CN108805217A - A kind of health state of lithium ion battery method of estimation and system based on support vector machines - Google Patents
A kind of health state of lithium ion battery method of estimation and system based on support vector machines Download PDFInfo
- Publication number
- CN108805217A CN108805217A CN201810636667.9A CN201810636667A CN108805217A CN 108805217 A CN108805217 A CN 108805217A CN 201810636667 A CN201810636667 A CN 201810636667A CN 108805217 A CN108805217 A CN 108805217A
- Authority
- CN
- China
- Prior art keywords
- regression
- training
- set data
- support vector
- optimal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000012706 support-vector machine Methods 0.000 title claims abstract description 34
- 230000036541 health Effects 0.000 title claims abstract description 25
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 title claims abstract description 19
- 229910001416 lithium ion Inorganic materials 0.000 title claims abstract description 19
- 238000012549 training Methods 0.000 claims abstract description 76
- 238000012360 testing method Methods 0.000 claims abstract description 68
- 238000010277 constant-current charging Methods 0.000 claims abstract description 46
- 239000013598 vector Substances 0.000 claims abstract description 13
- 238000010606 normalization Methods 0.000 claims abstract description 10
- 230000006870 function Effects 0.000 claims description 101
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 claims description 30
- 229910052744 lithium Inorganic materials 0.000 claims description 30
- 238000007600 charging Methods 0.000 claims description 15
- 230000009977 dual effect Effects 0.000 claims description 11
- 238000002790 cross-validation Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 4
- 125000004122 cyclic group Chemical group 0.000 claims description 4
- 238000007599 discharging Methods 0.000 claims description 4
- 238000002474 experimental method Methods 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 4
- 238000012417 linear regression Methods 0.000 claims description 3
- 230000005611 electricity Effects 0.000 abstract description 6
- 230000008901 benefit Effects 0.000 description 5
- 230000009467 reduction Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 206010021703 Indifference Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010280 constant potential charging Methods 0.000 description 1
- 238000010281 constant-current constant-voltage charging Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000003487 electrochemical reaction Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 238000013100 final test Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Evolutionary Biology (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Molecular Biology (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Secondary Cells (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
Abstract
The invention discloses a kind of health state of lithium ion battery method of estimation and system based on support vector machines, including：Determine the input variable and output variable of Support vector regression prediction；Input variable and output variable are divided into training set data group and test set data group；Regression model foundation is carried out to the training set data after normalization, obtains regression function；Test set data are brought into regression model after training, to predict the electricity being filled with when constant-current charging of battery reaches blanking voltage；The electricity that constant-current charge in training set data to blanking voltage is filled with is fitted with the current test capacity obtained after volume test, the equation that the electricity that test set data prediction obtains is brought into after fitting is obtained into current predictive capacity, to estimate cell health state.The present invention can reach the electricity that blanking voltage is filled with to the lithium ion battery constant-current charge under various constant-current charge environment and predict there is wide applicability.
Description
Technical Field
The invention belongs to the technical field of lithium ion battery health state estimation, and particularly relates to a lithium ion battery health state estimation method and system based on a support vector machine.
Background
Compared with fuel vehicles, the electric vehicles have greater advantages in the aspects of energy conservation, emission reduction and environmental protection, so that various excitation measures are strived by various countries to greatly promote the development of the electric vehicles. The lithium battery has the advantages of high specific energy, long service life, high rated voltage, high power bearing capacity, low self-discharge rate and the like, and is favored by electric automobile factories since the market. The rapid development Of electric vehicles makes people put higher demands on the performance Of lithium batteries, so that the State Of Health (SOH) estimation Of lithium batteries is receiving much attention. Due to the complexity of the battery aging mechanism, rapid and accurate estimation of the SOH of the battery is difficult.
The SOH is typically determined by estimating the value of the SOH based on a decrease in capacity or an increase in resistance. Among them, the extended kalman filter method is considered as the most reliable method for estimating SOH online. However, the accuracy of the method depends on the parameters of the established model, and the accuracy is easily influenced by the accuracy of the model. Therefore, a method for conveniently, simply and accurately acquiring the SOH value is of great interest.
According to the battery cycle data, under the same charging condition, the electric quantity Q charged when the battery reaches the cut-off voltage in constant current charging is reduced along with the reduction of SOH, and the correlation degree of the electric quantity Q and the SOH is higher. Due to the actual charging situation, the lithium battery cannot charge the terminal voltage to the cutoff voltage every time constant current charging is performed. Therefore, accurately predicting the electric quantity Q charged when the constant-current charging of the battery reaches the cut-off voltage under the same charging condition becomes a key step for predicting the SOH value of the lithium battery. Meanwhile, due to the hysteresis of the battery charging system, after the lithium battery reaches the charging cut-off voltage in the constant-current charging process, each charging related device can act, so that the overshoot of the battery and the damage to the battery are inevitably caused, and the service life of the battery is shortened. In order to solve the above problem, it is necessary to predict in advance the amount of electricity Q charged by the battery when the constant current charging reaches the cut-off voltage to prevent the terminal voltage from exceeding the cut-off voltage and further perform estimation of the SOH of the battery.
SOH is generally defined asWherein c isMIs the current test capacity of the battery, c0The rated capacity of the battery. Due to the test cMThe test period of the time is long and causes waste, so that the accurate, reliable and convenient estimation of the SOH of the battery is an important task of a battery management system.
Disclosure of Invention
The invention aims to solve the problems and provides a lithium ion battery health state estimation method and system based on a support vector machine algorithm. According to the method, the support vector machine accurately predicts the electric quantity Q charged when the constant current charging of the lithium battery reaches the cut-off voltage according to the historical data, the working state and the environmental data of the lithium battery, and meanwhile, the grid searching method is used for correspondingly optimizing the parameter selection of the support vector machine, so that the accuracy of the parameter selection is improved. Experiments show that under the same charging condition, the electric quantity charged when the constant current charging of the lithium battery reaches the cut-off voltage is reduced along with the reduction of the SOH value, and the SOH value and the cut-off voltage have higher correlation. Therefore, according to the related data of the previous test, the constant current charging capacity Q of the test set can be fitted by the least square method11The relation between the SOH value and the constant current charging capacity Q predicted by the support vector machine algorithm1An estimate is made of the SOH of the current lithium battery.
