Battery health status assessment method, system, storage medium and computer

Abstract

The present invention provides a battery health status assessment method, system, storage medium, and computer. The assessment method includes: obtaining basic data of a battery during a mixed pulse test; constructing a battery model, performing parameter fitting on the battery model based on the basic data, and obtaining parameter values ​​of each component in the battery model after parameter fitting; performing constant current-constant voltage charge and discharge simulation on the fitted battery model, obtaining state of charge (SOC) data of the battery model during the charge and discharge simulation, and obtaining state of health (SOH) data based on the component parameter values; using the voltage, current, temperature, and SOC data of the battery model during the charge and discharge simulation as input to a convolutional neural network, and using the SOH data as output to train the convolutional neural network; using the trained convolutional neural network as a battery assessment model, and assessing the battery health status based on the assessment model. The battery health status assessment method provided by the present invention has strong adaptability and high accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of battery health status assessment, and in particular to a battery health status assessment method, system, storage medium and computer. Background Art

[0002] In today's dual-carbon context, lithium-ion batteries have occupied an important position as a core energy source in many fields such as electric vehicles, consumer electronic devices and renewable energy storage systems due to their pollution-free, high energy density, long service life, high charge rate, extremely low self-discharge rate, excellent safety performance and stable operating characteristics.

[0003] Battery state of charge (SOC) has become a key technology in battery management systems (BMS). SOC affects battery safety, lifespan, and efficiency. To quantify the degree of aging in lithium-ion batteries, the state of health (SOH) concept has been proposed, providing an important reference for replacing aged lithium-ion batteries. Therefore, accurately assessing battery SOH data is crucial for achieving optimal performance and safe operation of lithium-ion batteries. Currently, conventional battery state of health degradation models are difficult to accurately model, relying on indirect data inference. Model parameter identification is complex and suffers from poor adaptability. Summary of the Invention

[0004] Based on this, the purpose of the present invention is to provide a battery health status assessment method, system, storage medium and computer to solve the technical problems existing in the prior art.

[0005] The present invention proposes a battery health status assessment method, comprising:

[0006] Obtain basic data of the battery during the charge and discharge process during mixed pulse testing;

[0007] Constructing a battery model, performing parameter fitting on the battery model according to the basic data, and obtaining parameter values ​​of each component in the battery model after parameter fitting;

[0008] Perform constant current-constant voltage charge and discharge simulations at different temperatures on the fitted battery model to obtain the SOC data of the battery model during the charge and discharge simulation process, and obtain the SOH data based on the component parameter values;

[0009] The voltage, current, temperature, and SOC data of the battery model during the charge and discharge simulation are used as input to the convolutional neural network, and the SOH data is used as output to train the convolutional neural network.

[0010] The trained convolutional neural network is used as a battery evaluation model, and the battery health status is evaluated according to the evaluation model.

[0011] Optionally, the basic data includes at least current data, voltage data, and charge data; and the steps of constructing a battery model, performing parameter fitting on the battery model according to the basic data, and obtaining parameter values ​​of each component in the battery model after parameter fitting include:

[0012] Construct the basic equivalent circuit of the battery model;

[0013] Importing current data in basic data at a certain temperature into the basic equivalent circuit, performing simulation in simulation software, and obtaining the open circuit voltage and external terminal voltage of the basic equivalent circuit;

[0014] The open circuit voltage and external terminal voltage obtained by simulation are compared and fitted with the voltage data in the basic data. The parameters of each component of the basic equivalent circuit are estimated according to the voltage fitting curve. The model after voltage curve fitting and parameter estimation is subjected to a charge and discharge simulation to measure the SOC data.

[0015] The current data in the basic data obtained at different temperatures is repeatedly imported into the basic equivalent circuit for simulation analysis to obtain the functional relationship between the parameters of each component of the basic equivalent circuit and the temperature and SOC data.

[0016] Optionally, the time domain expression of the basic equivalent circuit of the battery model is:

[0017]

[0018] The frequency domain expression of the basic equivalent circuit of the battery model is:

[0019]

[0020] Where, represents the open-circuit voltage of the basic equivalent circuit, 、 Represent the battery external terminal voltage in time domain and frequency domain respectively, 、 are the electrochemical polarization resistance and electrochemical polarization capacitance of the battery, 、 Represents the voltage of the battery's electrochemical polarization network and the corresponding voltage drop, 、 Represent the concentration polarization resistance and concentration polarization capacitance of the battery respectively, 、 Represents the voltage of the battery concentration polarization network and the corresponding voltage drop, I、 Represent the line current of the basic equivalent circuit in the time domain and frequency domain respectively, which is positive during discharge and negative during charge. represents the variables in the time-frequency domain Laplace transform;

[0021] The functional relationship between each component and temperature and SOC in the basic equivalent circuit of the battery model is expressed as follows:

[0022]

[0023]

[0024]

[0025]

[0026]

[0027] Where, Represents the internal resistance of the battery, Indicates the battery temperature.

