SEI film growth state prediction method and device, electronic equipment and storage medium

Abstract

The invention relates to a lithium ion battery SEI film growth state prediction method and device, electronic equipment and a storage medium, and belongs to the technical field of electrochemical engineering.The lithium ion battery SEI film growth state prediction method comprises the steps that DRT diagrams of a lithium ion battery under different impedances are determined, and DRT data are determined based on the DRT diagrams; analyzing the surface morphology of the SEI film, and determining SEI film parameter data; performing correlation analysis on the DRT data and the SEI film parameter data to obtain a correlation analysis result, and selecting first feature data meeting a preset condition according to the correlation result; and constructing an SEI film growth state prediction model based on the first feature data, and predicting the SEI film growth state of the lithium ion battery based on the SEI film growth state prediction model. According to the method, the SEI film growth state prediction model is established for prediction through the characteristic data, so that the model can predict the SEI film growth state, and the cycle life and the stability of the battery are improved.

Description

Technical Field

[0001] The present invention relates to the field of electrochemical engineering technology, and in particular to a method, device, electronic equipment and storage medium for predicting the growth state of a SEI film of a lithium ion battery. Background Art

[0002] Lithium-ion batteries are widely used in consumer electronics, energy storage systems and electric vehicles. However, as the battery life increases, the battery performance gradually deteriorates. Battery health assessment has become an important research topic in battery management systems. The SEI membrane, or solid electrolyte interface membrane, is a layer of solid electrolyte membrane formed in lithium-ion batteries. It serves to isolate the electrode from the electrolyte. During the cyclic charge and discharge process of lithium-ion batteries, the SEI membrane will continue to change dynamically, thus affecting the performance and life of the battery.

[0003] The formation and decomposition of the SEI film is a key process in the normal operation of the battery, but due to its non-uniform structure and complex composition, its growth law has always been a research problem. Therefore, studying the growth state of the battery SEI film is crucial to studying the health status assessment, performance improvement, and fault analysis of the battery.

[0004] Electrochemical impedance spectroscopy (EIS) technology has attracted widespread attention because of its ability to quickly and non-invasively evaluate battery status. Distribution time method (DRT) is an effective method for EIS data processing. By measuring EIS on electrode materials, various charge transfer processes in the electrochemical process can be separated and a DRT diagram can be established. However, how to study the growth state of the SEI film through the DRT diagram and improve the cycle life and stability of the battery is a technical problem that needs to be solved urgently. Summary of the invention

[0005] In view of this, it is necessary to provide a method, device, electronic device and storage medium for predicting the growth state of the SEI film to improve the cycle life and stability of the battery.

[0006] In order to achieve the above object, in a first aspect, the present invention provides a method for predicting the growth state of an SEI film, comprising: Determine a DRT diagram of a lithium-ion battery at different impedances, and determine DRT data based on the DRT diagram; Analyze the surface morphology of SEI film and determine the parameter data of SEI film; Performing a correlation analysis on the DRT data and the SEI film parameter data to obtain a correlation analysis result, and selecting first characteristic data that meets a preset condition according to the correlation result; A SEI film growth state prediction model is constructed based on the first characteristic data, and the SEI film growth state of the lithium-ion battery is predicted based on the SEI film growth state prediction model.

[0007] In a possible implementation, the step of establishing a DRT diagram under different impedances of lithium ions includes: Measure the electrochemical impedance spectroscopy of lithium-ion batteries at different SOC and charge and discharge cycle numbers; The DRT diagram of the lithium-ion battery at different impedances is determined based on the electrochemical impedance spectroscopy.

[0008] In one possible implementation, the DRT data includes a minimum time constant and the cathode internal resistance of lithium-ion batteries , the determining of DRT data based on the DRT graph comprises: Determine the characteristic peak of the DRT diagram, and determine the minimum time constant with the lowest impact on SOC and charge and discharge cycle number based on the characteristic peak of the DRT diagram ; Determine the DRT distribution function based on the DRT diagram, and determine the area surrounded by the curve corresponding to the DRT distribution function in the DRT diagram and the characteristic peak as the internal resistance of the lithium-ion battery. .

