which the internal protection mechanism of the inverter is triggered (when abnormal situations such as overcurrent and overvoltage occur), and this frequency can reflect the health status of the inverter. Aging may lead to abnormal protection mechanism trigger frequency; the internal component reliability refers to the reliability of each component inside the inverter (such as transistors, capacitors, etc.) during long-term operation. As it ages, components may fail, thus affecting the overall performance of the inverter.

[0071] Through data mining algorithms such as principal component analysis and correlation analysis, extract features related to the set of inverter aging-related performance from the multi-dimensional data stream of the standard inverter aging test. For example, for the conversion efficiency, the input power and output power at different time points can be found from the data stream, and the change of the conversion efficiency over time can be calculated; for the output power stability, the change of the fluctuation range of the output power over time can be analyzed. Using the extracted key features for attenuation degree evaluation, the current performance indicators can be compared with the initial state of the inverter or the standard performance indicators, and statistical analysis methods (such as linear regression) are used to evaluate the attenuation degree of these features, generating a set of inverter operation performance attenuation parameters. The set of inverter operation performance attenuation parameters can accurately reflect the performance attenuation situation of the inverter during operation, providing key data support for subsequent aging performance evaluation.

[0072] The above steps achieve in-depth processing and analysis of the inverter aging test data by obtaining a data preprocessing program, preprocessing the multi-dimensional data stream, determining the aging correlation performance set, and performing key feature extraction and attenuation degree evaluation. This not only improves the quality and usability of the data, but also accurately reflects the aging state of the inverter through key feature extraction and attenuation degree evaluation. The finally generated inverter operation performance attenuation parameter set provides high-quality data support for subsequent performance evaluation, significantly improving the accuracy and reliability of the aging test.

[0073] Further, step S44 includes:

[0074] Step S441: Extract correlation features from the multi-dimensional data stream of the standard inverter aging test based on the inverter aging correlation performance set to obtain an inverter performance correlation feature set.

[0075] Step S442: Evaluate the criticality of each correlation performance in the inverter aging correlation performance set to obtain an aging correlation performance criticality set.

[0076] Step S443: Perform in-depth feature selection and extraction on the inverter performance correlation feature set according to the aging correlation performance criticality set to obtain an inverter operation key feature set.

[0077] Step S444: Evaluate the performance attenuation degree based on the inverter operation key feature set to obtain an inverter operation performance attenuation parameter set.

[0078] Specifically, for each performance index in the inverter aging correlation performance set, search for related features in the multi-dimensional data stream of the standard inverter aging test. This can be achieved through the association rule mining algorithm in data mining technology. For example, for the performance index of output power stability, analyze data such as output power values and load change conditions at different times in the data stream, extract the data related to output power stability, and summarize them to form an inverter performance correlation feature set.

[0079] Evaluate the criticality of each correlation performance in the inverter aging correlation performance set to obtain an aging correlation performance criticality set. Methods such as the Analytic Hierarchy Process (AHP) or the expert scoring method can be used to evaluate the criticality of each correlation performance in the inverter aging correlation performance set. For example, through the Analytic Hierarchy Process, construct a hierarchical structure model, make pairwise comparisons of each performance index, and finally determine the weights of each index to obtain an aging correlation performance criticality set. Each element in this aging correlation performance criticality set represents the importance of the corresponding correlation performance to the overall aging performance evaluation of the inverter, providing a basis for subsequent selective feature extraction.

[0080] According to the aging - related performance criticality set, screen the inverter performance - related feature set, and retain the features with high criticality and close correlation with aging performance. The feature selection algorithm (such as the Recursive Feature Elimination method, RFE) can be used to achieve this. The greater the criticality, the greater the impact of the associated performance on the aging performance. Therefore, the greater the depth of extraction of the associated features corresponding to this associated performance, the more key features are extracted. By such selective feature extraction, the key feature set of inverter operation can be obtained, which can reduce unnecessary feature interference, focus on the most critical features for evaluating the degradation of inverter operation performance, and improve the accuracy and efficiency of the evaluation.

