A lithium battery health status assessment method and system based on AI algorithm

Abstract

The present invention relates to the technical field of lithium battery health assessment, and specifically to a lithium battery health status assessment method and system based on an AI algorithm. The method comprises the following steps: obtaining battery data and aging mechanism parameters based on a pulse curve and an input current; calculating the battery available capacity based on the battery aging mechanism parameters; collecting daily battery data and training a support vector machine (SVM) model in combination with the aging mechanism parameters; and calculating the remaining available days of the battery and the recommended replacement days based on the SVM model. The battery available capacity is thus calculated based on the battery aging mechanism parameters, and a user can intuitively view the battery health status while making predictions on the remaining available days and the recommended replacement days. The remaining life and replacement date are predicted based on the user's habits and available capacity, thereby ensuring the accuracy of the prediction so that staff can perform regular maintenance or replacement, and avoid the lithium battery not being replaced for a long time and having a poor health status that affects the user experience.

Description

Technical Field

[0001] The present invention relates to the technical field of lithium battery health assessment, and in particular to a lithium battery health status assessment method and system based on an AI algorithm. Background Art

[0002] With the increasing demand for electrochemical energy storage in new power systems, lithium-ion battery energy storage systems must consist of hundreds or even thousands of battery cells connected in series and parallel to meet the voltage and power requirements of these energy storage systems. Large-scale battery systems may consist of stacks of varying types, magnitudes, and generations. This can lead to more pronounced inconsistencies in system parameters and performance, leading to even more significant differences in the rate of cell life degradation. Lithium-ion battery life degradation is a dynamic electrochemical process, primarily driven by loss of active lithium, loss of active materials, and polarization losses.

[0003] In the aforementioned prior art, in order to improve the safety of lithium batteries, the safety status of lithium batteries is usually tested. However, in terms of the health status of lithium batteries, there is a lack of functions to predict the remaining useful life of lithium batteries and the specific date on which replacement is required. As a result, the staff will not know how to maintain or replace the lithium batteries, which affects the user experience of the lithium batteries. Summary of the Invention

[0004] The purpose of the present invention is to provide a lithium battery health status assessment method and system based on AI algorithm to solve the problem that in order to improve the safety of lithium batteries in the prior art, the safety status of lithium batteries is usually detected, but in terms of the health status of lithium batteries, there is a lack of function to predict the remaining useful life of lithium batteries and the specific date on which replacement is required. Therefore, it will cause staff to not know how to maintain or replace lithium batteries, affecting the lithium battery usage experience.

[0005] To achieve the above objectives, the present invention provides a lithium battery health status assessment method based on AI algorithm, which obtains battery data and aging mechanism parameters based on pulse curve and input current;

[0006] Calculate the battery available capacity based on the battery aging mechanism parameters;

[0007] Collect daily battery data and train an SVM model based on the aging mechanism parameters.

[0008] The remaining usable days of the battery and the recommended replacement days are calculated based on the SVM model.

[0009] Among them, in the step of calculating the battery available capacity based on the battery aging mechanism parameters:

[0010] Conduct sensitivity analysis on aging mechanism parameters to obtain sensitivity parameters;

[0011] Based on the sensitivity parameters, identification parameters of four aging mechanism parameters are obtained;

[0012] Combining the four identification parameters, the available battery capacity is calculated in real time.

[0013] The steps of collecting daily battery data and training an SVM model based on the aging mechanism parameters specifically include:

[0014] Collect data on daily usage habits;

[0015] Perform data preprocessing on the collected daily data, aging mechanism parameters and identification data;

[0016] 70% of the data is randomly selected to construct the training set, and the remaining 30% of the data is used to construct the test set;

[0017] Use SVM to map the dataset into a high-dimensional space through a radial basis function kernel to find the optimal hyperplane;

[0018] Set the parameters of SVM based on the hyperplane;

[0019] The SVM model is trained using the training set data, the selected function kernel and the set parameters.

