Lithium ion battery SOH estimation method based on impedance feature selection and optimization support vector regression
By adopting impedance feature selection and optimization support vector regression methods in lithium-ion batteries, the problem of feature subset selection in full-band EIS data is solved, efficient and accurate prediction of battery SOH is achieved, and the accuracy and application of battery health status monitoring is improved. efficiency.
Patent Information
- Application Number
- CN202411050524.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-01
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2044-08-01
AI Technical Summary
The prior art is difficult to select a subset of features closely related to lithium-ion battery SOH from the full-band EIS data, resulting in a long feature measurement time, difficult model training and low prediction accuracy, making it difficult to achieve accurate prediction of SOHs of different batteries.
Using the method of impedance feature selection and optimization of support vector regression, the impedance features are selected through the sequence forward search algorithm, combined with the multi-objective decision-making method to optimize the hyperparameters of the support vector regression model by using the sparrow search algorithm to construct Sine-SSA- SVR model to achieve accurate estimation of battery SOH.
It effectively reduces the characteristic measurement time, improves the prediction accuracy of the battery SOH, can accurately track the decay trajectory of lithium-ion batteries, and exhibits good generalization and prediction effects under different temperature conditions.
Smart Images

Figure CN118980954A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of power batteries, and in particular to a lithium-ion battery SOH estimation method based on impedance feature selection and optimized support vector regression. Background Art
[0002] Lithium batteries have the advantages of long life, fast charging speed and no memory effect. They have become the first choice for energy storage in pure electric vehicles and hybrid electric vehicles. However, as the number of charge and discharge cycles increases, the performance of lithium batteries will gradually decline, mainly manifested in an increase in internal resistance and a decrease in available capacity. Therefore, accurately estimating the state of health (SOH) of the battery during use is crucial to ensure the efficient operation and safety of the battery.
[0003] Electrochemical impedance spectroscopy contains a wealth of information about the material properties, interface phenomena, and electrochemical reactions inside the battery, and reflects the aging state of the battery from multiple angles. It is considered to be an effective means to achieve accurate SOH estimation. The data-driven estimation method does not require the construction of a complex battery model. It can autonomously learn the nonlinear relationship between the battery SOH and external characteristics through the measured real impedance, imaginary impedance, phase angle and other data. It has high transferability, robustness and generalization. However, directly using full-frequency EIS data as input increases the difficulty of model training, and the presence of irrelevant features will reduce the accuracy of the model. In addition, it takes a lot of time to carry out full-band EIS measurements, making practical applications difficult. Therefore, how to select a subset of features closely related to the battery SOH from the full-band EIS data, greatly reduce the feature measurement time, improve the prediction accuracy of the power battery SOH, and achieve accurate prediction of the SOH of different batteries is an urgent problem to be solved. Summary of the invention
[0004] 1. Technical issues to be resolved
[0005] In view of the shortcomings of the prior art, the present invention provides a lithium-ion battery SOH estimation method based on impedance feature selection and optimized support vector regression, which has the advantages of accurate estimation of battery SOH and solves the above technical problems.
[0006] (II) Technical solution
[0007] To achieve the above object, the present invention provides the following technical solution: a lithium-ion battery SOH estimation method based on impedance feature selection and optimized support vector regression, comprising the following steps:
[0008] S1. Data collection: Aging impedance experiments are performed on different lithium-ion batteries under different temperature conditions until the battery discharge capacity is less than 70% of the initial capacity. The battery charge and discharge and electrochemical impedance spectrum data are recorded in real time, including charge and discharge cycle data and impedance under different aging conditions.
[0009] S2. Data processing and feature extraction: pre-process the charge and discharge data and electrochemical impedance spectrum data obtained in step S1; analyze the relationship between electrochemical impedance and battery aging, select impedance features based on the sequence forward search algorithm, and apply the multi-objective decision-making method to optimize the feature subset obtained by the sequence forward search to obtain impedance features and SOH data.
