Composite electrode battery aging estimation method and apparatus, device, medium, and program

Abstract

A composite electrode battery aging estimation method and apparatus, a device, a medium, and a program. The method comprises: receiving the temperature, SOC and OCV of a composite electrode battery (S110); and on the basis of the temperature, the SOC, the OCV, and an aging degree estimation model, performing calculation to obtain the aging degree of the composite electrode battery (S120). The aging degree estimation model is preset and is obtained by training based on multiple groups of data samples, wherein each group of data samples comprises an independent variable and a dependent variable, the independent variable comprises the temperature, the SOC and the OCV of the battery, and the dependent variable comprises the aging degree of the battery.

Description

Composite electrode battery aging estimation method, device, equipment, medium and program

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Chinese patent application 202310784706.0, filed in China on June 29, 2023, entitled “Method, device, equipment, medium and procedure for estimating aging of composite electrode batteries,” the entire contents of which are incorporated herein by reference. Technical Field

[0003] The present application relates to the field of battery state estimation, and in particular to a method, device, equipment, medium and program for estimating aging of a composite electrode battery. Background Art

[0004] Composite electrode batteries refer to batteries that use composite electrode materials. Composite electrode materials are composed of two or more materials, each of which has its own unique properties. Therefore, the advantages of various materials can be fully utilized, making composite electrode batteries have the characteristics of high energy density, high power density, long life, and high safety.

[0005] As an electrochemical system, composite electrode batteries will age more rapidly with increasing charge and discharge cycles during use, leading to a decrease in available capacity. Improper battery use can lead to serious safety incidents. Therefore, accurately estimating the aging state of composite electrode batteries is of great practical significance. Related technologies for estimating the aging state of composite electrode batteries primarily treat the battery's SOC-OCV characteristic as a constant value and estimate the aging state of composite electrode batteries using data-driven or model-based methods.

[0006] Summary of the Invention

[0007] Embodiments of the present application provide a composite electrode battery aging estimation method, apparatus, device, medium, and program, which can improve the accuracy of aging estimation of composite electrode batteries.

[0008] In a first aspect, embodiments of the present application provide a method for estimating the aging of a composite electrode battery, wherein the relationship between the state of charge (SOC) and open circuit voltage (OCV) of the composite electrode battery varies with the number of cycles of the battery. The method comprises: receiving the temperature, SOC, and OCV of the composite electrode battery; and calculating the aging degree of the composite electrode battery based on the temperature, SOC, OCV, and an aging degree estimation model. The aging degree estimation model is pre-set and configured to be trained based on multiple sets of data samples, each set of data samples including independent variables and dependent variables, the independent variables including the battery's temperature, SOC, and OCV, and the dependent variable including the battery's aging degree.

[0009] The above-mentioned composite electrode battery aging estimation method regards the SOC-OCV characteristics of the composite electrode battery as variables, uses the battery temperature, SOC and OCV as independent variables, and the battery aging degree as the dependent variable, and trains an aging program estimation model. Based on the battery temperature, SOC, OCV and aging degree estimation model, the accurate aging degree of the composite electrode battery can be determined, thereby improving the accuracy of the aging degree estimation of the composite electrode battery.

[0010] As a possible implementation, a method for training an aging degree estimation model includes: obtaining multiple groups of data samples, dividing the multiple groups of data samples into a training set and a test set, wherein the training set is used to indicate the data samples for training the model, and the test set is used to indicate the data samples for determining the generalization error of the model after training. An initial model is established, and the parameters of the initial model are set. The independent variables of the initial model include the temperature, SOC, and OCV of the battery, and the dependent variable of the initial model includes the degree of aging of the battery. A loss function of the initial model is set, and the loss function is used to reflect the aging degree error of the model. The initial model is trained based on the training set and the test set to obtain an aging degree estimation model, and the aging degree error of the aging degree estimation model is less than a preset error threshold.

[0011] By the above method, an aging degree estimation model can be trained with the battery temperature, SOC and OCV as input and the battery aging degree as output, and the error of the aging degree estimation model is less than a preset error threshold.

[0012] As a possible implementation method, obtaining multiple sets of data samples includes: selecting battery cell samples, where the battery cell model is the same as the battery cell model of the composite electrode battery, testing the standard cycle life of the battery cell samples, obtaining aging parameters of the battery cell samples over their entire life cycle, and obtaining multiple sets of data samples based on the aging parameters. The aging parameters are configured as a function of temperature, SOC, OCV, and aging degree.

