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

Abstract

The invention provides a battery health state evaluation method and system, a storage medium and a computer. The evaluation method comprises the following steps: acquiring basic data of a battery during a mixed pulse test; constructing a battery model, performing parameter fitting on the battery model according to the basic data, and obtaining parameter values of each element in the battery model after parameter fitting; performing constant current-constant voltage charging and discharging simulation on the fitted battery model, acquiring SOC data of the battery model in the charging and discharging simulation process, and acquiring SOH data according to the element parameter values; taking the voltage, current, temperature and SOC data of the battery model in the charge and discharge simulation process as the input of the convolutional neural network, and taking the SOH data as the output to train the convolutional neural network; and taking the trained convolutional neural network as an evaluation model of the battery, and evaluating the health state of the battery according to the evaluation model. The battery health state evaluation method provided by the invention is high in adaptability and high in accuracy.

Description

Technical Field

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

[0002] Under the current dual-carbon background, lithium-ion batteries have occupied an important position as the 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 charging rate, extremely low self-discharge rate, excellent safety performance, and stable operating characteristics.

[0003] The state of charge (SOC) of the battery has become a key technology for the battery management system (BMS). The SOC affects the safety performance, the life, and the usage efficiency of the battery. In order to quantify the aging degree of lithium-ion batteries, the state of health (SOH) of lithium-ion batteries is proposed, which provides an important reference basis for the replacement of aging lithium-ion batteries. Therefore, accurately evaluating the SOH data of the battery is of great significance for the optimal performance and safe operation of lithium-ion batteries. At present, the degradation mode of the conventional battery state of health is difficult to accurately model, relying on indirect data inference, with complex model parameter identification and poor adaptability. Summary of the Invention

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

[0005] The present invention provides a method for battery state of health assessment, including: Obtaining basic data during the charge and discharge process of the battery during a hybrid pulse test; Constructing a battery model, fitting the parameters of the battery model according to the basic data, and obtaining the parameter values of each component in the battery model after parameter fitting; Performing constant current-constant voltage charge and discharge simulation on the battery model after fitting at different temperatures, obtaining the SOC data of the battery model during the charge and discharge simulation, and obtaining the SOH data according to the component parameter values; Using the voltage, current, temperature, and SOC data of the battery model during the charge and discharge simulation as the input of a convolutional neural network, and using the SOH data as the output to train the convolutional neural network; Using the trained convolutional neural network as the evaluation model of the battery, and evaluating the health state of the battery according to the evaluation model.

[0006] Optionally, the basic data at least includes current data, voltage data, and charge data; the steps of constructing the battery model and performing parameter fitting on the battery model according to the basic data to obtain the parameter values of each component in the battery model after parameter fitting include: Construct the basic equivalent circuit of the battery model; Import the current data in the basic data at a certain temperature into the basic equivalent circuit, perform simulation in simulation software, and obtain the open-circuit voltage and external terminal voltage of the basic equivalent circuit; Compare and fit the open-circuit voltage and external terminal voltage obtained from the 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, and perform a charge-discharge simulation on the model after voltage curve fitting and parameter estimation to measure the SOC data; 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 relationships between the parameters of each component of the basic equivalent circuit and temperature and SOC data.

[0007] Optionally, the time-domain expression of the basic equivalent circuit of the battery model is:

[0008] The frequency-domain expression of the basic equivalent circuit of the battery model is:

[0009] In the formula, represents the open-circuit voltage of the basic equivalent circuit, , respectively represent the external terminal voltage of the battery in the time domain and frequency domain, , respectively represent the electrochemical polarization resistance and electrochemical polarization capacitance of the battery, , represent the voltage of the electrochemical polarization network of the battery and the corresponding voltage drop, , respectively represent the concentration polarization resistance and concentration polarization capacitance of the battery, , represent the voltage of the concentration polarization network of the battery and the corresponding voltage drop, I、 respectively represent the line current of the basic equivalent circuit in the time domain and frequency domain, which is positive during discharge and negative during charge, represents the variable in the Laplace transform of the time-frequency domain; The expression of the functional relationships between each component in the basic equivalent circuit of the battery model and temperature and SOC is:

[0010]

[0011]

[0012]

[0013]

[0014]

[0015] wherein, represents the internal resistance of the battery, represents the battery temperature.