[0009] In a possible implementation, analyzing the surface morphology of the SEI film of the lithium-ion battery to determine the parameter data of the SEI film of the lithium-ion battery includes: The SEM image and TEM image of the SEI film of the lithium-ion battery are obtained, and the SEM image and TEM image are quantified based on a preset image processing software to obtain the roughness, thickness and grain size of the SEI film of the lithium-ion battery.

[0010] In a possible implementation, performing a correlation analysis on the DRT data and the lithium ion SEI film parameter data to obtain a correlation analysis result includes: The DRT data and the lithium ion SEI film parameter data are used as the second characteristic data, and the remaining battery life, the cathode resistance of the lithium battery and the battery voltage are used as the lithium ion battery SEI film growth state parameter data; The Pearson correlation coefficient and the grayscale correlation coefficient are used to perform correlation analysis on the second characteristic data and the SEI film growth state parameter data to obtain a first correlation analysis result and a second correlation analysis result, wherein the first correlation analysis result includes the Pearson correlation coefficient value of each second characteristic data, and the second correlation analysis result includes the grayscale correlation coefficient value of each second characteristic data.

[0011] In a possible implementation, selecting the first feature data satisfying a preset condition according to the correlation result includes: Determining third feature data having a Pearson correlation coefficient value greater than a first correlation threshold in the first correlation analysis result; Determine fourth feature data whose grayscale correlation coefficient value is greater than a second correlation threshold value in the second correlation analysis result; The first feature data is determined according to the third feature data and the fourth feature data.

[0012] In a possible implementation, the lithium-ion SEI film growth state prediction model is built based on the LightGBM algorithm; The LightGBM algorithm is:

[0013] in, is the objective function, is the loss function, For the front The result of round iteration, Ω is the regularization term, For the A tree, is the predicted target value.

[0014] In a second aspect, the present invention further provides a device for predicting the growth state of SEI film of a lithium ion battery, comprising: A DRT data determination module, used to determine a DRT graph of a lithium-ion battery under different impedances, and determine DRT data based on the DRT graph; SEI film parameter data determination module, used to analyze the surface morphology of the SEI film and determine the SEI film parameter data; A correlation analysis module, used for performing correlation analysis on the DRT data and the SEI film parameter data to obtain a correlation analysis result, and selecting first characteristic data that meets a preset condition according to the correlation result; A prediction module is used to construct a SEI film growth state prediction model based on the first characteristic data, and predict the SEI film growth state of the lithium-ion battery based on the SEI film growth state prediction model.

[0015] In a third aspect, the present invention further provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps in the above-mentioned method for predicting the growth state of the SEI film of a lithium-ion battery.

[0016] In a fourth aspect, the present invention further provides a computer storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned method for predicting the growth state of the SEI film of a lithium-ion battery are implemented.

[0017] The beneficial effects of the present invention are: The present invention determines a DRT diagram of a lithium-ion battery under different impedances, and determines DRT data based on the DRT diagram. The DRT diagram intuitively displays the time scales of different relaxation processes, which is helpful for understanding the polarization state of the lithium battery and the growth state of the SEI film; then the surface morphology of the SEI film is analyzed to determine the SEI film parameter data, so as to obtain more comprehensive characteristic data; then the DRT data and the SEI film parameter data are subjected to correlation analysis to obtain the correlation analysis result, and the first characteristic data satisfying the preset conditions are selected according to the correlation result to improve the accuracy of the model prediction; finally, an SEI film growth state prediction model is constructed based on the first characteristic data, and the growth state of the SEI film of the lithium-ion battery is predicted based on the SEI film growth state prediction model. By constructing the SEI film growth state prediction model, it can be applied to the analysis of large-scale retired battery data to improve the cycle life and stability of the battery. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 A method flow chart of an embodiment of a method for predicting the growth state of SEI film of a lithium-ion battery provided by the present invention; Figure 2 A DRT diagram of a lithium-ion battery provided by one embodiment of the present invention; Figure 3 A schematic diagram of the structure of an embodiment of a device for predicting the growth state of SEI film of a lithium-ion battery provided by the present invention; Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not used to limit the scope of the present invention.

