Energy storage converter back-to-back test platform

Abstract

The invention discloses a back-to-back test platform for an energy storage converter, and relates to the technical field of converter testing, and the platform comprises a data collection module which employs a voltage source converter to access a power grid, and collects different load condition data; the capacitance health prediction module is used for constructing a deep learning model to extract features and calculating a fitness function to predict a capacitance state value; the redundancy control path module is used for constructing a redundancy control path to predict the state of the backup capacitor; and a load balancing module. According to the method, through the CNN-PSO-SVR model, real-time response can be carried out when the state of the capacitor changes, it is ensured that the attenuation state of the capacitor can be rapidly fed back to a control system, it is ensured that the capacitor continuously and stably operates under the complex load condition, power output is compensated in time through a redundant path, and the situation that the whole system is shut down due to the fault of a single element is avoided; through dual-path capacitor health monitoring and Droop-MPC dynamic power distribution, power output can be adjusted in time when early attenuation of the capacitor occurs, and system shutdown caused by a single-point fault is avoided.

Description

Technical Field

[0001] The invention relates to the technical field of converter testing, in particular to a back-to-back testing platform for energy storage converters. Background Art

[0002] As the global energy structure transforms towards low-carbonization and sustainable development, the importance of energy storage technology in power systems has become increasingly prominent. As an important component of power electronic equipment, energy storage converters play a key role in grid frequency regulation, peak regulation, dynamic reactive power compensation and new energy grid connection. In recent years, energy storage converter technology has made great progress, gradually developing from the traditional unidirectional conversion mode to a more flexible bidirectional energy flow control direction. Among them, the back-to-back converter architecture has been widely used in energy storage system testing and grid AC / DC interconnection due to its bidirectional energy flow characteristics. Traditional energy storage converter test platforms mainly rely on constant load or single energy flow direction testing, which makes it difficult to fully reflect the dynamic response characteristics of the converter under complex working conditions and the health status of the capacitor. First, traditional test systems usually use fixed loads or discrete loads to verify converter performance, which makes it difficult to achieve comprehensive monitoring of the capacitor status under dynamic load changes, resulting in limited system test coverage. Second, existing capacitor health monitoring mostly relies on single model predictions or simple empirical formulas, lacking in-depth analysis of capacitor attenuation laws under complex load environments, and is prone to inaccurate capacitor failure predictions due to model deviations, which in turn causes system failures. In addition, in terms of converter power distribution, existing technologies have not yet fully utilized deep learning algorithms for multi-dimensional load feature extraction and real-time power flow optimization scheduling, resulting in uneven load distribution and low overall system operation efficiency. Especially during large-power load mutations or power cycle tests, traditional systems find it difficult to adjust converter output power in a timely manner, which can easily cause capacitor overload and shorten equipment life. Summary of the invention

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

[0004] Therefore, the present invention provides a back-to-back test platform for energy storage converters to solve the problem that traditional test systems usually use fixed loads or discrete loads to verify converter performance, which makes it difficult to achieve comprehensive monitoring of the capacitor status under conditions of dynamic load changes, resulting in limited system test coverage. Secondly, existing capacitor health monitoring mostly relies on single model predictions or simple empirical formulas, lacks in-depth analysis of the capacitor attenuation laws under complex load environments, and is prone to inaccurate capacitor failure predictions due to model deviations, thereby causing system failures. In addition, in terms of converter power distribution, the prior art has not fully utilized deep learning algorithms to perform multi-dimensional load feature extraction and real-time power flow optimization scheduling, resulting in uneven load distribution and low overall system operation efficiency. Especially during high-power load mutations or power cycle tests, it is difficult for traditional systems to adjust the converter output power in a timely manner, which can easily cause capacitor overload and shorten equipment life.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: In a first aspect, the present invention provides a back-to-back test platform for an energy storage converter, comprising: The data acquisition module uses a voltage source converter to access the power grid and collect data under different load conditions; The capacitor health prediction module builds a deep learning model to extract features and calculates the fitness function to predict the capacitor status value; A redundant control path module, which constructs a redundant control path to predict the state of the backup capacitor; A load balancing module, based on the prediction of the capacitance value, optimizes and balances the load of the converter according to the real-time power flow; Data synchronization module, which performs data synchronization monitoring through a power monitoring unit; Data simulation module, building a virtual simulation model for data simulation; The temperature management module dynamically adjusts the heat dissipation strategy according to temperature changes; The energy storage module performs energy feedback storage to realize energy circulation.

[0006] As a preferred solution of the back-to-back test platform for energy storage converters described in the present invention, the use of a voltage source converter to access the power grid refers to the use of a voltage source back-to-back converter VSC, which includes two bidirectional voltage source inverters, the AC output end of the first bidirectional voltage source inverter is connected to the grid side, and the AC output end of the second bidirectional voltage source inverter is connected to the load side.