[0016] Optionally, the expression for solving the temperature in the time domain of the battery model during the charge and discharge simulation is:

[0017] wherein, represents the heat capacity, is the internal temperature of the battery in the time domain, is the time, is the ambient temperature, is the convection resistance, is the power dissipated by the energy inside the battery; The expression for solving the temperature in the frequency domain of the battery model during the charge and discharge simulation is:

[0018] represents the internal temperature of the battery in the frequency domain, represents the variable in the Laplace transform of the time-frequency domain; The expression for the SOC data is:

[0019] wherein, represents the preset SOC condition of the battery at a certain moment, represents the change in the internal charge of the battery, represents the battery capacity under temperature change;

[0020] wherein, represents the main circuit current value, t represents the charge and discharge time;

[0021] wherein, is the average charge and discharge current of the battery, is the internal temperature of the battery; The expression of SOH data is as follows:

[0022] Wherein 、 、 respectively represent the end - of - life resistance of the battery, the internal resistance of the battery at the measurement moment, and the internal resistance of the battery when not in use at temperature .

[0023] Optionally, the step of using the voltage, current, temperature, and SOC data of the battery model in the charge - discharge simulation process as the input of the convolutional neural network and the SOH data as the output to train the convolutional neural network includes: Build the input layer, convolutional layer, pooling layer, fully - connected layer, and output layer of the convolutional neural network, set the training parameters of the convolutional neural network, and initialize the network weights and biases; Normalize the voltage, current, temperature, and SOC data of the battery model in the charge - discharge simulation process and use them as the training input of the built convolutional neural network, and use the SOH data generated during the training process of the convolutional neural network as the training output; Calculate the difference between the SOH data of the training output and the SOH data in the charge - 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; Analyze the trained convolutional neural network according to the preset evaluation function to evaluate the effectiveness of the convolutional neural network.

[0024] Optionally, the expressions for the network weights and biases of the convolutional neural network are:

[0025]

[0026] In the formula, F represents the objective function of the convolutional neural network, represents the network weights of the i -th layer of convolution, represents the bias of the i -th layer of convolution, represents the data item of the i -th layer of 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:

[0027] In the formula, 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:

[0028] The expression of the evaluation function is:

[0029] In the formula, is the evaluation value, is the actual value, is the sample sequence, is the total sample sequence.

[0030] The present invention also provides a battery health state evaluation system, including; An acquisition module, configured to acquire basic data during the charge and discharge process of the battery during a hybrid pulse test; A construction module, configured to construct a battery model, perform parameter fitting on the battery model according to the basic data, and obtain the parameter values of each component in the battery model after parameter fitting; A charge and discharge module, configured to perform constant current-constant voltage charge and discharge simulation on the battery model after fitting at different temperatures, obtain the SOC data of the battery model during the charge and discharge simulation process, and obtain the SOH data according to the component parameter values; A training module, configured to use the voltage, current, temperature, and SOC data of the battery model during the charge and discharge simulation process as the input of a 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 an evaluation model of the battery, and evaluate the health state of the battery according to the evaluation model.

[0031] The basic data at least includes current data, voltage data, and charge data; the construction module includes: A construction unit, configured to construct a basic equivalent circuit of the battery model; A simulation unit, configured to import the current data in the basic data at a certain temperature into the basic equivalent circuit, perform simulation in simulation software, and obtain the open circuit voltage and external terminal voltage of the basic equivalent circuit; An estimation and fitting unit, configured 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 is configured to repeatedly import the current data in the basic data obtained at different temperatures into the basic equivalent circuit for simulation analysis, so as to obtain the functional relationships between the parameters of each component of the basic equivalent circuit and the temperature and SOC data.

[0032] The present invention also provides a storage medium, on which a computer program is stored. When the program is executed by a processor, the above-mentioned battery health state evaluation method is implemented.

[0033] The present invention also provides a computer, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the above-mentioned battery health state evaluation method is implemented.