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention discloses a lithium ion battery health state estimation method based on a support vector machine, which comprises the following steps:
carrying out a cyclic charge and discharge experiment on the lithium battery, recording historical data of various working states of the lithium battery in real time, and determining an input variable and an output variable of regression prediction of a support vector machine;
the input variables and the output variables are divided into two groups: a training set data set and a test set data set;
carrying out normalization processing on the training set data group and the test set data group;
carrying out regression model establishment on the normalized training set data to obtain a regression function;
selecting RBF as kernel function, selecting optimal RBF kernel function parameter combination by using grid search method: width parameters of kernel functions, penalty coefficients and loss functions;
determining an optimal parameter regression model according to the optimal RBF kernel function parameter combination;
the data of the test set is substituted into the regression model after training, so that the electric quantity Q charged when the constant current charging of the battery reaches the cut-off voltage is predicted1；
Under the same constant current charging condition, the constant current in the training set data is charged to the electric quantity Q charged by the cut-off voltage11And the current testing capacity Q obtained after the capacity testing0Performing fitting by using a least square method, and predicting the Q obtained by the data of the test set1The fitted equation is substituted to obtain the current predicted capacity cMAnd thus the state of health of the battery is estimated.
Further, the determining the input variables and the output variables supporting the regression prediction of the vector machine specifically includes:
recording historical data of various working states of the lithium battery in real time, wherein the historical data comprises cycle times, cycle charging and discharging current, discharging depth, temperature and current of constant current charging to be carried out next time, and the historical data is used as an input variable for regression prediction of a support vector machine;
after a set cycle period, performing constant current charging and capacity testing on the lithium battery once, and counting the electric quantity Q charged when the constant current charging of the battery reaches a cut-off voltage as an output variable of regression prediction of the support vector machine.
Further, the normalizing the training set data group and the test set data group specifically includes:
the normalized sample value is the ratio of the difference between the sample value and the minimum value of the sample to the difference between the maximum value and the minimum value of the sample value.
Further, when the performance of the parameter training prediction model is the same, the parameter combination with the relatively small penalty coefficient is preferably selected.
Further, establishing a regression model for the normalized training set data to obtain a regression function; the method specifically comprises the following steps:
let the training set sample pair containing m training samples beWherein,is the input column vector for the ith training sample, is the corresponding output value;
the linear regression function established in the high-dimensional feature space is set as:
define the epsilon linear insensitive loss function as:
in order to find an optimal classification surface to minimize the error of all training samples from the optimal classification surface, a relaxation variable ξ is introducedi,ξi *Then, the following constraint relation needs to be satisfied:
wherein,in order to be a non-linear mapping function,is a regression coefficient vector, b is a threshold;a predicted value returned by the regression function is used, y is a corresponding true value, and epsilon is a set number larger than 0; and C is a penalty factor, wherein the larger C is the penalty larger for the sample with the training error larger than epsilon, epsilon specifies the error requirement of the regression function, and the smaller epsilon is the error of the regression function.
Further, solving the constraint relation, specifically, solving:
converting the constraint relation into a dual problem by adopting a Lagrange dual theory;
converting the minimum problem in the original Lagrange function into a maximization problem by Lagrange duality;
solving a Lagrange multiplier in the dual problem by adopting an SMO algorithm; further obtain the regression coefficient vectorAnd a threshold value b, determining a regression function.
Further, the regression function is specifically:
wherein,respectively the optimal solutions of the lagrange multipliers corresponding to sample i,is a kernel function, b*The obtained threshold value is solved according to the optimal solution of the Lagrange multiplier.
Further, selecting an RBF as a kernel function, and selecting an optimal RBF kernel function parameter combination by using a grid search method; the method specifically comprises the following steps:
the method comprises the following steps: performing cross validation on various possible RBF kernel function parameter combination values, and finding out a combination pair which enables the cross validation accuracy to be highest; arranging and combining the possible values of each parameter, and listing all possible combination results to generate a 'grid';
step two: using each RBF kernel function parameter combination for SVM training, and evaluating the performance by using cross validation;
step three: and after the fitting function tries all parameter combinations, returning to an optimal classification surface, and automatically adjusting to the optimal parameter combination to ensure that the error of all training samples from the optimal classification surface is minimum.
The second purpose of the present invention is to disclose a lithium ion battery health state estimation system based on support vector machine, which includes a server, the server includes a memory, a processor and a computer program stored in the memory and capable of running on the processor, the processor implements the following steps when executing the program:
determining an input variable and an output variable of the regression prediction of the support vector machine;
the input variables and the output variables are divided into two groups: a training set data set and a test set data set;
carrying out normalization processing on the training set data group and the test set data group;
carrying out regression model establishment on the normalized training set data to obtain a regression function;
selecting RBF as kernel function, selecting optimal RBF kernel function parameter combination by using grid search method: width parameters of kernel functions, penalty coefficients and loss functions;
determining an optimal parameter regression model according to the optimal RBF kernel function parameter combination;
the data of the test set is substituted into the regression model after training, so that the electric quantity Q charged when the constant current charging of the battery reaches the cut-off voltage is predicted1；
Under the same constant current charging condition, the constant current in the training set data is charged to the electric quantity Q charged by the cut-off voltage11And the current testing capacity Q obtained after the capacity testing0Performing fitting by using a least square method, and predicting the Q obtained by the data of the test set1The fitted equation is substituted to obtain the current predicted capacity cMAnd thus the state of health of the battery is estimated.
It is a third object of the present invention to disclose a computer readable storage medium, having a computer program stored thereon, which when executed by a processor, performs the steps of:
determining an input variable and an output variable of the regression prediction of the support vector machine;
the input variables and the output variables are divided into two groups: a training set data set and a test set data set;
carrying out normalization processing on the training set data group and the test set data group;
carrying out regression model establishment on the normalized training set data to obtain a regression function;
selecting RBF as kernel function, selecting optimal RBF kernel function parameter combination by using grid search method: width parameters of kernel functions, penalty coefficients and loss functions;
determining an optimal parameter regression model according to the optimal RBF kernel function parameter combination;
the data of the test set is substituted into the regression model after training, so that the electric quantity Q charged when the constant current charging of the battery reaches the cut-off voltage is predicted1；
Under the same constant current charging condition, the constant current in the training set data is charged to the value charged by the cut-off voltageElectric quantity Q11And the current testing capacity Q obtained after the capacity testing0Performing fitting by using a least square method, and predicting the Q obtained by the data of the test set1The fitted equation is substituted to obtain the current predicted capacity cMAnd thus the state of health of the battery is estimated.
The invention has the beneficial effects that:
(1) the lithium ion battery can be charged under various constant current charging environments to reach the electric quantity Q charged by cut-off voltage without aiming at the lithium battery made of specific materials1The prediction is carried out, and the method has wide applicability;
(2) the complex electrochemical reaction mechanism of the lithium battery does not need to be deeply researched, so that the calculation process is simplified;
(3) the SOH of the lithium battery can be estimated according to the charging data, and the capacity test is not required to be carried out independently, so that the test period is shortened, and the waste is reduced;
(4) in view of practical application, the battery does not have to be charged to the cutoff voltage every time.