[0020] The step of calculating the remaining useful days of the battery and the recommended replacement days based on the SVM model specifically includes:

[0021] Perform real-time battery testing to obtain battery capacity data;

[0022] Preprocess the battery capacity data to make it the same format as the training set data;

[0023] Inputting the battery capacity data into the SVM model;

[0024] The SVM model calculates the predicted value of the daily battery consumption capacity based on the representation of the input battery capacity data in the high-dimensional space and the position of the optimal hyperplane;

[0025] Divide the battery available capacity by the predicted value of the battery daily consumption capacity to obtain a remaining available predicted range and a recommended replacement predicted range;

[0026] Repeat the calculation of the four prediction ranges of the remaining available prediction range and the recommended replacement prediction range, and take the average value to obtain the remaining available days and the recommended replacement days respectively.

[0027] The step of performing sensitivity analysis on the aging mechanism parameters to obtain sensitivity parameters specifically includes:

[0028] Select the data when the battery is in a good health state as the benchmark point, and record the four battery mechanism parameters and the corresponding battery performance indicators;

[0029] Select a battery mechanism parameter, and use a value range of ±5% as a variation, and change the value of the aging mechanism parameter based on the variation;

[0030] Keeping other battery mechanism parameters unchanged, change the value of each battery mechanism parameter one by one, and observe the change value of battery performance index;

[0031] The change value of the battery performance index when each mechanism parameter changes is recorded to obtain the sensitivity parameter.

[0032] The step of preprocessing the collected daily data, aging mechanism parameters and identification data specifically includes:

[0033] Statistical methods were used to determine outliers, duplicate values, and missing values, and outliers and duplicate values ​​were deleted from the data;

[0034] Interpolation is used to fill in missing data points;

[0035] The data were transformed to a standard normal distribution by subtracting the mean and dividing by the standard deviation.

[0036] The present invention also provides a lithium battery health status assessment system based on an AI algorithm, which adopts the lithium battery health status assessment method based on an AI algorithm described above, including a current input module, an available capacity calculation module, a model building module, and a day prediction module;

[0037] The current input module is used to obtain battery data and aging mechanism parameters based on the pulse curve and input current;

[0038] The available capacity calculation module is used to calculate the available capacity of the battery according to the battery aging mechanism parameters;

[0039] The model building module is used to collect daily battery data and train an SVM model based on the aging mechanism parameters;

[0040] The days prediction module is used to calculate the remaining usable days of the battery and the recommended replacement days based on the SVM model.

[0041] The present invention provides a lithium battery health status assessment method and system based on an AI algorithm. The method obtains battery data and aging mechanism parameters based on a pulse curve and input current; calculates the battery's available capacity based on the battery aging mechanism parameters; collects daily battery data and trains a support vector machine (SVM) model based on the aging mechanism parameters; and calculates the remaining usable days and recommended replacement days of the battery based on the SVM model.

[0042] The battery's available capacity is calculated based on the battery aging mechanism parameters. Users can intuitively view the battery's health status and make predictions on the remaining usable days and recommended replacement days. The remaining life and replacement date are predicted based on the user's habits and available capacity to ensure the accuracy of the prediction, so that staff can perform regular maintenance or replacement to avoid the lithium battery not being replaced for a long time and its health condition being too poor, affecting the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art.

[0044] Figure 1 This is a curve diagram of the staged multi-pulse charging current of the present invention.

[0045] Figure 2 This is a sensitivity analysis diagram of the battery electrochemical aging parameters of the present invention.

[0046] Figure 3 This is a flowchart of the steps of the lithium battery health status assessment method based on AI algorithm of the present invention.

[0047] Figure 4 The present invention is a flowchart of the steps of calculating the available capacity of a battery based on the battery aging mechanism parameters.

[0048] Figure 5 This is a flowchart of the steps of collecting daily battery data, combining it with the aging mechanism parameters, and training an SVM model.

[0049] Figure 6 This is a flow chart of the steps of calculating the remaining usable days of the battery and the recommended replacement days based on the SVM model of the present invention.

[0050] Figure 7 This is a flow chart of the steps of performing sensitivity analysis on aging mechanism parameters and obtaining sensitivity parameters according to the present invention.

