Supercapacitor system health status estimation method, device, equipment and medium

Abstract

A method for estimating the state of health (SOH) of a supercapacitor system, which obtains a number of discharge segment data and a number of charging segment data based on the historical charge and discharge data of the supercapacitor system under actual operating conditions; obtains the SOH label of the supercapacitor system in different historical preset time periods based on each discharge segment data; obtains the power characteristics and module voltage characteristics of the supercapacitor system in different historical preset time periods based on each charging segment data, as health characteristics of different historical preset time periods; trains an estimation model based on the health characteristics and SOH labels of different historical preset time periods to obtain an SOH estimation model of the supercapacitor system; and uses the SOH estimation model to estimate the health state of the supercapacitor system. This application can accurately estimate the health state of the supercapacitor system in the actual operation of the electrified transportation system carrier and the renewable energy system, and improve the safety and economic benefits of the operation of the electrified transportation system carrier and the renewable energy system.

Description

Technical Field

[0001] The present application belongs to the field of supercapacitor technology, and specifically relates to a method, device, equipment and medium for estimating the health status of a supercapacitor system. Background Art

[0002] As a new energy storage technology, supercapacitors (including double-layer capacitors, lithium-ion capacitors, sodium-ion capacitors, etc.) have the advantages of high power density, fast charging speed, long service life, and wide operating temperature range. Therefore, energy storage systems that only use supercapacitors as energy storage devices, as well as hybrid energy storage systems composed of supercapacitors and other energy storage devices other than supercapacitors (such as lithium-ion batteries, hydrogen fuel cells, sodium-ion batteries, etc.) are widely used in electrified transportation system vehicles (such as electric vehicles, buses, trucks, rail transit, ships, aircraft, etc.) and renewable energy systems (such as power grids, microgrids, etc.).

[0003] In order to ensure the normal operation of vehicles and renewable energy systems in electrified transportation systems and to improve the safety and economy of supercapacitor systems during operation, it is necessary to effectively evaluate the state of health (SOH) of supercapacitor systems. Existing methods are based on laboratory test data of supercapacitor cells / modules, and are studied from two aspects: aging mechanism and data-driven. However, the SOH evaluation method based on laboratory test data of supercapacitor cells / modules is not fully applicable to supercapacitor systems under actual operating conditions. In addition, the data accuracy of supercapacitor systems under actual operating conditions is lower than that of laboratory test data. At the same time, the time and economic cost required for offline SOH evaluation of supercapacitor systems are high. Therefore, how to use the data of supercapacitor systems under actual operating conditions to estimate their health status has become an urgent problem to be solved. Summary of the Invention

[0004] In view of the shortcomings of the existing technology mentioned above, the present application designs a supercapacitor system health status estimation method, device, equipment and medium to accurately estimate the health status of supercapacitor systems in actual operating electrified transportation system vehicles and renewable energy systems, thereby increasing their operating safety and economic benefits.

[0005] To achieve the above-mentioned and other related objectives, the present application provides a method for estimating the health status of a supercapacitor system. The supercapacitor system can be applied to vehicles used in electrified transportation systems and renewable energy systems. The supercapacitor system includes an energy storage system that uses only supercapacitors as an energy storage device, and a hybrid energy storage system composed of supercapacitors and other energy storage devices in addition to supercapacitors.

[0006] The supercapacitor system health status estimation method includes:

[0007] Acquire a plurality of discharge segment data and a plurality of charge segment data according to historical charge and discharge data of the supercapacitor system under actual operating conditions;

[0008] Acquire the SOH tags of the supercapacitor system in different historical preset time periods according to each of the discharge segment data;

[0009] Acquire power characteristics and module voltage characteristics of the supercapacitor system in different historical preset time periods according to each of the charging segment data as health characteristics of the different historical preset time periods;

[0010] Performing estimation model training based on health characteristics and corresponding SOH labels in different historical preset time periods to obtain an SOH estimation model for the supercapacitor system;

[0011] The SOH estimation model is used to estimate the health state of the supercapacitor system.

[0012] In an optional embodiment of the present application, obtaining the SOH tag of the supercapacitor system in different historical preset time periods according to each of the discharge segment data includes:

[0013] Identify equivalent parameters of each discharge segment data through a resistance-capacitance equivalent model to obtain an equivalent capacitance corresponding to each discharge segment;

[0014] performing capacitance calibration according to the equivalent capacitance corresponding to each of the discharge segments to obtain capacitance labels of the supercapacitor system at different historical preset time periods;

[0015] The SOH labels of different historical preset periods are obtained according to the capacitance labels of different historical preset periods.