(5) The allowable charging amount of the battery can be determined, the phenomenon of overcharge of the battery in the constant-current charging process is prevented, and charging equipment and the lithium battery are effectively protected.
Drawings
FIG. 1 is a flow chart of battery SOH estimation;
FIG. 2 is a constant-current and constant-voltage charging diagram of lithium batteries under different SOH values;
FIG. 3(a) shows the amount of charge Q charged by the training set when the constant current charge reaches the cut-off voltage11Predicting a graph;
FIG. 3(b) shows the amount of charge Q charged by the test set when the constant current charge reaches the cut-off voltage1Predicting a graph;
FIG. 3(c) shows the amount of constant-current charged Q of the training set11And the current test capacity Q obtained by the capacity test0Fitting relation graph of (1).
Detailed Description
The present invention will be further described with reference to the accompanying drawings and specific embodiments.
The invention discloses a lithium ion battery health state estimation method based on a support vector machine, which comprises the following steps as shown in figure 1:
step (1): in the process of carrying out cyclic charge and discharge on the lithium battery, recording historical data of various working states of the lithium battery in real time, wherein the historical data comprises cycle times N and cyclic charge and discharge current ICharging deviceAnd IPutDepth of discharge D, temperature TemAnd the current magnitude I of the constant current charging to be performed next time is used as an input variable of the regression prediction of the support vector machine.
After a certain cycle period, performing constant current charging and capacity testing on the lithium battery once, and counting the electric quantity Q charged when the constant current charging of the battery reaches a cut-off voltage, wherein the electric quantity Q is used as an output variable of regression prediction.
Step (2): the input and output variable sets are divided into a training set data set and a test set data set, wherein the training set is used for training to obtain a regression model, and the test set is used for regression prediction and evaluation of the model performance. Since the input and output exist in pairs, the input and output of the first half can be used as a training set, and the input and output of the second half can be used as a prediction set.
And the data is adjusted to a format that meets the Libsvm toolbox requirements.
And (3): and carrying out normalization processing on the obtained input variable set and the output variable set so as to accelerate the speed of solving the optimal solution by the cross validation method and improve the prediction precision.
Before the regression model is established, normalization processing is carried out on data, namely input variables and output variables are unified and normalized to a value range of [0,1] according to a formula (1).
Wherein x isi、yiThe MaxValue and the MinValue are respectively the maximum value and the minimum value of the sample.
And (4): and (4) carrying out regression model establishment on the normalized training set data obtained in the last step to obtain a regression function.
Without loss of generality, let the training set sample pair containing m training samples asWherein,
is the input column vector for the ith training sample, is the corresponding output value. In practical application of the prediction, R needs to be mapped through non-linearity for such linear indifference problemdAnd → H, mapping the samples of the original input space into a high-dimensional feature space H, and constructing an optimal classification surface in the high-dimensional feature space H so that the error of all the training samples from the optimal classification surface is minimum. The linear regression function established in the high-dimensional feature space is shown in formula (2).
Wherein,in order to be a non-linear mapping function,in the form of a vector of regression coefficients,is a threshold value.
Define the epsilon linear insensitive loss function as:
where f (x) is the predicted value returned by the regression function, y is the corresponding true value and ε is a number greater than 0 that is taken in advance. The function is expressed asAnd y is less than or equal to epsilon, the loss is equal to 0.
In order to find an optimal classification surface, the error of all training samples from the optimal classification surface is minimized, but the condition that a few samples cannot meet the constraint condition is considered, so that the optimal classification surface cannot be found. For such cases, the above constraints are satisfiedat a minimum, it is necessary to introduce the relaxation variable ξi,ξi *And search the aboveThe problem of b is described by a mathematical language, namely, the formula (4) shows:
wherein, C is a penalty factor, the larger C represents the larger penalty to the sample with the training error larger than epsilon, epsilon specifies the error requirement of the regression function, and the smaller epsilon represents the smaller error of the regression function.
The solution to the above problem is a convex quadratic programming problem, and due to the complexity of the computation, direct solution is relatively difficult. Although it is possible to solve directly with the existing optimization computation packages, in contrast, a more efficient approach will be used. Namely, equation (4) is converted into a dual problem according to the Lagrangian dual theory, and the advantage of doing so is as follows: one dual problem tends to be easier to solve; the two can naturally introduce the kernel function, and further popularize to the nonlinear classification problem. The lagrangian function constructed in the method is shown in formula (5).
Wherein a ═ a1,a2,...,am)T，a*＝(a1 *,a2 *,...,am *)T，η＝(η1,η2,...,ηm)T，η*＝(η1 *,η2 *,...,ηm *)TIs the lagrange multiplier vector.
ξ the ξ solution ξ of ξ the ξ dual ξ problem ξ is ξ divided ξ into ξ 3 ξ steps ξ, ξ namely ξ, ξ firstly ξ, ξ L ξ (ξ omega ξ, ξ b ξ, ξ xi ξ, ξ a ξ, ξ eta ξ) ξ is ξ minimized ξ with ξ respect ξ to ξ omega ξ, ξ b ξ and ξ xi ξ, ξ then ξ the ξ maximum ξ of ξ the ξ pairs ξ a ξ, ξ eta ξ is ξ obtained ξ, ξ and ξ finally ξ, ξ the ξ SMO ξ algorithm ξ is ξ used ξ for ξ solving ξ the ξ Lagrangian ξ multiplier ξ in ξ the ξ dual ξ problem ξ. ξ
firstly fixing a, eta and eta, minimizing L relative to omega, b and xi, respectively, calculating partial derivatives of omega, b and xi, i.e. making L minimizeAndis equal to zero, thereby obtaining formula (6)
By introducing the equation (6) into the original Lagrangian function (5) from Lagrangian duality, the minimum problem can be converted into the maximum problem, as shown in equation (7)
Wherein,is a kernel function.
The optimal solution obtained when solving equation (7) is set toThen there is
Wherein N isnsvThe number of support vectors σ.
Thus, the regression function can be expressed as
Wherein only some of the parametersNot equal to 0, corresponding to sample xiI.e. the support vector in question.
And (5): from equation (9), to solve the regression function problem of the support vector machine algorithm, an appropriate kernel function must be selected. Commonly used kernel functions include: 1. a linear kernel function; a polynomial kernel of order d; 3. a radial basis kernel function (RBF); sigmoid kernel. Compared with other kernel functions, the RBF kernel function is relatively wide in application, and is applicable to small samples, large samples, high-dimensional and low-dimensional situations and the like. It has the following advantages over other functions:
1) the RBF kernel can map a sample to a higher dimensional space and the linear kernel is a special case of RBF, i.e. if the use of RBF is considered, the linear kernel need not be considered.
