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

Abstract

A supercapacitor system state of health (SOH) prediction method obtains a number of discharge segment data based on the historical charge and discharge data of the supercapacitor system under actual operating conditions; identifies the equivalent parameters of each discharge segment data through a resistance-capacitance equivalent model to obtain the equivalent capacitance corresponding to each discharge segment; calibrates the capacitance value according to the equivalent capacitance corresponding to each discharge segment to obtain the capacitance value labels of different historical preset time periods; constructs an SOH trajectory smoothing curve based on the capacitance value labels of different historical preset time periods; trains a prediction model based on the SOH trajectory smoothing curve to obtain an SOH prediction model; and uses the SOH prediction model to predict the health state of the supercapacitor system. This application can accurately predict the health state 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.

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 predicting 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 improve the safety and economy of supercapacitor systems during operation, it is necessary to effectively evaluate the state of health (SOH) of supercapacitor systems and accurately predict the remaining useful life (RUL) 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 predict 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, this application designs a supercapacitor system health status prediction method, device, equipment and medium to accurately predict the health status of supercapacitor systems in actual 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 predicting 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 prediction method includes:

[0007] A plurality of discharge segment data obtained based on historical charge and discharge data of the supercapacitor system under actual operating conditions;

[0008] Identify equivalent parameters of each discharge segment data through a resistance-capacitance equivalent model to obtain an equivalent capacitance corresponding to each discharge segment;

[0009] 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;

[0010] Constructing a SOH trajectory smooth curve of the supercapacitor system according to the capacitance value labels of different historical preset time periods;

[0011] Performing prediction model training according to the SOH trajectory smoothing curve of the supercapacitor system to obtain the SOH prediction model of the supercapacitor system;

[0012] The SOH prediction model is used to predict the health status of the supercapacitor system.

[0013] In an optional embodiment of the present application, a plurality of discharge segment data are obtained based on the historical charge and discharge data of the supercapacitor system under actual operating conditions, including:

[0014] Obtaining historical charge and discharge data of the supercapacitor system under actual operating conditions;

[0015] Performing data cleaning on the historical charge and discharge data under the actual operating conditions;

[0016] Segmenting the historical charge and discharge data under the actual operating conditions after cleaning to obtain initial data of a plurality of discharge segments;

[0017] 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.

[0018] In an optional embodiment of the present application, the resistor-capacitor equivalent model is a first-order resistor-capacitor equivalent model.

[0019] 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:

[0020] For each of the discharge segment data, the following steps are performed respectively:

[0021] Predicting a voltage prediction value of each data point in the discharge segment data by using the resistance-capacitance equivalent model;

[0022] 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;

[0023] 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.

[0024] In an optional embodiment of the present application, constructing the SOH trajectory curve of the supercapacitor system according to the capacitance value tags of different historical preset time periods includes:

[0025] Obtain the SOH values ​​of all historical preset periods based on the capacitance value tags of different historical preset periods;

[0026] Constructing an SOH trajectory curve of the supercapacitor system according to the SOH values ​​of all historical preset time periods;

[0027] The SOH trajectory curve of the supercapacitor system is smoothed to obtain a smoothed SOH trajectory curve of the supercapacitor system.

[0028] In an optional embodiment of the present application, the SOH values ​​of all historical preset periods are calculated based on the capacitance tags of different historical preset periods, including:

[0029] According to the capacitance value labels of different historical preset periods, a preset interpolation algorithm is used to obtain the capacitance value labels of the missing historical preset periods to obtain the capacitance value labels of all historical preset periods, and based on the capacitance value labels of all historical preset periods, the SOH values ​​of all historical preset periods are calculated; or

[0030] According to the capacitance labels of different historical preset periods, the SOH values ​​of different historical preset periods are calculated and obtained, and according to the SOH values ​​of different historical preset periods, the SOH values ​​of the missing historical preset periods are obtained by using a preset interpolation algorithm to obtain the SOH values ​​of all historical preset periods.

