CN110794319A - Method, device and readable storage medium for predicting parameters of lithium battery impedance model - Google Patents

Abstract

The invention discloses a method for predicting parameters of an impedance model of a lithium battery. The steps are as follows: establishing a least squares support vector machine model for predicting target parameters; obtaining a voltage response value of a lithium battery to be tested; and the voltage response value to obtain the target parameter of the lithium battery to be tested; it can be seen that the target parameter can be obtained according to the pre-established least squares support vector machine model and the obtained voltage response value; the use of artificial neural network is avoided. The parameters of the impedance model of the lithium battery are predicted, and the least squares support vector machine adopts the principle of minimizing the structural risk. When applied to the prediction problem, the upper bound of the model generalization error is reduced while the sample point error is minimized, and the model is improved. Therefore, the parameters of the battery impedance model can be more accurately predicted.

Description

Method, device and readable storage medium for predicting parameters of lithium battery impedance model

technical field

The present invention relates to the technical field of lithium batteries, in particular to a method, a device and a readable storage medium for predicting parameters of an impedance model of a lithium battery.

Background technique

With the continuous development of society, my country has made rapid development in new energy and energy conservation and emission reduction. Lithium batteries have begun to replace traditional lead-acid, nickel-metal hydride and nickel-cadmium batteries due to their higher energy and more environmental protection. When lithium batteries are used in electric vehicles, the working voltage of the lithium battery that needs to be loaded on the electric vehicle is 12V or 24V, but the working voltage of the single lithium battery is 3.7V, so multiple batteries need to be connected in series to increase the voltage, but the battery is difficult to carry out. Completely balanced charge and discharge, it is difficult to ensure the consistency of the battery, there will be insufficient charging and over-discharging, which directly leads to a sharp deterioration of the battery performance and greatly reduces the cycle life and reliability of the battery. Therefore, it is particularly important to improve the consistency of the battery. After a lot of research, it is found that the parameters in the impedance model of the lithium battery are the basis for evaluating the consistency of the dynamic performance of the battery.

In the prior art, an artificial neural network method is used to predict the parameters of the lithium battery impedance model. The artificial neural network simulates the nervous system of the human brain from the perspective of bionics to realize the functions of perception, learning and reasoning of the human brain. The artificial neural network is introduced into the parameter prediction of the lithium battery impedance model, which can quickly predict the battery Purpose of impedance model parameters. Although the artificial neural network has achieved certain success, because the artificial neural network follows the principle of empirical risk minimization, the modeling process requires a large amount of sample data, the generalization ability is poor, and it is easy to fall into the local optimum. Sometimes not ideal.

Therefore, how to more accurately predict the parameters of the lithium battery impedance model is a problem that needs to be solved by those skilled in the art.

SUMMARY OF THE INVENTION

Embodiments of the present invention aim to provide a method, a device, and a readable storage medium for predicting parameters of an impedance model of a lithium battery, so as to solve the above problems.

To achieve the above object, the present invention provides the following technical solutions:

A method for predicting parameters of an impedance model of a lithium battery, the steps are as follows:

S10: Establish a least squares support vector machine model for predicting target parameters;

S20: Obtain the voltage response value of the lithium battery to be tested;

S30: Obtain the target parameter of the lithium battery to be tested according to the least squares support vector machine model and the voltage response value.

In an optional solution: the steps of establishing a least squares support vector machine model for predicting target parameters include:

Obtain sample voltage response values of multiple sample lithium batteries;

obtaining reference parameters of the multiple sample lithium battery impedance models;

The least squares support vector machine model is established according to the sample voltage response values of the plurality of sample lithium batteries and the reference parameter.

In an optional solution: the kernel function of the support vector machine is a radial basis kernel function.

In an optional solution: the step of establishing the least squares support vector machine model according to the sample voltage response values of the plurality of sample lithium batteries and the reference parameters includes:

According to the sample voltage response values of the plurality of sample lithium batteries and the reference parameters, the least squares support vector machine model is determined by using a genetic annealing algorithm.

In an optional solution: the step of obtaining the reference parameters of the multiple sample lithium battery impedance models includes:

An electrochemical workstation is used to measure the reference parameters of the impedance models of the plurality of sample lithium batteries.