[0034] The beneficial effects of the present invention compared with the prior art are as follows: The battery health state evaluation method provided in this application first performs a hybrid pulse test on the physical battery to directly obtain the basic data during the charging and discharging process of the battery, and then constructs a battery model. According to the directly measured basic data of the battery, parameter fitting is performed on the constructed battery model, which improves the accuracy of parameter fitting in the battery model and reduces the complexity of model parameter identification; perform constant current-constant voltage charging and discharging simulations at different temperatures on the fitted battery model to obtain the SOC data of the battery model during the charging and discharging simulation process, and obtain the SOH data according to the component parameter values; then use the voltage, current, temperature, and SOC data during the simulation process as the input of the convolutional neural network, and use the SOH data as the output to train the convolutional neural network, and use the trained convolutional neural network as an evaluation model to evaluate the battery health state, with strong adaptability and suitable for wide promotion.

[0035] The additional aspects and advantages of the present invention will be partially given in the following description, partially become obvious from the following description, or be understood through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 is a flowchart of the battery health state evaluation method in the first embodiment of the present invention; Figure 2 is the basic equivalent circuit diagram of the battery model in the first embodiment of the present invention; Figure 3 is the structural block diagram of the computer in the fourth embodiment of the present invention.

[0037] The following specific embodiments will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0038] To facilitate the understanding of the present invention, the present invention will be described more comprehensively below with reference to the relevant accompanying drawings. Several embodiments of the present invention are shown in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, these embodiments are provided to make the disclosure of the present invention more thorough and comprehensive.

[0039] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0040] Embodiment 1 Please refer to Figure 1 , which shows the method for evaluating the state of health of a battery in the first embodiment of the present invention. The method for evaluating the state of health of the battery specifically includes steps S10 to S50: S10, obtaining basic data during the charge and discharge process of the battery during a hybrid pulse test; In specific implementation, a 18650PF lithium battery can be used to perform a Hybrid Pulse Power Characterization (HPPC) test to obtain the basic data during the charge and discharge process of this type of battery. The basic data at least includes current data, voltage data, and charge data during a complete charge and discharge process of the battery.

[0041] S20, constructing a battery model, fitting the parameters of the battery model according to the basic data, and obtaining the parameter values of each component in the battery model after parameter fitting; In specific implementation, a high-fidelity lithium battery model can be established by using Simulink (a visualization simulation tool in MATLAB), and the 18650PF lithium battery can be simulated by using MATLAB, Simulink, and Simscape languages. This model can explain all the dynamic characteristics of the battery, including non-linear open-circuit voltage, average discharge current, and the temperature inside the battery, etc.

[0042] Optionally, the step of fitting the parameters of the battery model according to the basic data and obtaining the parameter values of each component in the battery model after parameter fitting includes: Constructing a basic equivalent circuit of the battery model; Importing the current data in the 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; Compare and fit the open-circuit voltage and external terminal voltage obtained from the simulation with the voltage data in the basic data, estimate the parameters of each component in the basic equivalent circuit according to the voltage fitting curve, and perform a charge and discharge simulation on the model after voltage curve fitting and parameter estimation to obtain SOC data; Repeatedly import the current data in the basic data obtained at different temperatures into the basic equivalent circuit for simulation analysis to obtain the functional relationships between the parameters of each component in the basic equivalent circuit and the temperature and SOC data.

[0043] The curves corresponding to the open-circuit voltage and external terminal voltage can be generated using ParameterEstimation in Simulink, and curve fitting can be performed using the nonlinear least squares method.