[0021] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0022] A specific embodiment of the present invention, as Figure 1 As shown, Figure 1 A method flow chart of an embodiment of a method for predicting SEI film growth state of a lithium-ion battery provided by the present invention includes: S101: Determine a DRT graph of a lithium-ion battery under different impedances, and determine DRT data based on the DRT graph; S102: Analyze the surface morphology of the SEI film and determine the parameter data of the SEI film; S103: performing correlation analysis on the DRT data and the SEI film parameter data to obtain a correlation analysis result, and selecting first characteristic data that meets a preset condition according to the correlation result; S104: constructing a SEI film growth state prediction model based on the first characteristic data, and predicting the SEI film growth state of the lithium-ion battery based on the SEI film growth state prediction model.

[0023] The present invention determines a DRT diagram of a lithium-ion battery under different impedances, and determines DRT data based on the DRT diagram. The DRT diagram intuitively displays the time scales of different relaxation processes, which is helpful for understanding the polarization state of the lithium battery and the growth state of the SEI film; then the surface morphology of the SEI film is analyzed to determine the SEI film parameter data, so as to obtain more comprehensive characteristic data; then the DRT data and the SEI film parameter data are subjected to correlation analysis to obtain the correlation analysis result, and the first characteristic data satisfying the preset conditions are selected according to the correlation result to improve the accuracy of the model prediction; finally, an SEI film growth state prediction model is constructed based on the first characteristic data, and the growth state of the SEI film of the lithium-ion battery is predicted based on the SEI film growth state prediction model. By constructing the SEI film growth state prediction model, it can be applied to the analysis of large-scale retired battery data to improve the cycle life and stability of the battery.

[0024] In one embodiment of the present invention, establishing a DRT diagram under different impedances of lithium ions includes: Measure the electrochemical impedance spectroscopy of lithium-ion batteries at different SOC and charge and discharge cycle numbers; The DRT diagram of lithium-ion batteries at different impedances is determined based on electrochemical impedance spectroscopy.

[0025] It is understood that by measuring the electrochemical impedance spectrum of lithium-ion batteries at different SOCs and charge and discharge cycle numbers, the relaxation time distribution diagram of the AC impedance can be calculated. Specifically, the DRT curves when the battery charge and discharge cycle numbers are cycle 10, cycle 50, and cycle 100, and the state of charge is 10% SOC, 20% SOC, 30% SOC, 40% SOC, and 50% SOC are calculated. Please refer to Figure 2 , Figure 2 A DRT diagram of a lithium-ion battery provided by one embodiment of the present invention.

[0026] The meaning of the DRT graph of the lithium-ion battery is: the horizontal axis is the relaxation time represented by the logarithmic scale, and the vertical axis represents the distribution function value at a specific relaxation time. The specific resistance of the SEI film can be determined based on the closed area of ​​the curve. , according to the different characteristic peaks represented by the image , , The minimum time constant that has the least impact on SOC and number of charge and discharge cycles can be determined .

[0027] Specifically, the AC impedance spectrum of the battery is first measured using a low-frequency AC voltage signal as an excitation. The specific calculation formula for AC impedance is: Z(ω) = X(ω) / J(ω), where ω is the circular frequency of the applied AC voltage, Z(ω) is the AC impedance, X(ω) is the response signal, and J(ω) is the excitation signal. Then, the relaxation time distribution function is used to convert the electrochemical impedance data into a relaxation time distribution diagram. The relaxation time distribution function is: ,in, is the overall impedance, in units of , is the impedance in ohms. , is the absolute impedance distribution in logarithmic scale, in units of , i is the imaginary unit, , is the frequency in Hz, and τ is the relaxation time in s.