[0007] As a preferred solution of the back-to-back test platform for energy storage converters of the present invention, wherein: the data acquisition under different load conditions is based on different load conditions, and the data of voltage, current, temperature and resistance are recorded through a voltage sensor, a current sensor, a temperature sensor and a capacitor equivalent series resistance ESR sensor; A high-frequency sampling circuit is introduced on the DC bus to transmit the voltage pulsation signal to the ADC sampler; Perform fast Fourier transform on the DC bus voltage, extract high-frequency voltage spectrum feature data, and store it through a sliding window mechanism; Data storage adopts a dual-channel backup mechanism, the main storage channel is the internal memory, and the backup channel is the external storage device.

[0008] As a preferred solution of the back-to-back test platform for energy storage converters of the present invention, wherein: the deep learning model is constructed to extract features, and the fitness function is calculated to predict the state value of the capacitor, and the deep learning model is constructed based on a convolutional neural network, including an input layer, a convolutional layer and an output layer; The data collected under different load conditions are used as training data for model training. The cross entropy loss function is selected to calculate the computational loss between the category probability predicted by CNN and the actual label. The Adam optimizer is used for gradient descent optimization to update the weight parameters of the CNN model. If the model loss no longer decreases significantly during continuous iterations, the iteration is stopped. Based on the newly collected converter test data, the deep learning model is input, and the principal component analysis (PCA) is used to reduce the dimension of the model output data; The particle swarm optimization (PSO) algorithm is used to optimize the hyperparameters of the support vector regression (SVR) model, and the feature matrix after PCA dimension reduction is used as the input of the SVR model. The particle swarm size setting based on the particle swarm optimization PSO algorithm includes three categories, which are determined based on historical data and represent the hyperparameters of the SVR model, including penalty factors, kernel function parameters, and allowable error range; The SVR model is trained based on the hyperparameters of randomly initialized particles, and the root mean square error RMSE of the SVR model corresponding to the current particle on the test set is calculated as the fitness function; At the same time, the particle position and velocity are updated and iterative calculations are performed. When the drop in loss is no longer obvious, the iteration is stopped, and the SVR model corresponding to the particle with the smallest RMSE is selected as the final model; Based on the newly collected converter operation data, the equivalent capacitance value of the capacitor at the corresponding time point is output through the SVR model, and multiple capacitance prediction values ​​in continuous time are fitted into a decay curve to predict the capacitance state value.

[0009] As a preferred solution of the energy storage converter back-to-back test platform of the present invention, wherein: the redundant control path is constructed to predict the state of the backup capacitor, the output of the SVR model is used as the main control path, and a dual control path is introduced to add a redundant control path; Based on the attenuation curve data of the converter health prediction, a one-dimensional linear regression model is constructed by least squares fitting, which is expressed as: ; ; ; in represents the predicted value of linear capacitance, represents time, a represents the slope of the regression line, b represents the intercept of the regression line, represents the number of data points of the decay curve, represents the data at the i-th time point, represents the output value of the SVR model at the i-th time point, and Respectively and The average value of The SVR model output is compared in real time with the predicted output results of the redundant control path. The sum of the mean and standard deviation of the historical error values ​​is used as the deviation threshold. If the real-time comparison result is greater than or equal to the deviation threshold, it is judged that the deviation is large, and the predicted output results of the redundant control path are switched.

[0010] As a preferred solution of the energy storage converter back-to-back test platform of the present invention, wherein: based on the prediction of the capacitance value, the load of the converter is optimized according to the real-time power flow, the converter output power is dynamically allocated according to the prediction of the capacitance value, and the bus voltage and the current output power of the converter are monitored in real time through the voltage sensor and the current sensor; Basic Droop control calculates the current output power of the converter based on the difference between the actual voltage and the set voltage, expressed as: ; in represents the output power of converter i at time t, represents the maximum output power of converter i, k represents the Droop coefficient, represents the bus voltage at time t, Indicates the bus voltage setting value; Model predictive control (MPC) is introduced, and the load dynamic model is established by fitting the historical power curve, which is expressed as: ; in represents the load power at time t, Indicates the trend curvature of load change, Indicates the linear rate of change of load over time, Indicates the base load power; The power demand of future time steps is calculated based on the load dynamic model, and an adaptive dynamic compensation mechanism is introduced. The difference between the actual load power and the total output power of the converter is calculated at each time step as the power allocation error, which is expressed as: ; ; in represents the power allocation error, Indicates the total number of data. represents the modified Droop coefficient, represents the compensation gain; After correcting the Droop coefficient, the converter output power is dynamically calculated.

