A test platform and method for energy storage PCS converter

Abstract

The present invention discloses a test platform and method for an energy storage PCS converter, which relates to the field of converter testing technology. The platform and method include a data acquisition module for constructing a test platform and deploying sensors to collect PCS converter test data and historical test data; a dynamic test module for selecting test parameters based on historical test data and applying dynamic disturbances to test the PCS converter; a fault analysis module for constructing a fault analysis model to analyze the operating status of the PCS converter; and a display and storage module for displaying the fault analysis results and storing the test data. The present invention achieves accurate dynamic performance testing by constructing an objective function and using a genetic algorithm to select test parameters. The dynamic disturbances applied to the test parameters truly reflect the dynamic response characteristics of the PCS converter under complex operating conditions, improving the accuracy and authenticity of the test results and effectively helping personnel understand the performance of the PCS converter.

Description

Technical Field

[0001] The present invention relates to the technical field of converter testing, and in particular to a testing platform and method for an energy storage PCS converter. Background Art

[0002] With the rapid development of new energy technologies, energy storage systems have become an indispensable component of modern power systems. Within energy storage systems, power conversion system (PCS) converters serve as a crucial bridge connecting energy storage devices and the power grid, and their performance directly impacts the stability and reliability of the power system. The primary functions of PCS converters are to enable bidirectional energy flow, ensure power quality, and support grid regulation, such as frequency regulation and reactive power compensation. However, due to the complex operating environment and dynamic operation of PCS converters, performance and stability testing has become a research hotspot. Currently, testing methods for PCS converters primarily fall into two categories: static performance testing and dynamic performance testing. Static testing typically focuses on converter efficiency, power output capability, and harmonic suppression, while dynamic testing emphasizes response performance and stability under simulated dynamic disturbances or fault conditions. However, existing testing technologies still have numerous shortcomings in addressing complex dynamic operating conditions. These technologies lack real-time and intelligent data analysis methods, are unable to fully utilize historical test data for test parameter optimization, and lack comprehensive dynamic signal application strategies, making it difficult to truly reflect the dynamic response characteristics of PCS converters under complex operating conditions. Summary of the Invention

[0003] In view of the above existing problems, the present invention is proposed.

[0004] Therefore, the present invention provides a test platform and method for an energy storage PCS converter, which solves the problem that the existing technology cannot fully utilize historical test data for test parameter optimization and lacks a comprehensive dynamic signal application strategy, making it difficult to truly reflect the dynamic response characteristics of the energy storage PCS converter under complex working conditions.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] In a first aspect, the present invention provides an energy storage PCS converter test platform, which comprises:

[0007] Data acquisition module, used to build a test platform and deploy sensors to collect PCS converter test data and historical test data;

[0008] Dynamic test module, used to select test parameters based on historical test data and apply dynamic disturbances to perform PCS converter tests;

[0009] Fault analysis module, used to build a fault analysis model to analyze the operating status of the PCS converter;

[0010] The display and storage module is used to display the fault analysis results and store the test data.

[0011] As a preferred solution of the energy storage PCS converter test platform described in the present invention, the construction of the test platform and the deployment of sensors to collect PCS converter test data and historical test data refer to building a standardized test platform through test equipment, setting the sampling frequency and calibrating with standard signals, deploying sensors on the test platform to collect PCS converter test data, and obtaining PCS converter historical test data through query.

[0012] As a preferred solution of the energy storage PCS converter test platform of the present invention, wherein: the selecting test parameters according to historical test data refers to extracting historical test parameters and historical PCS converter response parameters from the PCS converter historical test data, extracting the test parameter range from the PCS converter specification, and generating a test condition point set based on the historical test parameters. ;

[0013] The Latin hypercube sampling method is used to collect the test condition points. Extract test points to generate a test point set , and extract the historical PCS converter response parameters corresponding to the test points, and construct the objective function J based on the historical PCS converter response parameters:

[0014] ;

[0015] in For test time, is the historical test output power of the PCS converter at time t, is the rated input power of the PCS converter, is the historical test output power change, is the time difference of change, is the hth harmonic power at time t, H is the harmonic order, 、 as well as is the weight factor;

[0016] Gather the test points Each test point and its corresponding historical PCS converter response parameter are used as genetic individuals, and all genetic individuals form an initial population. The objective function value of each test point is defined as the fitness value. The individual with the lowest fitness value is selected from the initial population for crossover mutation operation to generate the next generation population. The iterative operation is repeated and stopped when the fitness value converges. The genetic individual with the lowest fitness value in the population after stopping the iteration is output as the optimal individual, and the test parameters in the optimal genetic individual are extracted as the preferred test parameters.