[0028] Optionally, the temperature solution expression of the battery model in the time domain during the charge and discharge simulation is:

[0029]

[0030] Where, represents heat capacity, is the temperature inside the battery in the time domain, For time, is the ambient temperature, is the convection resistance, The power dissipated inside the battery for energy;

[0031] The temperature expression of the battery model in the frequency domain during the charge and discharge simulation is:

[0032]

[0033] represents the temperature inside the battery in the frequency domain, represents the variables in the time-frequency domain Laplace transform;

[0034] The expression of SOC data is:

[0035]

[0036] Where, Indicates preset The SOC status of the battery at all times, Indicates the change in charge inside the battery. Indicates the battery capacity under temperature changes;

[0037]

[0038] Where, Indicates the main current value. t Indicates the charge and discharge time;

[0039]

[0040] Where, is the average charge and discharge current of the battery, is the internal temperature of the battery;

[0041] The expression of SOH data is:

[0042]

[0043] in 、 、 Respectively, at temperature The end-of-life resistance of the battery, the internal resistance of the battery at the time of measurement, and the internal resistance of the battery when not in use.

[0044] Optionally, the step of using the voltage, current, temperature, and SOC data of the battery model during the charge and discharge simulation as inputs of the convolutional neural network and using the SOH data as output to train the convolutional neural network includes:

[0045] Build the input layer, convolution layer, pooling layer, fully connected layer, and output layer of the convolutional neural network, set the convolutional neural network training parameters, and initialize the network weights and biases;

[0046] The voltage, current, temperature, and SOC data of the battery model during the charge and discharge simulation are normalized and used as the training input of the constructed convolutional neural network. The SOH data generated during the convolutional neural network training process is used as the training output.

[0047] Calculate the difference between the SOH data output by training and the SOH data in charge and discharge simulation, and update the neural network parameters to minimize the objective function until the preset number of iterations is reached or the objective function converges;

[0048] The trained convolutional neural network is analyzed according to the preset evaluation function to evaluate the effectiveness of the convolutional neural network.

[0049] Optionally, the network weights and biases of the convolutional neural network are expressed as:

[0050]

[0051]

[0052] Where, F represents the objective function of the convolutional neural network, Indicates the i The network weights of the convolution layer, Indicates the i The bias of the convolution layer, Indicates the i The data item of the layer convolution, represents convolution, Represents the error term during the training process of the convolutional neural network, which is used to update the parameters of each layer of the convolutional neural network;

[0053] The expression of the normalization process is:

[0054] Where, is the data after normalization; is the original data; and are the maximum and minimum values ​​of the original data respectively;

[0055] The expression of the objective function is:

[0056]

[0057] The expression of the evaluation function is:

[0058]

[0059] Where, is the evaluation value, is the actual value, is the sample sequence, is the total sample sequence.

[0060] The present invention also provides a battery health status assessment system, comprising:

[0061] The acquisition module is used to obtain basic data of the battery during the charge and discharge process when performing a mixed pulse test;

[0062] A construction module is used to construct a battery model, perform parameter fitting on the battery model according to the basic data, and obtain parameter values ​​of each component in the battery model after parameter fitting;

[0063] The charge and discharge module is used to perform constant current-constant voltage charge and discharge simulations on the fitted battery model at different temperatures, obtain the SOC data of the battery model during the charge and discharge simulation, and obtain the SOH data based on the component parameter values;

[0064] The training module is used to use the voltage, current, temperature, and SOC data of the battery model during the charge and discharge simulation as the input of the convolutional neural network, and use the SOH data as the output to train the convolutional neural network;

[0065] An evaluation module is used to use the trained convolutional neural network as a battery evaluation model and evaluate the health status of the battery according to the evaluation model.

[0066] The basic data includes at least current data, voltage data, and charge data; the building block includes:

[0067] Building blocks for constructing basic equivalent circuits of battery models;

[0068] A simulation unit, configured to import current data from basic data at a certain temperature into the basic equivalent circuit, perform simulation in simulation software, and obtain an open-circuit voltage and an external terminal voltage of the basic equivalent circuit;

[0069] The estimation and fitting unit is used to compare and fit the open circuit voltage and external terminal voltage obtained by simulation with the voltage data in the basic data, estimate the parameters of each component of the basic equivalent circuit according to the voltage fitting curve, perform a charge and discharge simulation on the model after voltage curve fitting and parameter estimation, and measure the SOC data;

[0070] The analysis unit is used to repeatedly import the current data in the basic data obtained at different temperatures into the basic equivalent circuit for simulation analysis, and obtain the functional relationship between the parameters of each component of the basic equivalent circuit and the temperature and SOC data.