[0028] In one embodiment of the present invention, the DRT data includes a minimum time constant and the cathode internal resistance of lithium-ion batteries , determine the DRT data based on the DRT diagram, including: Determine the characteristic peak of the DRT graph, and determine the minimum time constant with the lowest impact on SOC and charge and discharge cycle number based on the characteristic peak of the DRT graph ; The DRT distribution function is determined based on the DRT diagram, and the area surrounded by the curve and characteristic peak corresponding to the DRT distribution function in the DRT diagram is determined as the cathode internal resistance of the lithium-ion battery. .

[0029] It is understandable that different characteristic peaks are obtained through the DRT graph under different impedances. The change law of each characteristic peak of the DRT graph is analyzed to find the minimum time constant with the lowest impact on SOC and charge and discharge cycle number. , and draw the electrochemical impedance spectrum; then associate each characteristic peak with different fuel cell polarization processes, and obtain the internal resistance of the lithium-ion battery through the peak value corresponding to the DRT distribution function image and the area contained in the curve .

[0030] Specifically, by finding the battery in different The relaxation time distribution function curve obtained under the state Follow The minimum time constant with the smallest range of charge and discharge cycle times ; Next, based on the fixed regularization parameter selection, the area contained in the peak value and the curve corresponding to the DRT distribution function is calculated , the specific calculation formula is: ;in, It represents the internal resistance of SEI film, and its unit is Ω. represents the relaxation time distribution function.

[0031] In one embodiment of the present invention, the surface morphology of the SEI film of the lithium-ion battery is analyzed to determine the parameter data of the SEI film of the lithium-ion battery, including: The SEM image and TEM image of the SEI film of the lithium-ion battery are obtained, and the SEM image and TEM image are quantified based on the preset image processing software to obtain the roughness, thickness and grain size of the SEI film of the lithium-ion battery.

[0032] It can be understood that the surface morphology of the SEI film of the lithium-ion battery after different charge and discharge cycles was observed by using a scanning electron microscope, and SEM images were taken and recorded. The microstructure of the SEI film after different cycles was observed by using a transmission electron microscope, and TEM images were taken and recorded. The changes in the SEI film after different cycles were analyzed, and the roughness of the SEI film was quantified using image processing software. , thickness, and grain size parameters.

[0033] Specifically, the lithium-ion batteries at different charge and discharge cycles and different SOCs are fully discharged to 0%. Next, the battery was disassembled to remove the negative electrode and prepare samples. The samples were observed and images were taken by SEM and TEM. The images were processed by image processing software and the surface roughness of the SEI film was calculated using a roughness calculation tool. , multiple sections are selected in the SEM image to measure the thickness of the SEI film and obtain the average thickness. Finally, the grains are identified and marked in the TEM image to obtain the size distribution of the grains.

[0034] In one embodiment of the present invention, correlation analysis is performed on DRT data and lithium ion SEI film parameter data to obtain correlation analysis results, including: The DRT data and the lithium ion SEI film parameter data are used as the second characteristic data, and the remaining battery life, the cathode resistance of the lithium battery and the battery voltage are used as the lithium ion battery SEI film growth state parameter data; The Pearson correlation coefficient and the grayscale correlation coefficient are used to perform correlation analysis on the second characteristic data and the SEI film growth state parameter data to obtain a first correlation analysis result and a second correlation analysis result, wherein the first correlation analysis result includes the Pearson correlation coefficient value of each second characteristic data, and the second correlation analysis result includes the grayscale correlation coefficient value of each second characteristic data.

[0035] Selecting first feature data that meets preset conditions according to the correlation result includes: Determining third feature data having a Pearson correlation coefficient value greater than a first correlation threshold in the first correlation analysis result; Determine fourth feature data whose grayscale correlation coefficient value is greater than a second correlation threshold value in the second correlation analysis result; The first feature data is determined based on the third feature data and the fourth feature data.

[0036] It can be understood that the characteristic data for building the prediction model are the characteristics that are highly correlated with the growth state of the SEI film and have low autocorrelation between different characteristics. The present invention regards the characteristics with a correlation with the growth state of the SEI film exceeding a preset threshold as highly correlated characteristics. Specifically, the data obtained from the DRT graph and the SEI film parameter data are subjected to correlation analysis, the data are fitted and the correlation coefficient is calculated, and finally the battery capacity, interface impedance, , battery voltage as characteristic data.