[0010] S3. Based on the radial basis kernel function, select the penalty coefficient, insensitive loss function parameters and kernel function parameters to build a support vector regression model.
[0011] S4. Sparrow search algorithm model hyperparameter optimization: Apply the sparrow search algorithm to the support vector regression model hyperparameter optimization to optimize the support vector regression model.
[0012] S5. The random initialization process of the initial value of the sparrow algorithm is replaced by the chaos of the Sine chaotic map, and the optimized support vector regression model is trained based on the data set obtained in step S2 to obtain a trained Sine-SSA-SVR model.
[0013] S6. Single cell SOH estimation: Based on the Sine-SSA-SVR model obtained in step S5, the SOH of the lithium-ion battery is estimated by inputting impedance characteristics.
[0014] As a preferred technical solution of the present invention, the process of battery charging and discharging in the data collected in step S1 is: in the charging stage, first charge at a constant current of 1C rate to a cut-off voltage of 4.2V, then charge at a constant voltage of 0.1C, and finally stand for 15 minutes; in the discharging stage, discharge at a constant current of 2C rate to a lower cut-off voltage of 3V, and then stand for 15 minutes.
[0015] As a preferred technical solution of the present invention, the specific expression of the support vector regression model in step S3 is as follows:
[0016]
[0017] Among them, ω and b represent the weight vector and bias term of the support vector regression model respectively, x represents the input variable, is the predicted output function corresponding to the input x, and by introducing the Lagrange multiplier, the above formula can be transformed into a convex quadratic optimization problem, where the dual function and constraints are:
[0018]
[0019]
[0020] in, is the optimization objective function of SVR, ||ω|| 2 is the regularization term, n represents the number of training sample sets, c represents the penalty parameter, ξ j and Represent two different relaxation factors, st represents constraint, x j represents the input feature vector of the jth sample, y j The true target value of the jth sample, the training data set is ε represents the insensitive loss function, and solving the above formula gives the following expression:
[0021]
[0022] Among them, nsv is the number of support vectors, K(x j ,x) represents the kernel function, which is used to calculate the support vector x in high-dimensional space. j The inner product between the current input vector x, α j , is the Lagrange multiplier corresponding to the jth sample, and the specific expression is as follows:
[0023] K(x j ,x)=exp(-g||xx j || 2 )
[0024] Among them, exp(*) represents the exponential function with the natural constant e as the base, g represents the radial basis kernel function parameter, ||xx i || 2 is the input vector x and the support vector x j The square of the Euclidean distance between them.
[0025] As a preferred technical solution of the present invention, the hyperparameter optimization of the sparrow search algorithm model in step S4 is performed by the following expression, specifically:
[0026] Finder's location update:
[0027]
[0028] Location update for joiners:
[0029]
[0030] Vigilante Location Update:
[0031]
[0032] Among them, i represents the index of the current individual, that is, the i-th group of SVR parameters, d represents the dimension of the SVR parameters, They represent the position of the i-th (discoverer, joiner, alerter) on the d-th dimension at time t+1, represents the position of the ith (discoverer, joiner, vigilant) in the dth dimension at time t. α is a positive constant used to control the step size and exponential decay rate in position update. exp(*) represents an exponential function with the natural constant e as the base. max represents the maximum number of iterations, Q is a random number Q~N(0,1) that obeys a normal distribution, L is a random number with a Laplace distribution, which is used to simulate the raid behavior of the discoverer, R2 is a random number R2~U(0,1) that obeys a uniform distribution, ST represents the warning value, It indicates the position of the worst individual in the t-th generation population on the d-th dimension, m indicates the population size, and indicates the number of individuals involved in the optimization process. represents the position of the pth randomly selected individual in the dth dimension at the t+1th generation, It represents the distance between the current individual and the randomly selected individual in the dth dimension. A is a random number A~U(-1,1) that obeys a uniform distribution. l is a constant used to control the step length. is the position of the best individual in the current population, represents the distance between the vigilant and the optimal individual, represents the distance between the vigilant and the worst individual, β is a uniformly distributed random number β~U(0,1), K is a normally distributed random number K~N(0,1), δ is a very small value to prevent the denominator from being 0, f i represents the fitness value of the i-th individual, f g and f w Represent the fitness values of the global optimal and worst individuals respectively.