[0071] The present invention also provides a storage medium storing a computer program, which implements any of the above-mentioned battery health status assessment methods when executed by a processor.

[0072] The present invention also provides a computer, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the above-mentioned battery health status assessment methods when executing the computer program.

[0073] Compared with the prior art, the beneficial effects of the present invention are as follows: the battery health status assessment method provided in the present application first performs a mixed pulse test on the physical battery to directly obtain the basic data of the battery charging and discharging process, and then constructs a battery model, and performs parameter fitting on the constructed battery model based on the directly measured basic battery data, thereby improving the accuracy of parameter fitting in the battery model and reducing the complexity of model parameter identification; the fitted battery model is subjected to constant current-constant voltage charge and discharge simulation at different temperatures to obtain the SOC data of the battery model during the charge and discharge simulation, and the SOH data is obtained according to the component parameter values; then the voltage, current, temperature, and SOC data in the simulation process are used as the input of the convolutional neural network, and the SOH data is used as the output to train the convolutional neural network, and the battery health status is assessed based on the trained convolutional neural network as an evaluation model, which has strong adaptability and is suitable for large-scale promotion.

[0074] Additional aspects and advantages of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description which follows, or may be learned by practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] Figure 1 is a flowchart of a battery health status assessment method according to a first embodiment of the present invention;

[0076] Figure 2 is a basic equivalent circuit diagram of a battery model according to the first embodiment of the present invention;

[0077] Figure 3 4 is a block diagram of the computer structure in the fourth embodiment of the present invention.

[0078] The following specific embodiments will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0079] To facilitate understanding of the present invention, the present invention will be described more fully below with reference to the accompanying drawings. The drawings illustrate several embodiments of the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and comprehensive understanding of the present invention.

[0080] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one skilled in the art to which this invention pertains. The terms used in this specification of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0081] Example 1

[0082] See also Figure 1 , which shows a battery health status assessment method in a first embodiment of the present invention, and the battery health status assessment method specifically includes steps S10 to S50:

[0083] S10, obtaining basic data of the battery during the charge and discharge process when performing the mixed pulse test;

[0084] In specific implementation, a hybrid power pulse characteristic (HPPC) test can be performed using an 18650PF lithium battery to obtain basic data during the charging and discharging process of this model of battery, where the basic data at least includes current data, voltage data, and charge data of the battery during a complete charging and discharging process.

[0085] S20, constructing a battery model, performing parameter fitting on the battery model according to the basic data, and obtaining parameter values ​​of each component in the battery model after parameter fitting;

[0086] In practice, a high-fidelity lithium-ion battery model can be built using Simulink (a visual simulation tool in MATLAB). The 18650PF lithium-ion battery can be simulated using MATLAB, Simulink, and Simscape. This model can account for all of the battery's dynamic characteristics, including nonlinear open-circuit voltage, average discharge current, and internal battery temperature.

[0087] Optionally, the step of performing parameter fitting on the battery model according to the basic data and obtaining parameter values ​​of each component in the battery model after parameter fitting includes:

[0088] Construct the basic equivalent circuit of the battery model;

[0089] Importing current data in basic data at a certain temperature into the basic equivalent circuit, performing simulation in simulation software, and obtaining the open circuit voltage and external terminal voltage of the basic equivalent circuit;

[0090] The open circuit voltage and external terminal voltage obtained by simulation are compared and fitted with the voltage data in the basic data. The parameters of each component of the basic equivalent circuit are estimated according to the voltage fitting curve. The model after voltage curve fitting and parameter estimation is subjected to a charge and discharge simulation to measure the SOC data.

[0091] The current data in the basic data obtained at different temperatures is repeatedly imported into the basic equivalent circuit for simulation analysis to obtain the functional relationship between the parameters of each component of the basic equivalent circuit and the temperature and SOC data.

[0092] The curves corresponding to the open circuit voltage and the external terminal voltage can be generated using ParameterEstimation in Simulink, and the curve fitting can be performed using the nonlinear least squares method.

[0093] In specific implementation, Figure 2 This is the basic equivalent circuit diagram of a high-fidelity lithium battery model;

[0094] The time domain expression of the basic equivalent circuit of the battery model is:

[0095]

[0096] The frequency domain expression of the basic equivalent circuit of the battery model is:

[0097]

[0098] Where, represents the open-circuit voltage of the basic equivalent circuit, 、 Represent the battery external terminal voltage in time domain and frequency domain respectively, 、 are the electrochemical polarization resistance and electrochemical polarization capacitance of the battery, 、 Represents the voltage of the battery's electrochemical polarization network and the corresponding voltage drop, 、 Represent the concentration polarization resistance and concentration polarization capacitance of the battery respectively, 、 Represents the voltage of the battery concentration polarization network and the corresponding voltage drop, I、 Represent the line current of the basic equivalent circuit in the time domain and frequency domain respectively, which is positive during discharge and negative during charge. represents the variables in the time-frequency domain Laplace transform;