In an optional solution: the obtaining the voltage response value of the lithium battery to be tested includes:

Obtain the corresponding voltage response values when the lithium battery to be tested is discharged at a current of 1C for 10s, 20s, 40s, 50s and 100s, respectively.

In an optional solution: the target parameters include: inductance, first resistance, second resistance, third resistance, fourth resistance, first capacitance, second capacitance, and third capacitance value and the fourth capacitance value.

A device for predicting parameters of an impedance model of a lithium battery, comprising:

a first model establishment unit, used for establishing a least squares support vector machine model for predicting target parameters;

a first obtaining unit, configured to obtain the voltage response value of the lithium battery;

a calculation unit, configured to obtain the parameter according to the least squares support vector machine model and the voltage response value;

An apparatus for predicting parameters of an impedance model of a lithium battery includes a processor configured to implement the steps of any of the above methods for predicting parameters of an impedance model of a lithium battery when executing a program stored in a memory.

A computer-readable storage medium on which a computer program is stored, the computer program being executed by a processor to implement the following steps:

Establish a least squares support vector machine model for predicting target parameters;

Obtain the voltage response value of the lithium battery to be tested;

According to the least squares support vector machine model and the voltage response value, the target parameter of the lithium battery to be tested is obtained.

Compared with the prior art, the beneficial effects of the embodiments of the present invention are as follows:

The invention establishes a least squares support vector machine model for predicting target parameters; obtains the voltage response value of the lithium battery to be tested; obtains the target parameter of the lithium battery to be tested according to the least squares support vector machine model and the voltage response value; it can be seen that, According to the pre-established least squares support vector machine model and the obtained voltage response value, the target parameters can be obtained. It avoids the use of artificial neural network to predict the parameters of the impedance model of lithium batteries, and the least squares support vector machine adopts the principle of structural risk minimization. The upper bound improves the generalization ability of the model, so the parameters of the battery impedance model can be predicted more accurately.

Description of drawings

1 is a flowchart of a method for predicting parameters of an impedance model of a lithium battery according to a first embodiment of the present invention;

2 is a flowchart of another method for predicting parameters of an impedance model of a lithium battery provided by the second embodiment of the present invention;

3 is a diagram of a lithium battery impedance model provided by a third embodiment of the present invention;

4 is a structural diagram of an apparatus for predicting parameters of an impedance model of a lithium battery provided by a fourth embodiment of the present invention;

FIG. 5 is a structural diagram of another apparatus for predicting parameters of an impedance model of a lithium battery according to a fifth embodiment of the present invention.

Detailed ways

The following embodiments will describe the present invention in detail with reference to the accompanying drawings. In the drawings or descriptions, similar or identical parts use the same reference numerals, and in practical applications, the shape, thickness or height of each component can be enlarged or reduced. The embodiments listed in the present invention are only used to illustrate the present invention, but not to limit the scope of the present invention. Any obvious modifications or changes made to the present invention do not depart from the spirit and scope of the present invention.

Example 1

Referring to FIG. 1, in an embodiment of the present invention, a method for predicting parameters of an impedance model of a lithium battery, the steps are as follows:

S10: Establish a least squares support vector machine model for predicting target parameters;

The target parameter can be the parameter or parameter value to be finally obtained, and the number and type of the target parameter can be pre-selected according to needs;

First, establish a least squares support vector machine model for predicting the target parameters. The least squares support vector machine model can be a specific calculation formula obtained, or it can not be directly embodied in a calculation formula, but through a computer program. implement the model;

Specifically, certain sample data can be collected in advance, and a least squares support vector machine model can be established according to the sample data.

S11: Obtain the voltage response value of the lithium battery to be tested;

The voltage response value can be one quantity or multiple, and a certain battery performance testing instrument can be used to obtain the voltage response value. Specifically, the ZM-7510 series battery performance detector can be used to obtain the voltage response value. It is used for performance testing of various types of batteries such as nickel-metal hydride, nickel-cadmium, nickel-zinc, lithium, etc. The detector has high measurement accuracy and fast detection speed. It can perform real-time monitoring and operation during the measurement process, and can store and display running curves. And complete measurement data, and can export data to EXCEL, WORD, TXT and other formats for archival analysis.