[0011] As a preferred solution of the energy storage converter back-to-back test platform of the present invention, wherein: the data synchronization monitoring is performed through the power monitoring unit, a power monitoring unit PMU is embedded in each converter, the output power, voltage, and current state parameters are monitored in real time, and the CAN bus communicates with other converters to form a distributed monitoring network; One converter is set as the master converter, which is responsible for summarizing the power status of each converter and distributing the load. Other converters are set as slave converters, which respond to the instructions of the master converter. Based on the monitoring cycle, the master converter collects the output power data of all slave converters, calculates the total load, and distributes it to each converter according to the calculated load ratio to balance the load.

[0012] As a preferred solution of the back-to-back test platform for energy storage converters of the present invention, wherein: the virtual simulation model is constructed to perform data simulation, and a virtual simulation model of the converter and capacitor is constructed based on MATLAB through digital twin technology; Through IoT devices and sensors, the data of the physical system is synchronized to the digital twin in real time, and load surge, overload and capacitance attenuation scenarios are simulated in the digital environment to optimize the Droop controller and MPC parameters.

[0013] As a preferred solution of the back-to-back test platform for energy storage converters of the present invention, the heat dissipation strategy is dynamically adjusted according to the temperature change, a temperature sensor is installed on the surface of the capacitor, the temperature change is monitored in real time, the safe temperature range of the capacitor is set, the temperature data is transmitted to the main control converter, and the heat dissipation strategy is dynamically adjusted according to the temperature change; A high temperature threshold is determined based on the device heat dissipation temperature standard. If the monitored temperature data exceeds the high temperature threshold, the heat dissipation fan is started to execute the heat dissipation strategy.

[0014] As a preferred solution of the back-to-back test platform for energy storage inverters described in the present invention, the energy feedback storage to achieve energy circulation refers to feeding back excess energy to the energy storage device during the back-to-back test, monitoring the energy flow direction between the DC bus and the power grid through the electric energy metering device, and when the load is reduced and the system has excess power, the inverter automatically switches to the energy feedback mode, feeding back the excess power to the power grid and the energy storage device, thereby achieving energy recycling.

[0015] The beneficial effects of the present invention are as follows: through the CNN-PSO-SVR model, real-time response can be made when the capacitor state changes, ensuring that the capacitor attenuation state can be quickly fed back to the control system, ensuring the continuous and stable operation of the capacitor under complex load conditions, and timely compensation of power output through redundant paths to avoid overall system shutdown due to single component failure. Through dual-path capacitor health monitoring and Droop-MPC dynamic power allocation, power output can be adjusted in time when the capacitor shows early attenuation, avoiding system shutdown due to single point failure. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0017] Figure 1 This is a schematic diagram of the structure of the back-to-back test platform for energy storage converters in Example 1.

[0018] Figure 2 This is a schematic diagram of the process of the back-to-back test platform for the energy storage converter in Example 1. DETAILED DESCRIPTION

[0019] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0020] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and 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.

[0021] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0022] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides a back-to-back test platform for energy storage converters, comprising the following steps: S1, using voltage source converter to access the grid and collect data under different load conditions; Preferably, using a voltage source converter to access the grid refers to using a voltage source back-to-back converter VSC, which includes two bidirectional voltage source inverters, the AC output end of the first bidirectional voltage source inverter is connected to the grid side, and the AC output end of the second bidirectional voltage source inverter is connected to the load side; The DC sides of the two bidirectional voltage source inverters share the same DC bus. A supercapacitor energy storage module (rated voltage 1000V, capacity 100F) is connected in parallel to the bus to provide short-time power support and ensure dynamic response speed. A bidirectional DC-DC converter is used to connect the DC bus and supercapacitor to control the bidirectional flow of energy between the DC bus and the energy storage module.

[0023] The supercapacitor energy storage module provides short-term power support. When power fluctuations occur on the grid side or the load side, it responds quickly to make up for the power gap, avoids bus voltage drops or inverter overcurrent protection caused by sudden load increases, reduces the risk of system shutdown, and improves the converter's ability to cope with impact loads (such as motor startup or high-power equipment input). It ensures continuous power supply to critical loads. The bidirectional DC-DC converter controls the energy flow between the supercapacitor and the DC bus, allowing energy to be fed back to the supercapacitor when the load is reduced to achieve energy recovery and storage. Through power complementarity between the grid side and the load side, bus power balance is achieved, the operating pressure of the inverter is reduced, and the service life of the equipment is extended. It supports parallel operation of multiple converters, improves system power redundancy, reduces the impact of a single converter failure on the system, and improves the overall system fault tolerance.

[0024] Furthermore, data under different load conditions are collected. Data collection is performed based on different load conditions, and voltage, current, temperature and resistance data are recorded through voltage sensors, current sensors, temperature sensors and capacitor equivalent series resistance (ESR) sensors; A high-frequency sampling circuit (bandwidth above 10kHz) is introduced on the DC bus to transmit the voltage pulsation signal to the ADC sampler, which is then processed by the DSP to extract the high-frequency component. Perform fast Fourier transform on the DC bus voltage, extract high-frequency voltage spectrum feature data, and store it through a sliding window mechanism; Data storage adopts a dual-channel backup mechanism, the main storage channel is the internal memory, and the backup channel is the external storage device.