[0031] In an optional embodiment of the present application, smoothing the SOH trajectory curve of the supercapacitor system to obtain a smoothed SOH trajectory curve of the supercapacitor system includes:

[0032] A preset regression algorithm is used to smooth the SOH trajectory curve of the supercapacitor system to obtain a smoothed SOH trajectory curve of the supercapacitor system.

[0033] To achieve the above-mentioned and other related purposes, the present application provides a supercapacitor system health status prediction 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;

[0034] The supercapacitor system health status prediction device includes:

[0035] A data acquisition module, configured to acquire a plurality of discharge segment data based on historical charge and discharge data of the supercapacitor system under actual operating conditions;

[0036] a parameter identification module, configured to identify equivalent parameters of each of the discharge segment data through a resistance-capacitance equivalent model, so as to obtain an equivalent capacitance corresponding to each of the discharge segments;

[0037] a capacitance calibration module, configured to perform capacitance calibration according to the equivalent capacitance corresponding to each of the discharge segments, so as to obtain capacitance labels of the supercapacitor system at different historical preset time periods;

[0038] A trajectory construction module, configured to construct a SOH trajectory smooth curve of the supercapacitor system according to capacitance value labels of different historical preset time periods;

[0039] A model training module, configured to perform prediction model training based on the SOH trajectory smoothing curve of the supercapacitor system to obtain an SOH prediction model of the supercapacitor system;

[0040] A state prediction module is used to predict the health state of the supercapacitor system using the SOH prediction model.

[0041] 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 prediction method.

[0042] 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 prediction method.

[0043] The supercapacitor system health status prediction method of the present application obtains a number of discharge segment data based on the historical charge and discharge data of the supercapacitor system under actual operating conditions; identifies equivalent parameters of each discharge segment data through a resistance-capacitance equivalent model to obtain the equivalent capacitance corresponding to each discharge segment; performs capacitance calibration based on the equivalent capacitance corresponding to each discharge segment to obtain capacitance labels of different historical preset time periods of the supercapacitor system; constructs a SOH trajectory smoothing curve of the supercapacitor system based on the capacitance labels of different historical preset time periods; performs prediction model training based on the SOH trajectory smoothing curve of the supercapacitor system to obtain the SOH prediction model of the supercapacitor system, and uses the SOH prediction model to predict the health status of the supercapacitor system. The present application can accurately predict the health status of supercapacitor systems in actually operating electrified transportation system carriers and renewable energy systems, thereby increasing the safety and economic benefits of the operation of electrified transportation system carriers and renewable energy systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 A flow chart of a method for predicting the health status of a supercapacitor system provided in this application;

[0045] Figure 2 The voltage-time curve of the discharge segment data of the supercapacitor system of this application;

[0046] Figure 3 The first-order resistance-capacitance model of the supercapacitor system of this application;

[0047] Figure 4 A comparison diagram of the SOH trajectory curves of the stage capacitor system of this application;

[0048] Figure 5 A schematic diagram of a supercapacitor system health status prediction device provided in this application;

[0049] Figure 6 A schematic diagram of an electronic device of the present application. DETAILED DESCRIPTION

[0050] 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.

[0051] 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.

[0052] Figure 1 The flowchart of the method for predicting the health status of a supercapacitor system in an exemplary embodiment of the present application is shown, including steps S10 to S60. Figure 1 The technical solution of this application will be described in detail.

[0053] First, step S10 is executed to obtain a plurality of discharge segment data based on the historical charge and discharge data of the supercapacitor system under actual operating conditions.

[0054] 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; then, perform 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; finally, remove the voltage abnormal points in each of the discharge segment initial data to obtain a number of the discharge segment data.

[0055] 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.

[0056] 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 and charge and discharge voltage timing signals.

[0057] 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.

[0058] 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.