2) Compared with a polynomial kernel function, the RBF needs less parameters to be determined, and the complexity of the function is directly influenced by the number of the kernel function parameters. In addition, when the order of the polynomial is relatively high, the element values of the kernel matrix tend to be infinite or infinitesimal. RBF reduces the difficulty of calculating the value in the above problem.
3) RBFs and sigmoids have similar performance for certain parameters.
Therefore, in the prediction of the electric quantity charged when the constant current charging reaches the cut-off voltage, an RBF kernel function is selected, and the expression of the RBF kernel function is shown as an expression (10).
Where σ is a width parameter of the function that controls the radial range of action of the function.
Because the kernel function model parameters have a large influence on the performance of the model, when the Libsvm toolbox is used, a better RBF kernel function parameter combination needs to be selected: a width parameter sigma of the kernel function, a penalty factor C and a loss function P. Considering that the parameters to be selected are relatively few, the complexity of the "grid search method" is not much different from that of the advanced algorithm, and has the advantages of high parallelism and capability of avoiding overfitting. Therefore, we apply "grid search" in the parameter selection. The specific implementation steps are as follows:
firstly, various possible combination values are tried, and then cross-validation is carried out to find out the combination pair which enables the accuracy of the cross-validation to be the highest. And (3) arranging and combining the possible values of each parameter, and listing all possible combination results to generate a 'grid'.
Two, each combination was then used for SVM training and performance was evaluated using cross-validation.
And thirdly, after all parameter combinations are tried by the fitting function, returning to a proper classification surface and automatically adjusting to the optimal parameter combination.
And (6): and training a prediction model by using the optimal parameters obtained by the grid searching method. When the performance of the models is the same, in order to reduce the calculation time, a parameter combination with a relatively small penalty factor C is preferably selected.
And (7): the data of the test set is substituted into the regression model after training, so that the electric quantity Q charged when the constant current charging of the battery reaches the cut-off voltage is predicted1Further predicting the SOH value and evaluating the accuracy of the prediction result of the final test set.
And (8): under the same constant current charging condition, the constant current in the training set data is charged to reach the electric quantity Q charged by the cut-off voltage11And the current testing capacity Q obtained after the capacity testing0Fitting by using a least square method, and predicting the electric quantity Q obtained by the data of the test set1Substituting the fitted equation to obtain the predicted current capacity cMAccording toAn estimation of the SOH of the battery is made.
The electric quantity Q charged by the constant current charging of the training set and the test set to the cut-off voltage11And Q1The prediction results are shown in fig. 3(a) and 3 (b).Training set constant-current charging electric quantity Q under same charging condition11And the current test capacity Q obtained by the capacity test0The fitting relationship of (c) is shown in FIG. 3 (c).
Training set and test set constant current charging to cut-off voltage charged electric quantity Q11And Q1The accuracy of the prediction result is determined by the mean square error E and the coefficient of determination R2The accuracy of the training set and the test set on the estimation of the SOH of the battery is evaluated by the mean absolute error rate, and the specific results are shown in table 1. From specific evaluation indexes, the quantity of electricity Q charged from constant current charging to cut-off voltage based on a support vector machine1The prediction and SOH estimation method has higher prediction precision.
TABLE 1 lithium cell constant current charging to cut-off voltage charged electric quantity Q prediction and SOH estimation method precision evaluation
| E | R2 | Mean absolute error rate of SOH estimation | |
| Training set | 0.00065566 | 0.99271 | 0.48％ |
| Test set | 0.00086036 | 0.99112 | 0.56％ |
Experiments show that under the same charging condition, the electric quantity Q charged when the constant current charging of the lithium battery reaches the cut-off voltage is shortened along with the reduction of the SOH value, and the correlation degree between the electric quantity Q and the SOH value is higher. Therefore, from the previously tested correlation data, Q can be fitted by a least squares method11The relation between the SOH value and the constant current charging capacity Q predicted by the support vector machine algorithm1An estimate is made of the SOH of the current lithium battery.
Fig. 2 shows a constant-current constant-voltage charging diagram of lithium batteries with different SOH values, and it can be seen from fig. 2 that under the same constant-current charging condition, the constant-current charging electric quantity is in a decreasing trend along with the reduction of the SOH value.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive efforts by those skilled in the art based on the technical solution of the present invention.
Claims (10)
1. A lithium ion battery health state estimation method based on a support vector machine is characterized by comprising the following steps:
carrying out a cyclic charge and discharge experiment on the lithium battery, recording historical data of various working states of the lithium battery in real time, and determining an input variable and an output variable of regression prediction of a support vector machine;
the input variables and the output variables are divided into two groups: a training set data set and a test set data set;
carrying out normalization processing on the training set data group and the test set data group;
carrying out regression model establishment on the normalized training set data to obtain a regression function;
selecting RBF as kernel function, selecting optimal RBF kernel function parameter combination by using grid search method: width parameters of kernel functions, penalty coefficients and loss functions;
determining an optimal parameter regression model according to the optimal RBF kernel function parameter combination;
the data of the test set is substituted into the regression model after training, so that the electric quantity Q charged when the constant current charging of the battery reaches the cut-off voltage is predicted1；
Under the same constant current charging condition, the constant current in the training set data is charged to the electric quantity Q charged by the cut-off voltage11And the current testing capacity Q obtained after the capacity testing0Performing fitting by using a least square method, and predicting the Q obtained by the data of the test set1The fitted equation is substituted to obtain the current predicted capacity cMAnd thus the state of health of the battery is estimated.
2. The method for estimating the state of health of a lithium ion battery based on a support vector machine according to claim 1, wherein the determining of the input variables and the output variables of the regression prediction of the support vector machine is specifically:
recording historical data of various working states of the lithium battery in real time, wherein the historical data comprises cycle times, cycle charging and discharging current, discharging depth, temperature and current of constant current charging to be carried out next time, and the historical data is used as an input variable for regression prediction of a support vector machine;
after a set cycle period, performing constant current charging and capacity testing on the lithium battery once, and counting the electric quantity Q charged when the constant current charging of the battery reaches a cut-off voltage, wherein the electric quantity Q is used as an output variable for regression prediction of the support vector machine.
3. The lithium ion battery health state estimation method based on the support vector machine according to claim 1, wherein the normalization processing is performed on the training set data group and the test set data group, specifically:
the normalized sample value is the ratio of the difference between the sample value and the minimum value of the sample to the difference between the maximum value and the minimum value of the sample value.