[0025] Through voltage sensors, current sensors, temperature sensors and ESR sensors, core parameters such as capacitance, current, voltage and temperature are fully monitored to realize all-round data collection of system operation status. Through ESR (equivalent series resistance) monitoring, the degree of capacitor aging can be directly reflected, and capacitor attenuation and failure risks can be warned in advance. By performing fast Fourier transform (FFT) on the DC bus voltage, the time domain signal is converted to the frequency domain, and the high-frequency voltage spectrum characteristics under the capacitor state are extracted. The frequency domain characteristics in the healthy state of the capacitor are extracted and compared with the standard spectrum. The source of abnormal capacitance or bus voltage fluctuation is quickly located. The sliding window mechanism can dynamically update the continuous data stream, always retain the latest key data, and delete expired data to ensure efficient use of storage space. By adopting a dual-channel backup mechanism, redundant storage of key monitoring data is ensured to avoid data loss due to single-channel failure or memory damage.

[0026] S2, build a deep learning model to extract features and calculate the fitness function to predict the capacitance state value; Preferably, a deep learning model is constructed to extract features, and a fitness function is calculated to predict the capacitance state value, and a deep learning model is constructed based on a convolutional neural network, including an input layer, a convolutional layer, and an output layer; The data collected under different load conditions are used as training data for model training. The cross entropy loss function is selected to calculate the computational loss between the category probability predicted by CNN and the actual label. The Adam optimizer is used for gradient descent optimization to update the weight parameters of the CNN model. If the model loss no longer decreases significantly during continuous iterations, the iteration is stopped. Based on the newly collected converter test data, the deep learning model is input, and the principal component analysis (PCA) is used to reduce the dimension of the model output data; The dimension reduction target can be set to retain 95% of the feature information, and finally reduce the dimension to the feature matrix of 5 principal components; The particle swarm optimization (PSO) algorithm is used to optimize the hyperparameters of the support vector regression (SVR) model, and the feature matrix after PCA dimension reduction is used as the input of the SVR model. The particle swarm size setting based on the particle swarm optimization PSO algorithm includes three categories, which are determined based on historical data and represent the hyperparameters of the SVR model, including penalty factors, kernel function parameters, and allowable error range; The SVR model is trained based on the hyperparameters of randomly initialized particles, and the root mean square error RMSE of the SVR model corresponding to the current particle on the test set is calculated as the fitness function, which is expressed as: ; in represents the root mean square error value, N represents the total number of samples, and Represent the SVR model predicted value and the actual measured value respectively; At the same time, the particle position and velocity are updated and iterative calculations are performed. When the drop in loss is no longer obvious, the iteration is stopped, and the SVR model corresponding to the particle with the smallest RMSE is selected as the final model; Based on the newly collected converter operation data, the equivalent capacitance value of the capacitor at the corresponding time point is output through the SVR model, and multiple capacitance prediction values ​​in continuous time are fitted into a decay curve to predict the capacitance state value.

[0027] The convolutional neural network (CNN) is used to extract complex capacitor data features, and the principal component analysis (PCA) is combined with the particle swarm optimization (PSO) to optimize the support vector regression model (SVR) to achieve high-precision prediction of the capacitor state. PSO can quickly search for the optimal solution in the multi-dimensional parameter space to ensure that the SVR model can operate stably under complex load and environmental conditions. PCA is used to reduce the dimension of the high-dimensional features extracted by CNN. While maintaining high prediction accuracy, the model's computational cost and storage requirements are reduced. It is suitable for embedded devices or industrial control systems. The SVR model is used to predict the capacitor state at continuous time points, fit the capacitor attenuation curve, and realize the capacitor life. The capacitor state decay curve can directly reflect the health of the capacitor, provide intuitive early warning information for operation and maintenance personnel, and replace or maintain the capacitor in advance. Based on the CNN-PSO-SVR model, it can respond in real time when the capacitor state changes, ensuring that the capacitor decay state can be quickly fed back to the control system to ensure the continuous and stable operation of the capacitor under complex load conditions. It is suitable for dynamic load fluctuation scenarios, and can quickly adjust the power flow distribution when the load changes drastically to prevent capacitor overload or failure, improve the anti-interference ability of the converter system, and reduce system fluctuations or bus voltage instability caused by abnormal capacitor state.