[0044] In specific implementation, Figure 2 is the basic equivalent circuit diagram of the high-fidelity lithium battery model; The time-domain expression of the basic equivalent circuit of the battery model is:

[0045] The frequency-domain expression of the basic equivalent circuit of the battery model is:

[0046] In the formula, represents the open-circuit voltage of the basic equivalent circuit, , respectively represent the external terminal voltage of the battery in the time domain and frequency domain, , respectively represent the electrochemical polarization resistance and electrochemical polarization capacitance of the battery, , represent the voltage of the electrochemical polarization network of the battery and the corresponding voltage drop, , respectively represent the concentration polarization resistance and concentration polarization capacitance of the battery, , represent the voltage of the concentration polarization network of the battery and the corresponding voltage drop, I、 respectively represent the line currents of the basic equivalent circuit in the time domain and frequency domain, which are positive during discharge and negative during charge, represents the variable in the Laplace transform of the time-frequency domain; Import the current data in the basic data at a certain temperature into the basic equivalent circuit, and perform simulation in the simulation software to obtain the open-circuit voltage 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-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 relationships between the components in the basic equivalent circuit of the battery model and temperature and SOC.

[0047] The expressions for the functional relationships between the components in the basic equivalent circuit of the battery model and temperature and SOC are as follows:

[0048]

[0049]

[0050]

[0051]

[0052]

[0053] In the formula, represents the internal resistance of the battery, represents the battery temperature.

[0054] S30. Perform constant current-constant voltage charge-discharge simulations on the fitted battery model at different temperatures, obtain the SOC data of the battery model during the charge-discharge simulation, and obtain the SOH data according to the component parameter values; In specific implementation, this application also considers the thermal effect on the basis of considering the circuit relationship, assumes that the internal temperature of the battery model is uniform, and the expression for solving the temperature in the time domain of the battery model during the charge-discharge simulation is:

[0055] In the formula, represents the heat capacity, is the internal temperature of the battery in the time domain, is the time, is the ambient temperature, is the convective resistance, is the power dissipated by the energy inside the battery; The expression for solving the temperature in the frequency domain of the battery model during the charge-discharge simulation is:

[0056] represents the internal temperature of the battery in the frequency domain, represents the variable in the Laplace transform of the time-frequency domain; The expression of the SOC data is as follows:

[0057] In the formula, represents the SOC status of the battery at the preset moment, represents the change in the internal charge of the battery, represents the battery capacity under temperature change;

[0058] In the formula, represents the main circuit current value, t represents the charge and discharge time; Optionally, the battery capacity depends on many factors, including: the average charge and discharge current of the battery, the charge and discharge time, the internal temperature of the battery, the charge and discharge voltage of the battery, and the number of charge and discharge cycles of the battery. In a short period of time, the determining factors of the battery capacity can be considered only as: the average discharge current of the battery, the discharge time, and the internal temperature of the battery; the battery capacity and the internal temperature have the following functional relationship:

[0059] In the formula, is the average charge and discharge current of the battery, is the internal temperature of the battery; Schematically, at 、 the expression of the battery capacity at temperature is:

[0060] Among them, 、 represent different temperatures of the battery, and respectively represent 、 the actual capacity of the battery at temperature, represents the temperature coefficient. Through the above expression, the battery capacity at other temperatures can be estimated at the current temperature.

[0061] Optionally, in specific implementation, the identified internal resistance parameter is used as the estimation index of SOH; the expression of the SOH data is:

[0062] Among them 、 、 respectively represent the end-of-life resistance of the battery, the internal resistance of the battery at the measurement moment, and the internal resistance of the battery when not in use at temperature .

[0063] S40. 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. Optionally, the step of using 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 using the SOH data as the output to train the convolutional neural network includes: Build the input layer, convolutional layer, pooling layer, fully connected layer, and output layer of the convolutional neural network, set the training parameters of the convolutional neural network, and initialize the network weights and biases. Normalize the voltage, current, temperature, and SOC data of the battery model during the charge and discharge simulation and use them as the training input of the built convolutional neural network, and use the SOH data generated during the training process of the convolutional neural network as the training output. Calculate the difference between the SOH data of the training output and the SOH data in the 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. Analyze the trained convolutional neural network according to the preset evaluation function to evaluate the effectiveness of the convolutional neural network.

[0064] Optionally, a typical convolutional neural network usually consists 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 this application is as follows: The first layer is the input layer, and its structure is the length of the input data sequence × the type of data. In this patent, only three types of data, namely voltage, current, and temperature, are considered for the type of data. The second, fourth, sixth, and eighth layers are all convolutional layers containing three filters. Each convolutional layer filter separately extracts the feature information of one type of input data. The filter contains convolutional kernels of corresponding numbers and corresponding sizes, and uses ReLU (Rectified Linear Unit, a commonly used activation function in neural networks) to activate and output the results.