[0037] Among them, the Pearson correlation coefficient calculation method includes:

[0038] in, For the The Pearson correlation coefficient value of the features, For the The feature in The value of the next cycle, For the The feature in The average value of the cycles, For the The remaining life of lithium-ion batteries after cycles, is the average remaining life of lithium-ion batteries; Grayscale correlation coefficient calculation method, including:

[0039] in, For the The feature in The grayscale correlation coefficient value of the cycle, is the discrimination coefficient, set to 0.5.

[0040] It can be understood that the Pearson correlation coefficient of each second feature data is the first correlation analysis result, and the grayscale correlation coefficient of each second feature data is the second correlation analysis result, and then the first correlation threshold of the Pearson correlation coefficient and the second correlation threshold of the grayscale correlation coefficient are set respectively. The third feature data whose Pearson correlation coefficient value in the first correlation analysis result is greater than the first correlation threshold and the fourth feature data whose grayscale correlation coefficient value in the second correlation analysis result is greater than the second correlation threshold are used as the first feature data for building the prediction model. In an embodiment of the present invention, the first correlation threshold of the Pearson correlation coefficient is set to 0.5, and the second correlation threshold of the grayscale correlation coefficient is set to 0.8.

[0041] Then, the first feature data is dimensionless processed, and the selected first feature data constitute the optimal feature set. By uniformly normalizing the first feature data, the influence of data value differences on the model is avoided. Specifically, the normalization formula is: , is the original feature data, is the normalized feature data, and are the maximum and minimum values ​​of the original feature data respectively.

[0042] Then, the SEI film growth state prediction model is built based on the selected first feature data, using the LightGBM algorithm. The LightGBM algorithm can be expressed as:

[0043] in, is the objective function, is the loss function, For the front The result of round iteration, Ω is the regularization term, For the A tree, is the predicted target value.

[0044] When building a SEI film growth state prediction model using the LightGBM algorithm, we first use the data in the first feature data as the optimal feature set based on the results of the PCC and GRG correlation analysis, and use this data set as the training data set, which is defined as , m is the number of feature data. Then, m is established based on the optimal feature set. n-dimensional feature sequence. The model feature sequence is defined as: , where n is the number of lithium-ion batteries in different The number of charge and discharge cycles under the optimal data set is m, and m is the number of features in the optimal data set. Before building the model, you need to set the model parameters, including but not limited to the learning rate (learning_rate), the maximum depth of the tree (max_depth), the minimum number of leaf node samples (min_child_samples), etc. The relevant parameter settings are shown in Table 1.

[0045] Table 1 Parameter settings of LightGBM model

[0046] After building the SEI film growth state prediction model using the LightGBM algorithm, it is necessary to verify the prediction accuracy of the model. In order to comprehensively analyze the effectiveness of the model, the present invention selects the following three indicators to evaluate the prediction accuracy of the SEI film growth state prediction model: mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE). The specific formula is as follows:

[0047]

[0048]

[0049] In the formula, is the actual growth state parameter of the SEI film, is the growth state parameter of the SEI film predicted by the model. N is the growth state parameter of the SEI film in different The number of charge and discharge cycles.

[0050] In addition, the present invention can also use the random forest algorithm to establish a growth state estimation model for the SEI film, and by selecting appropriate eigenvalues, further optimize the estimation effect of the model, so that the DRT method can be better used to estimate the growth state of the SEI film of the battery.

[0051] In order to better implement the method for predicting the growth state of the SEI film of a lithium-ion battery in the embodiment of the present invention, based on the method for predicting the growth state of the SEI film of a lithium-ion battery, correspondingly, Figure 3 As shown, the embodiment of the present invention further provides a lithium ion battery SEI film growth state prediction device, the lithium ion battery SEI film growth state prediction device 300 comprises: A DRT data determination module 301 is used to determine a DRT diagram of a lithium-ion battery under different impedances, and determine DRT data based on the DRT diagram; SEI film parameter data determination module 302, used to analyze the surface morphology of the SEI film and determine the SEI film parameter data; A correlation analysis module 303 is used to perform correlation analysis on the DRT data and the SEI film parameter data to obtain a correlation analysis result, and select first characteristic data that meets a preset condition according to the correlation result; The prediction module 304 is used to construct a SEI film growth state prediction model based on the first characteristic data, and predict the SEI film growth state of the lithium-ion battery based on the SEI film growth state prediction model.