[0016] In an optional embodiment of the present application, the equivalent parameters of each discharge segment data are identified through a resistance-capacitance equivalent model to obtain an equivalent capacitance corresponding to each discharge segment, including:

[0017] For each of the discharge segment data, the following steps are performed respectively:

[0018] Predicting a voltage prediction value of each data point in the discharge segment data by using the resistance-capacitance equivalent model;

[0019] Constructing a loss function according to the actual voltage value and the voltage prediction value of each data point in each of the discharge segment data;

[0020] The partial derivative of the loss function with respect to the target variable is obtained, and the optimization direction is determined by a gradient descent optimization strategy to perform iterative optimization to obtain the equivalent capacitance corresponding to the discharge segment data.

[0021] In an optional embodiment of the present application, the resistor-capacitor equivalent model is a first-order resistor-capacitor equivalent model.

[0022] In an optional embodiment of the present application, a plurality of discharge segment data and a plurality of charge segment data are obtained based on historical charge and discharge data of the supercapacitor system under actual operating conditions, including:

[0023] Obtaining historical charge and discharge data of the supercapacitor system under actual operating conditions;

[0024] Performing data cleaning on the historical charge and discharge data under the actual operating conditions;

[0025] Segmenting the historical charge and discharge data under the actual operating conditions after cleaning to obtain a plurality of discharge segment initial data and a plurality of charge segment data;

[0026] The voltage abnormal points in each of the initial data of the discharge segment are removed to obtain a plurality of the discharge segment data.

[0027] In an optional embodiment of the present application, the charging segment includes the charging voltage, charging current, maximum module voltage value, and minimum module voltage value at each sampling point;

[0028] Obtaining power characteristics and module voltage characteristics of the supercapacitor system in different historical preset time periods according to each of the charging segment data as health characteristics of the different historical preset time periods, including:

[0029] Obtaining power characteristics of the supercapacitor system in different historical preset time periods according to the charging voltage and charging current of each sampling point in each charging segment data;

[0030] Obtaining module voltage characteristics of the supercapacitor system in different historical preset time periods according to the module maximum voltage value and the module minimum voltage value of each sampling point in each of the charging segment data;

[0031] The power characteristics and module voltage characteristics of different historical preset time periods are used as health characteristics of different historical preset time periods.

[0032] In an optional embodiment of the present application, obtaining power characteristics of the supercapacitor system in different historical preset time periods according to the charging voltage and charging current of each sampling point in each charging segment data includes:

[0033] Calculating the power of each charging segment data according to the charging voltage and charging current of each sampling point in each charging segment data;

[0034] For each historical preset segment: based on the power of all the charging segment data in the historical preset time period, calculate the overall power average value, long segment power average value, short segment power average value, high voltage segment power average value and low voltage segment power average value of the historical preset time period as the power characteristics of the historical preset time period.

[0035] In an optional embodiment of the present application, obtaining the module voltage characteristics of the supercapacitor system in different historical preset time periods according to the module maximum voltage value and the module minimum voltage value of each sampling point in each of the charging segment data includes:

[0036] Obtaining a maximum voltage difference between modules at each sampling point in each charging segment data according to a maximum module voltage value and a minimum module voltage value at each sampling point in each charging segment data;

[0037] Obtaining the maximum voltage difference average value and the maximum voltage difference range of each charging segment data according to the maximum voltage difference between modules at each sampling point in each charging segment data;

[0038] For each historical preset period: the average value of the maximum voltage difference, the average value and the range of the maximum voltage difference of all the charging segment data in the historical preset period are calculated respectively as the module voltage feature of the historical preset period.

[0039] To achieve the above-mentioned and other related objectives, the present application provides a supercapacitor system health status estimation device, wherein the supercapacitor system can be applied to electrified transportation system vehicles and renewable energy systems, and the supercapacitor system includes an energy storage system that uses only supercapacitors as an energy storage device, and a hybrid energy storage system composed of supercapacitors and other energy storage devices in addition to supercapacitors;

[0040] The supercapacitor system health status estimation device includes:

[0041] A segment data acquisition module, configured to acquire a plurality of discharge segment data and a plurality of charge segment data based on historical charge and discharge data of the supercapacitor system under actual operating conditions;

[0042] An SOH tag acquisition module, configured to acquire the SOH tags of the supercapacitor system in different historical preset time periods according to each of the discharge segment data;

[0043] a health feature acquisition module, configured to acquire, based on each of the charging segment data, power features and module voltage features of the supercapacitor system in different historical preset time periods as health features of the supercapacitor system in different historical preset time periods;

[0044] A model training module is used to train an estimation model based on health characteristics and corresponding SOH labels of different historical preset time periods to obtain an SOH estimation model for the supercapacitor system;

[0045] A state estimation module is used to estimate the health state of the supercapacitor system using the SOH estimation model.

[0046] To achieve the above-mentioned purpose and other related purposes, the present invention application also provides an electronic device, characterized in that it includes a processor, a memory and a communication bus; the communication bus is used to connect the processor and the memory; the processor is used to execute a computer program stored in the memory to implement the above-mentioned supercapacitor system health status estimation method.

[0047] To achieve the above-mentioned purpose and other related purposes, the present application also provides a storage medium having a computer program stored thereon, wherein the computer program is used to enable a computer to execute the above-mentioned supercapacitor system health status estimation method.