[0059] After data cleaning, the cleaned historical charge and discharge data under the actual operating conditions needs to be segmented to filter out the discharge segment data required later. The criteria for determining whether two adjacent data points are in the same discharge behavior can be screened based on sampling time and current.

[0060] To filter from the sampling time aspect, taking into account 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, where the standard time interval can be set as needed, for example, 20s. 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. To filter from the current aspect, taking into account possible current fluctuations in actual data collection, a current difference standard is set at the sampling points as a current difference threshold, where 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, they 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 of a discharge segment. The historical charge and discharge data under the actual operating conditions after cleaning are filtered using the two dimensions of sampling time and current to select the initial data of the discharge segment in which 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.

[0061] 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. Figure 2 An example of a voltage-time curve of discharge segment data is shown.

[0062] Next, step S20 is executed to identify equivalent parameters of each discharge segment data using a resistor-capacitor equivalent model to obtain the equivalent capacitance corresponding to each discharge segment. Since the charge and discharge parameters of a supercapacitor system are primarily voltage and current, the equivalent parameters of each discharge segment data of the supercapacitor system obtained by the above steps can be identified using a first-order resistor-capacitor model to obtain the equivalent capacitance of the supercapacitor system corresponding to each discharge segment.

[0063] Figure 3 shows the first-order resistance-capacitance model of the supercapacitor system, where V out (t) and I out (t) represents the terminal voltage and terminal current of the supercapacitor system at different sampling points, V C (t) is the voltage of the equivalent capacitor in the first-order resistance-capacitance model. It can be understood that the charging and discharging data of the supercapacitor system mentioned in this application is the time series data of its terminal voltage and terminal current.

[0064] For each of the discharge segment data, the equivalent capacitance corresponding to the discharge segment may be obtained through the following steps S201 - S203 .

[0065] In step S201, 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 and current data of the i data points can be used to predict the voltage of each data point. Figure 3 The resistor-capacitor equivalent model shown can obtain the voltage prediction value of (i-1) data points

[0066]

[0067] Among them, 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, Iout (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.

[0068] In step S202, a loss function L is constructed according to the actual voltage value and the voltage prediction value of each data point in each of the discharge segment data.

[0069] In step S203, the partial derivative of the loss function with respect to the target variable is calculated, and an iterative optimization is performed using a gradient descent optimization strategy to determine the optimization direction to obtain the equivalent capacitance corresponding to the discharge segment data. The next iteration value is adjusted based on the gradient descent direction and the learning rate (η). The optimization termination condition is that the loss function L < 0.002 or the number of iterations k > 500. At this point, the identified equivalent resistance and equivalent capacitance parameters are the optimal parameters, and the equivalent capacitance obtained at this point can be used as the equivalent capacitance corresponding to the discharge segment data. It is understood that other optimization termination strategies can also be used.

[0070] Next, step S30 is executed to perform capacitance calibration according to the equivalent capacitance corresponding to each of the discharge segments, so as to obtain capacitance labels of the supercapacitor system in different historical preset time periods.

[0071] Taking the historical charge and discharge data of the supercapacitor system under actual operating conditions as an example, the charge and discharge data under actual operating conditions of only one day (of course it can be multiple days) in different historical preset time periods, such as each week, month or quarter, can be obtained. The equivalent capacitance corresponding to each discharge segment can be integrated, 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 current capacitance label can be used as the capacitance label of the current historical preset time period, such as the current week, current month, and current quarter.

[0072] Next, step S40 is executed to construct a SOH trajectory smooth curve of the supercapacitor system according to the capacitance value tags of different historical preset time periods.