[0081] For each feature in the key feature set of inverter operation, use statistical analysis methods (such as linear regression) to evaluate the change rate of each key feature, and obtain the degradation parameters of each performance during the aging process of the inverter. These degradation parameters constitute the inverter operation performance degradation parameter set. For example, the key feature set of inverter operation includes current fluctuation and voltage fluctuation. By linearly regressing the change trend of current fluctuation over time, it is found that the attenuation degree of current fluctuation increases by 0.1 A per month; the attenuation degree of voltage fluctuation increases by 0.2 V per month.

[0082] The above steps, through associated feature extraction, criticality evaluation, feature depth selection extraction, and performance attenuation degree evaluation, have achieved in - depth processing and analysis of inverter aging test data. It not only improves the accuracy and representativeness of feature selection but also, through the evaluation of performance attenuation degree, accurately reflects the aging state of the inverter, significantly enhancing the accuracy and reliability of the aging test.

[0083] Furthermore, step S5 includes:

[0084] Step S51 : Collect and obtain the inverter aging data set, where the inverter aging data set includes the historical operation performance degradation data of the inverter aging - related performance set and the corresponding aging degree evaluation data.

[0085] Step S52 : Take the historical operation performance degradation data of the inverter aging - related performance set as the independent variable, and the corresponding aging degree evaluation data as the dependent variable. Use the linear regression method to perform regression analysis and fitting on the independent variable and the dependent variable, establish an inverter aging performance analyzer, and store the inverter aging performance analyzer in the performance evaluation component.

[0086] Specifically, an inverter aging dataset is collected from the historical operation records and test data of inverters with similar performance and usage environments. This inverter aging dataset includes the historical operation performance decay data of the inverter aging associated performance set and the corresponding aging degree evaluation data. Among them, the historical operation performance decay data is a record of the decay of performance indicators such as conversion efficiency and output power stability over time or operation cycles during the past operation of the inverter; the corresponding aging degree evaluation data is the evaluation result of the overall aging degree of the inverter under these performance decay conditions, such as the quantitative or qualitative data corresponding to mild aging, moderate aging, or severe aging, etc. The inverter aging dataset provides a data basis for the subsequent establishment of an inverter aging performance analyzer, enabling the analyzer to build a model based on actual historical data and improving the accuracy and reliability of the analysis results.

[0087] Taking the historical operation performance decay data of the inverter aging associated performance set as the independent variable and the corresponding aging degree evaluation data as the dependent variable, input them into a linear regression model for linear regression analysis. The linear regression model will automatically calculate the regression coefficients and determine an optimal linear fitting equation to describe the relationship between the two, thereby establishing an inverter aging performance analyzer. Then store this analyzer in the performance evaluation component, which can be achieved through database operations or file storage for subsequent invocation when needed.

[0088] By establishing an inverter aging performance analyzer through the above steps, the aging degree of the inverter can be quickly and accurately evaluated based on the operation performance decay data, improving the efficiency and accuracy of the evaluation of the inverter aging performance.

[0089] In summary, the new energy inverter aging test method provided by the embodiments of this application has the following technical effects:

[0090] By integrating a perception test component, a data processor, and a performance evaluation component, an inverter aging test platform is built, providing a systematic operation environment for subsequent test processes and ensuring the coherence and efficiency of the test process. According to the attribute information of the target inverter and the test application requirements, a personalized test parameter table is generated to ensure that the test can accurately reflect the aging characteristics of the inverter in actual use. The inverter is tested with the optimized test parameter table to obtain multi-dimensional data streams. Not only the basic operation data of the inverter is collected, but also through anomaly recognition and data supplementation optimization, the dimension and depth of the data are further enriched, providing more comprehensive information for subsequent data processing and analysis. The multi-dimensional data streams are preprocessed, key features are extracted, and the attenuation degree is evaluated to obtain a set of inverter operation performance attenuation parameters. Through scientific data processing methods, the key features that can reflect the aging state of the inverter are extracted, providing an accurate basis for performance evaluation. Based on the performance evaluation component, the inverter aging performance analyzer is called to evaluate the set of operation performance attenuation parameters to determine the aging performance evaluation result, providing an accurate test conclusion for users.