[0013] In the above manner, multiple groups of data samples corresponding to the cell model of the composite electrode battery can be obtained. Model training based on the multiple groups of data samples can ensure that the aging degree estimation model finally trained can estimate the aging degree of the composite electrode battery of the cell model. In addition, by constructing data samples by performing standard cycle life tests on the cell samples, the validity of the data samples is guaranteed, and the accuracy of the trained aging degree estimation model is further improved.

[0014] As a possible implementation, the initial model includes a symbolic regression model or a neural network model.

[0015] The symbolic regression model, based on the symbolic regression method, leverages the advantages of machine learning methods, namely model independence and high precision. Using the symbolic regression model as the initial model enables the resulting aging estimation model to be an explicit mathematical formula that meets error precision requirements, allowing it to be used to accurately calculate the battery aging degree. The neural network model, composed of multiple neurons, features large-scale parallelism, distributed storage and processing, self-organization, self-adaptation, and self-learning capabilities. It is particularly well-suited for handling imprecise and ambiguous information processing problems that require simultaneous consideration of many factors and conditions, and can fully approximate complex nonlinear relationships. Using the neural network model as the initial model can improve the accuracy of the resulting aging estimation model.

[0016] As a possible implementation manner, setting the parameters of the initial model includes: setting various parameters of the symbolic regression model based on a genetic algorithm regressor, or setting various parameters of the neural network model based on a genetic algorithm regressor.

[0017] Through the above method, the genetic algorithm regressor can quickly and efficiently complete the setting of model parameters.

[0018] As a possible implementation manner, after training an initial model based on a training set and a test set to obtain an aging degree estimation model, the method further includes: deploying the aging degree estimation model in a battery management system.

[0019] The aging degree of the composite electrode battery is calculated based on the temperature, SOC, OCV and aging degree estimation model, including: in the battery management system, the aging degree of the composite electrode battery is calculated based on the temperature, SOC, OCV and aging degree estimation model.

[0020] In the above manner, by deploying the aging degree estimation model in the battery management system BMS, the aging degree of the composite electrode battery can be directly estimated in the BMS, thereby reducing data transmission and improving estimation efficiency.

[0021] In a second aspect, embodiments of the present application provide a composite electrode battery aging estimation device, wherein the relationship between the state of charge (SOC) and open circuit voltage (OCV) of a composite electrode battery varies with the number of cycles of the battery. The device comprises: a receiving module for receiving the temperature, SOC, and OCV of the composite electrode battery; and an aging degree calculation module for calculating the aging degree of the composite electrode battery based on the temperature, SOC, OCV, and an aging degree estimation model. The aging degree estimation model is pre-set and configured to be trained based on multiple sets of data samples, each set of data samples including independent variables and dependent variables, the independent variables including the battery's temperature, SOC, and OCV, and the dependent variable including the battery's aging degree.

[0022] As a possible implementation method, the device also includes: a model training module, the model training module includes: a data sample acquisition submodule, which is used to acquire multiple groups of data samples, a sample division submodule, which is used to divide the multiple groups of data samples into a training set and a test set, the training set is used to indicate the data samples for training the model, and the test set is used to indicate the data samples for determining the generalization error of the model after training. An initial model establishment submodule, which is used to establish an initial model, the independent variables of the initial model include the temperature, SOC and OCV of the battery, and the dependent variables of the initial model include the aging degree of the battery. A parameter setting submodule, which is used to set the parameters of the initial model. A loss function setting submodule, which is used to set the loss function of the initial model, and the loss function is used to reflect the aging degree error. A training submodule, which is used to train the initial model based on the training set and the test set to obtain an aging degree estimation model, and the aging degree error of the aging degree estimation model is less than a preset error threshold.

[0023] As a possible implementation, the data sample acquisition submodule is specifically configured to: select a battery cell sample, where the battery cell model is the same as the battery cell model of the composite electrode battery; test the standard cycle life of the battery cell sample; obtain aging parameters of the battery cell sample over its entire life cycle; and obtain multiple sets of data samples based on the aging parameters. The aging parameters are configured as a function of temperature, SOC, OCV, and aging degree.

[0024] As a possible implementation, the initial model includes a symbolic regression model or a neural network model.

[0025] As a possible implementation method, the parameter setting submodule is specifically used to set various parameters of the symbolic regression model based on the genetic algorithm regressor, or to set various parameters of the neural network model based on the genetic algorithm regressor.

[0026] As one possible implementation, the apparatus further includes a deployment module configured to train an initial model based on a training set and a test set to obtain an aging estimation model, and then deploy the aging estimation model in a battery management system. Accordingly, the aging calculation module is configured to calculate the aging degree of the composite electrode battery in the battery management system based on temperature, SOC, OCV, and the aging estimation model.