[0065] The third, fifth, seventh, and ninth layers are all Max pooling layers containing three filters. Each pooling layer filter separately extracts the feature information of one convolutional layer filter to merge the feature information while retaining the main information, thereby achieving the effect of reducing network parameters.

[0066] 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 convolutional layer and pooling layer into a one-dimensional data structure.

[0067] The eleventh layer is a fully connected layer, which outputs after using the ReLU activation function.

[0068] The twelfth layer is the output layer, which outputs the SOH estimation value estimated by the convolutional neural network.

[0069] In specific implementation, the voltage, current, temperature, and SOC data of the battery model during the charge and discharge simulation process 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 depth convolutional network to implement the mapping relationship between voltage, current, temperature, SOC, and SOH; the relationship between the input and the output is as follows:

[0070] Where, represents the estimated output of the convolutional neural network, ( | ) represents the calculation process of the convolutional layer, pooling layer, and fully connected layer, represents , the set of convolutional neural network layers. The learning rate is set to 0.00002, the first-order momentum decay coefficient is set to 0.87, the second-order momentum decay coefficient is 0.98, and the number of experimental iterations is set to 2000; the SOH estimation value estimated by the convolutional neural network is obtained and compared with the actual SOH data obtained during the charge and discharge simulation process to obtain the difference between the two, and the objective function is minimized, that is, the difference between the two is minimized.

[0071] The expressions for the network weights and biases of the convolutional neural network are:

[0072]

[0073] In the formula, F represents the objective function of the convolutional neural network, represents the i network weights of the th i layer of convolution, represents the i bias of the th layer of convolution, The expression for the normalization process is:

[0074] In the formula, is the data after normalization; is the original data; and are respectively the maximum and minimum values of the original data; The expression of the objective function is:

[0075] The expression of the evaluation function is:

[0076] In the formula, is the evaluation value, is the actual value, is the sample sequence, is the total sample sequence.

[0077] S50. Use the trained convolutional neural network as the evaluation model of the battery, and evaluate the health state of the battery according to the evaluation model.

[0078] In summary, the battery health state evaluation method provided by this application first performs a hybrid pulse test on the physical battery to directly obtain the basic data during the charging and discharging process of the battery, then constructs a battery model, and performs parameter fitting on the constructed battery model according to the directly measured basic data of the battery, improving the accuracy of parameter fitting in the battery model and reducing the complexity of model parameter identification; performs constant current-constant voltage charging and discharging simulations at different temperatures on the fitted battery model to obtain the SOC data of the battery model during the charging and discharging simulation process, and obtains the SOH data according to the component parameter values; then uses the voltage, current, temperature, and SOC data during the simulation process as the input of the convolutional neural network, and uses the SOH data as the output to train the convolutional neural network, and uses the trained convolutional neural network as the evaluation model to evaluate the battery health state, with strong adaptability and suitable for large-scale promotion.

[0079] Embodiment 2 This embodiment provides a battery health state evaluation system, including: An acquisition module, used to acquire the basic data during the charging and discharging process of the battery when performing a hybrid pulse test on the battery; A construction module, used to construct a battery model, perform parameter fitting on the battery model according to the basic data, and obtain the component parameter values in the battery model after parameter fitting; A charging and discharging module, used to perform constant current-constant voltage charging and discharging simulations at different temperatures on the fitted battery model to obtain the SOC data of the battery model during the charging and discharging simulation process, and obtain the SOH data according to the component parameter values; A training module, which is used to take the voltage, current, temperature, and SOC data of the battery model during the charge and discharge simulation process 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, which is used to take the trained convolutional neural network as the evaluation model of the battery, and evaluate the health state of the battery according to the evaluation model.