[0099] Import the current data in the basic data at a certain temperature into the basic equivalent circuit, and simulate in the simulation software to obtain the open circuit voltage of the basic equivalent circuit and external terminal voltage ; Compare and fit the simulation results with the voltage data in the basic data, estimate the parameters of each component of the basic equivalent circuit according to the voltage fitting curve, perform a charge and discharge simulation on the model after voltage curve fitting and parameter estimation, and measure the SOC data; then repeatedly import the basic data obtained at different temperatures into the battery model for simulation analysis to obtain the functional relationship between each component in the basic equivalent circuit of the battery model and temperature and SOC.

[0100] The functional relationship between each component and temperature and SOC in the basic equivalent circuit of the battery model is expressed as follows:

[0101]

[0102]

[0103]

[0104]

[0105]

[0106] Where, Represents the internal resistance of the battery, Indicates the battery temperature.

[0107] S30, performing constant current-constant voltage charge-discharge simulations at different temperatures on the fitted battery model, obtaining SOC data of the battery model during the charge-discharge simulation process, and obtaining SOH data based on component parameter values;

[0108] In specific implementation, this application not only considers the circuit relationship but also takes into account the thermal effect. Considering that the temperature inside the battery model is uniform, the temperature solution expression in the time domain of the battery model during the charge and discharge simulation is:

[0109]

[0110] Where, represents heat capacity, is the temperature inside the battery in the time domain, For time, is the ambient temperature, is the convection resistance, The power dissipated inside the battery for energy;

[0111] The temperature expression of the battery model in the frequency domain during the charge and discharge simulation is:

[0112]

[0113] represents the temperature inside the battery in the frequency domain, represents the variables in the time-frequency domain Laplace transform;

[0114] The expression of SOC data is:

[0115]

[0116] Where, Indicates preset The SOC status of the battery at all times, Indicates the change in charge inside the battery. Indicates the battery capacity under temperature changes;

[0117]

[0118] Where, Indicates the main current value, t Indicates the charge and discharge time;

[0119] Alternatively, battery capacity depends on many factors, including average battery charge and discharge current, charge and discharge time, internal battery temperature, battery charge and discharge voltage, and number of battery charge and discharge cycles. In a short period of time, the battery capacity may only be determined by average battery discharge current, discharge time, and internal battery temperature. The battery capacity has the following functional relationship with internal temperature:

[0120]

[0121] Where, is the average charge and discharge current of the battery, is the internal temperature of the battery;

[0122] Indicatively, in 、 The expression of battery capacity at temperature is:

[0123]

[0124] in, 、 Indicates different temperatures of the battery, and Respectively 、 The actual capacity of the battery at the temperature Represents the temperature coefficient. Through the above expression, the battery capacity at other temperatures can be estimated at the current temperature.

[0125] Optionally, in a specific implementation, the identified internal resistance parameter is used as an estimation index of SOH; the expression of SOH data is:

[0126]

[0127] in 、 、 Respectively, at temperature The end-of-life resistance of the battery, the internal resistance of the battery at the time of measurement, and the internal resistance of the battery when not in use.

[0128] S40, using the voltage, current, temperature, and SOC data of the battery model during the charge and discharge simulation process as inputs of the convolutional neural network, and using the SOH data as output to train the convolutional neural network;

[0129] Optionally, the step of using the voltage, current, temperature, and SOC data of the battery model during the charge and discharge simulation process as inputs of the convolutional neural network and using the SOH data as output to train the convolutional neural network includes:

[0130] Build the input layer, convolution layer, pooling layer, fully connected layer, and output layer of the convolutional neural network, set the convolutional neural network training parameters, and initialize the network weights and biases;

[0131] The voltage, current, temperature, and SOC data of the battery model during the charge and discharge simulation are normalized and used as the training input of the constructed convolutional neural network. The SOH data generated during the convolutional neural network training process is used as the training output.

[0132] Calculate the difference between the SOH data output by training and the SOH data in charge and discharge simulation, and update the neural network parameters to minimize the objective function until the preset number of iterations is reached or the objective function converges;

[0133] The trained convolutional neural network is analyzed according to the preset evaluation function to evaluate the effectiveness of the convolutional neural network.

[0134] Alternatively, a typical convolutional neural network is usually composed of a single input layer, multiple convolutional layers, multiple pooling layers, multiple fully connected layers, and a single output layer. The structure of the convolutional neural network of the present application is as follows:

[0135] The first layer is the input layer, whose structure is the input data sequence length × data type. In this patent, only three types of data are considered: voltage, current, and temperature.

[0136] The second, fourth, sixth, and eighth layers are all convolutional layers containing three filters. Each convolutional layer filter extracts feature information of a type of input data separately. The filter contains a corresponding number and size of convolution kernels, and uses ReLU (Rectified Linear Unit, a commonly used activation function in neural networks) to activate and output the results.