[0017] As a preferred solution of the energy storage PCS converter test platform of the present invention, the applying of dynamic disturbance to perform PCS converter testing refers to extracting the resistance, inductance and capacitance parameters of the LCL filter of the PCS converter to construct the filter state matrix A and input matrix B:

[0018] ;

[0019] in 、 and C are the resistance, inductance, and capacitance of the LCL filter respectively;

[0020] The optimal test parameters are combined to form a state vector x, and the state space model of the disturbance observer is constructed through the state matrix A and the input matrix B:

[0021] ;

[0022] in is the feedback matrix, D is the output matrix, u is the disturbance signal, and y is the output signal;

[0023] Discretize the state-space model:

[0024] ;

[0025] in is the state variable at discrete time k, is the disturbance signal at discrete time k, is the output signal at discrete time k, is the state variable at discrete time k+1, G is the discrete state transfer matrix, ;

[0026] The disturbance observer calculates the dynamic disturbance signal through the discretized state variables :

[0027] ;

[0028] Calculate the LCL filter impedance Z based on the LCL filter resistance, inductance and capacitance parameters;

[0029] The dynamic disturbance signal obtained by the disturbance observer The dynamic disturbance signal is generated by superposition of dynamic virtual network impedance :

[0030] ;

[0031] in is the input current, N is the number of online inverters in the PCS converter;

[0032] From the integrated dynamic disturbance signal The voltage disturbance term, frequency disturbance term and power disturbance term are extracted and added to the preferred test parameters to form the final test parameters, the PCS converter is tested based on the final test parameters, and the PCS converter response parameters are collected;

[0033] Calculate instantaneous output power based on PCS converter response parameters The power change rate e is calculated, and the output voltage and current in the PCS converter response parameters are converted into frequency domain signals by fast Fourier transform. The harmonic components and fundamental components are extracted from the frequency domain signals, and the total harmonic distortion THD of the output signal is calculated based on the harmonic components and fundamental components:

[0034] ;

[0035] in is the voltage of the hth harmonic, is the fundamental voltage;

[0036] Simultaneous calculation of the resonant frequency of the LCL filter ;

[0037] Comprehensive PCS converter power change rate e, total harmonic distortion THD and resonant frequency Output as test results.

[0038] As a preferred solution of the energy storage PCS converter test platform of the present invention, wherein: the construction of a fault analysis model to analyze the operating status of the PCS converter refers to constructing a fault analysis model through a convolutional neural network, setting the model input as the test result and the model output as the operating status of the PCS converter, iteratively training the fault analysis model using training data, and optimizing the model parameters using a loss function and an Adam optimizer;

[0039] The test results are input into the trained fault analysis model to obtain the operating status of the PCS converter.

[0040] As a preferred solution of the energy storage PCS converter test platform described in the present invention, the display of fault analysis results refers to the synchronous visual display of the PCS converter operating status and test results, and providing maintenance suggestions to staff based on the PCS converter operating status.

[0041] As a preferred solution of the energy storage PCS converter test platform described in the present invention, the storing of test data refers to generating test records for storage of test data and test results after the test is completed, sorting the test records by timestamp, and regularly comparing the test records with historical test records to evaluate the reliability of the test records.

[0042] In a second aspect, the present invention provides a method for testing an energy storage PCS converter, comprising:

[0043] Build a test platform and deploy sensors to collect PCS converter test data and historical test data;

[0044] Select test parameters based on historical test data and apply dynamic disturbances to test the PCS converter;

[0045] Construct a fault analysis model to analyze the operating status of the PCS converter;

[0046] Display the fault analysis results and store the test data.

[0047] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the energy storage PCS converter test platform as described in the first aspect of the present invention is implemented.

[0048] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the energy storage PCS converter test platform as described in the first aspect of the present invention is implemented.

[0049] The beneficial effects of the present invention are as follows: the present invention realizes accurate dynamic performance testing by constructing an objective function and selecting test parameters using a genetic algorithm, and applies dynamic interference to the test parameters to truly reflect the dynamic response characteristics of the PCS converter under complex working conditions, thereby improving the accuracy and authenticity of the test results and effectively helping staff understand the performance of the PCS converter. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0051] Figure 1 This is a structural diagram of the energy storage PCS converter test platform in Example 1.