[0051] Figure 8 It is a flow chart of the steps of preprocessing the collected daily data, aging mechanism parameters and identification data of the present invention. DETAILED DESCRIPTION

[0052] The embodiments of the present invention are described in detail below. Examples of the embodiments are shown in the accompanying drawings. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, but should not be understood as limiting the present invention.

[0053] See also Figures 1 to 8The present invention provides a lithium battery health status assessment method based on an AI algorithm, comprising the following steps:

[0054] S101: Obtain battery data and aging mechanism parameters based on the pulse curve and input current;

[0055] The pulse curve refers to the staged multi-pulse charging current curve diagram in the attached figure of this application, with an input current length of 1000 s and a maximum charging current of 1.6 C; the battery data includes voltage and temperature, and the aging mechanism parameters include the maximum lithium ion concentration of the battery negative electrode, the maximum lithium ion concentration of the battery positive electrode, the percentage of active materials in the battery negative electrode, and the percentage of active materials in the battery positive electrode.

[0056] S102: Calculating the battery available capacity based on the battery aging mechanism parameters;

[0057] Specifically include:

[0058] S1021: Perform sensitivity analysis on aging mechanism parameters to obtain sensitivity parameters;

[0059] Specifically include:

[0060] S10211: Select the data when the battery is in a good health state as the benchmark point, and record the four battery mechanism parameters and the corresponding battery performance indicators;

[0061] By recording the mechanical parameters and performance indicators of a battery in good health, a standard reference range can be established. This facilitates subsequent monitoring and evaluation of the battery's status, ensuring it remains in optimal working condition. This baseline data can be used to assess the battery's current performance. By comparing it with the baseline data, degradation or abnormality in battery performance can be detected promptly, allowing appropriate maintenance or replacement measures to be taken.

[0062] S10212: Select a battery mechanism parameter, and use a value range of ±5% as a variation, and change the value of the aging mechanism parameter based on the variation;

[0063] Assume that the initial capacity of the battery in good health is C0. Using a ±5% range as the variation, the battery capacity can vary between 95% (C0-5%C0) and 105% (C0+5%C0) of C0.

[0064] S10213: keeping other battery mechanism parameters unchanged, changing the value of each battery mechanism parameter one by one, and observing the change value of the battery performance index;

[0065] By varying the values ​​of battery mechanism parameters one by one, significant changes can be observed in battery performance indicators (such as energy density, power density, and cycle life). These changes reflect the direct impact of parameter adjustments on battery performance. Based on the experimental results of the controlled variable method, battery design can be optimized. The optimized battery typically exhibits significant improvements in performance indicators.

[0066] S10214: Record the change value of the battery performance index when each mechanism parameter changes to obtain the sensitivity parameter.

[0067] The changes in the battery performance indicators in the above steps are recorded in sequence, and the sensitivity of each parameter is finally obtained, referring to the battery electrochemical aging parameter sensitivity analysis diagram of this application.

[0068] S1022: Perform identification based on the sensitivity parameters to obtain identification parameters of four aging mechanism parameters;

[0069] Based on the electrochemical principle equation of the battery, combined with known conditions such as voltage, current, and temperature, the sensitive parameters are calculated in sequence. The parameter calculation objective function is as follows, that is, by finding a set of optimal parameter solutions, the error between the measured terminal voltage and the model terminal voltage is minimized:

[0070] Where θ * — Optimal parameter set, by minimizing the experimental voltage With analog voltage The goal is to find a set of parameters that minimizes the sum of squared errors between the experimental data and the model predictions.

[0071] — Maximum lithium ion concentration of the negative electrode material;

[0072] — The effective volume fraction of the negative electrode, which indicates the proportion of active material in the negative electrode.

[0073] — Maximum lithium ion concentration of the cathode material;

[0074] — The effective volume fraction of the positive electrode, which indicates the proportion of active material in the positive electrode.

[0075] S1023: Calculate the available battery capacity in real time by combining the four identification parameters.