[0091] Generally speaking, through the systematic test platform and customized test parameter generation in this application embodiment, the accurate evaluation of the aging state of new energy inverters is realized. It can not only generate personalized test parameters according to the characteristics and application conditions of different inverters, but also comprehensively reflect the aging characteristics of the inverter through the in-depth processing of multi-dimensional data streams and the extraction of key features. Finally, through the intelligent performance evaluation model, the aging performance of the inverter is scientifically evaluated, significantly improving the pertinence, adaptability of the inverter aging test and the accuracy of the test results, providing more scientific and reliable data support for the R & D, production and maintenance of the inverter.

[0092] Embodiment 2, as Figure 4 shown, based on the same inventive concept as the foregoing Embodiment 1, this application embodiment provides a new energy inverter aging test system, and the system includes:

[0093] A test platform building module 10, configured to build an inverter aging test platform, and the inverter aging test platform includes a perception test component, a data processor, and a performance evaluation component.

[0094] A test parameter analysis module 20, configured to connect the target new energy inverter to the inverter aging test platform, and perform test parameter analysis through the perception test component based on the attribute information of the target new energy inverter and the test application requirements to generate an inverter aging test parameter table.

[0095] An aging test module 30, configured to perform test optimization and monitoring perception on the target new energy inverter according to the inverter aging test parameter table to obtain multi-dimensional data streams of the inverter aging test.

[0096] The performance degradation evaluation module 40 is configured to extract key features and evaluate the degradation degree of the multi-dimensional data stream of the inverter aging test by using the data processor, so as to obtain an inverter operation performance degradation parameter set.

[0097] The aging performance evaluation module 50 is configured to call an inverter aging performance analyzer based on the performance evaluation component, and perform aging performance evaluation on the inverter operation performance degradation parameter set through the inverter aging performance analyzer to determine an inverter aging performance evaluation result.

[0098] Furthermore, the test parameter analysis module 20 in the embodiment of the present application is further configured to perform the following steps:

[0099] Obtain inverter attribute factor information, where the inverter attribute factor information includes model specifications, output waveforms, output phases, conversion methods, and power magnitudes; classify and identify the attribute information of the target new energy inverter according to the inverter attribute factor information to obtain inverter attribute factor parameters; perform scenario parameter parsing on the test application requirements of the target new energy inverter to obtain inverter application scenario parameters; construct an inverter aging test parameter library, and traverse and retrieve the inverter aging test parameter library based on the inverter attribute factor parameters and the inverter application scenario parameters to generate an inverter aging test parameter table.

[0100] Furthermore, the test parameter analysis module 20 in the embodiment of the present application is further configured to perform the following steps:

[0101] Perform data coding classification on the inverter aging test parameter library by using the inverter attribute factor information and application scenario information to obtain an inverter aging test coding parameter library; calculate the similarity between the inverter attribute factor parameters and the inverter application scenario parameters and each test parameter in the inverter aging test coding parameter library to obtain a test parameter Jaccard similarity coefficient set; sort the inverter aging test coding parameter library in descending order according to the test parameter Jaccard similarity coefficient set to determine an inverter aging test parameter sequence; set a similarity threshold according to the aging test accuracy requirement, and perform division and optimization on the inverter aging test parameter sequence based on the similarity threshold to generate the inverter aging test parameter table.

[0102] Furthermore, the aging test module 30 in the embodiment of the present application is further configured to perform the following steps:

[0103] Perform an aging test on the target new energy inverter according to the aging test parameter table of the inverter to obtain an initial inverter aging test data stream; collect and obtain an inverter abnormal operation database, and use a deep neural network to perform identification training on the inverter abnormal operation database to construct an inverter operation abnormality identifier; based on the inverter operation abnormality identifier, perform abnormality identification on the initial inverter aging test data stream to determine the inverter abnormal operation parameters; based on the inverter abnormal operation parameters, supplement and optimize the inverter aging test parameter table to obtain an optimized aging test parameter table; use the optimized aging test parameter table to perform test monitoring and perception on the target new energy inverter to obtain the multi-dimensional data stream of the inverter aging test.