[0052] Figure 2 This is a flow chart of the energy storage PCS converter testing method in Example 1. DETAILED DESCRIPTION

[0053] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0054] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0055] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0056] Example 1, with reference to Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides an energy storage PCS converter test platform, including the following steps:

[0057] S1, data acquisition module, is used to build a test platform and deploy sensors to collect PCS converter test data and historical test data;

[0058] Building a test platform and deploying sensors to collect PCS converter test data and historical test data refers to building a standardized test platform through test equipment, setting the sampling frequency and using standard signals for calibration, deploying sensors on the test platform to collect PCS converter test data, and obtaining PCS converter historical test data through queries.

[0059] Building a standardized test platform ensures the uniformity of the test environment, especially during the application of dynamic disturbance signals and data acquisition. The standardized test platform can eliminate errors caused by environmental differences (such as hardware performance differences or signal interference). The deployment of sensors enables the system to obtain dynamic parameters such as voltage, current, power, and temperature of the PCS converter in real time during operation. These parameters provide a high-precision data source for dynamic disturbance testing and fault analysis. By introducing historical test data, the present invention can optimize the current test parameter selection and dynamic disturbance design based on previous test results. The reference of historical data makes the test more accurate and controllable, reduces repetitive testing and resource waste, and by setting a reasonable sampling frequency, it can ensure that the acquisition of dynamic signals has sufficient time resolution, thereby accurately capturing the operating details of the PCS converter under dynamic disturbance.

[0060] S2, dynamic test module, used to select test parameters based on historical test data and apply dynamic disturbances to perform PCS converter testing;

[0061] Specifically, selecting test parameters based on historical test data refers to extracting historical test parameters and historical PCS converter response parameters from historical test data of the PCS converter, wherein the historical test parameters include historical test input voltage, historical test input frequency, and historical test input power, and the historical PCS converter response parameter refers to historical test output power. The test parameter range is extracted from the PCS converter specification, including rated input power, input voltage range, and input frequency range, and a test operating point set is generated based on the historical test parameters. :

[0062] ;

[0063] in is the PCS converter input voltage range, is the PCS converter input frequency range, is the rated input power of the PCS converter, is the test input voltage, f is the test input frequency, Input power for testing;

[0064] The Latin hypercube sampling method is used to collect the test condition points. Extract test points to generate a test point set ,Latin hypercube sampling is an efficient sampling method used to uniformly cover the multidimensional ,variable space, ensuring the uniformity and representativeness of the test point ,distribution, and extract the historical PCS converter response parameters corresponding to the ,test points. The objective function J is constructed based on the historical PCS converter ,response parameters:

[0065] ;

[0066] in For test time, is the historical test output power of the PCS converter at time t, is the rated input power of the PCS converter, is the historical test output power change, is the time difference of change, is the hth harmonic power at time t, H is the harmonic order, 、 as well as is the weight factor, which is allocated according to actual test requirements;

[0067] Gather the test points Each test point and its corresponding historical PCS converter response parameter are used as genetic individuals, and all genetic individuals form an initial population. The objective function value of each test point is defined as the fitness value. The individual with the lowest fitness value is selected from the initial population for crossover mutation operation to generate the next generation population. The iterative operation is repeated and stopped when the fitness value converges. The genetic individual with the lowest fitness value in the population after stopping the iteration is output as the optimal individual, and the test parameters in the optimal genetic individual are extracted as the preferred test parameters.

[0068] The combined method based on historical data and specifications avoids the generation of invalid test points, ensures the representativeness of the test conditions, and reduces the blindness of the test design. The introduction of the Latin hypercube sampling method overcomes the defect of uneven random sampling distribution. Under the condition of limited test resources, a set of test points with efficient coverage can be generated to avoid excessive testing or neglect of certain areas. Power fluctuation, harmonic components and test efficiency are used as comprehensive optimization goals, and the priority of different goals is adjusted by weight factors. Compared with the single-objective optimization method, this multi-objective function construction is more comprehensive and can more accurately reflect the dynamic characteristics of the PCS converter. By introducing the adjustment mechanism of harmonic power and weight factors, the practicality of the objective function and the accuracy of the test results are significantly improved. The introduction of the genetic algorithm, combined with the objective function, can screen out the optimal test parameters in an intelligent optimization manner. Compared with the traditional exhaustive search or empirical selection method, the genetic algorithm can quickly converge to the global optimal solution, significantly improving the optimization efficiency.