[0076] The battery capacity calculation formula is as follows:

[0077] Formula for calculating negative electrode capacity:

[0078]

[0079] Among them, Q neg — is the capacity of the negative electrode, Ah;

[0080] A—plate area;

[0081] F—Faraday constant;

[0082] L neg —Thickness of negative electrode plate;

[0083] —Electrochemical equivalent change value of the negative electrode.

[0084] Calculate the positive electrode capacity:

[0085]

[0086] Among them, Q pos — is the capacity of the positive electrode, Ah;

[0087] A—plate area;

[0088] F—Faraday constant;

[0089] L pos —Thickness of the positive electrode plate;

[0090] —Electrochemical equivalent change value of the positive electrode.

[0091] The actual maximum available capacity of the battery is the smaller of the two: ;

[0092] Combining four electrochemical calculation parameters ( ), the available battery capacity can be calculated in real time.

[0093] S103: Collect daily battery data and train an SVM (support vector machine) model based on the aging mechanism parameters.

[0094] Specifically include:

[0095] S1031: Collect daily usage habit data;

[0096] Daily habit data includes battery usage records, usage duration, usage behavior, usage intensity, ambient temperature and humidity, and discharge amount. Collecting a large amount of habit data can effectively reflect the user's daily usage habits and behaviors, and thus more accurately predict the final remaining battery life.

[0097] S1032: Preprocessing the collected daily data, aging mechanism parameters, and identification data;

[0098] Specifically include:

[0099] S10321: Use statistical methods to identify outliers, duplicates, and missing values, and remove outliers and duplicates from the data;

[0100] Outliers are data points in a dataset that deviate significantly from other observations. These values ​​may arise due to measurement error, data entry errors, natural variation, or extreme events. Statistical methods identify outliers by calculating the data's distribution characteristics (mean), setting thresholds, or using graphical tools such as boxplots. They also compare records in a dataset to identify records that are identical or partially identical, improving data accuracy and consistency.

[0101] S10322: Use interpolation to fill in missing data points;

[0102] Using two known data points, a straight line is constructed to estimate missing data. The calculation formula is: y = y1 +(y2 - y1) / (x2 - x1) × (x - x1), where y1 and y2 are the values ​​of the known data points, x1 and x2 are the independent variable values ​​corresponding to the known data points, x is the independent variable value corresponding to the missing data, and y is the missing data value estimated by linear interpolation. This can effectively fill in the missing data, making the dataset more complete, thereby meeting the needs of data analysis, modeling, and visualization. It can also reduce gaps and noise in the data and improve the accuracy and reliability of the data.

[0103] S10323: Transform the data to a standard normal distribution by subtracting the mean and dividing by the standard deviation.

[0104] Standardizing data helps eliminate the dimensionality of data, allowing different features to be compared on the same scale. Standardized data has a uniform scale and distribution, which helps improve the accuracy of data analysis. Standard normal distribution data has a mean of 0 and a standard deviation of 1, which makes comparison and analysis between data points more intuitive and convenient.

[0105] The principle of converting data to a standard normal distribution is based on a linear transformation, which involves subtracting the mean from each value of the original data and dividing it by the standard deviation. The core idea of ​​this method is to adjust the position and scale of the data so that the converted data follows a standard normal distribution with a mean of 0 and a standard deviation of 1. The conversion formula is:

[0106] Z = (X - μ) / σ

[0107] Where Z is the random variable of the transformed standard normal distribution, X is the random variable of the original data, μ is the mean of the original data, and σ is the standard deviation of the original data.

[0108] S1033: Randomly extract 70% of the data to construct the training set, and the remaining 30% of the data to construct the test set;

[0109] By dividing the dataset into two, the algorithm can be trained and tested on independent datasets, thereby evaluating its generalization performance. Random sampling ensures the independence of the training and test sets, avoiding the risk of data leakage. The training set is used to train the model, and the test set is used to test the model. By evaluating the performance of the algorithm on an independent test set, more accurate and reliable evaluation results can be obtained. This helps algorithm developers understand the strengths and weaknesses of the algorithm and make targeted optimizations and improvements.