[0073] In the present application, constructing the SOH trajectory curve of the supercapacitor system according to the capacitance value tags of different historical preset time periods may further include:

[0074] Step S401, obtaining the SOH values ​​of all historical preset periods according to the capacitance value tags of different historical preset periods;

[0075] Step S402: constructing the SOH trajectory curve of the supercapacitor system according to the SOH values ​​of all historical preset time periods (e.g. Figure 4 The interpolated SOH is shown by the black solid circle in );

[0076] Step S403: Smoothing the SOH trajectory curve of the supercapacitor system to obtain a smoothed SOH trajectory curve of the supercapacitor system (e.g. Figure 4 The black solid triangle in the figure shows the SOH smoothed by Gaussian Process Regression (GPR).

[0077] In step S401, due to the actual operation of the carrier, the data under the actual operating conditions of the supercapacitor system are missing some historical preset periods (such as months). Therefore, the capacitance label cannot be obtained for the missing historical preset period, and the SOH of the supercapacitor system cannot be evaluated.

[0078] To this end, in one example, the capacitance labels of missing historical preset periods can be obtained using a preset interpolation algorithm based on the capacitance labels of different historical preset periods to obtain the capacitance labels of all historical preset periods; then, based on the capacitance labels of all historical preset periods, the SOH values ​​of all historical preset periods are calculated and obtained as the SOH labels of each historical preset period, wherein the preset interpolation algorithm can be, for example, one of the interpolation algorithms such as linear interpolation, spline interpolation, Newton interpolation, and Lagrange interpolation.

[0079] In another example, the SOH values ​​of different historical preset periods can be calculated based on the capacitance labels of different historical preset periods; then, the SOH values ​​of missing historical preset periods can be obtained using a preset interpolation algorithm based on the SOH values ​​of different historical preset periods to obtain the SOH values ​​of all historical preset periods as the SOH labels of all historical preset periods, wherein the preset interpolation algorithm can be, for example, one of the interpolation algorithms such as linear interpolation, spline interpolation, Newton interpolation, and Lagrange interpolation.

[0080] Specifically, the SOH value of each historical preset period may be obtained by dividing the capacitance value label of each historical preset period by the capacitance value label of the first historical preset period.

[0081] In step S403, in order to eliminate the maximum and minimum values ​​caused by the interpolation of the missing capacitance labels, the SOH trajectory curve of the supercapacitor system can be smoothed by using a preset regression algorithm to obtain a smooth curve of the SOH trajectory of the supercapacitor system. It should be noted that in order to solve the autocorrelation between the SOH labels, a radial basis kernel function (RBF) can be selected and the optimal kernel scale parameter of the GPR can be determined by using a systematic sampling method. It is understandable that other kernel functions can also be used in the GPR, wherein the preset regression algorithm can be, for example, one of the regression algorithms such as Gaussian process regression, linear regression, logistic regression, polynomial regression, and ridge regression.

[0082] Next, step S50 is executed to perform prediction model training according to the SOH trajectory smoothing curve of the supercapacitor system to obtain the SOH prediction model of the supercapacitor system.

[0083] Specifically, the SOH trajectory smoothing curve of the supercapacitor system can be divided into a training set, a validation set, and a test set to train the time series prediction model to complete the SOH prediction model training. The training set and the validation set are used to obtain the optimal hyperparameter combination, thereby obtaining an SOH prediction model for the supercapacitor system. The SOH prediction model can be used to predict the SOH on the supercapacitor system test set. The prediction model can be, for example, a Prophet prediction model, a long short-term memory prediction model, or a gated recurrent unit prediction model.

[0084] Finally, step S60 is executed to predict the health status of the supercapacitor system using the SOH prediction model.

[0085] When using data from supercapacitors 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 prediction on the test set is less than 2.5%. Therefore, the SOH prediction model of the supercapacitor system of the present application can be used to accurately predict the SOH of the supercapacitor system of the carrier in actual operation, and to detect signs of a decrease in the SOH of the supercapacitor system in advance, so as to take preventive measures to avoid interruptions or accidents in the operation of the carrier caused by failure of the supercapacitor system, ensure that the system operates within a safe range, and increase the safety and economic benefits of the operation of the carrier.