[0033] Compared with the prior art, the present invention provides a lithium-ion battery SOH estimation method based on impedance feature selection and optimized support vector regression, which has the following beneficial effects:
[0034] The present invention realizes the selection of impedance features based on electrochemical impedance spectroscopy data, utilizes a sequence forward search strategy, and combines a multi-objective decision-making method. The chaotic sparrow search algorithm is applied to the hyperparameter optimization of a support vector regression model to construct a single-cell SOH estimation model, which can effectively track the decay trajectory of the SOH of lithium-ion batteries. Based on full-frequency EIS data, a feature optimization method is adopted to greatly reduce the number of features, remove the interference of irrelevant features, and reduce the EIS feature test time. The optimized support vector regression model established can realize accurate estimation of the battery SOH. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] Figure 1 It is a schematic diagram of the process of the present invention;
[0036] Figure 2 Represents the electrochemical impedance spectrum relationship diagram corresponding to different SOH;
[0037] Figure 3 Result diagram of feature subset optimization based on SFS-MOOA;
[0038] Figure 4 Represents the estimation results and error diagrams of different methods for the same battery;
[0039] Figure 5 It shows the comparison chart of the results and errors of different batteries at different temperatures. DETAILED DESCRIPTION
[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0041] See also Figure 1-Figure 5 , a lithium-ion battery SOH estimation method based on impedance feature selection and optimized support vector regression, comprising the following steps:
[0042] S1. Data collection: Aging impedance experiments were carried out at 25°C, 35°C, and 45°C, respectively. The experiments followed the same charge and discharge process, and each cycle included two parts: charging and discharging. In the charging stage, first charge at a constant current of 1C to a cut-off voltage of 4.2V, then charge at a constant voltage of 0.1C, and finally stand for 15 minutes. In the discharge stage, discharge at a constant current of 2C to a lower cut-off voltage of 3V, and then stand for 15 minutes. Electrochemical impedance spectroscopy tests and capacity tests are performed in an even number of charge and discharge cycles. The battery impedance spectrum is measured when the battery is fully charged and left to stand for 15 minutes. A total of 60 frequencies were selected in the frequency range of 0.02Hz to 20KHz, and the excitation current amplitude was 5mA. When the battery capacity decays to 70% of the initial capacity, the aging experiment is terminated;
[0043] S2. Data processing and feature extraction: The charge-discharge data and electrochemical impedance spectroscopy data obtained in step S1 are preprocessed. The electrochemical impedance spectra under different SOH are as follows: Figure 2 As shown in the figure, as the battery SOH decreases, the EIS curve in the high-frequency region moves to the right as a whole. There are two arcs in the medium-high frequency region and the medium-low frequency region, and as the battery SOH decreases, they show an expanding trend. As the battery cycle aging proceeds, the oxide deposition on the electrode surface becomes thicker, resulting in a decrease in the electrochemical reaction rate. At the same time, lithium precipitation occurs at the negative electrode, causing the real and imaginary parts of the impedance in the low-frequency region to increase as a whole. By analyzing the EIS curve of the battery, it can be found that it contains rich information about battery aging. Based on the battery test data, the impedance of 60 frequencies measured in each cycle is split into the real part of the impedance and the imaginary part of the impedance, and 120 impedance features are obtained. Considering the influence of model accuracy and the number of features on the model, the optimization goal is to minimize the comprehensive score. The sequential forward search algorithm (SFS) is used to select the impedance features, and the feature subsets obtained by the SFS search are optimized based on the multi-objective decision method to obtain the impedance features and SOH data. The feature optimization process is as follows: Figure 3 As shown;
[0044] S3, based on the radial basis kernel function, select the penalty coefficient, insensitive loss function parameters and kernel function parameters to build a support vector regression model (SVR model);
[0045] The specific expression of the support vector regression model is as follows:
[0046]