S12: According to the least squares support vector machine model and the voltage response value, the target parameters of the lithium battery to be tested are obtained;

The parameters of the lithium battery impedance model can be calculated and obtained according to the least squares support vector machine model established in step S10 and the voltage response value obtained in step S11. Specifically, the obtained voltage response value can be input into the least squares support vector machine model, and the output of the least squares support vector machine model can be the target parameter, and the parameter is calculated and obtained;

Optionally, after the voltage response value is obtained, the voltage response value may be normalized first, and then input to the least squares support vector machine, and the output of the least squares support vector machine is then subjected to inverse normalization processing. Get reference parameters. In order to eliminate the differences between dimensions, the prediction results are more accurate;

The least squares support vector machine model for predicting the target parameters is established, the voltage response value of the lithium battery to be tested is obtained, and the target parameters are obtained according to the least squares support vector machine model and the voltage response value. It can be seen that the target parameters can be obtained according to the pre-established least squares support vector machine model and the obtained voltage response value. The least squares support vector machine adopts the principle of structural risk minimization. When it is used to predict problems, it minimizes the error of sample points and reduces the upper bound of the generalization error of the model, which improves the generalization ability of the model, so it can be more accurate. Predict the parameters of the battery impedance model.

Example 2

Please refer to FIG. 2 , the difference between this embodiment and Embodiment 1 is that the method for establishing the least squares support vector machine model of the predicted target parameter in step S10 is as follows:

S20: Obtain sample voltage response values of multiple sample lithium batteries;

Multiple lithium batteries can be selected as samples to obtain sample data for training the least squares support vector machine model. In theory, the more the number of sample lithium batteries, the more sample data can be obtained. The least squares obtained by final training The support vector machine model is more accurate, but obtaining too many samples may sometimes consume a lot of time, so it needs to be comprehensively considered in combination with the actual engineering situation. For example, the number of sample lithium batteries can be 10, of course, in order to obtain more sample data, the number of sample lithium batteries can also be 50. The voltage response value may include only one physical quantity, or may include multiple physical quantities.

A certain main control circuit and battery charge and discharge control circuit can be designed to automatically obtain the voltage response value of the lithium battery. The voltage signal of the battery is measured and obtained by a certain detection instrument and input into the single-chip microcomputer. The single-chip computer can communicate with the upper computer through the Ethernet module, so that the upper computer can control the work of the charging and discharging circuit and transmit the voltage sampling value to the upper computer in real time.

Measure the voltage response of multiple lithium batteries. A certain battery performance testing instrument can be selected to obtain the voltage response value. Specifically, the ZM-7510 series battery performance detector can be used as the charge and discharge control circuit, and the voltage response value can be obtained. The detector can be used for the performance testing of various types of batteries such as nickel-metal hydride, nickel-cadmium, nickel-zinc, lithium, etc. The detector has high measurement accuracy and fast detection speed. Store and display the running curve and complete measurement data, and export the data to EXCEL, WORD, TXT and other formats for archival analysis. Optionally, the lithium battery sample can be connected to the detection instrument, and each time a lithium battery is connected, the two ends of the lithium battery can be excited successively with a step pulse current, the voltage sampling value can be obtained, and then the next lithium battery can be replaced, and the sequence is continued. , until the sample voltage response value of each sample lithium battery is obtained.

S21: Obtain reference parameters of multiple sample lithium battery impedance models.

The reference parameter can be considered as a standard more accurate parameter value. A certain measuring instrument can be used to obtain the reference parameters of the lithium battery impedance model. Measure the reference parameters of each sample lithium battery impedance model in turn.

S22: Establish a least squares support vector machine model according to the sample voltage response values and reference parameters of a plurality of sample lithium batteries.

The least squares support vector machine model can be expressed as:

Where K(x, x _i ) is the kernel function, n is the number of sample lithium batteries, the type of the kernel function can be selected according to the needs, when the least squares support vector machine is used to predict the lithium battery impedance model, x is the input, It can be the voltage response value of the lithium battery to be tested, f(x) is the parameter of the impedance model of the lithium battery to be tested, and x _i is the voltage response value of the ith sample. The process of establishing and training the least squares support vector machine model can be is to determine the parameters, a _i , b in the kernel function in the above expression through the sample voltage response value and the reference parameter. In this way, the calculation formula of the parameters of the impedance model can be determined.