[0110] S1034: Use SVM to map the dataset into a high-dimensional space using a radial basis function kernel to find the optimal hyperplane;

[0111] The radial basis function (RBF) kernel is a commonly used kernel function in support vector machines (SVMs). It maps samples in the input space to a high-dimensional feature space, enabling nonlinear classification and regression. For each training sample, the distance between it and other samples is calculated, and the kernel value is calculated according to the kernel function definition. These kernel values ​​form a kernel matrix, which is used in subsequent classification or regression tasks. In the feature space, the SVM algorithm solves a quadratic programming problem to find the optimal hyperplane. This hyperplane maximizes the margin between different classes, thereby improving classification accuracy and generalization. Once the optimal hyperplane is found, it can be used to classify new input samples. For a given input sample, the distance to the hyperplane is calculated, and the sign of the distance determines the sample's class.

[0112] S1035: Setting the parameters of the SVM based on the hyperplane;

[0113] The SVM parameter settings directly affect the position and shape of the hyperplane. For example, the penalty parameter C and the kernel function parameters (such as the gamma parameter of the RBF kernel) both affect the decision boundary of the hyperplane. The penalty parameter C controls the degree of penalty for misclassified samples. A larger C value increases the penalty for misclassification, which may cause the hyperplane to fit the training data more closely but may reduce generalization ability. A smaller C value reduces the penalty for misclassification, allows for a certain error, and may improve generalization ability. By carefully setting the SVM parameters, an optimal hyperplane can be found to maximize classification accuracy.

[0114] S1036: Train an SVM model using the training set data, the selected function kernel, and the set parameters.

[0115] The SVM model is trained for subsequent prediction of the remaining available days.

[0116] S104: Calculate the remaining usable days of the battery and the recommended replacement days based on the SVM model.

[0117] Specifically include:

[0118] S1041: Perform real-time testing on the battery to obtain battery capacity data;

[0119] The battery can more comprehensively reflect the current usage of the battery by collecting a large amount of data, thereby improving the accuracy of subsequent prediction days.

[0120] S1042: Preprocess the battery capacity data to make it the same format as the training set data;

[0121] By applying the same processing method to the battery capacity data as to the daily habit data, outliers and duplicates are removed, and missing values ​​are filled, reducing errors and uncertainties during model training and improving the model's accuracy and generalization capabilities. The processed data is formatted consistently and of high quality, accelerating model training. Furthermore, through techniques such as feature extraction and data augmentation, the time and resources required for model training can be further reduced, helping to improve model performance.

[0122] S1043: Inputting the battery capacity data into the SVM model;

[0123] The above preprocessed data is input and subsequent model calculations are performed to obtain the predicted value.

[0124] S1044: The SVM model calculates a predicted value of the daily battery consumption capacity based on the representation of the input battery capacity data in the high-dimensional space and the position of the optimal hyperplane;

[0125] After training, the SVM model has mastered the laws and characteristics of the battery. At this time, the latest battery capacity data is input, and then the representation in high-dimensional space and the position of the optimal hyperplane are calculated to obtain the predicted value of the battery daily consumption capacity.

[0126] S1045: Divide the battery available capacity by the predicted value of the battery daily consumption capacity to obtain a remaining available predicted range and a recommended replacement predicted range;

[0127] Divide the battery available capacity obtained by the above formula by the predicted value of the battery daily consumption capacity predicted by the above model to obtain the remaining available prediction range, that is, the remaining available days. Arrange the remaining available days in reverse order to obtain the recommended replacement prediction range, that is, it is recommended to replace it on a certain day in the future.

[0128] S1046: Repeatedly calculate the four prediction ranges of the remaining available prediction range and the recommended replacement prediction range, and take the average value to obtain the remaining available days and the recommended replacement days respectively.

[0129] The above-mentioned range calculation method is repeated four times, and the average values ​​within the four ranges of the remaining available prediction range and the recommended replacement prediction range are taken respectively, so that the obtained number of days is more accurate and avoids excessive deviation; the obtained remaining available days indicates how many days the battery can be used according to the current user's usage habits; the obtained recommended replacement days indicates on which day in the future the battery needs to be replaced according to the current user's usage habits, otherwise the battery health will decline and the performance will be greatly reduced.