[0027] In a third aspect, an embodiment of the present application provides an electronic device comprising: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, the composite electrode battery aging estimation method of the first aspect is implemented.

[0028] In a fourth aspect, an embodiment of the present application provides a computer storage medium, wherein the computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the composite electrode battery aging estimation method according to the first aspect is implemented.

[0029] In a fifth aspect, an embodiment of the present application provides a computer program product. When instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the composite electrode battery aging estimation method of the first aspect.

[0030] The composite electrode battery aging estimation method, device, equipment, medium and program of the embodiments of the present application regard the SOC-OCV characteristics of the composite electrode battery as variables, use the battery temperature, SOC and OCV as independent variables, and the battery aging degree as the dependent variable, and train an aging program estimation model. Based on the battery temperature, SOC, OCV and aging program estimation model, the accurate aging degree of the composite electrode battery can be determined, thereby improving the accuracy of the aging degree estimation of the composite electrode battery. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions of the embodiments of the present application, a brief introduction to the drawings required for use in the embodiments of the present application is given below.

[0032] FIG1 is a schematic flow chart of a composite electrode battery aging estimation method provided in an embodiment of the present application;

[0033] FIG2 is a flow chart of an aging degree estimation model training method provided in an embodiment of the present application;

[0034] FIG3 is a schematic diagram of an aging degree estimation model training provided by an embodiment of the present application;

[0035] FIG4 is a schematic diagram of another aging degree estimation model training provided by an embodiment of the present application;

[0036] FIG5 is a schematic structural diagram of a composite electrode battery aging estimation device provided in an embodiment of the present application;

[0037] FIG6 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0038] The features and exemplary embodiments of various aspects of the present application will be described in detail below. To make the objectives, technical solutions, and advantages of the present application more clearly understood, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are intended only to explain the present application and not to limit the present application.

[0039] It should be noted that, in this document, relational terms such as first and second, etc. are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations.

[0040] In order to facilitate understanding of the embodiments of the present application, the terms involved in the embodiments of the present application are first explained.

[0041] Composite electrode battery, the battery's electrodes include a positive electrode and a negative electrode, and a composite electrode battery refers to a battery in which a composite electrode material is used for the positive electrode and / or the negative electrode. For example, a battery in which the positive electrode includes two or more positive electrode active materials, and / or the negative electrode includes two or more negative electrode active materials is a composite electrode battery. The positive electrode active materials include but are not limited to lithium cobalt oxide (LCO), lithium manganese oxide (LMO), lithium iron phosphate (LFP), ternary materials (lithium nickel cobalt manganese oxide: NCM) and lithium nickel cobalt aluminum oxide (NCA)), etc., and the negative electrode active materials include but are not limited to graphite, silicon, hard carbon, soft carbon, etc. The battery cells of the composite electrode battery can be sodium ion batteries, lithium ion batteries, and other types of secondary batteries.

[0042] SOC, the full name of which is State of Charge, is the ratio of the remaining capacity of a battery after it has been used for a period of time or has been left unused for a long time to its capacity in a fully charged state.

[0043] OCV, the full name of which is open circuit voltage, refers to the potential difference between the positive and negative electrodes of the battery when the battery is not working.

[0044] A BMS, or Battery Management System, monitors the battery's status and manages its charging and discharging. In some implementations of this application, the BMS can be implemented in the form of a printed circuit board (PCB), which can be equipped with electronic components including a microcontroller (MCU), a charging switch, a discharging switch, resistors, capacitors, and the like.

[0045] In order to improve the problem of inaccurate battery aging estimation in related technologies, the embodiments of the present application provide a novel composite electrode battery aging estimation method, device, equipment, medium and program for estimating the aging of a composite electrode battery.

[0046] The following first introduces the composite electrode battery aging estimation method provided in the embodiment of the present application.

[0047] FIG1 is a flow chart of a composite electrode battery aging estimation method according to an embodiment of the present application. As shown in FIG1 , the method may include the following steps S110 - S120 .

[0048] S110. Receive the temperature, SOC, and OCV of the composite electrode battery.

[0049] The temperature may be the temperature of the composite electrode battery itself, or the temperature of the environment in which the composite electrode battery is located.

[0050] The inventors of this application discovered that the SOC-OCV relationship characteristic of a composite electrode battery varies with the number of battery cycles, and that the number of cycles is linearly correlated with the degree of aging. Based on this, this embodiment associates the SOC-OCV relationship characteristic of a composite electrode battery with the aging estimation of the composite electrode battery. Furthermore, the SOC-OCV relationship characteristic is also affected by temperature. Therefore, to ensure the accuracy of the battery aging estimation result, the OCV, SOC, and temperature of the composite electrode battery are received, and the degree of battery aging is determined based on the temperature, SOC, and OCV of the composite electrode battery.