Specifically, when establishing the least squares support vector machine model, the sample voltage response value can be used as the input of the least squares support vector machine, and the reference parameters can be used as the expected output of the least squares support vector machine model. The difference between the actual output and the expected output can be calculated in each training. When the difference reaches a predetermined range, the currently selected parameters are considered to meet the requirements, and the parameters in the kernel function, a _i , b. Preferably, the sample voltage response value, reference parameter and expected output can be normalized respectively, and then used as the input and expected output of the least squares support vector machine. Correspondingly, the actual value of the least squares support vector machine The output is transformed with an inverse normalization. In this way, the difference between the dimensions can be eliminated, and the model of the least squares support vector machine established is more accurate.

Obtain the sample voltage response values of multiple sample lithium batteries, obtain the reference parameters of the impedance models of multiple sample lithium batteries, establish a least squares support vector machine model according to the sample voltage response values and reference parameters of multiple sample lithium batteries, and obtain the test The voltage response value of the lithium battery is obtained according to the least squares support vector machine model and the voltage response value to obtain the target parameters. It can be seen that the target parameters can be obtained according to the pre-established least squares support vector machine model and the obtained voltage response value. The parameters of the battery impedance model can be predicted more accurately;

In order to determine the parameters in the least squares support vector machine model faster and more accurately, as a preferred embodiment, establishing the least squares support vector machine model according to the sample voltage response values and reference parameters of a plurality of sample lithium batteries includes: For the sample voltage response values and reference parameters of multiple sample lithium batteries, genetic annealing algorithm is used to determine the least squares support vector machine model;

In establishing the least squares support vector machine model, it is necessary to determine the parameter values in the model. For example, if the kernel function in the least squares support vector machine is a radial basis kernel function, the expression of the least squares support vector machine model is:

The parameters that need to be determined include σ, a _i and b. If the final parameter value is determined by manual trial and error, the efficiency is extremely low. Therefore, computer algorithms are often employed to determine parameter values. For example, genetic annealing algorithm. The specific steps of the genetic annealing algorithm may include: firstly, coding work is performed to generate an initial population. The initial population can be the parameters to be obtained in the least squares support vector machine model; an individual fitness evaluation method is designed to evaluate the population fitness. Optionally, the error of the output value can be used as the fitness, and the error of the output value can be the error between the value of the parameters of the output impedance model and the reference parameters of the impedance model; design a conventional genetic operator; select the next generation population, and keep it. Some of the excellent individuals are crossed and mutated to generate crossed offspring and mutant offspring; the crossed offspring and mutant offspring individuals generated in the previous step are subjected to simulated annealing operation to generate new individuals, and together with the retained excellent individuals form a new population, Then continue to design the individual fitness evaluation method to evaluate the population fitness until the fitness meets the requirements. The parameters of the population set at this time can be used as the parameters of the least squares support vector machine model. Exemplarily, when the fitness represents the error, that is, the error meets the final required value;

In order to measure the target parameters of the impedance model of the lithium battery to be measured more conveniently, quickly and accurately, as a preferred embodiment, obtaining the reference parameters of the impedance models of multiple samples of lithium batteries includes: using an electrochemical workstation to measure the impedance models of multiple samples of lithium batteries the reference parameters;

Optionally, an electrochemical workstation can be used to measure the impedance spectrum of the lithium battery, and then the electrochemical impedance software ZSimp Win can be used to fit and analyze the experimental data, which can manually specify a specific battery impedance model before measurement;

Exemplarily, when measuring with an electrochemical workstation, the positive electrode of the lithium battery can be connected to the working electrode of the electrochemical workstation and the measuring probes of the sensing electrode, and the negative electrode of the lithium battery can be connected to the two probes of the auxiliary electrode and the reference electrode;

Exemplarily, when using the software ZSimp Win to fit the measured impedance spectrum, the measured impedance spectrum can be first stored and converted into a data file, and then the data is imported into the ZSimp Win software to perform fitting. And select the impedance model circuit to be fitted, the fitting result can be obtained, and the parameters of the lithium battery impedance model can be obtained at the same time;