[0047] Among them, ω and b represent the weight vector and bias term of the support vector regression model respectively, x represents the input variable, is the predicted output function corresponding to the input x, and by introducing the Lagrange multiplier, the above formula can be transformed into a convex quadratic optimization problem, where the dual function and constraints are:
[0048]
[0049]
[0050] in, is the optimization objective function of SVR, ||ω|| 2 is the regularization term, n represents the number of training sample sets, c represents the penalty parameter, ξ j and Represent two different relaxation factors, st represents constraint, x j represents the input feature vector of the jth sample, y j The true target value of the jth sample, the training data set is ε represents the insensitive loss function, and solving the above formula gives the following expression:
[0051]
[0052] Among them, nsv is the number of support vectors, K(x j ,x) represents the kernel function, which is used to calculate the support vector x in high-dimensional space. j The inner product between the current input vector x, α j , is the Lagrange multiplier corresponding to the jth sample, and the specific expression is as follows:
[0053] K(x j ,x)=exp(-g||xx j || 2 )
[0054] Among them, exp(*) represents the exponential function with the natural constant e as the base, g represents the radial basis kernel function parameter, ||xx j || 2 is the input vector x and the support vector x j The square of the Euclidean distance between them.
[0055] S4. Sparrow search algorithm model hyperparameter optimization: Apply the sparrow search algorithm to the support vector regression model hyperparameter optimization to optimize the support vector regression model;
[0056] Hyperparameter optimization of the sparrow search algorithm model: In order to solve the problem of long time and poor effect when optimizing the SVR hyperparameters c, ε and g, the SSA method is used to optimize the hyperparameter optimization process of SVR, and improve the optimization speed and optimization accuracy of the hyperparameters c, ε and g. First, a random hyperparameter combination is generated, and the fitness value is calculated on the validation set using the SVR model and the initial hyperparameter combination. According to the update rule of SSA, the hyperparameter combination of the sparrow individual is adjusted, and the fitness and position update are repeatedly calculated through iterative optimization until the convergence condition is met. Finally, the hyperparameter combination with the best fitness is selected to train the SVR model, and the final SSA-SVR model is obtained, thereby improving the prediction performance of the model.
[0057] The hyperparameter optimization process of the sparrow search algorithm can be abstracted into a discoverer-joiner model, and a detection and early warning mechanism is added;
[0058] Finder's location update:
[0059]
[0060] Location update for joiners:
[0061]
[0062] Vigilante Location Update:
[0063]
[0064] Among them, i represents the index of the current individual, that is, the i-th group of SVR parameters, d represents the dimension of the SVR parameters, They represent the position of the i-th (discoverer, joiner, alerter) on the d-th dimension at time t+1, represents the position of the ith (discoverer, joiner, vigilant) in the dth dimension at time t. α is a positive constant used to control the step size and exponential decay rate in position update. exp(*) represents an exponential function with the natural constant e as the base. max represents the maximum number of iterations, Q is a random number Q~N(0,1) that obeys a normal distribution, L is a random number with a Laplace distribution, which is used to simulate the raid behavior of the discoverer, R2 is a random number R2~U(0,1) that obeys a uniform distribution, ST represents the warning value, It indicates the position of the worst individual in the t-th generation population on the d-th dimension, m indicates the population size, and indicates the number of individuals involved in the optimization process. represents the position of the pth randomly selected individual in the dth dimension at the t+1th generation, It represents the distance between the current individual and the randomly selected individual in the dth dimension. A is a random number A~U(-1,1) that obeys a uniform distribution. l is a constant used to control the step length. is the position of the best individual in the current population, represents the distance between the vigilant and the optimal individual, represents the distance between the vigilant and the worst individual, β is a uniformly distributed random number β~U(0,1), K is a normally distributed random number K~N(0,1), δ is a very small value to prevent the denominator from being 0, f i represents the fitness value of the i-th individual, f g and f w Represent the fitness values of the global optimal and worst individuals respectively.