[0069] Furthermore, applying dynamic disturbances to test the PCS converter means extracting the resistance, inductance, and capacitance parameters of the PCS converter's LCL filter to construct the filter state matrix A and input matrix B:

[0070] ;

[0071] in 、 and C are the resistance, inductance, and capacitance of the LCL filter, respectively, which are obtained from the PCS converter equipment specifications;

[0072] The state matrix A describes the internal dynamic behavior of the system, and the input matrix B describes how external inputs affect the system state. Constructing the state matrix from the filter parameters (resistance, inductance, and capacitance) closely aligns the model with actual device characteristics, ensuring the physical authenticity and computational accuracy of the dynamic disturbance signal.

[0073] The optimal test parameters are combined to form a state vector x, and the state space model of the disturbance observer is constructed through the state matrix A and the input matrix B:

[0074] ;

[0075] in is the feedback matrix, which is used to correct the observation error and is designed according to the stability condition of the discrete system. For example, the gain value that satisfies the feedback stability principle is selected. D is the output matrix, which is used to associate the state vector with the observable signal. , u is the disturbance signal, corresponding to the state vector content, initially set to zero, and corrected by the disturbance superposition model in the next step, y is the output signal, obtained by real-time acquisition of voltage and current;

[0076] Discretize the state-space model:

[0077] ;

[0078] in is the state variable at discrete time k, is the disturbance signal at discrete time k, is the output signal at discrete time k, is the state variable at discrete time k+1, G is the discrete state transfer matrix, ;

[0079] Discretization converts the continuous-time state-space model into a discrete-time model, making it suitable for real-time computation in digital control systems. The discretization process preserves the dynamic characteristics of the continuous model while being compatible with the computational requirements of the digital test system, ensuring the applicability of the model.

[0080] The disturbance observer calculates the dynamic disturbance signal through the discretized state variables :

[0081] ;

[0082] The generation of dynamic disturbance signals involves real-time calculation of state variables by the disturbance observer. This, combined with filter parameters and dynamic virtual network impedance, creates a more complex dynamic signal. The disturbance observer dynamically corrects state errors, allowing the disturbance signal to adapt to changes in the test environment in real time. This real-time and adaptability is not available in traditional methods.

[0083] Calculate the LCL filter impedance Z based on the LCL filter resistance, inductance and capacitance parameters:

[0084] ;

[0085] Where j is an imaginary singular number, is the angular frequency;

[0086] The dynamic disturbance signal obtained by the disturbance observer The dynamic disturbance signal is generated by superposition of dynamic virtual network impedance :

[0087] ;

[0088] in is the input current, obtained through real-time sampling, and N is the number of online inverters in the PCS converter;

[0089] The integrated dynamic disturbance signal superimposes voltage, frequency, and power disturbance terms and extracts them as final test parameters, ensuring the comprehensiveness of the test process. By dynamically superimposing voltage, frequency, and power disturbances, more complex grid conditions can be simulated during the test, fully evaluating the dynamic performance of the PCS converter.

[0090] From the integrated dynamic disturbance signal The voltage disturbance term, frequency disturbance term and power disturbance term are extracted and added to the preferred test parameters to form the final test parameters, the PCS converter is tested based on the final test parameters, and the PCS converter response parameters are collected;

[0091] Calculate instantaneous output power based on PCS converter response parameters The power change rate e is calculated, and the output voltage and current in the PCS converter response parameters are converted into frequency domain signals by fast Fourier transform. The harmonic components and fundamental components are extracted from the frequency domain signals, and the total harmonic distortion THD of the output signal is calculated based on the harmonic components and fundamental components:

[0092] ;

[0093] in is the voltage of the hth harmonic, is the fundamental voltage;

[0094] Simultaneous calculation of the resonant frequency of the LCL filter :

[0095] ;

[0096] in is the grid side filter inductor;

[0097] Comprehensive PCS converter power change rate e, total harmonic distortion THD and resonant frequency Output as test results.

[0098] Comprehensive consideration is given to dynamic performance (power change rate), signal quality (THD), and stability (resonant frequency) to ensure that the test results can reflect the full range of characteristics of the equipment. This closely combines the LCL filter parameters and dynamic disturbance model, fully considering real-time, adaptability, and comprehensiveness, significantly improving the scientific nature and practicality of the test.