[0137] The third, fifth, seventh, and ninth layers are all Max pooling layers containing three filters. Each pooling layer filter extracts the feature information of a convolutional layer filter separately, which is used to merge the feature information while retaining the main information, thereby achieving the effect of reducing network parameters.

[0138] The tenth layer is the Flatten layer, which is essentially a fully connected layer. Its main function is to convert the multi-dimensional data structure in the convolution layer and pooling layer into a one-dimensional data structure.

[0139] The eleventh layer is a fully connected layer, which is output after using the ReLU activation function.

[0140] The twelfth layer is the output layer, which outputs the SOH estimated value estimated by the convolutional neural network.

[0141] In specific implementation, the voltage, current, temperature, and SOC data of the battery model during the charge and discharge simulation are used as the input of the convolutional neural network. The current, voltage, temperature, and SOC data are all one-dimensional time series data that change with time at a given temperature. Therefore, this patent uses a one-dimensional deep convolutional network to realize the mapping relationship between voltage, current, temperature, SOC, and SOH; the relationship between input and output is as follows:

[0142]

[0143] in, represents the estimated output of the convolutional neural network, ( | ) Represents the calculation process of convolutional layer, pooling layer, and fully connected layer, express 、 The learning rate, first-order momentum decay coefficient, second-order momentum decay coefficient, and number of experimental iterations were set to 0.00002, 0.87, and 0.98, respectively. The SOH estimated by the convolutional neural network was compared with the actual SOH data obtained during the charge and discharge simulation to obtain the difference between the two. The objective function was minimized, that is, the difference between the two was minimized.

[0144] The expressions of network weights and biases of convolutional neural networks are:

[0145]

[0146]

[0147] Where, F represents the objective function of the convolutional neural network, Indicates the i The network weights of the convolution layer, Indicates the i The bias of the convolution layer, Indicates the i The data item of the layer convolution, represents convolution, Represents the error term during the training process of the convolutional neural network, which is used to update the parameters of each layer of the convolutional neural network;

[0148] The expression of the normalization process is:

[0149] Where, is the data after normalization; is the original data; and are the maximum and minimum values ​​of the original data respectively;

[0150] The expression of the objective function is:

[0151]

[0152] The expression of the evaluation function is:

[0153]

[0154] Where, is the evaluation value, is the actual value, is the sample sequence, is the total sample sequence.

[0155] S50: Using the trained convolutional neural network as a battery evaluation model, and evaluating the battery health status according to the evaluation model.

[0156] In summary, the battery health status assessment method provided in this application first performs a mixed pulse test on the physical battery to directly obtain the basic data during the battery charging and discharging process, and then constructs a battery model. The constructed battery model is fitted with parameters based on the directly measured basic battery data to improve the accuracy of parameter fitting in the battery model and reduce the complexity of model parameter identification; the fitted battery model is subjected to constant current-constant voltage charge and discharge simulation at different temperatures to obtain the SOC data of the battery model during the charge and discharge simulation, and the SOH data is obtained based on the component parameter values; then the voltage, current, temperature, and SOC data during the simulation process are used as the input of the convolutional neural network, and the SOH data is used as the output to train the convolutional neural network, and the battery health status is assessed based on the trained convolutional neural network as an evaluation model. The method has strong adaptability and is suitable for large-scale promotion.

[0157] Example 2

[0158] This embodiment provides a battery health status assessment system, including:

[0159] The acquisition module is used to obtain basic data of the battery during the charge and discharge process when performing a mixed pulse test;

[0160] A construction module is used to construct a battery model, perform parameter fitting on the battery model according to the basic data, and obtain parameter values ​​of each component in the battery model after parameter fitting;

[0161] The charge and discharge module is used to perform constant current-constant voltage charge and discharge simulations on the fitted battery model at different temperatures, obtain the SOC data of the battery model during the charge and discharge simulation, and obtain the SOH data based on the component parameter values;

[0162] The training module is used to use the voltage, current, temperature, and SOC data of the battery model during the charge and discharge simulation as the input of the convolutional neural network, and use the SOH data as the output to train the convolutional neural network;

[0163] An evaluation module is used to use the trained convolutional neural network as a battery evaluation model and evaluate the health status of the battery according to the evaluation model.

[0164] Optionally, the basic data includes at least current data, voltage data, and charge data; and the steps of constructing a battery model, performing parameter fitting on the battery model according to the basic data, and obtaining parameter values ​​of each component in the battery model after parameter fitting include:

[0165] Construct the basic equivalent circuit of the battery model;

[0166] Importing current data in basic data at a certain temperature into the basic equivalent circuit, performing simulation in simulation software, and obtaining the open circuit voltage and external terminal voltage of the basic equivalent circuit;

[0167] The open circuit voltage and external terminal voltage obtained by simulation are compared and fitted with the voltage data in the basic data. The parameters of each component of the basic equivalent circuit are estimated according to the voltage fitting curve. The model after voltage curve fitting and parameter estimation is subjected to a charge and discharge simulation to measure the SOC data.