[0048] The supercapacitor system health status estimation method of the present application obtains a number of discharge segment data and a number of charging segment data based on the historical charge and discharge data of the supercapacitor system under actual operating conditions; obtains the SOH label of the supercapacitor system in different historical preset time periods based on each of the discharge segment data; obtains the health characteristics of the supercapacitor system in different historical preset time periods based on each of the charging segment data, wherein the health characteristics include power characteristics and module voltage characteristics; trains an estimation model based on the health characteristics of different historical preset time periods and the corresponding SOH labels to obtain the SOH estimation model of the supercapacitor system; and uses the SOH estimation model to estimate the health status of the supercapacitor system. The present application can be used to accurately estimate the health status of the supercapacitor system in the actual operation of the electrified transportation system carrier and the renewable energy system, thereby improving the safety and economic benefits of the operation of the electrified transportation system carrier and the renewable energy system. And the average absolute percentage error of the health status of the supercapacitor system in the actual operation of the electrified transportation system carrier and the renewable energy system estimated by the present application can be as low as 0.913%. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 A flow chart of a method for estimating the health status of a supercapacitor system provided in this application;

[0050] Figure 2 This is a schematic diagram of a supercapacitor system health status estimation process in a specific embodiment of the present application;

[0051] Figure 3The charging starting voltage distribution diagram of the charging segment data of a supercapacitor system in a certain month;

[0052] Figure 4 The charging time distribution diagram of the charging segment data of a supercapacitor system in a certain month;

[0053] Figure 5 A schematic diagram of a supercapacitor system health status estimation device provided in this application;

[0054] Figure 6 A schematic diagram of an electronic device of the present application. DETAILED DESCRIPTION

[0055] The following describes the embodiments of the present application through specific examples. Those skilled in the art can easily understand the other advantages and effects of the present application from the content disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments. The details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other unless they conflict.

[0056] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application. Therefore, the illustrations only show components related to the present application and are not drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component can be changed at will, and the component layout type may also be more complicated.

[0057] Figure 1 The flowchart of the method for estimating the health status of a supercapacitor system in an exemplary embodiment of the present application is shown, including steps S10 to S50. Figure 2 A schematic diagram of the process flow for estimating the health status of a supercapacitor system in a specific embodiment of the present application is given. Figure 1 and Figure 2 The technical solution of this application will be described in detail.

[0058] First, step S10 is executed to obtain a plurality of discharge segment data and a plurality of charge segment data according to the historical charge and discharge data of the supercapacitor system under actual operating conditions.

[0059] Specifically, when obtaining a number of discharge segment data based on the historical charge and discharge data of the supercapacitor system under actual operating conditions, it is necessary to first obtain the historical charge and discharge data of the supercapacitor system under actual operating conditions as original data; then perform preprocessing operations such as data cleaning on the historical charge and discharge data under actual operating conditions; then perform data segmentation on the cleaned historical charge and discharge data under actual operating conditions to obtain a number of discharge segment initial data and a number of charging segment data; finally, remove the voltage abnormal points in each of the discharge segment initial data to obtain a number of the discharge segment data.

[0060] The supercapacitor system can be applied to vehicles used in electrified transportation systems and renewable energy systems. The supercapacitor system includes energy storage systems that use only supercapacitors as energy storage devices, as well as hybrid energy storage systems consisting of supercapacitors and other energy storage devices other than supercapacitors. The electrified transportation system vehicles include one or more vehicles used to transport people and goods, such as trams, passenger cars, trucks, buses, ships, and aircraft; the renewable energy system includes one or more power grids and microgrids; and other energy storage devices include other energy storage devices other than supercapacitors, such as lithium-ion batteries, hydrogen fuel cells, and sodium-ion batteries.

[0061] This application will be illustrated using the supercapacitor system in a vehicle as an example. The historical charge and discharge data under actual operating conditions are data generated over a period of time during the actual operation of the vehicle, such as the charge and discharge data of the supercapacitor system under actual operating conditions for several years. The historical charge and discharge data under actual operating conditions include at least charge and discharge current timing signals, charge and discharge voltage timing signals, and the maximum voltage value and minimum voltage value in the module.

[0062] It should be noted that in order to reduce the amount of calculation and taking into account that the equivalent capacitance of the supercapacitor system is relatively stable in a short period of time, when obtaining the historical charge and discharge data of the supercapacitor system under actual operating conditions, only one day (of course, it can be multiple days) of charge and discharge data can be obtained in different historical preset time periods, such as weekly, monthly or quarterly.

[0063] Since uncertain external working conditions may affect the quality of data collection, the charging and discharging data of the vehicle under the actual operating conditions collected may have data missing and data duplication. Therefore, it is necessary to clean the historical charging and discharging data under the actual operating conditions before data segmentation to remove this part of the data.