[0104] Further, the performance decay evaluation module 40 of the embodiment of the present application is further configured to perform the following steps:

[0105] Obtain a data preprocessing program according to the data processor, where the data preprocessing program includes abnormal data identification, abnormal data cleaning, and data standardization; preprocess the multi-dimensional data stream of the inverter aging test based on the data preprocessing program to obtain a standard multi-dimensional data stream of the inverter aging test; according to the inverter aging test target, determine an inverter aging associated performance set, where the inverter aging associated performance set includes conversion efficiency, output power stability, output waveform quality, protection mechanism trigger frequency, and internal component reliability; based on the inverter aging associated performance set, perform key feature extraction and decay degree evaluation on the standard multi-dimensional data stream of the inverter aging test to obtain an inverter operation performance decay parameter set.

[0106] Further, the performance decay evaluation module 40 of the embodiment of the present application is further configured to perform the following steps:

[0107] Perform associated feature extraction on the standard multi-dimensional data stream of the inverter aging test based on the inverter aging associated performance set to obtain an inverter performance associated feature set; perform key degree evaluation on each associated performance in the inverter aging associated performance set to obtain an aging associated performance key degree set; perform feature depth selection and extraction on the inverter performance associated feature set according to the aging associated performance key degree set to obtain an inverter operation key feature set; perform performance decay degree evaluation based on the inverter operation key feature set to obtain an inverter operation performance decay parameter set.

[0108] Further, the aging performance evaluation module 50 of the embodiment of the present application is further configured to perform the following steps:

[0109] Collect and obtain the inverter aging dataset, where the inverter aging dataset includes the historical operation performance decay data of the inverter aging associated performance set and the corresponding aging degree evaluation data; use the historical operation performance decay data of the inverter aging associated performance set as the independent variable and the corresponding aging degree evaluation data as the dependent variable, and perform regression analysis and fitting on the independent variable and the dependent variable using the linear regression method to establish an inverter aging performance analyzer, and store the inverter aging performance analyzer in the performance evaluation component.

[0110] Through the foregoing detailed description of a new energy inverter aging test method in this specification, those skilled in the art can clearly know a new energy inverter aging test system in this embodiment. For the system disclosed in Embodiment 2, since it corresponds to the method disclosed in Embodiment 1, it has corresponding functional modules and beneficial effects. For the relevant parts, refer to the description in the method part.

[0111] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to these embodiments shown herein, but will be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for aging test of a new energy inverter, characterized in that, The method includes: Construct an inverter aging test platform, where the inverter aging test platform includes a sensing test component, a data processor, and a performance evaluation component; Connect the target new energy inverter to the inverter aging test platform. Through the sensing test component, analyze the test parameters based on the attribute information of the target new energy inverter and the test application requirements, and generate an inverter aging test parameter table; According to the inverter aging test parameter table, perform test optimization and monitoring perception on the target new energy inverter to obtain the multi-dimensional data stream of inverter aging test; Use the data processor to extract key features and evaluate the attenuation degree of the multi-dimensional data stream of inverter aging test, and obtain a set of inverter operation performance attenuation parameters; Based on the performance evaluation component, call the inverter aging performance analyzer, and use the inverter aging performance analyzer to evaluate the aging performance of the set of inverter operation performance attenuation parameters to determine the inverter aging performance evaluation result.

2. The aging test method of a new energy inverter according to claim 1, wherein The generation of the inverter aging test parameter table includes: Obtain the inverter attribute factor information, where the inverter attribute factor information includes model specifications, output waveform, output phase number, conversion method, and power size; Classify and label the attribute information of the target new energy inverter according to the inverter attribute factor information to obtain inverter attribute factor parameters; Analyze the scenario parameters of the test application requirements of the target new energy inverter to obtain inverter application scenario parameters; Construct an inverter aging test parameter library, and traverse and retrieve the inverter aging test parameter library based on the inverter attribute factor parameters and the inverter application scenario parameters to generate an inverter aging test parameter table.

3. The aging test method of a new energy inverter according to claim 2, characterized in that, The generation of the inverter aging test parameter table includes: Use the inverter attribute factor information and application scenario information to perform data coding and classification on the inverter aging test parameter library to obtain an inverter aging test coding parameter library; Based on the inverter attribute factor parameters and the inverter application scenario parameters, calculate the similarity with each test parameter in the inverter aging test coding parameter library to obtain a set of test parameter Jaccard similarity coefficients; Arrange the inverter aging test coding parameter library in descending order according to the set of test parameter Jaccard similarity coefficients to determine the inverter aging test parameter sequence; Set a similarity threshold according to the aging test accuracy requirement, and based on the similarity threshold, divide and optimize the inverter aging test parameter sequence to generate the inverter aging test parameter table.