[0051] In practical applications, data such as OCV, SOC, and temperature of the composite electrode battery can be collected through relevant collection devices. The collection devices may include sensors and an analog front end (AFE) circuit provided on the BMS.

[0052] As an example, during the use of the composite electrode battery, the OCV, SOC and temperature of the composite electrode battery can be collected in real time through the AFE on the BMS.

[0053] S120. Calculate the aging degree of the composite electrode battery based on the temperature, SOC, OCV, and aging degree estimation model.

[0054] Among them, the aging degree estimation model can be pre-set in the BMS and configured to be trained based on multiple groups of data samples, each group of data samples includes independent variables and dependent variables, the independent variables include the battery temperature, SOC and OCV, and the dependent variable includes the battery aging degree.

[0055] As an example, before performing aging estimation on a composite electrode battery, multiple sets of data samples can be obtained, and model training can be performed based on these multiple sets of data samples, thereby obtaining an aging estimation model that takes the battery's temperature, SOC, and OCV as input and outputs the battery's aging degree. Based on this, when performing aging estimation on a composite electrode battery, the temperature, SOC, and OCV of the composite electrode battery are received, and the received temperature, SOC, and OCV are input into the aging estimation model. The aging degree output by the aging estimation model is obtained, and the aging degree corresponds to the input temperature, SOC, and OCV. The aging degree output by the aging estimation model is used as the aging degree of the composite electrode battery, i.e., the aging estimation result.

[0056] The composite electrode battery aging estimation method in this embodiment regards the SOC-OCV characteristics of the composite electrode battery as variables, uses the battery temperature, SOC and OCV as independent variables, and the battery aging degree as the dependent variable, and trains an aging program estimation model. Based on the battery temperature, SOC, OCV and aging degree estimation model, the accurate aging degree of the composite electrode battery can be determined, thereby improving the accuracy of the aging degree estimation of the composite electrode battery.

[0057] In some embodiments, as shown in FIG2 , the training method of the aging degree estimation model may specifically include the following steps:

[0058] S210. Obtain multiple groups of data samples.

[0059] In order to ensure that the aging degree estimation model finally trained can perform aging estimation on the composite electrode battery in S110 (hereinafter referred to as "current composite electrode battery" for ease of description), multiple groups of data samples corresponding to the cell model of the current composite electrode battery can be obtained.

[0060] As described above, each set of data samples includes independent variables and dependent variables. The independent variables include the temperature, SOC and OCV of the battery, and the dependent variable includes the degree of aging of the battery. The value of the independent variable corresponds to the value of the dependent variable, that is, the degree of aging in a set of data samples corresponds to the temperature, SOC and OCV of the battery in the set of data samples.

[0061] S220. Divide multiple groups of data samples into training sets and test sets.

[0062] The training set is used to represent the data samples used to train the model, and the test set is used to represent the data samples used to determine the generalization error of the trained model. There is no overlapping data between the training set and the test set. It is understood that after the aging estimation model is trained using the training set, the test set can be used to verify the accuracy of the aging estimation model.

[0063] As an example, a partition ratio can be pre-set, which is the ratio of the data volume of the training set to the data volume of the test set. Based on this partition ratio, multiple groups of sample data are divided into training sets and test sets. The partition ratio can be set according to actual conditions. For example, the partition ratio can be set to 7:3. Assuming there are 1000 groups of data samples, based on the partition ratio, 700 groups of data samples are used as training sets, and the remaining 300 groups of data samples are used as test sets.

[0064] As another example, multiple sets of data samples can be preprocessed to obtain a test set. For example, if there are 100 sets of data samples, the 100 sets of data samples can be used as the training set, and the 100 sets of data samples can be preprocessed, such as by interpolation or random noise processing, to obtain the test set.

[0065] S230. Establish an initial model and set parameters of the initial model.

[0066] The independent variables of the initial model include the temperature, SOC, and OCV of the battery, and the dependent variables of the initial model include the aging degree of the battery.

[0067] S240. Set the loss function of the initial model.

[0068] Among them, the loss function is used to reflect the aging error of the model.

[0069] S250. Train an initial model based on the training set and the test set to obtain an aging degree estimation model.

[0070] The aging degree error of the aging degree estimation model is less than a preset error threshold, where the error threshold can be set according to actual model accuracy requirements.