[0099] S3, fault analysis module, used to build a fault analysis model to analyze the operating status of the PCS converter;

[0100] Specifically, building a fault analysis model to analyze the operating status of the PCS converter involves building a fault analysis model using a convolutional neural network, setting the model input as the test results and the model output as the operating status of the PCS converter, iteratively training the fault analysis model using training data, and optimizing the model parameters using a loss function and an Adam optimizer.

[0101] The test results are input into the trained fault analysis model to obtain the operating status of the PCS converter.

[0102] CNN uses convolution kernels to extract high-order features within the local receptive field of the input data. It exhibits excellent automation and generalization capabilities. Through multi-layer convolution operations, the model can gradually extract features from low-order to high-order features, enabling in-depth analysis of the operating status of the PCS converter. The input is test results (including multi-dimensional parameters), and the output is the operating status (specific classification). This design not only meets the practical needs of the problem, but also fully utilizes the feature extraction capabilities of CNN to extract fault characteristics from multi-dimensional test results. By directly inputting test results and outputting the operating status, the complex process of manual analysis and classification is eliminated, achieving efficient automated diagnosis.

[0103] S4, a display and storage module, used to display the fault analysis results and store the test data;

[0104] Specifically, displaying the fault analysis results means visually displaying the PCS converter operating status and test results synchronously, and providing maintenance suggestions to staff based on the PCS converter operating status.

[0105] Furthermore, storing the test data means generating test records for storage of the test data and test results after the test is completed, sorting the test records by timestamp, and regularly comparing the test records with historical test records to evaluate the reliability of the test records, which can be analyzed and compared through artificial intelligence.

[0106] This embodiment also provides a method for testing an energy storage PCS converter, including:

[0107] Build a test platform and deploy sensors to collect PCS converter test data and historical test data;

[0108] Select test parameters based on historical test data and apply dynamic disturbances to test the PCS converter;

[0109] Construct a fault analysis model to analyze the operating status of the PCS converter;

[0110] Display the fault analysis results and store the test data.

[0111] This embodiment also provides a computer device suitable for the case of an energy storage PCS converter test platform, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the energy storage PCS converter test platform proposed in the above embodiment.

[0112] The computer device may be a terminal, comprising a processor, memory, a communication interface, a display, and an input device connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores an operating system and computer programs. The internal memory provides an environment for the operating system and computer programs stored in the non-volatile storage media. The communication interface of the computer device is used to communicate with external terminals via wired or wireless communication. Wireless communication may be achieved via Wi-Fi, a carrier network, NFC (near-field communication), or other technologies. The display of the computer device may be a liquid crystal display or an electronic ink display. The input device may be a touchscreen overlay on the display, buttons, a trackball, or a touchpad on the computer device housing, or an external keyboard, touchpad, or mouse.

[0113] This embodiment also provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the energy storage PCS converter test platform proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0114] In summary, the present invention achieves accurate dynamic performance testing by constructing an objective function and using a genetic algorithm to select test parameters. Dynamic interference is applied to the test parameters to truly reflect the dynamic response characteristics of the PCS converter under complex working conditions, thereby improving the accuracy and authenticity of the test results and effectively helping staff understand the performance of the PCS converter.

[0115] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An energy storage PCS converter test platform, characterized by: include, Data acquisition module, used to build a test platform and deploy sensors to collect PCS converter test data and historical test data; Dynamic test module, used to select test parameters based on historical test data and apply dynamic disturbances to perform PCS converter tests; Fault analysis module, used to build a fault analysis model to analyze the operating status of the PCS converter; Display and storage module, used to display fault analysis results and store test data; The said building a test platform and deploying sensors to collect PCS converter test data and historical test data refers to building a standardized test platform by using test equipment, setting a sampling frequency and calibrating it with a standard signal, deploying sensors on the test platform to collect PCS converter test data, and obtaining PCS converter historical test data through query; The selecting of test parameters according to historical test data refers to extracting historical test parameters and historical PCS converter response parameters from the PCS converter historical test data, extracting the test parameter range from the PCS converter specification, and generating a test operating point set Q based on the historical test parameters. test ; The Latin hypercube sampling method is used to select the test condition point set Q test Extract test points to generate test point set X test , and extract the historical PCS converter response parameters corresponding to the test points, and construct the objective function J based on the historical PCS converter response parameters: Where T is the test time, P out (t) is the historical test output power of the PCS converter at time t, P r is the rated input power of the PCS converter, ΔP out (t) is the historical test output power change, Δt is the change time difference, P h (t) is the hth harmonic power at time t, H is the harmonic order, and a1, a2, and a3 are weight factors; The test point set X test Each test point and its corresponding historical PCS converter response parameter are used as genetic individuals, and all genetic individuals form an initial population. The objective function value of each test point is defined as the fitness value. The individual with the lowest fitness value is selected from the initial population for crossover mutation operation to generate the next generation population. The iterative operation is repeated and stopped when the fitness value converges. The genetic individual with the lowest fitness value in the population after stopping the iteration is output as the optimal individual, and the test parameters in the optimal genetic individual are extracted as the preferred test parameters.