[0028] S3, constructing a redundant control path to predict the state of the backup capacitor; Preferably, a redundant control path is constructed to predict the state of the backup capacitor, the output of the SVR model is used as the main control path, and a dual control path is introduced to add a redundant control path; Based on the attenuation curve data of the converter health prediction, a one-dimensional linear regression model is constructed by least squares fitting, which is expressed as: ; ; ; in represents the predicted value of linear capacitance, represents time, a represents the slope of the regression line, b represents the intercept of the regression line, represents the number of data points of the decay curve, represents the data at the i-th time point, represents the output value of the SVR model at the i-th time point, and Respectively and The average value of The SVR model output is compared in real time with the predicted output results of the redundant control path. The sum of the mean and standard deviation of the historical error values ​​is used as the deviation threshold. If the real-time comparison result is greater than or equal to the deviation threshold, it is judged that the deviation is large, and the predicted output results of the redundant control path are switched.

[0029] The dual-path architecture of the SVR model main control path and the linear regression redundant path ensures that when the main path prediction is abnormal or has a large deviation, it automatically switches to the redundant path to ensure continuous and stable operation of the system. The linear regression model fits the attenuation curve based on the least squares method, and can provide stable prediction results even in complex environments, reducing the system failure rate. When the main path has calculation anomalies or short-term prediction distortion, the redundant path can quickly take over to prevent the capacitor health monitoring system from being interrupted, ensuring uninterrupted operation of the system and improving the test effect. The linear regression model has low computational complexity and can provide effective results even under conditions of limited hardware performance. Capacitor health prediction: By comparing the SVR model output with the redundant path prediction value in real time, the prediction accuracy of the main path is continuously monitored to ensure timely identification and correction of abnormal deviations. When abnormal fluctuations occur in the prediction of the main control path, the redundant path can intervene in time to avoid system overload or capacitor failure due to misjudgment of the capacitor state, and to warn of potential risks in advance. The capacitor attenuation curve is fitted using the least squares method to convert the capacitor state change trend into an intuitive mathematical model, providing long-term and reliable data support for capacitor maintenance and replacement. The linear regression model accurately fits the long-term attenuation characteristics, allowing maintenance personnel to intuitively predict the capacitor failure time point and optimize maintenance strategies. Under different load conditions, the system can continuously monitor the health status of the capacitors and dynamically adjust the inverter output power according to real-time power demand. When the load suddenly increases or decreases, the system can respond quickly to prevent large fluctuations in the bus voltage, ensuring that the entire system continues to operate stably under complex working conditions. Even if some capacitors attenuate or fail, the power output can be compensated in time through redundant paths to avoid overall system shutdown due to failure of a single component.

[0030] S4, based on the prediction of the capacitance value, optimizes the load of the balanced converter according to the real-time power flow; Preferably, based on the prediction of the capacitance value, the load of the converter is balanced according to the real-time power flow optimization, the converter output power is dynamically allocated according to the prediction of the capacitance value, and the bus voltage and the current output power of the converter are monitored in real time through the voltage sensor and the current sensor. Basic Droop control calculates the current output power of the converter based on the difference between the actual voltage and the set voltage, expressed as: ; in represents the output power of converter i at time t, represents the maximum output power of converter i, k represents the Droop coefficient, which is determined by experiment. represents the bus voltage at time t, Indicates the bus voltage setting value; The output power of the converter is adjusted by reducing the output voltage to achieve automatic power distribution. The core of Droop control is to adjust the output power of the converter according to the real-time load conditions, so that each parallel converter can share the load and prevent uneven power distribution; Model predictive control (MPC) is introduced, and the load dynamic model is established by fitting the historical power curve, which is expressed as: ; in represents the load power at time t, Indicates the trend curvature of load change, Indicates the linear change rate of load over time, represents the base load power, , and The least square method is used to fit the known load power data and minimize the error between the predicted power and the actual power to solve the problem; Although Droop control can respond quickly when the load fluctuates, it mainly relies on real-time feedback and has a certain delay. In order to further improve the dynamic response speed, model predictive control (MPC) is introduced. MPC can predict the future load in advance based on the load change trend and add feedforward control in the power distribution process to reduce the hysteresis of Droop control, distribute power in advance, and avoid capacitor overload. The power demand of future time steps is calculated based on the load dynamic model, and an adaptive dynamic compensation mechanism is introduced. The difference between the actual load power and the total output power of the converter is calculated at each time step as the power allocation error, which is expressed as: ; ; in represents the power allocation error, Indicates the total number of data. represents the modified Droop coefficient, represents the compensation gain, which is usually set between 0.05 and 0.1 based on experimental settings; Although Droop control and MPC can optimize power distribution under most working conditions, due to the uncertainty and nonlinear fluctuation of the load, the Droop coefficient k may deviate after a long period of operation, resulting in inaccurate power distribution. Therefore, the system introduces an adaptive dynamic compensation mechanism to achieve more accurate power flow distribution by dynamically adjusting the Droop coefficient through real-time monitoring of power distribution errors. After correcting the Droop coefficient, the converter output power is dynamically calculated.