[0168] The current data in the basic data obtained at different temperatures is repeatedly imported into the basic equivalent circuit for simulation analysis to obtain the functional relationship between the parameters of each component of the basic equivalent circuit and the temperature and SOC data.

[0169] Optionally, the time domain expression of the basic equivalent circuit of the battery model is:

[0170]

[0171] The frequency domain expression of the basic equivalent circuit of the battery model is:

[0172]

[0173] Where, represents the open-circuit voltage of the basic equivalent circuit, 、 Represent the battery external terminal voltage in time domain and frequency domain respectively, 、 are the electrochemical polarization resistance and electrochemical polarization capacitance of the battery, 、 Represents the voltage of the battery's electrochemical polarization network and the corresponding voltage drop, 、 Represent the concentration polarization resistance and concentration polarization capacitance of the battery respectively, 、 Represents the voltage of the battery concentration polarization network and the corresponding voltage drop, I、 Represent the line current of the basic equivalent circuit in the time domain and frequency domain respectively, which is positive during discharge and negative during charge. represents the variables in the time-frequency domain Laplace transform;

[0174] The functional relationship between each component and temperature and SOC in the basic equivalent circuit of the battery model is expressed as follows:

[0175]

[0176]

[0177]

[0178]

[0179]

[0180] Where, Represents the internal resistance of the battery, Indicates the battery temperature.

[0181] Optionally, the temperature solution expression of the battery model in the time domain during the charge and discharge simulation is:

[0182]

[0183] Where, represents heat capacity, is the temperature inside the battery in the time domain, For time, is the ambient temperature, is the convection resistance, The power dissipated inside the battery for energy;

[0184] The temperature expression of the battery model in the frequency domain during the charge and discharge simulation is:

[0185]

[0186] represents the temperature inside the battery in the frequency domain, represents the variables in the time-frequency domain Laplace transform;

[0187] The expression of SOC data is:

[0188]

[0189] Where, Indicates preset The SOC status of the battery at all times, Indicates the change in charge inside the battery. Indicates the battery capacity under temperature changes;

[0190]

[0191] Where, Indicates the main current value, t Indicates the charge and discharge time;

[0192]

[0193] Where, is the average charge and discharge current of the battery, is the internal temperature of the battery;

[0194] The expression of SOH data is:

[0195]

[0196] in 、 、 Respectively, at temperature The end-of-life resistance of the battery, the internal resistance of the battery at the time of measurement, and the internal resistance of the battery when not in use.

[0197] Optionally, the step of using the voltage, current, temperature, and SOC data of the battery model during the charge and discharge simulation as inputs of the convolutional neural network and using the SOH data as output to train the convolutional neural network includes:

[0198] Build the input layer, convolution layer, pooling layer, fully connected layer, and output layer of the convolutional neural network, set the convolutional neural network training parameters, and initialize the network weights and biases;

[0199] The voltage, current, temperature, and SOC data of the battery model during the charge and discharge simulation are normalized and used as the training input of the constructed convolutional neural network. The SOH data generated during the convolutional neural network training process is used as the training output.

[0200] Calculate the difference between the SOH data output by training and the SOH data in charge and discharge simulation, and update the neural network parameters to minimize the objective function until the preset number of iterations is reached or the objective function converges;

[0201] The trained convolutional neural network is analyzed according to the preset evaluation function to evaluate the effectiveness of the convolutional neural network.

[0202] Optionally, the network weights and biases of the convolutional neural network are expressed as:

[0203]

[0204]

[0205] Where, F represents the objective function of the convolutional neural network, Indicates the i The network weights of the convolution layer, Indicates the i The bias of the convolution layer, Indicates the i The data item of the layer convolution, represents convolution, Represents the error term during the training process of the convolutional neural network, which is used to update the parameters of each layer of the convolutional neural network;

[0206] The expression of the normalization process is:

[0207] Where, is the data after normalization; is the original data; and are the maximum and minimum values ​​of the original data respectively;

[0208] The expression of the objective function is:

[0209]

[0210] The expression of the evaluation function is:

[0211]

[0212] Where, is the evaluation value, is the actual value, is the sample sequence, is the total sample sequence.

[0213] Example 3

[0214] This embodiment provides a storage medium having a computer program stored thereon. When the program is executed by a processor, the battery health status assessment method described above is implemented.

[0215] Example 4

[0216] The present invention also provides a computer, see Figure 3 , shown is a computer in an embodiment of the present invention, including a memory 10, a processor 20, and a computer program 30 stored in the memory 10 and executable on the processor 20. When the processor 20 executes the computer program 30, the above-mentioned battery health status assessment method is implemented.