[0130] The present invention also provides a lithium battery health status assessment system based on an AI algorithm, which adopts the lithium battery health status assessment method based on the AI ​​algorithm, including a current input module, an available capacity calculation module, a model construction module and a day prediction module; the current input module is used to obtain battery data and aging mechanism parameters based on the pulse curve and input current; the available capacity calculation module is used to calculate the battery available capacity according to the battery aging mechanism parameters; the model construction module is used to collect daily battery data and train an SVM model in combination with the aging mechanism parameters; the day prediction module is used to calculate the remaining available days of the battery and the recommended replacement days based on the SVM model.

[0131] The current input module is used to obtain battery data and aging mechanism parameters based on the pulse curve and input current. The pulse curve refers to the staged multi-pulse charging current curve diagram in the accompanying drawings of this application, with an input current length of 1000 s and a maximum charging current of 1.6 C. The battery data includes voltage and temperature, and the aging mechanism parameters include the maximum lithium ion concentration of the battery negative electrode, the maximum lithium ion concentration of the battery positive electrode, the percentage of active material in the battery negative electrode, and the percentage of active material in the battery positive electrode. The available capacity calculation module is used to calculate the battery available capacity based on the battery aging mechanism parameters. A sensitivity analysis is performed on the aging mechanism parameters to obtain sensitivity parameters. The data when the battery is in a good health state is selected as the benchmark point. The four battery mechanism parameters and corresponding battery performance indicators are recorded. By recording the mechanism parameters and performance indicators of the battery in a good health state, a standard reference range can be established. This helps in the subsequent monitoring and evaluation of the battery status, ensuring that the battery always maintains the best working condition; these benchmark data can be used to evaluate the current performance status of the battery, select a battery mechanism parameter, and use the value range of ±5% as the variation, based on the variation, change the value of the aging mechanism parameter, keep other battery mechanism parameters unchanged, change the value of each battery mechanism parameter one by one, and observe the change value of the battery performance index; when changing the value of the battery mechanism parameter one by one, it will be found that the battery performance indicators (such as energy density, power density, cycle life, etc.) change significantly. These changes reflect the direct impact of parameter adjustment on battery performance. Record the change value of the battery performance index when each mechanism parameter changes to obtain the sensitivity parameter; identify based on the sensitivity parameter, obtain the identification parameters of the four aging mechanism parameters, and finally calculate the battery available capacity in real time. The model construction module is used to collect daily battery data and train an SVM model in combination with the aging mechanism parameters; collect daily usage habit data; perform data preprocessing on the collected daily data, aging mechanism parameters and identification data, use statistical methods to determine outliers, duplicate values ​​and missing values, and delete outliers and duplicate values ​​from the data, use interpolation to fill data points with missing values, and convert the data into a standard normal distribution by subtracting the mean and dividing by the standard deviation; achieve data standardization, which helps to eliminate the dimensional influence of the data so that different features can be compared on the same scale; the standardized data has a uniform scale and distribution characteristics, which helps to improve the accuracy of data analysis, randomly extract 70% of the data to construct a training set, and the remaining 30% of the data to construct a test set, use SVM, map the data set to a high-dimensional space through a radial basis function kernel to find the optimal hyperplane, set the SVM parameters based on the hyperplane, and train the SVM model using the training set data, the selected function kernel and the set parameters.The days prediction module is used to calculate the remaining usable days of the battery and the recommended replacement days based on the SVM model; after training, the SVM model has mastered the laws and characteristics of the battery. At this time, the latest battery capacity data is input, and then the representation in the high-dimensional space and the position of the optimal hyperplane are calculated to obtain the battery daily consumption capacity prediction value; the battery available capacity is divided by the battery daily consumption capacity prediction value to obtain the remaining usable prediction range and the recommended replacement prediction range; the four prediction ranges of the remaining usable prediction range and the recommended replacement prediction range are repeatedly calculated, and the average value is taken to obtain the remaining usable days and the recommended replacement days respectively.