[0064] After data cleaning, the cleaned historical charge and discharge data under the actual operating conditions must be segmented to filter out the required discharge and charge segments. Discharge segments are selected as segments with current less than zero, and charge segments are selected as segments with current greater than zero. The criteria for determining whether two adjacent data points share the same discharge behavior can be determined based on sampling time and current; the criteria for determining whether two adjacent data points share the same charge behavior can be determined based on sampling time and current.

[0065] Discharge segment data screening: Filtering from the perspective of sampling time. Considering possible transmission errors in actual data collection, such as delays in data collection or recording, a sampling time interval standard can be set as a standard time interval. The standard time interval can be set as needed, for example, 20 seconds. When the sampling time interval between two adjacent data points is no greater than the standard time interval, the two data points are considered to be in the same discharge behavior; otherwise, they are considered to be in different discharge behaviors. Filtering from the perspective of current. Considering possible current fluctuations in actual data collection, a current difference standard is set as a current difference threshold. The current difference threshold can be set as needed, for example, 2A. When the current difference between two adjacent data points is no greater than the current difference threshold, the two data points are considered to be in the same discharge behavior; otherwise, they are considered to be in different discharge behaviors. Data points with the same discharge behavior constitute the initial data for a discharge segment. The historical charge and discharge data under the actual operating conditions after cleaning are screened using the two dimensions of sampling time and current to select the initial data for the discharge segment where the sampling time interval between two adjacent data points is no greater than the standard time interval and the current difference between the two adjacent data points is no greater than the current difference threshold.

[0066] It should be noted that individual outliers may still exist in the segmented initial discharge segment data. This is particularly evident when voltage outliers appear in the initial discharge segment data of a period of continuous, stable current. To account for the potential outliers in actual data collection, a voltage difference standard for the sampling points, also known as a voltage difference threshold, can be set. The voltage difference threshold can be set as needed, for example, to 2V. When the voltage difference between two adjacent data points is no greater than the voltage difference threshold, the points are considered to be in the same discharge behavior. Otherwise, the voltage outlier is removed from the initial discharge segment data, thereby obtaining the final discharge segment data.

[0067] Charging fragment data screening: Screening from the aspect of sampling time, taking into account the transmission errors that may occur in the actual collection, such as delays in collection, or delays in recording, the sampling time interval standard can be set as the standard time interval, wherein the standard time interval can be set as needed, for example, 20s. When the sampling time interval between two adjacent data points is not greater than the standard time interval, the two data points are considered to be in the same charging behavior, otherwise they are considered to be not in the same charging behavior. Screening from the current direction, when the large currents of two adjacent data points are both greater than 0, they can be considered to be in the same charging behavior, otherwise they are considered to be not in the same charging behavior. The historical charge and discharge data under the actual operating conditions after cleaning are screened by the two dimensions of sampling time and current to screen out the fragment data whose sampling time interval between two adjacent data points is not greater than the standard time interval and whose currents of two adjacent data points are both greater than zero as charging fragment data.

[0068] Next, step S20 is executed to obtain the SOH tags of the supercapacitor system in different historical preset time periods according to each of the discharge segment data.

[0069] Specifically, when obtaining the SOH labels of the supercapacitor system in different historical preset time periods based on each of the discharge segment data, the equivalent parameters of each of the discharge segment data can be first identified through a resistance-capacitance equivalent model to obtain the equivalent capacitance corresponding to each of the discharge segments (step S201); then, the capacitance is calibrated according to the equivalent capacitance corresponding to each of the discharge segments to obtain the capacitance labels of the supercapacitor system in different historical preset time periods (step S202); and the SOH labels of different historical preset time periods are obtained based on the capacitance labels of different historical preset time periods (step S203).

[0070] Since the charge and discharge parameters of a supercapacitor system are primarily voltage and current, the equivalent parameters of each discharge segment of the supercapacitor system obtained through the screening process can be identified using a first-order resistance-capacitance model to obtain the equivalent capacitance of the supercapacitor system corresponding to each discharge segment. For each discharge segment, the equivalent capacitance corresponding to that discharge segment can be obtained through the following steps S2011-S2013.

[0071] In step S2011, the voltage prediction value of each data point in the discharge segment data is predicted by the resistor-capacitor equivalent model. It can be understood that, assuming that there are i data points in a discharge segment data, the voltage prediction value of (i-1) data points can be obtained based on the voltage and current data of the i data points by the first-order resistor-capacitor equivalent model.

[0072]

[0073] Where V out (t1) represents the actual voltage value of the current data point, I out (t1) represents the actual current value of the current data point, I out (t2) represents the actual current value of the next data point, and C and R represent the equivalent capacitance and equivalent resistance in the resistor-capacitor model.

[0074] In step S2012, a loss function L is constructed according to the true voltage value and the voltage estimation value of each data point in each of the discharge segment data.