[0071] As an example, a supervised training method can be used to train the initial model based on a training set and a test set to obtain an aging estimation model. During training, the independent variable values ​​in the data samples in the training set are input into the model to obtain the prediction results corresponding to the sample data output by the model. Based on the dependent variable values ​​in the data samples, the prediction results, and the loss function, the aging error of the trained model is determined. If the aging error is greater than or equal to an error threshold, the parameters in the model are adjusted. The model with adjusted parameters is then trained again based on the training set until the aging error of the trained model is less than the error threshold. The model obtained from the last training is then used as the aging estimation model.

[0072] By the above method, an aging degree estimation model can be trained with the battery temperature, SOC and OCV as input and the battery aging degree as output, and the error of the aging degree estimation model is less than a preset error threshold.

[0073] In some embodiments, in the above step S210, multiple sets of data samples corresponding to the current composite electrode battery may be obtained based on a battery aging experiment, which may specifically include the following steps:

[0074] Selecting a cell sample, where the model of the cell sample is the same as the cell model of the current composite electrode battery;

[0075] Test the standard cycle life of the battery sample and obtain the aging parameters of the battery sample throughout its life cycle;

[0076] Based on the aging parameters, multiple sets of data samples are obtained.

[0077] The aging parameters are configured as functions among temperature, SOC, OCV and aging degree.

[0078] As an example, taking advantage of the fact that the SOC-OCV characteristics of composite electrode batteries change with the number of cycles, standard cycle life tests are carried out on battery cell samples in the laboratory to obtain the aging parameters of the battery cell samples throughout their life cycle. The aging parameters include the SOC and OCV data of the battery cell samples at different temperatures and different cycle numbers. When conducting the test, multiple test temperatures can be selected according to actual needs. For each test temperature, a standard cycle life test is carried out on the battery cell sample at the test temperature to measure the aging parameters of the battery cell sample at multiple different cycle numbers. For example, based on the fact that the battery temperature is usually between -20℃ and 45℃, -20℃, -10℃, 0℃, 25℃, and 45℃ can be selected as the test temperatures, and then standard cycle life tests can be carried out on the battery cell samples at -20℃, -10℃, 0℃, 25℃, and 45℃, respectively.

[0079] The number of cycles under standard laboratory conditions is linearly correlated with the degree of battery aging. From this, a mapping relationship between the number of cycles and the degree of aging can be obtained. Based on the mapping relationship, the degree of aging corresponding to each number of cycles can be determined. Based on this, a functional relationship between temperature, aging degree, OCV and SOC can be further established to obtain the aging parameters corresponding to the battery cell model. Based on the aging parameters, multiple groups of data samples can be constructed according to the independent variables and dependent variables.

[0080] In this embodiment, the aging parameter may be expressed as a table, a function, or a graph to represent the functional relationship among the temperature, battery aging degree, OCV, and SOC.

[0081] As an example, the aging parameter can be expressed as a functional relationship between temperature, battery aging degree, OCV and SOC by a table as shown in Table 1 below:

[0082] Table 1:

[0083] In Table 1, except for the first row, which is also the title row, each row corresponds to a set of aging parameters obtained based on experiments.

[0084] Based on the aging parameters shown in Table 1, a set of data samples can be constructed for each row of aging parameters. Specifically, for each row, the values ​​corresponding to temperature, OCV, and SOC in that row are used as a set of independent variable values, and the value corresponding to the aging degree in that row is used as the dependent variable value. This set of independent variable values ​​and dependent variable values ​​forms a set of data samples.

[0085] As an example, taking n groups of aging parameters obtained based on experiments as an example, n groups of independent variables and n dependent variables can be obtained based on the n groups of aging parameters, where the n groups of independent variables and the n dependent variables are respectively as follows:

[0086] Independent variables:

[0087] Dependent Variable:

[0088] y = [aging level 1, aging level 2, ..., aging level n]

[0089] Among them, "Temperature 1", "OCV1" and "SOC1" constitute a set of independent variable values, and this set of independent variable values ​​and the dependent variable value of "Aging Degree 1" together constitute a set of data samples. Similarly, "Temperature 2", "OCV2" and "SOC2" constitute a set of independent variable values, and this set of independent variable values ​​and the dependent variable value of "Aging Degree 2" together constitute a set of data samples. And so on, n sets of data samples can be obtained.

[0090] This approach allows for the acquisition of multiple sets of data samples corresponding to the cell model of the current composite electrode battery. Model training based on these data samples ensures that the resulting aging estimation model is capable of accurately estimating the aging of the current composite electrode battery. Furthermore, by constructing data samples through standard cycle life testing of cell samples, the validity of the data samples is ensured, further improving the accuracy of the trained aging estimation model.