4. The lithium ion battery state of health estimation method based on support vector machine of claim 1, characterized in that, when the performance of the parameter training prediction model is the same, the parameter combination with relatively small penalty coefficient is selected preferentially.
5. The lithium ion battery state of health estimation method based on support vector machine of claim 1, characterized in that, the normalized training set data is subjected to regression model establishment to obtain a regression function; the method specifically comprises the following steps:
let the training set sample pair containing m training samples beWherein,is the input column vector for the ith training sample, is the corresponding output value;
the linear regression function established in the high-dimensional feature space is set as:
define the epsilon linear insensitive loss function as:
in order to find an optimal classification surface to minimize the error of all training samples from the optimal classification surface, a relaxation variable ξ is introducedi,ξi *Then, the following constraint relation needs to be satisfied:
wherein,in order to be a non-linear mapping function,is a regression coefficient vector, b is a threshold;a predicted value returned by the regression function is used, y is a corresponding true value, and epsilon is a set number larger than 0; and C is a penalty factor, wherein the larger C is the penalty larger for the sample with the training error larger than epsilon, epsilon specifies the error requirement of the regression function, and the smaller epsilon is the error of the regression function.
6. The lithium ion battery state of health estimation method based on a support vector machine according to claim 5, characterized in that the constraint relation is solved, specifically:
converting the constraint relation into a dual problem by adopting a Lagrange dual theory;
converting the minimum problem in the original Lagrange function into a maximization problem by Lagrange duality;
solving a Lagrange multiplier in the dual problem by adopting an SMO algorithm; further obtain the regression coefficient vectorAnd a threshold value b, determining a regression function.
7. The lithium ion battery state of health estimation method based on a support vector machine according to claim 6, characterized in that the regression function is specifically:
wherein,respectively the optimal solutions of the lagrange multipliers corresponding to sample i,is a kernel function, b*The obtained threshold value is solved according to the optimal solution of the Lagrange multiplier.
8. The method according to claim 1, wherein the RBFs are selected as kernel functions, and an optimal RBF kernel function parameter combination is selected by using a grid search method; the method specifically comprises the following steps:
the method comprises the following steps: performing cross validation on various possible RBF kernel function parameter combination values, and finding out a combination pair which enables the cross validation accuracy to be highest; arranging and combining the possible values of each parameter, and listing all possible combination results to generate a 'grid';
step two: using each RBF kernel function parameter combination for SVM training, and evaluating the performance by using cross validation;
step three: and after the fitting function tries all parameter combinations, returning to an optimal classification surface, and automatically adjusting to the optimal parameter combination to ensure that the error of all training samples from the optimal classification surface is minimum.
9. A system for estimating state of health of a lithium ion battery based on a support vector machine, comprising a server including a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the program:
determining an input variable and an output variable of the regression prediction of the support vector machine;
the input variables and the output variables are divided into two groups: a training set data set and a test set data set;
carrying out normalization processing on the training set data group and the test set data group;
carrying out regression model establishment on the normalized training set data to obtain a regression function;
selecting RBF as kernel function, selecting optimal RBF kernel function parameter combination by using grid search method: width parameters of kernel functions, penalty coefficients and loss functions;
determining an optimal parameter regression model according to the optimal RBF kernel function parameter combination;
the data of the test set is substituted into the regression model after training, so that the electric quantity Q charged when the constant current charging of the battery reaches the cut-off voltage is predicted1；
Under the same constant current charging condition, the constant current in the training set data is charged to the electric quantity Q charged by the cut-off voltage11And the current testing capacity Q obtained after the capacity testing0Performing fitting by using a least square method, and predicting the Q obtained by the data of the test set1The fitted equation is substituted to obtain the current predicted capacity cMAnd thus the state of health of the battery is estimated.
10. A computer-readable storage medium on which a computer program is stored, the program, when executed by a processor, performing the steps of:
determining an input variable and an output variable of the regression prediction of the support vector machine;
the input variables and the output variables are divided into two groups: a training set data set and a test set data set;
carrying out normalization processing on the training set data group and the test set data group;
carrying out regression model establishment on the normalized training set data to obtain a regression function;
selecting RBF as kernel function, selecting optimal RBF kernel function parameter combination by using grid search method: width parameters of kernel functions, penalty coefficients and loss functions;
determining an optimal parameter regression model according to the optimal RBF kernel function parameter combination;
the data of the test set is substituted into the regression model after training, so that the electric quantity Q charged when the constant current charging of the battery reaches the cut-off voltage is predicted1；