[0065] S5, applying the chaos of the Sine chaotic map to replace the random initialization process of the initial value of the sparrow algorithm, and training the optimized support vector regression model based on the data set obtained in step S2 to obtain a trained Sine-SSA-SVR model;
[0066] S6. Single cell SOH estimation: Based on the optimized Sine-SSA-SVR model obtained in step S5, all health characteristics and SOH of a battery obtained by impedance testing after cyclic charge and discharge in step S2 are extracted as a model training set. After repeating steps S3-S5, other battery health characteristics are input into the optimized model to achieve SOH estimation of lithium-ion batteries.
[0067] Using R-squared (R 2 ), maximum absolute error (MAE), mean absolute error (AAE) and root mean square error (RMSE) are used to evaluate the performance of the proposed method. The calculation formula is as follows:
[0068]
[0069] like Figure 4 As shown in the figure, the SOH estimation results of different data-driven methods are compared and analyzed, and the comparison results are shown in Table 1. In addition, it can be seen from the figure that the trained Sine-SSA-SVR model can accurately estimate the SOH of the battery throughout its life cycle, and the predicted values can be well distributed near the true values. The model can better track the battery health state decay trajectory, and the prediction effect of the battery SOH is better. Further, as Figure 5 As shown, the model was verified on different batteries at different temperatures, showing that the proposed method has good prediction accuracy and generalization, indicating the powerful estimation performance of the method, which makes it show broad application prospects in the field of battery health status prediction.
[0070] Table 1 Estimation results and errors of different methods
[0071]
[0072] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.
Claims
1. A lithium-ion battery SOH estimation method based on impedance feature selection and optimized support vector regression, Features: The following steps are involved: S1. Data collection: Perform aging impedance experiments on different lithium-ion batteries under different temperature conditions until the battery discharge capacity is less than 70% of the initial capacity, and record the battery charge and discharge and electrochemical impedance spectrum data in real time, including charge and discharge cycle data and impedance under different aging conditions; S2, data processing and feature extraction: pre-processing the charge and discharge data and electrochemical impedance spectrum data obtained in step S1; analyzing the relationship between electrochemical impedance and battery aging, selecting impedance features based on a sequence forward search algorithm, and applying a multi-objective decision method to optimize the feature subset obtained by the sequence forward search to obtain impedance features and SOH data; S3, based on the radial basis kernel function, select the penalty coefficient, insensitive loss function parameters and kernel function parameters to build a support vector regression model; S4. Sparrow search algorithm model hyperparameter optimization: Apply the sparrow search algorithm to the support vector regression model hyperparameter optimization to optimize the support vector regression model; S5, applying the chaos of the Sine chaotic map to replace the random initialization process of the initial value of the sparrow algorithm, and training the optimized support vector regression model based on the data set obtained in step S2 to obtain a trained Sine-SSA-SVR model; S6. Single cell SOH estimation: Based on the Sine-SSA-SVR model obtained in step S5, the SOH of the lithium-ion battery is estimated by inputting impedance characteristics.
2. According to claim 1, a lithium-ion battery SOH estimation method based on impedance feature selection and optimized support vector regression, Features: The battery charging and discharging process in the data collected in step S1 is: in the charging stage, first charge at a constant current of 1C to an upper cut-off voltage of 4.2V, then charge at a constant voltage of 0.1C, and finally stand for 15 minutes; in the discharging stage, discharge at a constant current of 2C to a lower cut-off voltage of 3V, and then stand for 15 minutes.