4. The aging test method of a new energy inverter according to claim 1, characterized in that, The acquisition of the multi-dimensional data stream of inverter aging test includes: Perform an aging test on the target new energy inverter according to the inverter aging test parameter table to obtain an initial multi-dimensional data stream of inverter aging test; Collect and obtain an inverter abnormal operation database, and use a deep neural network to perform identification training on the inverter abnormal operation database to construct an inverter operation abnormal identifier; Based on the inverter operation abnormal identifier, perform abnormal identification on the initial multi-dimensional data stream of inverter aging test to determine the inverter abnormal operation parameters; Supplement and optimize the inverter aging test parameter table based on the abnormal operation parameters of the inverter to obtain an optimized aging test parameter table; Use the optimized aging test parameter table to test, monitor, and sense the target new energy inverter to obtain the multi-dimensional data stream of the inverter aging test.

5. The aging test method for a new energy inverter according to claim 1, characterized in that The obtained inverter operation performance decay parameter set includes: Obtain a data preprocessing program according to the data processor, and the data preprocessing program includes abnormal data identification, abnormal data cleaning, and data standardization; Preprocess the multi-dimensional data stream of the inverter aging test based on the data preprocessing program to obtain a standard multi-dimensional data stream of the inverter aging test; According to the inverter aging test target, determine the inverter aging associated performance set, and the inverter aging associated performance set includes conversion efficiency, output power stability, output waveform quality, protection mechanism trigger frequency, and internal component reliability; Extract key features and evaluate the decay degree of the standard multi-dimensional data stream of the inverter aging test based on the inverter aging associated performance set to obtain an inverter operation performance decay parameter set.

6. The aging test method for a new energy inverter according to claim 5, characterized in that, The obtained inverter operation performance decay parameter set includes: Extract associated features of the inverter performance from the standard multi-dimensional data stream of the inverter aging test based on the inverter aging associated performance set to obtain an inverter performance associated feature set; Evaluate the criticality of each associated performance in the inverter aging associated performance set to obtain an aging associated performance criticality set; Select and extract the feature depth of the inverter performance associated feature set according to the aging associated performance criticality set to obtain an inverter operation key feature set; Evaluate the performance decay degree based on the inverter operation key feature set to obtain an inverter operation performance decay parameter set.

7. The aging test method for a new energy inverter according to claim 6, characterized in that, The calling of the inverter aging performance analyzer based on the performance evaluation component includes: Collect and obtain an inverter aging data set, and the inverter aging data set includes historical operation performance decay data and corresponding aging degree evaluation data of the inverter aging associated performance set; Use the historical operation performance decay data of the inverter aging associated performance set as the independent variable and the corresponding aging degree evaluation data as the dependent variable, and perform regression analysis and fitting on the independent variable and the dependent variable using the linear regression method to establish an inverter aging performance analyzer, and store the inverter aging performance analyzer in the performance evaluation component.

8. A new energy inverter aging test system, characterized in that, The system is used to execute the method for aging test of a new energy inverter according to any one of claims 1-7, including: A test platform building module for building an inverter aging test platform, and the inverter aging test platform includes a sensing test component, a data processor, and a performance evaluation component; A test parameter analysis module for connecting the target new energy inverter to the inverter aging test platform, and generating an inverter aging test parameter table through the sensing test component based on the attribute information and test application requirements of the target new energy inverter; An aging test module, configured to perform test optimization and monitoring perception on the target new energy inverter according to the inverter aging test parameter table, and obtain a multi-dimensional data stream of inverter aging test; A performance decay evaluation module, configured to extract key features and evaluate the decay degree of the multi-dimensional data stream of the inverter aging test by using the data processor, so as to obtain a set of inverter operation performance decay parameters; An aging performance evaluation module, configured to call an inverter aging performance analyzer based on the performance evaluation component, and perform aging performance evaluation on the set of inverter operation performance decay parameters through the inverter aging performance analyzer, so as to determine the inverter aging performance evaluation result.

Images