[0052] The lithium-ion battery SEI film growth state prediction device 300 provided in the above embodiment can implement the technical solution described in the above lithium-ion battery SEI film growth state prediction method embodiment. The specific implementation principles of the above modules or units can refer to the corresponding contents in the above lithium-ion battery SEI film growth state prediction method embodiment, which will not be repeated here.

[0053] like Figure 4 As shown, the present invention also provides an electronic device 400. The electronic device 400 includes a processor 401, a memory 402 and a display 403. Figure 4 Only some components of the electronic device 400 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0054] In some embodiments, the processor 401 may be a central processing unit (CPU), a microprocessor or other data processing chip, and is used to run program codes or process data stored in the memory 402, such as the method for predicting the growth state of the SEI film of a lithium-ion battery in the present invention.

[0055] In some embodiments, processor 401 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, processor 401 may be local or remote. In some embodiments, processor 401 may be implemented in a cloud platform. In one embodiment, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-cloud, etc., or any combination thereof.

[0056] In some embodiments, the memory 402 may be an internal storage unit of the electronic device 400, such as a hard disk or memory of the electronic device 400. In other embodiments, the memory 402 may also be an external storage device of the electronic device 400, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the electronic device 400.

[0057] Furthermore, the memory 402 may include both an internal storage unit of the electronic device 400 and an external storage device. The memory 402 is used to store application software installed in the electronic device 400 and various data.

[0058] In some embodiments, the display 403 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 403 is used to display information of the electronic device 400 and to display a visual user interface. The components 401-403 of the electronic device 400 communicate with each other via a system bus.

[0059] In some embodiments, when the processor 401 executes the lithium-ion battery SEI film growth state prediction program in the memory 402, the following steps may be implemented: Determine the DRT graph of the lithium-ion battery at different impedances, and determine the DRT data based on the DRT graph; Analyze the surface morphology of SEI film and determine the parameter data of SEI film; Performing correlation analysis on the DRT data and the SEI film parameter data to obtain a correlation analysis result, and selecting first characteristic data that meets a preset condition according to the correlation result; A SEI film growth state prediction model is constructed based on the first characteristic data, and the SEI film growth state of the lithium ion battery is predicted based on the SEI film growth state prediction model.

[0060] It should be understood that: when the processor 401 executes the lithium-ion battery SEI film growth state prediction program in the memory 402, in addition to the above functions, other functions can also be implemented. For details, please refer to the description of the corresponding method embodiment above.

[0061] Furthermore, the embodiment of the present invention does not specifically limit the type of the electronic device 400 mentioned, and the electronic device 400 may be a portable electronic device such as a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, etc. Exemplary embodiments of portable electronic devices include but are not limited to portable electronic devices equipped with IOS, Android, Microsoft or other operating systems. The above-mentioned portable electronic devices may also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the present invention, the electronic device 400 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0062] Accordingly, an embodiment of the present application also provides a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the program or instructions are executed by a processor, the steps or functions in the lithium-ion battery SEI film growth state prediction method provided by the above-mentioned method embodiments can be implemented.

[0063] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0064] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.

Claims

1. A method for predicting the growth state of SEI film of lithium-ion battery, characterized in that: include: Determine a DRT diagram of a lithium-ion battery at different impedances, and determine DRT data based on the DRT diagram; Analyze the surface morphology of SEI film and determine the parameter data of SEI film; Performing a correlation analysis on the DRT data and the SEI film parameter data to obtain a correlation analysis result, and selecting first characteristic data that meets a preset condition according to the correlation result; A SEI film growth state prediction model is constructed based on the first characteristic data, and the SEI film growth state of the lithium-ion battery is predicted based on the SEI film growth state prediction model.