[0080] Optionally, the basic data at least includes current data, voltage data, and charge data; the step of constructing the battery model and performing parameter fitting on the battery model according to the basic data to obtain the parameter values of each component in the battery model after parameter fitting includes: Construct the basic equivalent circuit of the battery model; Import the current data in the basic data at a certain temperature into the basic equivalent circuit, perform simulation in the simulation software, and obtain the open-circuit voltage and external terminal voltage of the basic equivalent circuit; Compare and fit the open-circuit voltage and external terminal voltage obtained by the 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; 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.

[0081] Optionally, the time-domain expression of the basic equivalent circuit of the battery model is:

[0082] The frequency-domain expression of the basic equivalent circuit of the battery model is:

[0083] In the formula, represents the open-circuit voltage of the basic equivalent circuit, , respectively represent the external terminal voltage of the battery in the time domain and the frequency domain, , respectively represent the electrochemical polarization resistance and electrochemical polarization capacitance of the battery, , represent the voltage of the electrochemical polarization network of the battery and the corresponding voltage drop, , respectively represent the concentration polarization resistance and concentration polarization capacitance of the battery, , represent the voltage of the concentration polarization network of the battery and the corresponding voltage drop, I、 respectively represent the line currents of the basic equivalent circuits in the time domain and the frequency domain, which are positive during discharge and negative during charge, represents the variable in the Laplace transform of the time-frequency domain; The expressions of the functional relationships between the components in the basic equivalent circuit of the battery model and temperature and SOC are as follows:

[0084]

[0085]

[0086]

[0087]

[0088]

[0089] In the formula, represents the internal resistance of the battery, represents the battery temperature.

[0090] Optionally, the expression for solving the temperature in the time domain of the battery model during the charge and discharge simulation is:

[0091] In the formula, represents the heat capacity, is the internal temperature of the battery in the time domain, is the time, is the ambient temperature, is the convection resistance, is the power dissipated by the energy inside the battery; The expression for solving the temperature in the frequency domain of the battery model during the charge and discharge simulation is:

[0092] represents the internal temperature of the battery in the frequency domain, represents the variable in the Laplace transform of the time-frequency domain; The expression for the SOC data is:

[0093] In the formula, represents the preset SOC condition of the battery at a certain moment, represents the change in the internal charge of the battery, represents the battery capacity under temperature change;

[0094] Wherein, represents the main circuit current value, t represents the charge and discharge time;

[0095] Wherein, is the average charge and discharge current of the battery, is the internal temperature of the battery; The expression of the SOH data is:

[0096] Wherein , , respectively represent the end-of-life resistance of the battery, the internal resistance of the battery at the measurement moment, and the internal resistance of the battery when not in use at the temperature .

[0097] Optionally, the step of using the voltage, current, temperature, and SOC data of the battery model in the charge and discharge simulation process as the input of the convolutional neural network and using the SOH data as the output to train the convolutional neural network includes: Construct the input layer, convolutional layer, pooling layer, fully connected layer, and output layer of the convolutional neural network, set the training parameters of the convolutional neural network, and initialize the network weights and biases; Normalize the voltage, current, temperature, and SOC data of the battery model in the charge and discharge simulation process and use them as the training input of the constructed convolutional neural network, and use the SOH data generated during the training process of the convolutional neural network as the training output; Calculate the difference between the SOH data of the training output and the SOH data in the 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; Analyze the trained convolutional neural network according to the preset evaluation function to evaluate the effectiveness of the convolutional neural network.

[0098] Optionally, the expressions of the network weights and biases of the convolutional neural network are:

[0099]

[0100] Wherein, F represents the objective function of the convolutional neural network, represents the network weight of the i th layer of convolution, represents the bias of the i th layer of convolution, represents the data item of the i th layer of convolution, Represents convolution, Indicates the error term in the training process of the convolutional neural network and is used for updating the parameters of each layer of the convolutional neural network; The expression of the normalization process is:

[0101] In the formula, Is the data after normalization; Is the original data; And Are respectively the maximum and minimum values of the original data; The expression of the objective function is:

[0102] The expression of the evaluation function is:

[0103] In the formula, Is the evaluation value, Is the actual value, Is the sample sequence, Is the total sample sequence.