In order to establish the least squares support vector machine model more accurately, as a preferred embodiment, acquiring the voltage response value of the lithium battery to be tested may include: The corresponding voltage values at 50s and 100s respectively;

Usually, with the increase of current rate, the difference of charge-discharge response of lithium battery also increases. In order to make the difference between different single cells more obvious, the size of the discharge excitation current is selected as the maximum working current of the battery 1C ;

Regarding the acquisition of the voltage response value of the lithium battery to be tested, a specific example is given below: the lithium battery can be connected to the sorting equipment first, and the constant current charging can be performed at a charging rate of 0.5C. The cut-off voltage is 4.2V, and then the voltage Keep it at 4.2V for constant voltage charging with a cut-off current of 50mA. Then discharge with a current of 1C for 10s, 20s, 40s, 50s and 100s respectively, and pause for 5min after each pulse discharge of different cycles. Finally, the data can be exported to EXCEL format with testing equipment for archiving;

In order to more accurately predict the parameters of the lithium battery impedance model, as a preferred embodiment, the target parameters of the lithium battery impedance model to be measured include: inductance, first resistance, second resistance, third resistance, fourth resistance resistance value, first capacitance value, second capacitance value, third capacitance value and fourth capacitance value;

Example 3

Referring to FIG. 3, in an embodiment of the present invention, an impedance model diagram of a lithium battery is shown. Optionally, the impedance model of the battery may be as shown in FIG. 3, including an inductance L, a first resistance RL, a second resistance R1, a Three resistors RS, a fourth resistor R2, a first electric double layer capacitor Q1, and a second electric double layer capacitor Q2. The first end and the second end of the inductor L are respectively connected with the first end and the second end of the first resistor RL, and the second end of the first resistor RL is simultaneously connected with the first electric double layer capacitor Q1 and the second end of the second resistor R1. One end is connected, the second end of the second resistor R1 is connected to the second end of the first electric double layer capacitor Q1 and the first end of the third resistor RS, and the second end of the third resistor RS is connected to the second electric double layer at the same time. The first end of the capacitor Q2 is connected to the first end of the fourth resistor R2, and the second end of the second electric double layer capacitor Q2 is connected to the second end of the fourth resistor R2. This model can be used as an effective basis for screening battery consistency . The first electric double-layer capacitor Q1 and the second electric double-layer capacitor Q2 each include two parameters, and the two parameters of the first electric double-layer capacitor Q1 are a first capacitance value and a second capacitance value, and the second electric double-layer capacitance Two parameter values of the double-layer capacitor Q2 are a third capacitance value and a fourth capacitance value. Correspondingly, the parameters of the battery impedance model may be the inductance of the inductor L, the first resistance of the first resistor RL, the second resistance of the second resistor R1, the third resistance of the third resistor RS, and the fourth resistance. The fourth resistance value of R2, the first capacitance value and the second capacitance value of the first electric double layer capacitor Q1, the third capacitance value and the fourth capacitance value of the second electric double layer capacitor Q2;

The embodiment of the method for predicting the impedance model of a lithium battery is described in detail above. Based on the method for predicting the parameters of the impedance model of the lithium battery described in the above embodiments, the embodiment of the present invention provides a method for predicting the impedance of the lithium battery corresponding to the method. Model device. Since the embodiments of the apparatus part correspond to the embodiments of the method part, the embodiments of the apparatus part refer to the description of the embodiments of the method part, and details are not repeated here.

Example 4

Referring to FIG. 4 , an embodiment of a method for predicting an impedance model of a lithium battery is described in detail above. Based on the method for predicting an impedance model of a lithium battery described in the foregoing embodiment, an embodiment of the present invention provides a prediction method corresponding to the method. Apparatus for Lithium Battery Impedance Modeling. Since the embodiments of the apparatus part correspond to the embodiments of the method part, the embodiments of the apparatus part refer to the description of the embodiments of the method part, and details are not repeated here.

A device for predicting parameters of an impedance model of a lithium battery, comprising a first model establishment unit 40, a first acquisition unit 41 and a calculation unit 42;

a first model establishment unit 40, used for establishing a least squares support vector machine model for predicting target parameters;

The first obtaining unit 41 is used to obtain the voltage response value of the lithium battery to be tested;

The first acquisition unit 41 may specifically be a collection device or a collection instrument;

The calculation unit 42 is configured to obtain target parameters of the lithium battery to be tested according to the least squares support vector machine model and the voltage response value.