2. The method for predicting the growth state of SEI film of lithium ion battery according to claim 1, characterized in that: The method of establishing a DRT diagram under different impedances of lithium ions includes: Measure the electrochemical impedance spectroscopy of lithium-ion batteries at different SOC and charge and discharge cycle numbers; The DRT diagram of the lithium-ion battery at different impedances is determined based on the electrochemical impedance spectroscopy.

3. The method for predicting the growth state of a lithium ion SEI film according to claim 2, characterized in that: The DRT data includes the minimum time constant and the cathode internal resistance of lithium-ion batteries , the determining of DRT data based on the DRT graph comprises: Determine the characteristic peak of the DRT diagram, and determine the minimum time constant with the lowest impact on SOC and charge and discharge cycle number based on the characteristic peak of the DRT diagram ; Determine the DRT distribution function based on the DRT diagram, and determine the area surrounded by the curve corresponding to the DRT distribution function in the DRT diagram and the characteristic peak as the cathode internal resistance of the lithium ion battery. .

4. The method for predicting the growth state of SEI film of lithium ion battery according to claim 1, characterized in that: The analysis of the surface morphology of the SEI film of the lithium-ion battery to determine the parameter data of the SEI film of the lithium-ion battery includes: The SEM image and TEM image of the SEI film of the lithium-ion battery are obtained, and the SEM image and TEM image are quantified based on a preset image processing software to obtain the roughness, thickness and grain size of the SEI film of the lithium-ion battery.

5. The method for predicting the growth state of SEI film of lithium ion battery according to claim 1, characterized in that: The performing correlation analysis on the DRT data and the lithium ion SEI film parameter data to obtain the correlation analysis result includes: The DRT data and the lithium ion SEI film parameter data are used as the second characteristic data, and the remaining battery life, the cathode resistance of the lithium battery and the battery voltage are used as the lithium ion battery SEI film growth state parameter data; The Pearson correlation coefficient and the grayscale correlation coefficient are used to perform correlation analysis on the second characteristic data and the SEI film growth state parameter data to obtain a first correlation analysis result and a second correlation analysis result, wherein the first correlation analysis result includes the Pearson correlation coefficient value of each second characteristic data, and the second correlation analysis result includes the grayscale correlation coefficient value of each second characteristic data.

6. The method for predicting the growth state of SEI film of lithium ion battery according to claim 5, characterized in that: The selecting, according to the correlation result, first feature data that meets a preset condition comprises: Determining third feature data having a Pearson correlation coefficient value greater than a first correlation threshold in the first correlation analysis result; Determine fourth feature data whose grayscale correlation coefficient value is greater than a second correlation threshold value in the second correlation analysis result; The first feature data is determined according to the third feature data and the fourth feature data.

7. The method for predicting the growth state of a lithium ion SEI film according to claim 1, characterized in that: The lithium ion SEI film growth state prediction model is built based on the LightGBM algorithm; The LightGBM algorithm includes: in, is the objective function, is the loss function, For the front The result of round iteration, Ω is the regularization term, For the A tree, is the predicted target value.

8. A device for predicting the growth state of SEI film of a lithium-ion battery, characterized in that: include: A DRT data determination module, used to determine a DRT graph of a lithium-ion battery under different impedances, and determine DRT data based on the DRT graph; SEI film parameter data determination module, used to analyze the surface morphology of the SEI film and determine the SEI film parameter data; A correlation analysis module, used for performing correlation analysis on the DRT data and the SEI film parameter data to obtain a correlation analysis result, and selecting first characteristic data that meets a preset condition according to the correlation result; A prediction module is used to construct a SEI film growth state prediction model based on the first characteristic data, and predict the SEI film growth state of the lithium-ion battery based on the SEI film growth state prediction model.

9. An electronic device, characterized in that: comprising a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the method for predicting the growth state of the SEI film of a lithium-ion battery as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps in the method for predicting the growth state of the SEI film of a lithium-ion battery as described in any one of claims 1 to 7.

Images