[0132] The above disclosure is merely one or more preferred embodiments of the present application and is not intended to limit the scope of the present application. A person skilled in the art will understand that all or part of the processes of the above embodiments and equivalent changes made in accordance with the claims of the present application are still within the scope of the present application.

Claims

1. A lithium battery health status assessment method based on AI algorithm, characterized in that: The steps include: Based on the pulse curve and input current, obtain battery data and aging mechanism parameters; Calculate the battery available capacity based on the battery aging mechanism parameters; Collect daily battery data and train an SVM model based on the aging mechanism parameters. Calculate the remaining useful days of the battery and the recommended replacement days based on the SVM model; The step of calculating the remaining useful days of the battery and the recommended replacement days based on the SVM model specifically includes: Perform real-time battery testing to obtain battery capacity data; Preprocess the battery capacity data to make it the same format as the training set data; Inputting the battery capacity data into the SVM model; The SVM model calculates the predicted value of the daily battery consumption capacity based on the representation of the input battery capacity data in the high-dimensional space and the position of the optimal hyperplane; Divide the battery available capacity by the predicted value of the battery daily consumption capacity to obtain a remaining available predicted range and a recommended replacement predicted range; Repeat the calculation of the four prediction ranges of the remaining available prediction range and the recommended replacement prediction range, and take the average value to obtain the remaining available days and the recommended replacement days respectively.

2. The lithium battery health status assessment method based on AI algorithm according to claim 1, characterized in that: The step of calculating the battery available capacity based on the battery aging mechanism parameters specifically includes: Conduct sensitivity analysis on aging mechanism parameters to obtain sensitivity parameters; Based on the sensitivity parameters, identification parameters of four aging mechanism parameters are obtained; Combining the four identification parameters, the available battery capacity is calculated in real time.

3. The lithium battery health status assessment method based on AI algorithm according to claim 2, characterized in that: The steps of collecting daily battery data and training an SVM model based on the aging mechanism parameters specifically include: Collect data on daily usage habits; Perform data preprocessing on the collected daily data, aging mechanism parameters and identification data; 70% of the data is randomly selected to construct the training set, and the remaining 30% of the data is used to construct the test set; Use SVM to map the dataset into a high-dimensional space through a radial basis function kernel to find the optimal hyperplane; Set the parameters of SVM based on the hyperplane; The SVM model is trained using the training set data, the selected function kernel and the set parameters.

4. The lithium battery health status assessment method based on AI algorithm according to claim 3, characterized in that: The step of performing sensitivity analysis on the aging mechanism parameters to obtain sensitivity parameters specifically includes: Select the data when the battery is in a good health state as the benchmark point, and record the four battery mechanism parameters and the corresponding battery performance indicators; Select a battery mechanism parameter, and use a value range of ±5% as a variation, and change the value of the aging mechanism parameter based on the variation; Keeping other battery mechanism parameters unchanged, change the value of each battery mechanism parameter one by one, and observe the change value of battery performance index; The change value of the battery performance index when each mechanism parameter changes is recorded to obtain the sensitivity parameter.

5. The lithium battery health status assessment method based on AI algorithm according to claim 4, characterized in that: The steps of preprocessing the collected daily data, aging mechanism parameters and identification data specifically include: Statistical methods were used to determine outliers, duplicate values, and missing values, and outliers and duplicate values ​​were deleted from the data; Interpolation is used to fill in missing data points; The data were transformed to a standard normal distribution by subtracting the mean and dividing by the standard deviation.

6. A lithium battery health status assessment system based on an AI algorithm, using the lithium battery health status assessment method based on an AI algorithm as claimed in claim 5, characterized in that: It includes current input module, available capacity calculation module, model building module and days prediction module; The current input module is used to obtain battery data and aging mechanism parameters based on the pulse curve and input current; The available capacity calculation module is used to calculate the available capacity of the battery according to the battery aging mechanism parameters; The model building module is used to collect daily battery data and train an SVM model based on the aging mechanism parameters; The days prediction module is used to calculate the remaining usable days of the battery and the recommended replacement days based on the SVM model.

Images