[0031] By combining Droop control with MPC model predictive control, the output power of the converter can be dynamically allocated according to the real-time fluctuation of the bus voltage and the future load change trend, preventing individual converters from being overloaded or unloaded, and improving the operating efficiency and stability of the overall system. After long-term operation, the Droop coefficient may deviate due to capacitor aging or load fluctuations. The adaptive compensation mechanism can automatically correct the error to ensure the accuracy of power distribution and prevent uneven power distribution. Especially in the environment of multi-converter parallel operation, it helps to optimize the power flow distribution and maintain the stable operation state of the system. Through dual-path capacitor health monitoring and Droop-MPC dynamic power distribution, the power output can be adjusted in time when the capacitor decays early, avoiding single-point failures and causing system shutdowns. This strategy has high redundancy, ensuring that even if the main path fails, the redundant path can still maintain the basic operation of the system and reduce unplanned downtime. Through the power flow optimization control strategy, it can effectively prevent the capacitor from being in a high-load state for a long time, reduce capacitor overcurrent and overtemperature, and reduce capacitor loss; Real-time monitoring of the health status of capacitors is achieved through the main path (PSO-SVR model) and the redundant path (linear regression model). However, the monitoring of the health status only provides feedback on the system operation status and fails to directly intervene in the power flow distribution of the system. Therefore, in order to ensure that the capacitors participate in the system operation reasonably under different health states and balance the loads of each converter to prevent local equipment overload or uneven operating efficiency, it is necessary to introduce a real-time power flow optimization control strategy. According to the real-time health status of the capacitor, the output power of each converter is dynamically adjusted to match the system load demand, and the power is evenly distributed according to the load conditions of each converter module to avoid overload operation of individual converters. When the health status of the capacitor gradually declines, the system can issue an early warning signal through the capacitor attenuation curve, allowing the operation and maintenance personnel to perform necessary maintenance or replacement before the capacitor fails. This prevents the impact of sudden capacitor failure on the system, reduces the possibility of unexpected downtime, and ensures the continuity and stability of production and power supply.

[0032] S5, data synchronization monitoring is performed through the power monitoring unit; Preferably, data synchronization monitoring is performed through a power monitoring unit, a power monitoring unit PMU is embedded in each converter, output power, voltage, and current state parameters are monitored in real time, and the converter communicates with other converters through a CAN bus to form a distributed monitoring network; One converter is set as the master converter, which is responsible for summarizing the power status of each converter and distributing the load. Other converters are set as slave converters, which respond to the instructions of the master converter. Based on the monitoring cycle, the master converter collects the output power data of all slave converters, calculates the total load, and distributes it to each converter according to the calculated load ratio to balance the load.

[0033] Through the power monitoring unit (PMU) to monitor each converter in real time, the master converter can dynamically grasp the operating status and output power of each converter. Power is distributed in real time according to the load conditions to ensure that the output power of each converter remains balanced. When the load suddenly increases or is unevenly distributed, the master converter can quickly redistribute the load to prevent a converter from being overloaded for a long time and reduce the risk of overheating or damage to local converters. Even in the case of instantaneous load changes, the system can quickly adjust the power output of each converter to prevent bus voltage fluctuations or short-term converter overload. Real-time monitoring enables the system to have higher dynamic response capabilities and meet the operating requirements of scenarios with rapid load changes.

[0034] S6, building a virtual simulation model for data simulation; Preferably, a virtual simulation model is constructed for data simulation, and a virtual simulation model of the converter and the capacitor is constructed based on MATLAB through digital twin technology; Through IoT devices and sensors, the data of the physical system is synchronized to the digital twin in real time, and load surge, overload and capacitance attenuation scenarios are simulated in the digital environment to optimize the Droop controller and MPC parameters.

[0035] By improving the digital twin system's ability to simulate the operating status of capacitors and converters in a virtual environment, and predicting the capacitor attenuation process and potential failure risks through real-time monitoring and simulation, the converter and capacitor system can be fully debugged and loaded in the digital twin before actual deployment, thus reducing on-site equipment debugging time, speeding up equipment commissioning, simulating various complex working conditions in virtual simulation, optimizing control strategies and hardware configurations in advance, and reducing on-site repeated debugging and experimental costs.

[0036] S7, dynamically adjusts the cooling strategy according to temperature changes; Preferably, the heat dissipation strategy is dynamically adjusted according to temperature changes, a temperature sensor is installed on the surface of the capacitor, the temperature change is monitored in real time, a safe temperature range of the capacitor is set, the temperature data is transmitted to the main control converter, and the heat dissipation strategy is dynamically adjusted according to the temperature change; A high temperature threshold is determined based on the device heat dissipation temperature standard. If the monitored temperature data exceeds the high temperature threshold, the heat dissipation fan is started to execute the heat dissipation strategy.