2. The energy storage PCS converter test platform according to claim 1, characterized in that: The application of dynamic disturbance to test the PCS converter refers to extracting the resistance, inductance and capacitance parameters of the LCL filter of the PCS converter to construct the filter state matrix A and input matrix B: where R f , L f and C are the resistance, inductance, and capacitance of the LCL filter respectively; The optimal test parameters are combined to form a state vector x, and the state space model of the disturbance observer is constructed through the state matrix A and the input matrix B: Where M is the feedback matrix, D is the output matrix, u is the disturbance signal, and y is the output signal; Discretize the state-space model: x k+1 =(G-MD)x k +Bu k +My k ; where x k is the state variable at discrete time k, u k is the disturbance signal at discrete time k, y k is the output signal at discrete time k, x k+1 is the state variable at discrete time k+1, G is the discrete state transfer matrix, G=e At ; The disturbance observer calculates the dynamic disturbance signal u(t) through the discretized state variables: u(t)=||x k+1 -x k ||*u k ; Calculate the LCL filter impedance Z based on the LCL filter resistance, inductance and capacitance parameters; The dynamic disturbance signal u(t) obtained by the disturbance observer is superimposed on the dynamic virtual network impedance to generate a comprehensive dynamic disturbance signal u * (t): Where I(t) is the input current and N is the number of online inverters in the PCS converter; From the integrated dynamic disturbance signal u * (t) extracting the voltage disturbance term, the frequency disturbance term, and the power disturbance term, respectively, and superimposing them into the preferred test parameters to form final test parameters, testing the PCS converter based on the final test parameters, and collecting the PCS converter response parameters; Calculate the instantaneous output power P according to the PCS converter response parameters o (t) and calculate the power change rate e, perform fast Fourier transform on the output voltage and current in the PCS converter response parameters to convert them into frequency domain signals, extract the harmonic components and fundamental components from the frequency domain signals, and calculate the total harmonic distortion THD of the output signal based on the harmonic components and fundamental components: Where V h is the voltage of the hth harmonic, V1 is the fundamental voltage; Simultaneously calculate the resonant frequency f of the LCL filter r ; Comprehensive PCS converter power change rate e, total harmonic distortion THD and resonant frequency f r Output as test results.

3. The energy storage PCS converter test platform according to claim 2, characterized in that: Constructing a fault analysis model to analyze the operating status of the PCS converter refers to constructing a fault analysis model through a convolutional neural network, setting the model input as the test result and the model output as the operating status of the PCS converter, iteratively training the fault analysis model using training data, and optimizing the model parameters through a loss function and an Adam optimizer; The test results are input into the trained fault analysis model to obtain the operating status of the PCS converter.

4. The energy storage PCS converter test platform according to claim 3, characterized in that: The display of the fault analysis results refers to the synchronous visual display of the PCS converter operating status and the test results, and providing maintenance suggestions to the staff based on the PCS converter operating status.

5. The energy storage PCS converter test platform according to claim 4, characterized in that: Storing the test data refers to generating test records from the test data and test results for storage after the test is completed, sorting the test records by timestamp, and regularly comparing the test records with historical test records to evaluate the reliability of the test records.

6. A method for testing an energy storage PCS converter, based on the energy storage PCS converter testing platform according to any one of claims 1 to 5, characterized in that: include, Build a test platform and deploy sensors to collect PCS converter test data and historical test data; Select test parameters based on historical test data and apply dynamic disturbances to test the PCS converter; Construct a fault analysis model to analyze the operating status of the PCS converter; Display the fault analysis results and store the test data.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the energy storage PCS converter test platform according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the energy storage PCS converter test platform according to any one of claims 1 to 5 are implemented.

Images