[0086] Based on the same concept, Figure 5 As shown, the present application also provides a supercapacitor system health status prediction device 11, which includes a data acquisition module 111, a parameter identification module 112, a capacitance calibration module 113, a trajectory construction module 114, a model training module 115 and a status prediction module 116.

[0087] The data acquisition module 111 is used to acquire a plurality of discharge segment data based on the historical charge and discharge data of the supercapacitor system under actual operating conditions;

[0088] The parameter identification module 112 is used to identify equivalent parameters of each discharge segment data through a resistance-capacitance equivalent model to obtain an equivalent capacitance corresponding to each discharge segment;

[0089] The capacitance calibration module 113 is configured to perform capacitance calibration according to the equivalent capacitance corresponding to each of the discharge segments, so as to obtain capacitance labels of the supercapacitor system in different historical preset time periods;

[0090] The trajectory construction module 114 is used to construct a SOH trajectory smooth curve of the supercapacitor system according to the capacitance value labels of different historical preset time periods;

[0091] The model training module 115 is used to perform prediction model training according to the SOH trajectory smooth curve of the supercapacitor system to obtain the SOH prediction model of the supercapacitor system;

[0092] The state prediction module 116 is configured to use the SOH prediction model to predict the health state of the supercapacitor system.

[0093] It should be noted that the supercapacitor system health status prediction device 11 provided in the above embodiment and the supercapacitor system health status prediction method provided in the above embodiment are of 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 prediction device 11 provided in the above embodiment can, as needed, allocate the above functions to different functional modules, 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.

[0094] like Figure 6 FIG. 1 is a schematic diagram of the structure of an electronic device for implementing the method for predicting the health status of a supercapacitor system according to the present application.

[0095] 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 prediction program.

[0096] 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 predicting the health status of the supercapacitor system, but can also be used to temporarily store data that has been output or is to be output.

[0097] 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 prediction program, etc.), and calls data stored in the memory 12 to perform various functions of the electronic device 1 and process data.

[0098] 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 prediction method, such as Figure 2 Steps shown.

[0099] In summary, the supercapacitor system SOH prediction method of the present application obtains a number of discharge segment data based on the historical charge and discharge data of the supercapacitor system under actual operating conditions; identifies the equivalent parameters of each discharge segment data through a resistance-capacitance equivalent model to obtain the equivalent capacitance corresponding to each discharge segment; calibrates the capacitance according to the equivalent capacitance corresponding to each discharge segment to obtain the capacitance label of the supercapacitor system in different historical preset time periods; constructs the SOH trajectory smooth curve of the supercapacitor system according to the capacitance label of different historical preset time periods; trains the prediction model according to the SOH trajectory smooth curve of the supercapacitor system to obtain the SOH prediction model of the supercapacitor system, and uses the SOH prediction model to predict the health status of the supercapacitor system. The present application can accurately predict the health status of the supercapacitor system in the electrified transportation system carrier and renewable energy system in actual operation, thereby improving the safety and economic benefits of the operation of the electrified transportation system carrier and renewable energy system.

[0100] 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.

[0101] 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.