[0217] The memory 10 includes at least one type of storage medium, including flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 10 may be an internal storage unit of a computer, such as the computer's hard disk. In other embodiments, the memory 10 may also be an external storage device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. Furthermore, the memory 10 may include both an internal storage unit of the computer and an external storage device. The memory 10 can be used not only to store application software installed in the computer and various types of data, but also to temporarily store data that has been output or is about to be output.

[0218] Among them, in some embodiments, the processor 20 can be an electronic control unit (Electronic Control Unit, abbreviated as ECU, also known as a vehicle computer), a central processing unit (CPU), a controller, a microcontroller, a microprocessor or other data processing chip, used to run the program code stored in the memory 10 or process data, such as executing access restriction programs.

[0219] It should be pointed out that Figure 3 The structure shown does not constitute a limitation of the computer. In other embodiments, the computer may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0220] Those skilled in the art will appreciate that the logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device), or in conjunction with such instruction execution system, apparatus, or device. For purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by an instruction execution system, apparatus, or device, or in conjunction with such instruction execution system, apparatus, or device.

[0221] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting, or processing it in another suitable manner as necessary, and then storing it in a computer memory.

[0222] It should be understood that various components of the present invention may be implemented using hardware, software, firmware, or a combination thereof. In the aforementioned embodiments, multiple steps or methods may be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one or a combination of the following technologies known in the art may be used: a discrete logic circuit having logic gates for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gates, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0223] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0224] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A battery health status assessment method, characterized in that: Obtain basic data of the battery during the charge and discharge process during mixed pulse testing; Constructing a battery model, performing parameter fitting on the battery model according to the basic data, and obtaining parameter values ​​of each component in the battery model after parameter fitting; Perform constant current-constant voltage charge and discharge simulations at different temperatures on the fitted battery model to obtain the SOC data of the battery model during the charge and discharge simulation process, and obtain the SOH data based on the component parameter values; The voltage, current, temperature, and SOC data of the battery model during the charge and discharge simulation are used as input to the convolutional neural network, and the SOH data is used as output to train the convolutional neural network. Using the trained convolutional neural network as a battery evaluation model, and evaluating the battery health status according to the evaluation model; The basic data includes at least current data, voltage data, and charge data; The steps of constructing a battery model, performing parameter fitting on the battery model according to the basic data, and obtaining parameter values ​​of each component in the battery model after parameter fitting include: Construct the basic equivalent circuit of the battery model; Importing current data in basic data at a certain temperature into the basic equivalent circuit, performing simulation in simulation software, and obtaining the open circuit voltage and external terminal voltage of the basic equivalent circuit; The open circuit voltage and external terminal voltage obtained by simulation are compared and fitted with the voltage data in the basic data. The parameters of each component of the basic equivalent circuit are estimated according to the voltage fitting curve. The model after voltage curve fitting and parameter estimation is subjected to a charge and discharge simulation to measure the SOC data. Repeatedly importing the current data from the basic data obtained at different temperatures into the basic equivalent circuit for simulation analysis to obtain the functional relationship between the parameters of each component of the basic equivalent circuit and the temperature and SOC data; The time domain expression of the basic equivalent circuit of the battery model is: The frequency domain expression of the basic equivalent circuit of the battery model is: Where, represents the open-circuit voltage of the basic equivalent circuit, 、 Represent the battery external terminal voltage in the time domain and frequency domain respectively, 、 They represent the electrochemical polarization resistance and electrochemical polarization capacitance of the battery, 、 Represents the voltage of the battery's electrochemical polarization network and the corresponding voltage drop, 、 Represent the concentration polarization resistance and concentration polarization capacitance of the battery respectively, 、 Represents the voltage of the battery concentration polarization network and the corresponding voltage drop, I、 Represent the line current of the basic equivalent circuit in the time domain and frequency domain respectively, which is positive during discharge and negative during charge. represents the variables in the time-frequency domain Laplace transform; The functional relationship between each component and temperature and SOC in the basic equivalent circuit of the battery model is expressed as follows: Where, Represents the internal resistance of the battery, Indicates the battery temperature.

2. The battery health status assessment method according to claim 1, characterized in that: The temperature expression of the battery model in the time domain during the charge and discharge simulation is: Where, represents heat capacity, is the temperature inside the battery in the time domain, For time, is the ambient temperature, is the convection resistance, The power dissipated inside the battery for energy; The temperature expression of the battery model in the frequency domain during the charge and discharge simulation is: represents the temperature inside the battery in the frequency domain, represents the variables in the time-frequency domain Laplace transform; The expression of SOC data is: Where, Indicates preset The SOC status of the battery at all times, Indicates the change in charge inside the battery. Indicates the battery capacity under temperature changes; Where, Indicates the main current value, t Indicates the charge and discharge time; Where, is the average charge and discharge current of the battery, is the internal temperature of the battery; The expression of SOH data is: in 、 、 Respectively, at temperature The end-of-life resistance of the battery, the internal resistance of the battery at the time of measurement, and the internal resistance of the battery when not in use.