The first model establishment unit establishes a least squares support vector machine model for predicting target parameters, the first acquisition unit obtains the voltage response value of the lithium battery to be measured, and the calculation unit obtains the to-be-measured lithium battery according to the least squares support vector machine model and the voltage response value Target parameters for lithium batteries. It can be seen that the target parameters can be obtained according to the pre-established least squares support vector machine model and the obtained voltage response value. The least squares support vector machine adopts the principle of structural risk minimization. When it is applied to prediction problems, it minimizes the error of the sample points and reduces the upper bound of the model generalization error, which improves the generalization ability of the model, so it can be more accurate. Predict the parameters of the battery impedance model.

The first model building unit 40 includes a second obtaining unit, a third obtaining unit and a second model building unit. Wherein, the second acquisition unit may be used to acquire sample voltage response values of multiple sample lithium batteries; the third acquisition unit may be used to acquire reference parameters of impedance models of multiple sample lithium batteries; The least squares support vector machine model is established based on the sample voltage response value and reference parameters of the lithium battery;

The kernel function of the least squares support vector machine model established by the first model establishment unit may be a radial basis kernel function;

The second model establishment unit may be specifically configured to use a simulated annealing algorithm to determine a least squares support vector machine model according to the sample voltage response values and reference parameters of a plurality of sample lithium batteries;

The third acquisition unit can be specifically used to measure the reference parameters of the impedance models of the lithium batteries of multiple samples by using an electrochemical workstation;

The first obtaining unit can be specifically used to obtain the voltage values corresponding to the lithium battery to be tested when the lithium battery is discharged at a current of 1C for 10s, 20s, 40s, 50s and 100s respectively;

Example 5

Please refer to Figure 5, an apparatus for predicting parameters of an impedance model of a lithium battery, including:

memory 50 and processor 51;

a memory 50 for storing computer programs;

When the processor 51 is used to execute the computer program stored in the memory 50, the following steps can be implemented:

Establish a least squares support vector machine model for predicting target parameters;

Obtain the voltage response value of the lithium battery to be tested;

According to the least squares support vector machine model and the voltage response value, the target parameters of the lithium battery to be tested are obtained.

In some embodiments of the present invention, the above-mentioned processor 51 can also be used to execute the computer program in the memory 50 to implement the following steps:

Obtain sample voltage response values of multiple sample lithium batteries;

Obtain reference parameters of multiple sample lithium battery impedance models;

A least squares support vector machine model is established based on the sample voltage response values and reference parameters of multiple sample lithium batteries.

The above-mentioned processor 51 can also be used to execute the computer program in the memory 50 to realize the following steps:

According to the sample voltage response values and reference parameters of multiple sample lithium batteries, the least squares support vector machine model is determined by genetic annealing algorithm.

The above-mentioned processor 51 can also be used to execute the computer program in the memory 50 to realize the following steps:

Obtain the corresponding voltage response values when the lithium battery to be tested is discharged at a current of 1C for 10s, 20s, 40s, 50s and 100s.

In the device for predicting an impedance model of a lithium battery provided by this embodiment, when the processor executes the computer program in the memory, a least squares support vector machine model for predicting target parameters is established, and the voltage response value of the lithium battery to be measured is obtained. Multiply the support vector machine model and the voltage response value to get the target parameters. It can be seen that the target parameters can be obtained according to the pre-established least squares support vector machine model and the obtained voltage response value. The least squares support vector machine adopts the principle of structural risk minimization. When it is applied to prediction problems, it minimizes the error of the sample points and reduces the upper bound of the model generalization error, which improves the generalization ability of the model, so it can be more accurate. Predict the parameters of the battery impedance model.

Example 6

This embodiment provides a computer-readable storage medium corresponding to the above-mentioned embodiment of the method for predicting parameters of an impedance model of a lithium battery. Since the embodiments of the computer-readable storage medium correspond to the embodiments of the method, the computer can For the embodiment of reading the storage medium part, please refer to the description of the embodiment in the method part, and details are not repeated here;

A computer-readable storage medium on which a computer program is stored, and the computer program is executed by a processor to realize the following steps:

Establish a least squares support vector machine model for predicting target parameters;

Obtain the voltage response value of the lithium battery to be tested;

According to the least squares support vector machine model and the voltage response value, the target parameters of the lithium battery to be tested are obtained.