[0102] 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 predicting 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 prediction method includes: Acquire a plurality of discharge segment data based on historical charge and discharge data of the supercapacitor system under actual operating conditions; 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; Constructing a SOH trajectory smooth curve of the supercapacitor system according to the capacitance value labels of different historical preset time periods; Performing prediction model training according to the SOH trajectory smoothing curve of the supercapacitor system to obtain the SOH prediction model of the supercapacitor system; Using the SOH prediction model to predict the health status of the supercapacitor system; The SOH trajectory curve of the supercapacitor system is constructed according to the capacitance value labels of different historical preset time periods, including: Obtain the SOH values ​​of all historical preset periods based on the capacitance value tags of different historical preset periods; Constructing an SOH trajectory curve of the supercapacitor system according to the SOH values ​​of all historical preset time periods; Smoothing the SOH trajectory curve of the supercapacitor system to obtain a smoothed SOH trajectory curve of the supercapacitor system; The SOH values ​​for all historical preset periods are calculated based on the capacitance tags of different historical preset periods, including: According to the capacitance value labels of different historical preset periods, a preset interpolation algorithm is used to obtain the capacitance value labels of the missing historical preset periods to obtain the capacitance value labels of all historical preset periods, and based on the capacitance value labels of all historical preset periods, the SOH values ​​of all historical preset periods are calculated; or According to the capacitance labels of different historical preset periods, the SOH values ​​of different historical preset periods are calculated and obtained, and according to the SOH values ​​of different historical preset periods, the SOH values ​​of the missing historical preset periods are obtained by using a preset interpolation algorithm to obtain the SOH values ​​of all historical preset periods.

2. The method for predicting the health status of a supercapacitor system according to claim 1, wherein: A plurality of discharge 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 initial data of a plurality of discharge segments; 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.

3. The method for predicting the health status of a supercapacitor system according to claim 1, wherein: The resistor-capacitor equivalent model is a first-order resistor-capacitor equivalent model.

4. The method for predicting the health status of a supercapacitor system according to claim 3, 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.

5. The supercapacitor system health status method according to claim 1, characterized in that: Smoothing the SOH trajectory curve of the supercapacitor system to obtain a smoothed SOH trajectory curve of the supercapacitor system includes: The SOH trajectory curve of the supercapacitor system is smoothed by using a preset regression method to obtain a smoothed SOH trajectory curve of the supercapacitor system.

6. A health status prediction 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 prediction device of the supercapacitor system includes: A data acquisition module, configured to acquire a plurality of discharge segment data based on historical charge and discharge data of the supercapacitor system under actual operating conditions; a parameter identification module, configured to identify equivalent parameters of each of the discharge segment data through a resistance-capacitance equivalent model, so as to obtain an equivalent capacitance corresponding to each of the discharge segments; a capacitance calibration module, configured to perform capacitance calibration according to the equivalent capacitance corresponding to each of the discharge segments, so as to obtain capacitance labels of the supercapacitor system at different historical preset time periods; A trajectory construction module, configured to construct a SOH trajectory smooth curve of the supercapacitor system according to capacitance value labels of different historical preset time periods; A model training module, configured to perform prediction model training based on the SOH trajectory smoothing curve of the supercapacitor system to obtain an SOH prediction model of the supercapacitor system; A state prediction module, configured to predict the health state of the supercapacitor system using the SOH prediction model; The SOH trajectory curve of the supercapacitor system is constructed according to the capacitance value labels of different historical preset time periods, including: Obtain the SOH values ​​of all historical preset periods based on the capacitance value tags of different historical preset periods; Constructing an SOH trajectory curve of the supercapacitor system according to the SOH values ​​of all historical preset time periods; Smoothing the SOH trajectory curve of the supercapacitor system to obtain a smoothed SOH trajectory curve of the supercapacitor system; The SOH values ​​for all historical preset periods are calculated based on the capacitance tags of different historical preset periods, including: According to the capacitance value labels of different historical preset periods, a preset interpolation algorithm is used to obtain the capacitance value labels of the missing historical preset periods to obtain the capacitance value labels of all historical preset periods, and based on the capacitance value labels of all historical preset periods, the SOH values ​​of all historical preset periods are calculated; or According to the capacitance labels of different historical preset periods, the SOH values ​​of different historical preset periods are calculated and obtained, and according to the SOH values ​​of different historical preset periods, the SOH values ​​of the missing historical preset periods are obtained by using a preset interpolation algorithm to obtain the SOH values ​​of all historical preset periods.

7. An electronic device, characterized in that: It 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 prediction method according to any one of claims 1 to 5.

8. 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 prediction method according to any one of claims 1 to 5.

Images