Under the same constant current charging condition, the constant current in the training set data is charged to the electric quantity Q charged by the cut-off voltage11And the current testing capacity Q obtained after the capacity testing0Performing fitting by using a least square method, and predicting the Q obtained by the data of the test set1The fitted equation is substituted to obtain the current predicted capacity cMAnd thus the state of health of the battery is estimated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810636667.9A CN108805217B (en) | 2018-06-20 | 2018-06-20 | Lithium ion battery health state estimation method and system based on support vector machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810636667.9A CN108805217B (en) | 2018-06-20 | 2018-06-20 | Lithium ion battery health state estimation method and system based on support vector machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108805217A true CN108805217A (en) | 2018-11-13 |
| CN108805217B CN108805217B (en) | 2020-10-23 |
Family
ID=64083726
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810636667.9A Active CN108805217B (en) | 2018-06-20 | 2018-06-20 | Lithium ion battery health state estimation method and system based on support vector machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108805217B (en) |
Cited By (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109543759A (en) * | 2018-11-27 | 2019-03-29 | 北京石油化工学院 | A kind of prediction technique of single flow gas-liquid cyclone separator separating property |
| CN109927575A (en) * | 2019-02-28 | 2019-06-25 | 福建工程学院 | A kind of battery performance detection method for direct-current charging post |
| CN110080882A (en) * | 2019-04-16 | 2019-08-02 | 新奥能源动力科技（上海）有限公司 | A kind of the starting method and starter of gas turbine |
| CN110275129A (en) * | 2019-06-18 | 2019-09-24 | 中国电力科学研究院有限公司 | A kind of method and system of determining high-voltage electric-energy meter resultant error |
| CN110398697A (en) * | 2019-07-23 | 2019-11-01 | 北京工业大学 | A kind of lithium ion health status estimation method based on charging process |
| CN110501646A (en) * | 2019-08-29 | 2019-11-26 | 中国人民解放军国防科技大学 | Off-line lithium battery residual capacity estimation method |
| CN110568374A (en) * | 2019-09-02 | 2019-12-13 | 东北电力大学 | Lithium ion battery residual service life prediction method based on consideration of internal and external characteristics |
| CN110608660A (en) * | 2019-08-28 | 2019-12-24 | 西安理工大学 | Eddy current sensor displacement and temperature prediction method |
| CN110850315A (en) * | 2019-11-29 | 2020-02-28 | 北京邮电大学 | Method and device for estimating state of charge of battery |
| CN111274539A (en) * | 2020-02-18 | 2020-06-12 | 金陵科技学院 | Lithium battery SOH estimation method based on alternating least square method |
| CN111308375A (en) * | 2020-02-04 | 2020-06-19 | 浙江大学 | LSTM-FFNN-based electric forklift lithium ion battery health state prediction method |
| CN111323705A (en) * | 2020-03-19 | 2020-06-23 | 山东大学 | Battery parameter identification method and system based on robust recursive least squares |
| CN111443293A (en) * | 2020-03-30 | 2020-07-24 | 青岛大学 | Lithium battery state of health (SOH) estimation method based on data driving |
| CN111999656A (en) * | 2020-08-28 | 2020-11-27 | 广州小鹏汽车科技有限公司 | Method and device for detecting short circuit in vehicle battery and electronic equipment |
| CN112213643A (en) * | 2020-09-30 | 2021-01-12 | 蜂巢能源科技有限公司 | Method, system and equipment for predicting initial capacity and health state of battery |
| CN112255559A (en) * | 2020-10-12 | 2021-01-22 | 江苏慧智能源工程技术创新研究院有限公司 | Method for predicting residual life of lithium battery energy storage power station based on multiple linear regression |
| CN112287597A (en) * | 2020-09-22 | 2021-01-29 | 国网天津市电力公司电力科学研究院 | Lead-acid storage battery SOH estimation method based on VPGA-GPR algorithm |
| CN112347692A (en) * | 2020-09-21 | 2021-02-09 | 深圳前海有电物联科技有限公司 | Method and device for realizing predictive maintenance of battery of uninterruptible power supply and electronic device |
| CN112540318A (en) * | 2020-12-22 | 2021-03-23 | 武汉理工大学 | Method for estimating health state of lead-acid storage battery for starting internal combustion engine |
| CN112580211A (en) * | 2020-12-23 | 2021-03-30 | 天津大学 | Lead-acid storage battery SOH estimation method based on SA and ANN algorithm |
| CN112684356A (en) * | 2020-10-31 | 2021-04-20 | 浙江锋锂新能源科技有限公司 | Cycle test method of lithium ion battery |
| CN112731184A (en) * | 2020-12-28 | 2021-04-30 | 深圳供电局有限公司 | Battery service life detection method and system |
| CN112834927A (en) * | 2021-01-06 | 2021-05-25 | 合肥工业大学 | Lithium battery residual life prediction method, system, device and medium |
| CN112924886A (en) * | 2021-01-23 | 2021-06-08 | 青岛大学 | Battery state of health (SOH) prediction method and device |
| CN113011464A (en) * | 2021-02-25 | 2021-06-22 | 沈阳工业大学 | Comprehensive prediction method for running state of transformer based on multi-dimensional data evaluation |
| CN113219341A (en) * | 2021-03-23 | 2021-08-06 | 陈九廷 | Model generation and battery degradation estimation device, method, medium, and apparatus |
| CN113267733A (en) * | 2021-04-13 | 2021-08-17 | 西安理工大学 | Automatic configuration method for lithium battery health state estimation based on Gaussian process regression |
| CN113866644A (en) * | 2021-09-30 | 2021-12-31 | 国网福建省电力有限公司龙岩供电公司 | Method and device for predicting usable time and capacity of battery |
| CN113935225A (en) * | 2020-06-29 | 2022-01-14 | 中国科学院大连化学物理研究所 | Flow battery stack optimization and performance prediction method based on machine learning |
| CN114355222A (en) * | 2021-12-23 | 2022-04-15 | 厦门大学 | Battery state of health estimation method and device based on voltage curve and readable medium |
| CN114895206A (en) * | 2022-04-26 | 2022-08-12 | 合肥工业大学 | Lithium ion battery SOH estimation method based on RBF neural network of improved wolf optimization algorithm |
| CN115267586A (en) * | 2022-07-11 | 2022-11-01 | 国网综合能源服务集团有限公司 | Lithium battery SOH evaluation method |
| CN116413609A (en) * | 2023-06-08 | 2023-07-11 | 江苏正力新能电池技术有限公司 | Battery diving identification method and device, electronic equipment and storage medium |
| CN118275903A (en) * | 2024-06-04 | 2024-07-02 | 河南师范大学 | Battery performance test method based on data analysis |
| CN118348812A (en) * | 2024-06-18 | 2024-07-16 | 浙江维度仪表有限公司 | Intelligent control valve regulation and control method and system based on Internet of things |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102680907A (en) * | 2012-05-31 | 2012-09-19 | 浙江大学 | Battery charging stress optical coefficient (SOC) detection method in photovoltaic system |
| CN102749585A (en) * | 2011-04-21 | 2012-10-24 | 李昌 | Multi-layer SVM (support vector machine) based storage battery on-line monitoring method |
| CN104021238A (en) * | 2014-03-25 | 2014-09-03 | 重庆邮电大学 | Lead-acid power battery system fault diagnosis method |
| CN104391252A (en) * | 2014-12-04 | 2015-03-04 | 上海理工大学 | Automobile lead-acid battery health state detection method |
| EP2975421A1 (en) * | 2014-07-18 | 2016-01-20 | Samsung Electronics Co., Ltd | Method and apparatus for estimating state of battery |