3. The battery health status assessment method according to claim 1, characterized in that: The step of using the voltage, current, temperature, and SOC data of the battery model during the charge and discharge simulation as inputs of the convolutional neural network and using the SOH data as output to train the convolutional neural network includes: Build the input layer, convolution layer, pooling layer, fully connected layer, and output layer of the convolutional neural network, set the convolutional neural network training parameters, and initialize the network weights and biases; The voltage, current, temperature, and SOC data of the battery model during the charge and discharge simulation are normalized and used as the training input of the constructed convolutional neural network. The SOH data generated during the convolutional neural network training process is used as the training output. Calculate the difference between the SOH data output by training and the SOH data in charge and discharge simulation, and update the neural network parameters to minimize the objective function until the preset number of iterations is reached or the objective function converges; The trained convolutional neural network is analyzed according to the preset evaluation function to evaluate the effectiveness of the convolutional neural network.

4. The battery health status assessment method according to claim 3, characterized in that: The expressions of network weights and biases of convolutional neural networks are: Where, F represents the objective function of the convolutional neural network, Indicates the i The network weights of the convolution layer, Indicates the i The bias of the convolution layer, Indicates the i The data item of the layer convolution, represents convolution, Represents the error term during the training process of the convolutional neural network, which is used to update the parameters of each layer of the convolutional neural network; The expression of the normalization process is: Where, is the data after normalization; is the original data; and are the maximum and minimum values ​​of the original data respectively; The expression of the objective function is: The expression of the evaluation function is: Where, is the evaluation value, is the actual value, is the sample sequence, is the total sample sequence.

5. A battery health status assessment system, characterized in that: include: The acquisition module is used to obtain basic data of the battery during the charge and discharge process when performing a mixed pulse test; A construction module is used to construct a battery model, perform parameter fitting on the battery model according to the basic data, and obtain parameter values ​​of each component in the battery model after parameter fitting; The charge and discharge module is used to perform constant current-constant voltage charge and discharge simulations on the fitted battery model at different temperatures, obtain the SOC data of the battery model during the charge and discharge simulation, and obtain the SOH data based on the component parameter values; The training module is used to use the voltage, current, temperature, and SOC data of the battery model during the charge and discharge simulation as the input of the convolutional neural network, and use the SOH data as the output to train the convolutional neural network; An evaluation module, configured to use the trained convolutional neural network as a battery evaluation model and evaluate the battery's health status based on the evaluation model; The basic data includes at least current data, voltage data, and charge data; the building block includes: Building blocks for constructing basic equivalent circuits of battery models; A simulation unit, configured to import current data from basic data at a certain temperature into the basic equivalent circuit, perform simulation in simulation software, and obtain an open-circuit voltage and an external terminal voltage of the basic equivalent circuit; The estimation and fitting unit is used to compare and fit the open circuit voltage and external terminal voltage obtained by simulation with the voltage data in the basic data, estimate the parameters of each component of the basic equivalent circuit according to the voltage fitting curve, perform a charge and discharge simulation on the model after voltage curve fitting and parameter estimation, and measure the SOC data; an analysis unit, configured to repeatedly import current data from the basic data obtained at different temperatures into the basic equivalent circuit for simulation analysis, and obtain a functional relationship between parameters of each component of the basic equivalent circuit and temperature and SOC data; The time domain expression of the basic equivalent circuit of the battery model is: The frequency domain expression of the basic equivalent circuit of the battery model is: Where, represents the open-circuit voltage of the basic equivalent circuit, 、 Represent the battery external terminal voltage in the time domain and frequency domain respectively, 、 They represent the electrochemical polarization resistance and electrochemical polarization capacitance of the battery, 、 Represents the voltage of the battery's electrochemical polarization network and the corresponding voltage drop, 、 Represent the concentration polarization resistance and concentration polarization capacitance of the battery respectively, 、 Represents the voltage of the battery concentration polarization network and the corresponding voltage drop, I、 Represent the line current of the basic equivalent circuit in the time domain and frequency domain respectively, which is positive during discharge and negative during charge. represents the variables in the time-frequency domain Laplace transform; The functional relationship between each component and temperature and SOC in the basic equivalent circuit of the battery model is expressed as follows: Where, Represents the internal resistance of the battery, Indicates the battery temperature.

6. A storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the battery health status assessment method according to any one of claims 1 to 4 is implemented.

7. A computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the battery health status assessment method according to any one of claims 1 to 4 is implemented.

Images