[0075] In step S2013, the partial derivative of the loss function with respect to the target variable is obtained, and an optimization direction is determined by a gradient descent optimization strategy to perform iterative optimization to obtain the equivalent capacitance corresponding to the discharge segment data.

[0076] It should be noted that, when obtaining the historical charge and discharge data of the supercapacitor system under actual operating conditions, taking the charge and discharge data of only one day (of course it can be multiple days) under actual operating conditions in different historical preset time periods, such as each week, month or quarter, as an example, the capacitance is calibrated according to the equivalent capacitance corresponding to each of the discharge segments to obtain the capacitance labels of different historical preset time periods of the supercapacitor system, and in the step of obtaining the SOH labels of different historical preset time periods according to the capacitance labels of different historical preset time periods, the equivalent capacitance corresponding to each of the discharge segments can be integrated first, and the equivalent capacitance corresponding to all the discharge segments of the day can be averaged in units of days to obtain the capacitance label of the day, and the capacitance label of the day can be used as the capacitance label of the current historical preset time period, such as the current month (of course it can also be the current week or current quarter). Then, the SOH value of each historical preset time period can be obtained by dividing the capacitance label of each historical preset time period by the capacitance label of the first historical preset time period, as the SOH label of each historical preset time period.

[0077] Next, step S30 is executed to obtain the power characteristics and module voltage characteristics of the supercapacitor system in different historical preset time periods according to each of the charging segment data as health characteristics of different historical preset time periods.

[0078] In the present application, the charging segment may include the charging voltage, charging current, module maximum voltage value and module minimum voltage value of each sampling point; according to each of the charging segment data, the power characteristics and module voltage characteristics of the supercapacitor system in different historical preset time periods are obtained as health characteristics of different historical preset time periods, which may further include steps S301-S303.

[0079] In step S301, the power characteristics of the supercapacitor system for different historical preset time periods are obtained based on the charging voltage and charging current at each sampling point in each charging segment data. Specifically, the power of each charging segment data can be calculated based on the charging voltage and charging current at each sampling point in each charging segment data. For each historical preset segment: based on the power of all the charging segment data in the historical preset time period, the overall power average, long segment power average, short segment power average, high voltage segment power average, and low voltage segment power average of the historical preset time period are calculated as the power characteristics of the historical preset time period.

[0080] When calculating the power of each charging segment data based on the charging voltage and charging current at each sampling point in each charging segment data, a preset interpolation algorithm such as linear interpolation, spline interpolation, Newton interpolation, or Lagrange interpolation can be used to perform difference interpolation on each charging segment data to shorten the time interval between data points in the charging segment data. After interpolation, the time interval between two data points in the charging segment data can be reduced from 20s to 1s, for example. Then, the power of each charging segment data can be calculated according to the following formula:

[0081]

[0082] Where, P fragment is the power of each charging segment data, M is the number of data points in the segment after interpolation, V m and I m are the voltage and current of each data point in the interpolated segment, and Δt is the new time interval.

[0083] After obtaining the power of each charging segment data, for each historical preset period (such as daily, weekly, monthly, and quarterly):

[0084] The average power value of all charging segment data in the historical preset period can be obtained as the overall power average value of the historical preset period;

[0085] Then, the duration t of each charging segment data within the historical preset period can be used to calculate the charging time. c and charging start voltage V cs , divide the charging segment data into long segment data (t c >60s (configurable)), short fragment data (t c ≤60s (configurable)) and high voltage segment data (V cs >800V (configurable)), low voltage segment data (V cs ≤800V (configurable), calculate the average power P of these four types of fragments in the historical preset period respectively. long_mean(long segment power average), P short_mean (short segment power average), P high_mean (average power of high-voltage segment) and P low_mean (low-voltage segment power average value), four power-related features can be further obtained. These four power-related features and the overall power average value together constitute the power features of the historical preset period. Figure 3 The figure shows the charging starting voltage distribution diagram of a supercapacitor system in a certain month. Figure 4 The figure shows the charging time distribution of a supercapacitor system in a certain month.

[0086] In step S302 , module voltage characteristics of the supercapacitor system in different historical preset time periods are obtained according to the module maximum voltage value and the module minimum voltage value of each sampling point in each charging segment data.

[0087] Specifically, the maximum voltage difference (Max Voltage Difference, MVD) between modules of each sampling point in each charging segment data can be obtained based on the module maximum voltage value and module minimum voltage value of each sampling point in each charging segment data, wherein the MVD of each sampling point in each charging segment data is the difference between the module maximum voltage value and the module minimum voltage value of each sampling point in each charging segment data.

[0088] Next, the maximum voltage difference mean (MVDM) and the maximum voltage difference range (MVDR) of each charging segment data are obtained according to the maximum voltage difference between modules at each sampling point in each charging segment data. The calculation formula is:

[0089]

[0090] MVDR=max(MVD n )-min(MVD n )

[0091] Where N is the number of sampling points in the segment, and n is the nth sampling point in the segment.