| CN105334465A (en) * | 2015-09-15 | 2016-02-17 | 重庆长安汽车股份有限公司 | Method for online evaluating state of health of lithium ion battery |
| CN107132490A (en) * | 2017-07-05 | 2017-09-05 | 福州大学 | A kind of method for realizing the estimation of lithium battery group state-of-charge |
| CN107290679A (en) * | 2017-07-03 | 2017-10-24 | 南京能瑞电力科技有限公司 | The Intelligentized battery method for detecting health status of charging pile is shared for electric automobile |
-
2018
- 2018-06-20 CN CN201810636667.9A patent/CN108805217B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102749585A (en) * | 2011-04-21 | 2012-10-24 | 李昌 | Multi-layer SVM (support vector machine) based storage battery on-line monitoring method |
| CN102680907A (en) * | 2012-05-31 | 2012-09-19 | 浙江大学 | Battery charging stress optical coefficient (SOC) detection method in photovoltaic system |
| CN104021238A (en) * | 2014-03-25 | 2014-09-03 | 重庆邮电大学 | Lead-acid power battery system fault diagnosis method |
| EP2975421A1 (en) * | 2014-07-18 | 2016-01-20 | Samsung Electronics Co., Ltd | Method and apparatus for estimating state of battery |
| CN104391252A (en) * | 2014-12-04 | 2015-03-04 | 上海理工大学 | Automobile lead-acid battery health state detection method |
| CN105334465A (en) * | 2015-09-15 | 2016-02-17 | 重庆长安汽车股份有限公司 | Method for online evaluating state of health of lithium ion battery |
| CN107290679A (en) * | 2017-07-03 | 2017-10-24 | 南京能瑞电力科技有限公司 | The Intelligentized battery method for detecting health status of charging pile is shared for electric automobile |
| CN107132490A (en) * | 2017-07-05 | 2017-09-05 | 福州大学 | A kind of method for realizing the estimation of lithium battery group state-of-charge |
Non-Patent Citations (4)
| Title |
|---|
| HUANG HAI ET AL: "Aging Performances and Cycle-life Predictions of Li-ion Battery", 《PROCEEDINGS OF THE 35TH CHINESE CONTROL CONFERENCE》 * |
| WENWEI HUANG ET AL: "SOC Prediction of Lithium Battery Based on Fuzzy Information Granulation and Support Vector Regression", 《 2017 4TH INTERNATIONAL CONFERENCE ON ELECTRICAL AND ELECTRONIC ENGINEERING (ICEEE)》 * |
| 何旭等: "基于SVM的小样本条件下继电保护可靠性参数估计", 《电网技术》 * |
| 李睿琪等: "一种基于支持向量机的锂电池健康状态评估方法", 《第17届中国系统仿真技术及其应用学术年会(17TH CCSSTA 2016)》 * |
Cited By (52)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109543759A (en) * | 2018-11-27 | 2019-03-29 | 北京石油化工学院 | A kind of prediction technique of single flow gas-liquid cyclone separator separating property |
| CN109927575A (en) * | 2019-02-28 | 2019-06-25 | 福建工程学院 | A kind of battery performance detection method for direct-current charging post |
| CN110080882A (en) * | 2019-04-16 | 2019-08-02 | 新奥能源动力科技（上海）有限公司 | A kind of the starting method and starter of gas turbine |
| CN110275129A (en) * | 2019-06-18 | 2019-09-24 | 中国电力科学研究院有限公司 | A kind of method and system of determining high-voltage electric-energy meter resultant error |
| CN110275129B (en) * | 2019-06-18 | 2022-10-04 | 中国电力科学研究院有限公司 | Method and system for determining synthetic error of high-voltage electric energy metering device |
| CN110398697A (en) * | 2019-07-23 | 2019-11-01 | 北京工业大学 | A kind of lithium ion health status estimation method based on charging process |
| CN110608660B (en) * | 2019-08-28 | 2021-11-16 | 西安理工大学 | Eddy current sensor displacement and temperature prediction method |
| CN110608660A (en) * | 2019-08-28 | 2019-12-24 | 西安理工大学 | Eddy current sensor displacement and temperature prediction method |
| CN110501646A (en) * | 2019-08-29 | 2019-11-26 | 中国人民解放军国防科技大学 | Off-line lithium battery residual capacity estimation method |
| CN110568374A (en) * | 2019-09-02 | 2019-12-13 | 东北电力大学 | Lithium ion battery residual service life prediction method based on consideration of internal and external characteristics |
| CN110568374B (en) * | 2019-09-02 | 2021-04-27 | 东北电力大学 | Lithium ion battery residual service life prediction method based on consideration of internal and external characteristics |
| CN110850315A (en) * | 2019-11-29 | 2020-02-28 | 北京邮电大学 | Method and device for estimating state of charge of battery |
| CN111308375A (en) * | 2020-02-04 | 2020-06-19 | 浙江大学 | LSTM-FFNN-based electric forklift lithium ion battery health state prediction method |
| CN111274539A (en) * | 2020-02-18 | 2020-06-12 | 金陵科技学院 | Lithium battery SOH estimation method based on alternating least square method |
| CN111323705B (en) * | 2020-03-19 | 2021-07-23 | 山东大学 | Battery parameter identification method and system based on robust recursive least squares |
| CN111323705A (en) * | 2020-03-19 | 2020-06-23 | 山东大学 | Battery parameter identification method and system based on robust recursive least squares |
| CN111443293A (en) * | 2020-03-30 | 2020-07-24 | 青岛大学 | Lithium battery state of health (SOH) estimation method based on data driving |
| CN113935225B (en) * | 2020-06-29 | 2024-05-07 | 中国科学院大连化学物理研究所 | Flow battery pile optimization and performance prediction method based on machine learning |
| CN113935225A (en) * | 2020-06-29 | 2022-01-14 | 中国科学院大连化学物理研究所 | Flow battery stack optimization and performance prediction method based on machine learning |
| CN111999656A (en) * | 2020-08-28 | 2020-11-27 | 广州小鹏汽车科技有限公司 | Method and device for detecting short circuit in vehicle battery and electronic equipment |
| CN112347692A (en) * | 2020-09-21 | 2021-02-09 | 深圳前海有电物联科技有限公司 | Method and device for realizing predictive maintenance of battery of uninterruptible power supply and electronic device |
| CN112347692B (en) * | 2020-09-21 | 2024-02-06 | 深圳有电物联科技有限公司 | Method and device for realizing battery predictive maintenance of uninterruptible power supply and electronic device |
| CN112287597B (en) * | 2020-09-22 | 2023-10-03 | 国网天津市电力公司电力科学研究院 | Lead-acid storage battery SOH estimation method based on VPGA-GPR algorithm |
| CN112287597A (en) * | 2020-09-22 | 2021-01-29 | 国网天津市电力公司电力科学研究院 | Lead-acid storage battery SOH estimation method based on VPGA-GPR algorithm |
| CN112213643B (en) * | 2020-09-30 | 2023-06-23 | 蜂巢能源科技有限公司 | Method, system and equipment for predicting initial capacity and state of health of battery |
| CN112213643A (en) * | 2020-09-30 | 2021-01-12 | 蜂巢能源科技有限公司 | Method, system and equipment for predicting initial capacity and health state of battery |
| CN112255559B (en) * | 2020-10-12 | 2023-05-09 | 启东沃太新能源有限公司 | Lithium battery energy storage power station residual life prediction method based on multiple linear regression |
| CN112255559A (en) * | 2020-10-12 | 2021-01-22 | 江苏慧智能源工程技术创新研究院有限公司 | Method for predicting residual life of lithium battery energy storage power station based on multiple linear regression |
| CN112684356A (en) * | 2020-10-31 | 2021-04-20 | 浙江锋锂新能源科技有限公司 | Cycle test method of lithium ion battery |