[0037] By monitoring the capacitor temperature in real time, the cooling system can be quickly activated when the capacitor approaches or exceeds the safe temperature range to prevent the capacitor from being damaged or performance degradation due to overheating. By dynamically adjusting the cooling strategy, the loss of capacitor materials due to long-term high-temperature operation can be avoided, ensuring stable system operation, reducing the risk of capacitor failure caused by overheating, ensuring the continuous and stable operation of the inverter system, and reducing system shutdowns or unexpected failures due to capacitor failure.

[0038] S8, performing capability feedback storage to realize capability circulation; Preferably, performing energy feedback storage to achieve energy circulation means that during the back-to-back test, excess energy is fed back to the energy storage device, and the energy flow direction between the DC bus and the power grid is monitored through the electric energy metering device. When the load is reduced or the system has excess power, the inverter automatically switches to the energy feedback mode and feeds the excess power back to the power grid or the energy storage device to achieve energy recycling.

[0039] Through the energy circulation mechanism, excess energy is stored and released again when the load increases, ensuring that energy is fully utilized and improving the overall energy efficiency ratio. When the load suddenly decreases, excess electrical energy will be fed back to the energy storage device or the power grid to avoid inverter overload or damage due to increased bus voltage, effectively protecting the safety of system equipment and reducing the impact of load fluctuations on equipment. In industrial scenarios with large fluctuations in energy consumption, the system can quickly adjust the direction of power flow to avoid insufficient or excessive power supply, thereby improving the load adaptability and stability of the system.

[0040] In summary, the present invention can respond in real time when the capacitor state changes through the CNN-PSO-SVR model, ensure that the capacitor attenuation state can be quickly fed back to the control system, ensure that the capacitor can continue to operate stably under complex load conditions, and timely compensate for power output through redundant paths to avoid overall system shutdown due to single component failure. Through dual-path capacitor health monitoring and Droop-MPC dynamic power allocation, the power output can be adjusted in time when the capacitor decays early, avoiding system shutdown due to single point failure.

[0041] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the 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. A back-to-back test platform for energy storage converters, characterized in that: include: The data acquisition module uses a voltage source converter to access the power grid and collect data under different load conditions; The capacitor health prediction module builds a deep learning model to extract features and calculates the fitness function to predict the capacitor status value; A redundant control path module, which constructs a redundant control path to predict the state of the backup capacitor; A load balancing module, based on the prediction of the capacitance value, optimizes and balances the load of the converter according to the real-time power flow; Data synchronization module, which performs data synchronization monitoring through a power monitoring unit; Data simulation module, building a virtual simulation model for data simulation; The temperature management module dynamically adjusts the heat dissipation strategy according to temperature changes; The energy storage module performs energy feedback storage to realize energy circulation.

2. The energy storage converter back-to-back test platform according to claim 1, characterized in that: The use of a voltage source converter to access the grid refers to the use of a voltage source back-to-back converter VSC, which includes two bidirectional voltage source inverters, the AC output end of the first bidirectional voltage source inverter is connected to the grid side, and the AC output end of the second bidirectional voltage source inverter is connected to the load side.

3. The energy storage converter back-to-back test platform according to claim 2, characterized in that: The collecting of data under different load conditions is based on collecting data under different load conditions, and recording the data of voltage, current, temperature and resistance through a voltage sensor, a current sensor, a temperature sensor and a capacitor equivalent series resistance (ESR) sensor; A high-frequency sampling circuit is introduced on the DC bus to transmit the voltage pulsation signal to the ADC sampler; Perform fast Fourier transform on the DC bus voltage, extract high-frequency voltage spectrum feature data, and store it through a sliding window mechanism; Data storage adopts a dual-channel backup mechanism, the main storage channel is the internal memory, and the backup channel is the external storage device.

4. The energy storage converter back-to-back test platform according to claim 3, characterized in that: The deep learning model is constructed to extract features and calculate the fitness function to predict the capacitance state value. The deep learning model is constructed based on a convolutional neural network, including an input layer, a convolutional layer and an output layer; The data collected under different load conditions are used as training data for model training. The cross entropy loss function is selected to calculate the computational loss between the category probability predicted by CNN and the actual label. The Adam optimizer is used for gradient descent optimization to update the weight parameters of the CNN model. If the model loss no longer decreases significantly during continuous iterations, the iteration is stopped. Based on the newly collected converter test data, the deep learning model is input, and the principal component analysis (PCA) is used to reduce the dimension of the model output data; The particle swarm optimization (PSO) algorithm is used to optimize the hyperparameters of the support vector regression (SVR) model, and the feature matrix after PCA dimension reduction is used as the input of the SVR model. The particle swarm size setting based on the particle swarm optimization PSO algorithm includes three categories, which are determined based on historical data and represent the hyperparameters of the SVR model, including penalty factors, kernel function parameters, and allowable error range; The SVR model is trained based on the hyperparameters of randomly initialized particles, and the root mean square error RMSE of the SVR model corresponding to the current particle on the test set is calculated as the fitness function; At the same time, the particle position and velocity are updated and iterative calculations are performed. When the drop in loss is no longer obvious, the iteration is stopped, and the SVR model corresponding to the particle with the smallest RMSE is selected as the final model; Based on the newly collected converter operation data, the equivalent capacitance value of the capacitor at the corresponding time point is output through the SVR model, and multiple capacitance prediction values ​​in continuous time are fitted into a decay curve to predict the capacitance state value.