[0092] Finally, for each historical preset period: calculate the maximum voltage difference average value V of all the charging segment data in the historical preset period respectively. MVDM_mean Mean and range V MVDM_var , and the average value of the maximum voltage difference V MVDR_mean and range V MVDR_var , these four voltage-related features are used as the module voltage features of the historical preset period.

[0093] In step S303 , the power characteristics and module voltage characteristics of different historical preset time periods are taken together as health characteristics of different historical preset time periods.

[0094] It is understandable that in other embodiments, the health feature may also be other features besides the power feature and the module voltage feature.

[0095] It should be noted that, in the present application, the order of step S20 and step S30 can be interchanged, or they can be executed simultaneously, that is, step S30 can be executed first and then step S20, or step S20 and step S30 can be executed synchronously.

[0096] Next, step S40 is executed to train an estimation model based on the health characteristics of different historical preset time periods and the corresponding SOH labels to obtain an SOH estimation model for the supercapacitor system.

[0097] Specifically, the health characteristics of the supercapacitor system in different historical preset time periods and the corresponding SOH labels can be divided into a training set, a validation set, and a test set to train the estimation model, so as to automatically obtain the optimal hyperparameter combination in the estimation model, and then use the optimal hyperparameter combination to obtain an SOH estimation model for the supercapacitor system. The SOH estimation model can be used to estimate the SOH on the supercapacitor system test set. When using data of the supercapacitor under real operating conditions, for the SOH trajectories of the four supercapacitor systems of the carrier used for model evaluation, the average absolute percentage error of the SOH estimation on the test set can be as low as 0.913%. Among them, the estimation model can be, for example, a random forest (RF) estimation model or other machine learning algorithm model.

[0098] Finally, step S50 is executed to estimate the health state of the supercapacitor system using the SOH estimation model.

[0099] Specifically, when using the SOH estimation model to estimate the health status of the supercapacitor system, the charging data of the supercapacitor system in the current estimation period (current day, current week, current month, current quarter, etc.) can be obtained, and all charging segment data can be obtained according to the method described in step S10. Based on all the charging segment data, the method in step S30 is used to obtain the health characteristics of the supercapacitor system in the current estimation period. The health characteristics are input into the SOH estimation model to estimate the health status of the supercapacitor system in the current estimation period.

[0100] Based on the same concept, Figure 5As shown, the present application also provides a supercapacitor system health status estimation device 11, which includes a fragment data acquisition module 111, a SOH label acquisition module 112, a health feature acquisition module 113, a model training module 114 and a state estimation module 115.

[0101] The segment data acquisition module 111 is used to acquire a plurality of discharge segment data and a plurality of charge segment data according to the historical charge and discharge data of the supercapacitor system under actual operating conditions;

[0102] The SOH tag acquisition module 112 is configured to acquire the SOH tags of the supercapacitor system in different historical preset time periods according to each of the discharge segment data;

[0103] The health feature acquisition module 113 is configured to acquire the power features and module voltage features of the supercapacitor system in different historical preset time periods according to each of the charging segment data, as health features of the supercapacitor system in different historical preset time periods;

[0104] The model training module 114 is used to perform estimation model training based on health characteristics and corresponding SOH labels of different historical preset time periods to obtain an SOH estimation model for the supercapacitor system;

[0105] The state estimation module 115 is configured to estimate the health state of the supercapacitor system using the SOH estimation model.

[0106] It should be noted that the supercapacitor system health status estimation device 11 provided in the above embodiment and the supercapacitor system health status estimation method provided in the above embodiment are based on the same concept, wherein the specific manner in which each module and unit performs operations has been described in detail in the method embodiment and will not be repeated here. In actual applications, the supercapacitor system health status estimation device 11 provided in the above embodiment can allocate the above functions to different functional modules as needed, that is, divide the internal structure of the device into different functional modules to complete all or part of the functions described above, and this is not limited here.

[0107] like Figure 6 , which is a structural diagram of an electronic device for implementing the method for estimating the health status of a supercapacitor system in the present application.

[0108] The electronic device 1 may include a memory 12 , a processor 13 and a bus, and may further include a computer program stored in the memory 12 and executable on the processor 13 , such as a supercapacitor system health status estimation program.

[0109] Among them, the memory 12 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (for example, SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory 12 can be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 12 can also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. Furthermore, the memory 12 can also include both an internal storage unit of the electronic device 1 and an external storage device. The memory 12 can not only be used to store application software and various types of data installed on the electronic device 1, such as the code for supercapacitor system health status estimation, etc., but can also be used to temporarily store data that has been output or is to be output.

[0110] In some embodiments, the processor 13 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and a combination of various control chips. The processor 13 is the control core (Control Unit) of the electronic device 1, and utilizes various interfaces and lines to connect the various components of the entire electronic device 1. It executes or runs programs or modules stored in the memory 12 (such as a supercapacitor system health status estimation program, etc.), and calls data stored in the memory 12 to perform various functions of the electronic device 1 and process data.