[0091] In some embodiments, to further ensure the validity of data samples, before obtaining multiple sets of data samples based on aging parameters, the aging parameters may be preprocessed, and then multiple sets of data samples may be obtained based on the preprocessed aging parameters.

[0092] The data preprocessing for the aging parameters may include data cleaning, which can complete the actual values ​​of the aging parameters, eliminate noise data, identify or delete outliers, and resolve inconsistencies.

[0093] By preprocessing the aging parameters, the validity of the data samples can be further improved.

[0094] In some embodiments, when establishing the initial model, a symbolic regression model or a neural network model can be used as the initial model.

[0095] As an example, taking the symbolic regression model as the initial model, when conducting model training, a symbolic regression model is established and various parameters of the model algorithm are set, as shown in FIG3 . The established regression model is trained based on the data samples in the training set. After the model training is completed, a mathematical mapping relationship between the independent variables [x1, x2, x3] and the dependent variable y that meets the error requirements is obtained, and the relationship is output in the form of the following formula. Thus, the following formula is the aging degree estimation model obtained by training.

[0096] y=f(x1,x2,x3)

[0097] Among them, the symbolic regression model is a model based on the symbolic regression algorithm. The symbolic regression algorithm (SR) fully leverages the advantages of machine learning methods in terms of model independence and high precision. Using the symbolic regression model as the initial model can ensure that the final aging estimation model is an explicit mathematical formula that meets the error accuracy requirements and can be used to calculate the exact solution to the battery aging degree.

[0098] As another example, taking the neural network model as the initial model, when performing model training, the neural network model is established and the various parameters of the model algorithm are set, as shown in Figure 4, and the neural network model is trained using the data samples in the training set. After the model training is completed, a neural network model that meets the error requirements is obtained, and the neural network model is used as an aging degree estimation model.

[0099] It can be understood that the neural network model shown in Figure 4 is only an example and does not constitute a limitation on the neural network model used in the embodiments of the present application. The neural network model used in the embodiments of the present application may include one or more hidden layers.

[0100] The neural network model is composed of multiple neurons and has large-scale parallel, distributed storage and processing, self-organization, self-adaptation and self-learning capabilities. It is particularly suitable for processing imprecise and fuzzy information processing problems that require considering many factors and conditions at the same time. It can fully approximate complex nonlinear relationships. Using the neural network model as the initial model can improve the accuracy of the final aging estimation model.

[0101] In some embodiments, the parameters of the initial model may be set based on genetic algorithm regression, specifically including:

[0102] When the initial model is a symbolic regression model, various parameters of the symbolic regression model are set based on the genetic algorithm regressor.

[0103] When the initial model is a neural network model, various parameters of the neural network model are set based on the genetic algorithm regressor.

[0104] Here, setting various parameters of the model refers to initializing various parameters in the model.

[0105] The model training process can be understood as a parameter optimization process. Through model training, the parameters that make the model error meet the preset error conditions are found. Therefore, before model training, the various parameters of the model are initialized first, so that the parameters can be adjusted based on the initial values ​​during the training process.

[0106] It is understandable that different models require different parameter settings. For example, the parameters required for a symbolic regression model may include the population, population size, and population execution method. The parameters required for a neural network model may include the center point and width vector of the hidden layer, that is, the weights and thresholds of the output layer.

[0107] Through the above method, the genetic algorithm regressor can quickly and efficiently complete the setting of model parameters.

[0108] In some embodiments, after the initial model is trained based on the training set and the test set to obtain the aging degree estimation model, the following steps may be further performed:

[0109] Deploy the aging estimation model in the battery management system.

[0110] Accordingly, the above step S120 calculates the aging degree of the composite electrode battery based on the temperature, SOC, OCV and aging degree estimation model, which may include:

[0111] In the battery management system, the aging degree of the composite electrode battery is calculated based on temperature, SOC, OCV and aging degree estimation model.

[0112] The battery management system (BMS) is usually used to monitor the status of the battery, so it usually receives data such as battery temperature, SOC, OCV, etc. Based on this, the aging degree estimation model is deployed in the BMS, so that the battery aging degree can be estimated directly in the BMS based on the received battery temperature, SOC and OCV.

[0113] In the above manner, the aging degree of the composite electrode battery is directly estimated in the BMS, thereby reducing data transmission and improving estimation efficiency.

[0114] Based on the composite electrode battery aging estimation method provided in the above embodiment, the present application also provides a specific implementation of a composite electrode battery aging estimation device. Please refer to the following embodiment.

[0115] 5 , a composite electrode battery aging estimation device 500 provided in an embodiment of the present application includes the following modules: a receiving module 501 and an aging degree calculation module 502 .