[0104] Embodiment III This embodiment proposes a storage medium on which a computer program is stored. When the program is executed by a processor, the battery health state evaluation method as described above is implemented.

[0105] Embodiment IV The present invention also proposes a computer. Please refer to Figure 3 , which shows the computer in the embodiment of the present invention, including a memory 10, a processor 20, and a computer program 30 stored on the memory 10 and executable on the processor 20. When the processor 20 executes the computer program 30, the battery health state evaluation method as described above is implemented.

[0106] Among them, the memory 10 includes at least one type of storage medium, and the storage medium includes flash memory, hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), magnetic memory, magnetic disk, optical disc, etc. The memory 10 can be an internal storage unit of a computer in some embodiments, such as the hard disk of the computer. The memory 10 can also be an external storage device in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Further, the memory 10 can also include both an internal storage unit of a computer and an external storage device. The memory 10 can be used not only to store application software installed on the computer and various types of data, but also to temporarily store data that has been output or will be output.

[0107] Among them, the processor 20 can be an Electronic Control Unit (ECU, also known as a vehicle computer), a Central Processing Unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments, and is used to run the program code stored in the memory 10 or process data, such as executing an access restriction program, etc.

[0108] It should be noted that Figure 3 The structure shown does not constitute a limitation on the computer. In other embodiments, the computer may include fewer or more components than shown in the figure, or combine certain components, or have a different component layout.

[0109] Those skilled in the art can understand that the logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a definite sequence list of executable instructions for implementing a logical function, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch instructions from the instruction execution system, apparatus, or device and execute the instructions), or in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device.

[0110] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection (electronic device) having one or more wirings, a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable media can even be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing as appropriate, and then storing it in a computer memory.

[0111] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0112] The technical features of the above-described embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as within the scope described in this specification.

[0113] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the appended claims.

Claims

1. A method for evaluating the state of health of a battery, characterized in that: Obtain the basic data during the charge and discharge process of the battery during a hybrid pulse test; Construct a battery model, perform parameter fitting on the battery model according to the basic data, and obtain the parameter values of each component in the battery model after parameter fitting; Perform constant current-constant voltage charge and discharge simulation on the battery model after fitting at different temperatures, obtain the SOC data of the battery model during the charge and discharge simulation, and obtain the SOH data according to the component parameter values; 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; Use the trained convolutional neural network as the evaluation model of the battery, and evaluate the state of health of the battery according to the evaluation model.

2. The battery health state assessment method according to claim 1, wherein The basic data at least includes current data, voltage data, and charge data; the steps of constructing the battery model and performing parameter fitting on the battery model according to the basic data to obtain the parameter values of each component in the battery model after parameter fitting include: Construct the basic equivalent circuit of the battery model; Import the current data in the basic data at a certain temperature into the basic equivalent circuit, perform simulation in the simulation software, and obtain the open circuit voltage and external terminal voltage of the basic equivalent circuit; Compare and fit the open circuit voltage and external terminal voltage obtained by the 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, and perform a charge and discharge simulation on the model after voltage curve fitting and parameter estimation to measure the SOC data; 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.

3. The method for evaluating the battery health state according to claim 2, wherein 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: Wherein, represents the open-circuit voltage of the basic equivalent circuit, and respectively represent the external terminal voltage of the battery in the time domain and the frequency domain, and respectively represent the electrochemical polarization resistance and the electrochemical polarization capacitance of the battery, and represent the voltage of the electrochemical polarization network of the battery and the corresponding voltage drop, and respectively represent the concentration polarization resistance and the concentration polarization capacitance of the battery, and represent the voltage of the concentration polarization network of the battery and the corresponding voltage drop, I、 respectively represent the line currents of the basic equivalent circuit in the time domain and the frequency domain, which are positive during discharge and negative during charge, represents the variable in the Laplace transform of the time-frequency domain; The expression of the functional relationship between each component in the basic equivalent circuit of the battery model and temperature and SOC is as follows: In the formula, represents the internal resistance of the battery, represents the battery temperature.