[0111] The processor 13 executes the operating system of the electronic device 1 and various installed applications. The processor 13 executes the applications to implement the steps in the above-mentioned supercapacitor system health status estimation method, such as Figure 1 Steps shown.

[0112] In summary, the supercapacitor system SOH estimation method of the present application obtains a number of discharge segment data and a number of charging segment data based on the historical charge and discharge data of the supercapacitor system under actual operating conditions; obtains the SOH label of the supercapacitor system in different historical preset time periods based on each of the discharge segment data; obtains the health characteristics of the supercapacitor system in different historical preset time periods based on each of the charging segment data, wherein the health characteristics include power characteristics and module voltage characteristics; trains an estimation model based on the health characteristics of different historical preset time periods and the corresponding SOH labels to obtain the SOH estimation model of the supercapacitor system; and uses the SOH estimation model to estimate the health status of the supercapacitor system. The present application can be used to accurately estimate the health status of supercapacitor systems in actually operating electrified transportation system vehicles and renewable energy systems, thereby improving the safety and economic benefits of the operation of electrified transportation system vehicles and renewable energy systems. And the average absolute percentage error of the health status of supercapacitor systems in actually operating electrified transportation system vehicles and renewable energy systems estimated by the present application can be as low as 0.913%

[0113] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Anyone skilled in the art may modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by one of ordinary skill in the art without departing from the spirit and technical concepts disclosed in this application shall be covered by the claims of this application.

[0114] The above description of the embodiments shown in the present application (including the content described in the abstract of the specification) is not intended to be an exhaustive list or to limit the present application to the precise form disclosed herein. Although the specific embodiments of the present application and the examples of the present application are described herein for illustrative purposes only, as those skilled in the art will recognize and understand, various equivalent modifications are possible within the spirit and scope of the present application. As noted, these modifications can be made to the present application according to the above description of the embodiments described in the present application, and these modifications will be within the spirit and scope of the present application.

[0115] Thus, although the present application has been described herein with reference to specific embodiments thereof, freedom of modification, various changes and substitutions are also within the foregoing disclosure, and it should be understood that in some cases, some features of the present application will be adopted without the corresponding use of other features without departing from the scope and spirit of the application. Therefore, many modifications can be made to adapt a particular environment or material to the substantial scope and spirit of the present application. The present application is not intended to be limited to the specific terminology used in the claims below and / or the specific embodiments disclosed as the best mode contemplated for carrying out the present application, but the present application will include any and all embodiments and equivalents falling within the scope of the appended claims. Therefore, the scope of the present application will be determined solely by the appended claims.

Claims

1. A method for estimating the health status of a supercapacitor system, characterized in that: The supercapacitor system can be applied to electrified transportation system vehicles and renewable energy systems, and includes energy storage systems that use only supercapacitors as energy storage devices, and hybrid energy storage systems composed of supercapacitors and other energy storage devices in addition to supercapacitors; The supercapacitor system health status estimation method includes: Acquire a plurality of discharge segment data and a plurality of charge segment data based on historical charge and discharge data of the supercapacitor system under actual operating conditions, wherein the charge segment data includes a charge voltage, a charge current, a maximum voltage value of the module, and a minimum voltage value of the module at each sampling point; Acquire the SOH tags of the supercapacitor system in different historical preset time periods according to each of the discharge segment data; Acquire power characteristics and module voltage characteristics of the supercapacitor system in different historical preset time periods according to each of the charging segment data as health characteristics of the different historical preset time periods; Performing estimation model training based on health characteristics and corresponding SOH labels in different historical preset time periods to obtain an SOH estimation model for the supercapacitor system; Estimating the state of health of the supercapacitor system using the SOH estimation model; The power characteristics and module voltage characteristics of the supercapacitor system in different historical preset time periods are obtained according to each of the charging segment data as health characteristics of different historical preset time periods, including: Obtaining power characteristics of the supercapacitor system in different historical preset time periods according to the charging voltage and charging current of each sampling point in each of the charging segment data, wherein the power characteristics of each historical preset time period include the overall power average, the long segment power average, the short segment power average, the high-voltage segment power average, and the low-voltage segment power average of the historical preset time period, and dividing the charging segment data into long segment data, short segment data, high-voltage segment data, and low-voltage segment data according to the duration and charging start voltage of each charging segment data in each historical preset time period; Obtaining the maximum inter-module voltage difference at each sampling point in each charging segment data according to the module maximum voltage value and the module minimum voltage value at each sampling point in each charging segment data; obtaining the maximum voltage difference average value and the maximum voltage difference range of each charging segment data according to the maximum inter-module voltage difference at each sampling point in each charging segment data; and for each historical preset period: calculating the average value and the range of the maximum voltage difference average value and the average value and the range of the maximum voltage difference range of all the charging segment data in the historical preset period, respectively, as the module voltage feature basis for the historical preset period; The power characteristics and module voltage characteristics of different historical preset time periods are used as health characteristics of different historical preset time periods.