It should be noted that the computer-readable storage medium in the present invention may be a medium such as a U disk or an optical disk, which is not specifically limited;

When the computer program in the computer-readable storage medium provided by the present invention is executed by the processor, a least squares support vector machine model for predicting parameters is established, and the voltage response value of the lithium battery is obtained. According to the least squares support vector machine model and the voltage response value, get the parameter. It can be seen that the parameters can be obtained according to the pre-established least squares support vector machine model and the obtained voltage response value. The least squares support vector machine adopts the principle of structural risk minimization. When it is applied to prediction problems, it minimizes the error of the sample points and reduces the upper bound of the model generalization error, which improves the generalization ability of the model, so it can be more accurate. Predict the parameters of the battery impedance model;

The method, device and computer-readable storage medium for predicting parameters of an impedance model of a lithium battery provided by the present invention have been described in detail above. The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same and similar parts between the various embodiments can be referred to each other.

The above are only specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited to this. should be included within the scope of protection of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims (10)

1. a method for predicting the parameter of a lithium battery impedance model, is characterized in that, step is as follows: S10: Establish a least squares support vector machine model for predicting target parameters; S20: Obtain the voltage response value of the lithium battery to be tested; S30: Obtain the target parameter of the lithium battery to be tested according to the least squares support vector machine model and the voltage response value. 2. The method for predicting the parameters of a lithium battery impedance model according to claim 1, wherein the step of establishing a least squares support vector machine model for predicting target parameters comprises: Obtain sample voltage response values of multiple sample lithium batteries; obtaining reference parameters of the multiple sample lithium battery impedance models; The least squares support vector machine model is established according to the sample voltage response values of the plurality of sample lithium batteries and the reference parameter. 3 . The method for predicting parameters of a lithium battery impedance model according to claim 2 , wherein the kernel function of the least squares support vector machine model is a radial basis kernel function. 4 . 4 . The method for predicting parameters of a lithium battery impedance model according to claim 2 , wherein the least squares support vector machine is established according to the sample voltage response values of the plurality of sample lithium batteries and the reference parameters. 5 . The steps of the model include: According to the sample voltage response values of the plurality of sample lithium batteries and the reference parameters, the least squares support vector machine model is determined by using a genetic annealing algorithm. 5. The method for predicting parameters of a lithium battery impedance model according to claim 2, wherein the step of obtaining the reference parameters of the multiple sample lithium battery impedance models comprises: An electrochemical workstation is used to measure the reference parameters of the impedance models of the plurality of sample lithium batteries. 6. The method for predicting parameters of a lithium battery impedance model according to claim 2, wherein the acquiring the voltage response value of the lithium battery to be measured comprises: Obtain the corresponding voltage response values when the lithium battery to be tested is discharged at a current of 1C for 10s, 20s, 40s, 50s and 100s, respectively. 7. The method for predicting parameters of an impedance model of a lithium battery according to claim 2, wherein the target parameters comprise: inductance, first resistance, second resistance, third resistance, and fourth resistance value, a first capacitance value, a second capacitance value, a third capacitance value, and a fourth capacitance value. 8. A device for predicting the parameters of a lithium battery impedance model, comprising: a first model establishment unit, used for establishing a least squares support vector machine model for predicting target parameters; a first obtaining unit, used for obtaining the voltage response value of the lithium battery to be tested; A calculation unit, configured to obtain the target parameter of the lithium battery to be tested according to the least squares support vector machine model and the voltage response value. 9. A device for predicting the parameters of a lithium battery impedance model, characterized in that it comprises a processor, which implements the predicted lithium battery impedance model according to any one of claims 1-7 when the processor is used to execute a program stored in a memory The parameters of the method steps. 10. A computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and the computer program is executed by a processor to realize the following steps: Establish a least squares support vector machine model for predicting target parameters; Obtain the voltage response value of the lithium battery to be tested; According to the least squares support vector machine model and the voltage response value, the target parameter of the lithium battery to be tested is obtained.

Images