5. The energy storage converter back-to-back test platform according to claim 4, characterized in that: The redundant control path is constructed to predict the state of the backup capacitor, the output of the SVR model is used as the main control path, and a dual control path is introduced to add a redundant control path; Based on the attenuation curve data of the converter health prediction, a one-dimensional linear regression model is constructed by least squares fitting, which is expressed as: ； ； ； in represents the predicted value of linear capacitance, represents time, a represents the slope of the regression line, b represents the intercept of the regression line, represents the number of data points of the decay curve, represents the data at the i-th time point, represents the output value of the SVR model at the i-th time point, and Respectively and The average value of The SVR model output is compared in real time with the predicted output results of the redundant control path. The sum of the mean and standard deviation of the historical error values ​​is used as the deviation threshold. If the real-time comparison result is greater than or equal to the deviation threshold, it is judged that the deviation is large, and the predicted output results of the redundant control path are switched.

6. The energy storage converter back-to-back test platform according to claim 5, characterized in that: The load of the converter is balanced based on the prediction of the capacitance value, according to the real-time power flow optimization, the output power of the converter is dynamically allocated according to the prediction of the capacitance value, and the bus voltage and the current output power of the converter are monitored in real time through the voltage sensor and the current sensor; Basic Droop control calculates the current output power of the converter based on the difference between the actual voltage and the set voltage, expressed as: ； in represents the output power of converter i at time t, represents the maximum output power of converter i, k represents the Droop coefficient, represents the bus voltage at time t, Indicates the bus voltage setting value; Model predictive control (MPC) is introduced, and the load dynamic model is established by fitting the historical power curve, which is expressed as: ； in represents the load power at time t, Indicates the trend curvature of load change, Indicates the linear change rate of load over time, Indicates the base load power; The power demand of future time steps is calculated based on the load dynamic model, and an adaptive dynamic compensation mechanism is introduced. The difference between the actual load power and the total output power of the converter is calculated at each time step as the power allocation error, which is expressed as: ； ； in represents the power allocation error, Indicates the total number of data. represents the modified Droop coefficient, represents the compensation gain; After correcting the Droop coefficient, the converter output power is dynamically calculated.

7. The back-to-back test platform for energy storage converters according to claim 6, characterized in that: The data is synchronously monitored by the power monitoring unit, and a power monitoring unit PMU is embedded in each converter to monitor the output power, voltage, and current state parameters in real time, and communicate with other converters through the CAN bus to form a distributed monitoring network; One converter is set as the master converter, which is responsible for summarizing the power status of each converter and distributing the load. Other converters are set as slave converters, which respond to the instructions of the master converter. Based on the monitoring cycle, the master converter collects the output power data of all slave converters, calculates the total load, and distributes it to each converter according to the calculated load ratio to balance the load.

8. The back-to-back test platform for energy storage converters according to claim 7, characterized in that: The virtual simulation model is constructed to perform data simulation, and a virtual simulation model of the converter and the capacitor is constructed based on MATLAB through the digital twin technology; Through IoT devices and sensors, the data of the physical system is synchronized to the digital twin in real time, and load surge, overload and capacitance attenuation scenarios are simulated in the digital environment to optimize the Droop controller and MPC parameters.

9. The energy storage converter back-to-back test platform according to claim 8, characterized in that: According to the temperature change, the heat dissipation strategy is dynamically adjusted, a temperature sensor is installed on the surface of the capacitor, the temperature change is monitored in real time, a safe temperature range of the capacitor is set, the temperature data is transmitted to the main control converter, and the heat dissipation strategy is dynamically adjusted according to the temperature change; A high temperature threshold is determined based on the device heat dissipation temperature standard. If the monitored temperature data exceeds the high temperature threshold, the heat dissipation fan is started to execute the heat dissipation strategy.

10. The energy storage converter back-to-back test platform according to claim 9, characterized in that: The energy feedback storage to achieve energy circulation refers to feeding back excess energy to the energy storage device during the back-to-back test, monitoring the energy flow direction between the DC bus and the power grid through the electric energy metering device, and when the load is reduced and the system has excess power, the inverter automatically switches to the energy feedback mode, feeding back the excess power to the power grid and the energy storage device, thereby achieving energy recycling.

Images