4. The battery health state assessment method according to claim 3, wherein The temperature solution expression in the time domain of the battery model during the charge and discharge simulation is: In the formula, represents the heat capacity, is the temperature inside the battery in the time domain, is the time, is the ambient temperature, is the convection resistance, is the power dissipated by energy inside the battery; The temperature solution expression in the frequency domain of the battery model during the charge and discharge simulation is: represents the temperature inside the battery in the frequency domain, represents the variable in the Laplace transform in the time-frequency domain; The expression of the SOC data is: In the formula, represents the SOC condition of the battery at a preset moment, represents the change in the internal charge of the battery, represents the battery capacity under temperature change of the battery; In the formula, represents the main circuit current value, t represents the charge and discharge time; Wherein, is the average charge and discharge current of the battery, is the internal temperature of the battery; The expression of the SOH data is: Among them , , respectively represent the end-of-life resistance of the battery, the internal resistance of the battery at the measurement time, and the internal resistance of the battery when not in use at a temperature of .

5. The method for evaluating the battery health state according to claim 2, wherein The steps of using 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 using the SOH data as the output to train the convolutional neural network include: Build the input layer, convolutional layer, pooling layer, fully connected layer, and output layer of the convolutional neural network, set the training parameters of the convolutional neural network, and initialize the network weights and biases; Normalize the voltage, current, temperature, and SOC data of the battery model during the charge and discharge simulation and use them as the training input of the built convolutional neural network, and use the SOH data generated during the training process of the convolutional neural network as the training output; Calculate the difference between the SOH data of the training output and the SOH data in the charge and discharge simulation, and update the neural network parameters to minimize the objective function until the preset number of iterations or the objective function converges; Analyze the trained convolutional neural network according to a preset evaluation function to evaluate the effectiveness of the convolutional neural network.

6. The method for evaluating the battery health state according to claim 5, wherein The expressions of the network weights and biases of the convolutional neural network are: In the formula, F represents the objective function of the convolutional neural network, represents the i network weights of the th convolutional layer, i represents the bias of the th convolutional layer, i represents the data item of the th convolutional layer, represents convolution, and represents the error term in 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 for the normalization process is as follows: In the formula, 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: In the formula, is the evaluation value, is the actual value, is the sample sequence, is the total sample sequence.

7. A battery health state assessment system, characterized in that, Including: An acquisition module for acquiring basic data during the charge and discharge process of the battery during a hybrid pulse test; A construction module for constructing a battery model, fitting the parameters of the battery model according to the basic data, and obtaining the parameter values of each component in the battery model after parameter fitting; A charge and discharge module for performing constant current-constant voltage charge and discharge simulations of the fitted battery model at different temperatures, obtaining the SOC data of the battery model during the charge and discharge simulation process, and obtaining the SOH data according to the component parameter values; A training module for using the voltage, current, temperature, and SOC data of the battery model during the charge and discharge simulation process as the input of the convolutional neural network and the SOH data as the output to train the convolutional neural network; An evaluation module for using the trained convolutional neural network as an evaluation model of the battery and evaluating the health state of the battery according to the evaluation model.

8. The battery health state assessment system according to claim 7, characterized in that, The basic data at least includes current data, voltage data, and charge data; the construction module includes: A construction unit for constructing a basic equivalent circuit of the battery model; A simulation unit for importing the current data in the 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; An estimation and fitting unit for comparing and fitting the open-circuit voltage and external terminal voltage obtained by simulation with the voltage data in the basic data, estimating the parameters of each component of the basic equivalent circuit according to the voltage fitting curve, performing a charge and discharge simulation on the model after voltage curve fitting and parameter estimation, and measuring the SOC data; An analysis unit for repeatedly importing the current data in the basic data obtained at different temperatures into the basic equivalent circuit for simulation analysis, and obtaining the functional relationship between the parameters of each component of the basic equivalent circuit and the temperature and SOC data.

9. A storage medium, on which a computer program is stored, characterized in that, When the program is executed by a processor, it implements the battery health state evaluation method according to any one of claims 1 to 6.

10. A computer, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the battery health state evaluation method according to any one of claims 1 to 6.

Images