[0116] A receiving module 501 is used to receive the temperature, SOC and OCV of the composite electrode battery;

[0117] An aging degree calculation module 502 is configured to calculate the aging degree of the composite electrode battery based on temperature, SOC, OCV, and an aging degree estimation model;

[0118] The aging degree estimation model is pre-set and configured to be trained based on multiple groups of data samples, wherein each group of data samples includes independent variables and dependent variables, the independent variables include the temperature, SOC and OCV of the battery, and the dependent variable includes the aging degree of the battery.

[0119] The composite electrode battery aging estimation device in this embodiment regards the SOC-OCV characteristics of the composite electrode battery as variables, uses the battery temperature, SOC and OCV as independent variables, and the battery aging degree as the dependent variable, and trains an aging process estimation model. Based on the battery temperature, SOC, OCV and aging process estimation model, the accurate aging degree of the composite electrode battery can be determined, thereby improving the accuracy of the aging degree estimation of the composite electrode battery.

[0120] In some embodiments, the apparatus 500 may further include: a model training module, the model training module including:

[0121] A data sample acquisition submodule is used to obtain multiple groups of data samples;

[0122] A sample partitioning submodule is used to divide multiple groups of data samples into training sets and test sets, wherein the training set is used to indicate the data samples for training the model, and the test set is used to indicate the data samples for determining the generalization error of the model after training;

[0123] The initial model establishment submodule is used to establish the initial model. The independent variables of the initial model include the battery temperature, SOC and OCV, and the dependent variables of the initial model include the battery aging degree;

[0124] Parameter setting submodule, used to set the parameters of the initial model;

[0125] The loss function setting submodule is used to set the loss function of the initial model. The loss function is used to reflect the aging error.

[0126] The training submodule is used to train the initial model based on the training set and the test set to obtain an aging degree estimation model; wherein the aging degree error of the aging degree estimation model is less than a preset error threshold.

[0127] In some embodiments, the data sample acquisition submodule is specifically configured to:

[0128] Selecting battery cell samples, where the model of the battery cell samples is the same as the model of the battery cell of the composite electrode battery; testing the standard cycle life of the battery cell samples to obtain aging parameters of the battery cell samples over their entire life cycle; obtaining multiple sets of data samples based on the aging parameters; where the aging parameters are configured as a function of temperature, SOC, OCV, and aging degree.

[0129] In some embodiments, the initial model comprises a symbolic regression model or a neural network model.

[0130] In some embodiments, the parameter setting submodule is specifically used to:

[0131] Based on the genetic algorithm regressor, various parameters of the symbolic regression model are set; or, based on the genetic algorithm regressor, various parameters of the neural network model are set.

[0132] In some embodiments, the apparatus 500 further includes a deployment module configured to:

[0133] After training the initial model based on the training set and the test set to obtain the aging degree estimation model, the aging degree estimation model is deployed in the battery management system;

[0134] Accordingly, the aging degree calculation module 502 is specifically configured to calculate the aging degree of the composite electrode battery based on the temperature, SOC, OCV and the aging degree estimation model in the battery management system.

[0135] The composite electrode battery aging estimation device provided in the embodiments of the present application can implement each process implemented in any of the above method embodiments, and to avoid repetition, it will not be described here.

[0136] FIG6 shows a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application.

[0137] The electronic device 600 may include a processor 601 and a memory 602 storing computer program instructions.

[0138] Specifically, the processor 601 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0139] Memory 602 may include a large-capacity memory for data or instructions. By way of example, and not limitation, memory 602 may include a hard disk drive (HDD), a floppy disk drive, flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 602 may include removable or non-removable (or fixed) media. Where appropriate, memory 602 may be internal or external to the integrated gateway disaster recovery device. In certain embodiments, memory 602 is non-volatile solid-state memory. Memory 602 may include read-only memory (ROM), random access memory (RAM), a magnetic disk storage media device, an optical storage media device, a flash memory device, or an electrical, optical, or other physical / tangible memory storage device. Therefore, generally, memory 602 includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it may perform the operations described in any of the composite electrode battery aging estimation methods described in the above-described embodiments.

[0140] The processor 601 reads and executes computer program instructions stored in the memory 602 to implement any one of the composite electrode battery aging estimation methods in the above embodiments.

[0141] In one example, the electronic device 600 may further include a communication interface 603 and a bus 610. As shown in FIG6, the processor 601, the memory 602, and the communication interface 603 are connected via the bus 610 and communicate with each other.