3. A lithium-ion battery SOH estimation method based on impedance feature selection and optimized support vector regression according to claim 1, Features: The specific expression of the support vector regression model in step S3 is as follows: Among them, ω and b represent the weight vector and bias term of the support vector regression model respectively, x represents the input variable, is the predicted output function corresponding to the input x, and by introducing the Lagrange multiplier, the above formula can be transformed into a convex quadratic optimization problem, including the dual function and constraints: in, is the optimization objective function of SVR, ||ω|| 2 is the regularization term, n represents the number of training sample sets, c represents the penalty parameter, ξ j and Represent two different relaxation factors, st represents constraint, x j represents the input feature vector of the jth sample, y j The true target value of the jth sample, the training data set is ε represents the insensitive loss function, and solving the above formula gives the following expression: Among them, nsv is the number of support vectors, K(x j ,x) represents the kernel function, which is used to calculate the support vector x in high-dimensional space. j The inner product between the current input vector x, α j , is the Lagrange multiplier corresponding to the jth sample, and the specific expression is as follows: K(x j ,x)=exp(-g||x-x j || 2 ) Among them, exp(*) represents the exponential function with the natural constant e as the base, g represents the radial basis kernel function parameter, ||xx j || 2 is the input vector x and the support vector x j The square of the Euclidean distance between them.
4. A lithium-ion battery SOH estimation method based on impedance feature selection and optimized support vector regression according to claim 3, Features: In step S4, the hyperparameter optimization of the sparrow search algorithm model is performed by the following expression: Finder's location update: Location update for joiners: Vigilante Location Update: Among them, i represents the index of the current individual, that is, the i-th group of SVR parameters, d represents the dimension of the SVR parameters, They represent the positions of the i-th discoverer, joiner, and vigilant on the d-th dimension at time t+1, respectively. represents the position of the ith discoverer, joiner, or vigilant in the dth dimension at time t. α is a positive constant used to control the step size and exponential decay rate in position updates. exp(*) represents an exponential function with the natural constant e as the base. max represents the maximum number of iterations, Q is a random number Q~N(0,1) that follows a normal distribution, L is a random number with a Laplace distribution, which is used to simulate the surprise behavior of the discoverer, and R 2 is a random number R that follows a uniform distribution 2 ~U(0,1), ST represents the warning value, It indicates the position of the worst individual in the t-th generation population on the d-th dimension, m indicates the population size, and indicates the number of individuals involved in the optimization process. represents the position of the pth randomly selected individual in the dth dimension at the t+1th generation, It represents the distance between the current individual and the randomly selected individual in the dth dimension. A is a random number A~U(-1,1) that obeys a uniform distribution. l is a constant used to control the step length. is the position of the best individual in the current population, represents the distance between the vigilant and the optimal individual, represents the distance between the vigilant and the worst individual, β is a uniformly distributed random number β~U(0,1), K is a normally distributed random number K~N(0,1), δ represents the value to prevent the denominator from being 0, and f i represents the fitness value of the i-th individual, f g and f w Represent the fitness values of the global optimal and worst individuals respectively.
Citation Information
Patent Citations
Sparrow search and least square support vector machine-based battery state of health estimation and residual life prediction method
CN112485692A
Battery health state estimation and residual life prediction method based on sparrow search and least square support vector machine
CN113484785A
Lithium battery model parameter identification method based on chaotic quantum sparrow search algorithm
CN114970332A
Lithium ion battery SOH estimation method based on SSA-SVR model
CN115684972A
Lithium battery health estimation method based on alternating current impedance test
CN117250519A
Cited By
Method and device for constructing open-circuit voltage-state of charge model of battery
CN119716577A
A method and device for constructing an open circuit voltage-state of charge model of a battery
CN119716577B
Intelligent optimization method for lithium battery disassembling process based on knowledge graph
CN122414342A
Lithium battery disassembly process intelligent optimization method based on knowledge graph
CN122414342B