2. The method for estimating the health status of a supercapacitor system according to claim 1, wherein: Obtaining the SOH tag of the supercapacitor system in different historical preset time periods according to each of the discharge segment data includes: Identify equivalent parameters of each discharge segment data through a resistance-capacitance equivalent model to obtain an equivalent capacitance corresponding to each discharge segment; performing capacitance calibration according to the equivalent capacitance corresponding to each of the discharge segments to obtain capacitance labels of the supercapacitor system at different historical preset time periods; The SOH labels of different historical preset periods are obtained according to the capacitance labels of different historical preset periods.

3. The method for estimating the health status of a supercapacitor system according to claim 2, wherein: Identifying equivalent parameters of each discharge segment data through a resistance-capacitance equivalent model to obtain an equivalent capacitance corresponding to each discharge segment includes: For each of the discharge segment data, the following steps are performed respectively: Predicting a voltage prediction value of each data point in the discharge segment data by using the resistance-capacitance equivalent model; Constructing a loss function according to the actual voltage value and the voltage prediction value of each data point in each of the discharge segment data; The partial derivative of the loss function with respect to the target variable is obtained, and the optimization direction is determined by a gradient descent optimization strategy to perform iterative optimization to obtain the equivalent capacitance corresponding to the discharge segment data.

4. The method for estimating the health status of a supercapacitor system according to claim 1, wherein: A plurality of discharge segment data and a plurality of charge segment data are obtained based on the historical charge and discharge data of the supercapacitor system under actual operating conditions, including: Obtaining historical charge and discharge data of the supercapacitor system under actual operating conditions; Performing data cleaning on the historical charge and discharge data under the actual operating conditions; Segmenting the historical charge and discharge data under the actual operating conditions after cleaning to obtain a plurality of discharge segment initial data and a plurality of charge segment data; The voltage abnormal points in each of the initial data of the discharge segment are removed to obtain a plurality of the discharge segment data.

5. A health status estimation device for a supercapacitor system, characterized in that: The supercapacitor system can be applied to electrified transportation system vehicles and renewable energy systems, and includes energy storage systems that use only supercapacitors as energy storage devices, and hybrid energy storage systems composed of supercapacitors and other energy storage devices in addition to supercapacitors; The health status estimation device of the supercapacitor system includes: A data acquisition module, configured to acquire a plurality of discharge segment data and a plurality of charge segment data based on historical charge and discharge data of the supercapacitor system under actual operating conditions, wherein the charge segment data includes the charge voltage, charge current, maximum module voltage value, and minimum module voltage value at each sampling point; An SOH tag acquisition module, configured to acquire the SOH tags of the supercapacitor system in different historical preset time periods according to each of the discharge segment data; a health feature acquisition module, configured to acquire, based on each of the charging segment data, power features and module voltage features of the supercapacitor system in different historical preset time periods as health features of the supercapacitor system in different historical preset time periods; A model training module is used to train an estimation model based on health characteristics and corresponding SOH labels of different historical preset time periods to obtain an SOH estimation model for the supercapacitor system; A state estimation module, configured to estimate the health state of the supercapacitor system using the SOH estimation model; The power characteristics and module voltage characteristics of the supercapacitor system in different historical preset time periods are obtained according to each of the charging segment data as health characteristics of different historical preset time periods, including: Obtaining power characteristics of the supercapacitor system in different historical preset time periods according to the charging voltage and charging current of each sampling point in each of the charging segment data, wherein the power characteristics of each historical preset time period include the overall power average, the long segment power average, the short segment power average, the high-voltage segment power average, and the low-voltage segment power average of the historical preset time period, and dividing the charging segment data into long segment data, short segment data, high-voltage segment data, and low-voltage segment data according to the duration and charging start voltage of each charging segment data in each historical preset time period; Obtaining the maximum inter-module voltage difference at each sampling point in each charging segment data according to the module maximum voltage value and the module minimum voltage value at each sampling point in each charging segment data; obtaining the maximum voltage difference average value and the maximum voltage difference range of each charging segment data according to the maximum inter-module voltage difference at each sampling point in each charging segment data; and for each historical preset period: calculating the average value and the range of the maximum voltage difference average value and the average value and the range of the maximum voltage difference range of all the charging segment data in the historical preset period, respectively, as the module voltage feature basis for the historical preset period; The power characteristics and module voltage characteristics of different historical preset time periods are used as health characteristics of different historical preset time periods.

6. An electronic device, characterized in that: The method comprises a processor, a memory and a communication bus; the communication bus is used to connect the processor and the memory; the processor is used to execute a computer program stored in the memory to implement the supercapacitor system health status estimation method according to any one of claims 1 to 4.

7. A storage medium, characterized in that: A computer program is stored thereon, and the computer program is used to enable a computer to execute the supercapacitor system health status estimation method according to any one of claims 1 to 4.

Images