[0142] The communication interface 603 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0143] Bus 610 includes hardware, software or both, and the parts of online data flow metering equipment are coupled to each other. For example, but not limitation, bus can include accelerated graphics port (AGP) or other graphics bus, enhanced industry standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industry standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 610 can include one or more buses. Although the present application embodiment describes and shows specific bus, the application considers any suitable bus or interconnection.

[0144] In addition, in conjunction with the composite electrode battery aging estimation method described in the above embodiments, embodiments of the present application may provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when executed by a processor, the computer program instructions implement any of the composite electrode battery aging estimation methods described in the above embodiments.

[0145] It should be understood that the present application is not limited to the specific configurations and processes described above and illustrated in the figures. For the sake of brevity, a detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and illustrated as examples. However, the method process of the present application is not limited to the specific steps described and illustrated. Those skilled in the art can make various changes, modifications, and additions, or change the order of the steps after understanding the spirit of the present application.

[0146] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium that can store or transmit information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROMs, flash memories, erasable ROMs (EROMs), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0147] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps. In other words, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0148] Aspects of the present disclosure have been described above with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor or a field programmable logic circuit. It is also understood that each box in the block diagram and / or flowchart and the combination of the boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0149] The above description is only a specific embodiment of the present application. Those skilled in the art will clearly understand that for the convenience and brevity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the scope of protection of the present application.

Claims

1. A composite electrode battery aging estimation method, wherein: include: receiving a temperature, SOC and OCV of a composite electrode battery; Calculating the aging degree of the composite electrode battery based on the temperature, the SOC, the OCV and an aging degree estimation model; The aging degree estimation model is preset and configured to be trained based on multiple groups of data samples; Each group of data samples includes independent variables and dependent variables, the independent variables include the temperature, SOC and OCV of the battery, and the dependent variable includes the aging degree of the battery.

2. The method according to claim 1, wherein: The training method of the aging degree estimation model includes: Obtain multiple sets of data samples; Dividing the plurality of groups of data samples into a training set and a test set, wherein the training set is used to indicate data samples for training a model, and the test set is used to indicate data samples for determining a generalization error of the trained model; Establishing an initial model and setting parameters of the initial model, wherein the independent variables of the initial model include the temperature, SOC and OCV of the battery, and the dependent variable of the initial model includes the aging degree of the battery; Setting a loss function of the initial model, wherein the loss function is used to reflect the aging error of the model; Training the initial model based on the training set and the test set to obtain an aging degree estimation model; Wherein, an aging degree error of the aging degree estimation model is less than a preset error threshold.

3. The method according to claim 2, wherein: The obtaining of multiple sets of data samples comprises: Selecting a battery cell sample, wherein the model of the battery cell sample is the same as the model of the battery cell of the composite electrode battery; Test the standard cycle life of the battery sample to obtain the full life cycle of the battery sample. Aging parameters; Based on the aging parameter, obtaining a plurality of groups of data samples; The aging parameter is configured as a function of temperature, SOC, OCV and aging degree.

4. The method according to claim 2 or 3, wherein: The initial model includes a symbolic regression model or a neural network model.

5. The method according to claim 4, wherein: The step of setting the parameters of the initial model comprises: Based on a genetic algorithm regressor, setting various parameters of the symbolic regression model; or, Based on the genetic algorithm regressor, various parameters of the neural network model are set.

6. The method according to claim 2 or 3, wherein: After training the initial model based on the training set and the test set to obtain an aging degree estimation model, the method further includes: Deploying the aging degree estimation model in a battery management system; The calculating the aging degree of the composite electrode battery based on the temperature, the SOC, the OCV and the aging degree estimation model includes: In the battery management system, the aging degree of the composite electrode battery is calculated based on the temperature, the SOC, the OCV and the aging degree estimation model.

7. A composite electrode battery aging estimation method, wherein: include: A receiving module, used for receiving the temperature, SOC and OCV of the composite electrode battery; An aging degree calculation module, used to calculate the aging degree of the composite electrode battery based on the temperature, the SOC, the OCV and the aging degree estimation model; The aging degree estimation model is preset and configured to be trained based on multiple groups of data samples; Each group of data samples includes independent variables and dependent variables, the independent variables include the temperature, SOC and OCV of the battery, and the dependent variable includes the aging degree of the battery.

8. An electronic device, wherein: The device comprises: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, it implements any one of claims 1-6 The composite electrode battery aging estimation method.

9. A computer-readable storage medium, wherein: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the composite electrode battery aging estimation method according to any one of claims 1 to 6 is implemented.

10. A computer program product, wherein: When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the composite electrode battery aging estimation method according to any one of claims 1 to 6.

Images