| CN112684356B (en) * | 2020-10-31 | 2024-06-04 | 浙江锋锂新能源科技有限公司 | Circulation test method of lithium ion battery |
| CN112540318A (en) * | 2020-12-22 | 2021-03-23 | 武汉理工大学 | Method for estimating health state of lead-acid storage battery for starting internal combustion engine |
| CN112540318B (en) * | 2020-12-22 | 2022-01-04 | 武汉理工大学 | Method for estimating health state of lead-acid storage battery for starting internal combustion engine |
| CN112580211A (en) * | 2020-12-23 | 2021-03-30 | 天津大学 | Lead-acid storage battery SOH estimation method based on SA and ANN algorithm |
| CN112731184A (en) * | 2020-12-28 | 2021-04-30 | 深圳供电局有限公司 | Battery service life detection method and system |
| CN112731184B (en) * | 2020-12-28 | 2023-03-03 | 深圳供电局有限公司 | Battery service life detection method and system |
| CN112834927A (en) * | 2021-01-06 | 2021-05-25 | 合肥工业大学 | Lithium battery residual life prediction method, system, device and medium |
| CN112924886A (en) * | 2021-01-23 | 2021-06-08 | 青岛大学 | Battery state of health (SOH) prediction method and device |
| CN113011464A (en) * | 2021-02-25 | 2021-06-22 | 沈阳工业大学 | Comprehensive prediction method for running state of transformer based on multi-dimensional data evaluation |
| CN113219341A (en) * | 2021-03-23 | 2021-08-06 | 陈九廷 | Model generation and battery degradation estimation device, method, medium, and apparatus |
| CN113267733A (en) * | 2021-04-13 | 2021-08-17 | 西安理工大学 | Automatic configuration method for lithium battery health state estimation based on Gaussian process regression |
| CN113267733B (en) * | 2021-04-13 | 2023-11-17 | 西安理工大学 | Automatic configuration method for lithium battery health state estimation based on Gaussian process regression |
| CN113866644A (en) * | 2021-09-30 | 2021-12-31 | 国网福建省电力有限公司龙岩供电公司 | Method and device for predicting usable time and capacity of battery |
| CN114355222A (en) * | 2021-12-23 | 2022-04-15 | 厦门大学 | Battery state of health estimation method and device based on voltage curve and readable medium |
| CN114895206B (en) * | 2022-04-26 | 2023-04-28 | 合肥工业大学 | Lithium ion battery SOH estimation method based on RBF neural network of improved gray wolf optimization algorithm |
| CN114895206A (en) * | 2022-04-26 | 2022-08-12 | 合肥工业大学 | Lithium ion battery SOH estimation method based on RBF neural network of improved wolf optimization algorithm |
| CN115267586A (en) * | 2022-07-11 | 2022-11-01 | 国网综合能源服务集团有限公司 | Lithium battery SOH evaluation method |
| CN116413609B (en) * | 2023-06-08 | 2023-08-29 | 江苏正力新能电池技术有限公司 | Battery diving identification method and device, electronic equipment and storage medium |
| CN116413609A (en) * | 2023-06-08 | 2023-07-11 | 江苏正力新能电池技术有限公司 | Battery diving identification method and device, electronic equipment and storage medium |
| CN118275903A (en) * | 2024-06-04 | 2024-07-02 | 河南师范大学 | Battery performance test method based on data analysis |
| CN118275903B (en) * | 2024-06-04 | 2024-09-03 | 河南师范大学 | Battery performance test method based on data analysis |
| CN118348812A (en) * | 2024-06-18 | 2024-07-16 | 浙江维度仪表有限公司 | Intelligent control valve regulation and control method and system based on Internet of things |
| CN118348812B (en) * | 2024-06-18 | 2024-08-20 | 浙江维度仪表有限公司 | Intelligent control valve regulation and control method and system based on Internet of things |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108805217B (en) | 2020-10-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108805217B (en) | Lithium ion battery health state estimation method and system based on support vector machine | |
| Li et al. | Prognostic health condition for lithium battery using the partial incremental capacity and Gaussian process regression | |
| Hu et al. | Health prognosis for electric vehicle battery packs: A data-driven approach | |
| Wei et al. | Remaining useful life prediction and state of health diagnosis for lithium-ion batteries using particle filter and support vector regression | |
| Cui et al. | A dynamic spatial-temporal attention-based GRU model with healthy features for state-of-health estimation of lithium-ion batteries | |
| Xiong et al. | A novel practical state of charge estimation method: an adaptive improved ampere‐hour method based on composite correction factor | |
| Meng et al. | Lithium polymer battery state-of-charge estimation based on adaptive unscented Kalman filter and support vector machine | |
| US20220179009A1 (en) | Method and Apparatus for Operating a System for Providing Predicted States of Health of Electrical Energy Stores for a Device Using Machine Learning Methods | |
| CN107066722A (en) | A kind of combined estimation method of electrokinetic cell system state-of-charge and health status based on electrochemical model | |
| US20220099743A1 (en) | Method and Apparatus for Operating a System for Providing Predicted States of Health of Electrical Energy Stores for a Device Using Machine Learning Methods | |
| CN105911476B (en) | A kind of battery energy storage system SOC prediction techniques based on data mining | |
| Shi et al. | Estimation of battery state-of-charge using ν-support vector regression algorithm | |
| CN115684947A (en) | Battery model construction method and battery degradation prediction device | |
| Cui et al. | State of health diagnosis and remaining useful life prediction for lithium-ion battery based on data model fusion method | |
| Zhang et al. | State of health estimation method for lithium-ion batteries using incremental capacity and long short-term memory network | |
| Wang et al. | Health diagnosis for lithium-ion battery by combining partial incremental capacity and deep belief network during insufficient discharge profile | |
| US20230349977A1 (en) | Method and apparatus for estimating state of health of battery | |
| CN111950205A (en) | Lithium battery SOH prediction method based on FWA optimization extreme learning machine | |
| Jibhkate et al. | Development of low complexity open circuit voltage model for state of charge estimation with novel curve modification technique | |
| CN113125969B (en) | Battery data processing method, device and medium based on AUKF | |
| CN115308608A (en) | All-vanadium redox flow battery voltage prediction method, device and medium | |
| Vedhanayaki et al. | Certain investigation and implementation of Coulomb counting based unscented Kalman filter for state of charge estimation of lithium-ion batteries used in electric vehicle application | |
| Shin et al. | Feature construction for on-board early prediction of electric vehicle battery cycle life | |
| Zhang et al. | Joint estimation of state-of-charge and state-of-power for hybrid supercapacitors using fractional-order adaptive unscented Kalman filter | |
| CN116774045A (en) | Lithium battery health state prediction method based on HHO-SVR |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |