CN113125960A - Vehicle-mounted lithium ion battery charge state prediction method based on random forest model - Google Patents
Vehicle-mounted lithium ion battery charge state prediction method based on random forest model Download PDFInfo
- Publication number
- CN113125960A CN113125960A CN201911402542.0A CN201911402542A CN113125960A CN 113125960 A CN113125960 A CN 113125960A CN 201911402542 A CN201911402542 A CN 201911402542A CN 113125960 A CN113125960 A CN 113125960A
- Authority
- CN
- China
- Prior art keywords
- random forest
- lithium ion
- ion battery
- different
- model
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/385—Arrangements for measuring battery or accumulator variables
- G01R31/387—Determining ampere-hour charge capacity or SoC
- G01R31/388—Determining ampere-hour charge capacity or SoC involving voltage measurements
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Secondary Cells (AREA)
Abstract
The invention discloses a method for predicting the charge state of a vehicle-mounted lithium ion battery based on a random forest model, which comprises the following steps: in the discharging process of the lithium ion battery of the electric automobile, acquiring external characteristic parameters of the lithium ion battery for predicting the SOC of the battery; establishing random forest system models with different input characteristic parameters according to the collected data sets with different characteristic parameters; establishing a training set and a testing set of random forest models with different input parameters by using the random forest system model; establishing prediction models of estimating the state of charge of the lithium ion battery with different input parameters by utilizing the training set and the testing set of the random forest model; and according to the random forest prediction models with different parameters, carrying out precision analysis on the predicted value, determining an optimal solution, and obtaining a prediction result. The method analyzes the influence of different input parameter combinations on the SOC value, utilizes the random forest model to realize the estimation of the battery SOC, has high calculation speed of a prediction result and small error, meets the requirements on the lithium ion battery SOC prediction result under different operating conditions, and has high usability.
Description
Technical Field
The issue belongs to the field of artificial intelligence, and relates to a method for predicting and estimating the state of charge of a vehicle-mounted lithium ion battery.
Background
With the increasing environmental pollution problem, more and more automobile manufacturers begin to research and develop new energy automobiles, and the electric automobiles replacing fuel oil automobiles have become the future development trend. The lithium ion battery has the advantages of long cycle life, strong continuous capability, high specific energy, short charging time, high green and environmental protection performance and the like, and becomes a main power part of the electric automobile. In order to ensure the normal operation of an electric vehicle, a Battery Management System (BMS) is now a research focus, and in the health evaluation of a lithium ion battery management system, the state of charge (SOC) of a battery is a very important part. The SOC, which is an internal feature of the lithium ion battery, cannot be directly measured during the operation of the vehicle, and can be predicted only by external parameters, such as voltage, current, temperature, and internal resistance, which can be directly measured.
The existing battery SOC prediction method comprises a model method and an artificial intelligence method, wherein the model method needs to establish a complex battery equivalent circuit model based on chemical reaction, the accuracy of prediction data depends on the accuracy of the model, and accurate prediction is difficult in practice. The artificial intelligence method is the mainstream method at present, and comprises methods such as a neural network and a support vector machine, on one hand, the methods require huge data quantity and large calculation quantity, and depend on the initial value of data, and the accuracy of the predicted value is low. On the other hand, most methods for predicting the SOC of the lithium ion battery by using an artificial intelligence algorithm are characterized in that the voltage or the current of the battery is independently selected as an input characteristic parameter, so that the method meets the requirement of rapid prediction in the actual situation, but the accuracy is poor. With the increasing quantity of the existing electric automobiles, the data quantity collected by people is more and more huge, the external parameters influencing the battery of the electric automobile not only comprise current and voltage, but also influence of temperature and resistance on the SOC of the battery is considered, the problems of large data quantity and complex calculation process can be caused if all the parameters are calculated by the traditional artificial intelligence method, and the comprehensive prediction is not easy to realize under the actual condition that the prediction is required to be simple, accurate and rapid.
Aiming at the problems, the invention provides a method for predicting the charge state of a vehicle-mounted lithium ion battery based on a random forest model, which has the advantages that: the data of a plurality of characteristics can be processed under the condition of not selecting the characteristics; an initial value independent of data; the training speed is high, and a parallelization method is easy to make; a large part of the features are lost, and the accuracy can still be maintained by using a random forest algorithm; the anti-interference capability is very strong; the overfitting resistance is strong. Meanwhile, the influence of various external parameter combinations of voltage, current, temperature and internal resistance is considered, so that an optimal external parameter combination is found, and the most accurate prediction result is obtained by trying to use the least external parameters.
Disclosure of Invention
In order to solve the problems of the estimation method, the invention provides a vehicle-mounted lithium ion battery state-of-charge prediction method based on a random forest model, the estimation precision of the method is not influenced by an initial value of the battery state-of-charge, the method has automatic identification capability on the working condition used in the process of establishing the model, and the estimation precision is higher; meanwhile, the influence of various external parameters of voltage, current, temperature and internal resistance is considered, and the problem of predicting and evaluating the state of charge of the battery can be better solved.
The method for predicting the charge state of the vehicle-mounted lithium ion battery based on the random forest model comprises the following steps:
s1: in the discharging process of the lithium ion battery of the electric automobile, acquiring external characteristic parameters of the lithium ion battery for predicting the SOC of the battery;
s2: establishing random forest system models with different input characteristic parameters according to the collected data sets with different characteristic parameters;
s3: establishing a training set and a testing set of random forest models with different input parameters by using the random forest system model;
s4: establishing prediction models of estimating the state of charge of the lithium ion battery with different input parameters by utilizing the training set and the testing set of the random forest model;
s5: and according to the random forest prediction models with different parameters, carrying out precision analysis on the predicted value, determining an optimal solution, and obtaining a prediction result.
In step S1, the external characteristic parameters of the battery including voltage (u), current (i), temperature (T), internal resistance (R), and the true value of the battery SOC are collected in real time during the operation of the electric vehicle.
Wherein, in the step S2, the data sets of different input feature parameters are five groups, including:
firstly, voltage, current and temperature; secondly, voltage, current and internal resistance; thirdly, voltage, temperature and internal resistance; fourthly, current, temperature and internal resistance; fifthly, voltage, current, temperature and internal resistance.
In step S3, the training set and the test set are obtained by dividing the data set under each set of feature parameters, and the training set and the test set are divided by 70% and 30%.
In step S4, the random forest prediction model belongs to an artificial intelligence algorithm, and has a three-layer structure including: input layer, intermediate layer, output layer. Wherein:
the input layer is different input characteristic parameter data set combinations in the step S2;
the middle layer is a corresponding mathematical relation between an input layer and an output layer found by machine learning of the random forest model;
the output layer is the SOC value of the lithium ion battery which is wanted.
The process of the constructed random forest prediction model is as follows:
(1) training sets are generated by sampling.
(2) And (5) constructing a decision tree.
(3) Forest formation and algorithm execution.
The random forest prediction model comprises the following specific steps:
(1) and (5) respectively putting the multiple groups of data sets in the step (S2) into parallel random forest prediction models for training to obtain a plurality of different parallel random forest prediction models.
(2) And putting the test sets input by different data sets into parallel random forest prediction models for testing to obtain different SOC output values of the lithium ion battery.
(3) And carrying out error analysis on SOC output values of different lithium ion batteries and actual values of the test set.
Wherein, in the step S5, the performing precision analysis on the predicted value includes: mean Square Error (MSE), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE). The MSE can evaluate the change degree of data, and the smaller the MSE value is, the better the accuracy of the prediction model is. RMSE is the arithmetic square root of MSE. MAE can better reflect the actual situation of predicted value error. Wherein:
the specific calculation formula of the mean square error is as follows:
the specific calculation formula of the root mean square error is as follows:
the average absolute error is specifically calculated by the formula:
the invention provides a vehicle-mounted lithium ion battery state of charge prediction method based on a random forest model, which takes the practical problem that the SOC of an electric vehicle lithium ion battery is directly predicted in operation under the actual condition into consideration. The influence of different input parameter combinations on the SOC value is analyzed, the estimation of the battery charge state is realized by utilizing a random forest model, the calculation speed of the model on the prediction result of the lithium ion charge state is high, the error is small, the requirement of the model on the lithium ion battery charge state prediction result under different operating conditions is met, and the model has high usability.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate an exemplary embodiment of the invention and together with the description, serve to explain the principles of the invention.
FIG. 1 is a flow chart of an implementation of the present invention;
FIG. 2 is a schematic diagram of the basic idea of a regression tree model;
FIG. 3 is a schematic diagram of the basic idea of a random forest model;
fig. 4 is a schematic flow chart of the method for predicting the state of charge of the vehicle-mounted lithium ion battery based on the random forest model.
FIG. 5 is a structural flow chart of the method for predicting the state of charge of the vehicle-mounted lithium ion battery based on the random forest model.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention clearer, the following detailed description of the main embodiments of the present invention will be provided with reference to the accompanying drawings, and those skilled in the art will be able to modify or change the present invention without departing from the scope of the present invention after understanding the present invention. As used herein, "comprising," "including," "having," "containing," and the like are open-ended terms that mean including, but not limited to.
As shown in fig. 1, the method for predicting the state of charge of the vehicle-mounted lithium ion battery based on the random forest model comprises the following steps:
s1: in the discharging process of the lithium ion battery of the electric automobile, acquiring external characteristic parameters of the lithium ion battery for predicting the SOC of the battery;
s2: establishing random forest system models with different input characteristic parameters according to the collected data sets with different characteristic parameters;
s3: establishing a training set and a testing set of random forest models with different input parameters by using the random forest system model;
s4: establishing prediction models of estimating the state of charge of the lithium ion battery with different input parameters by utilizing the training set and the testing set of the random forest model;
s5: and according to the random forest prediction models with different parameters, carrying out precision analysis on the predicted value, determining an optimal solution, and obtaining a prediction result.
More specifically, in step S1, during the operation of the electric vehicle, the external characteristic parameters of the battery including voltage (u), current (i), temperature (T), internal resistance (R), and the true value of the battery SOC are collected in real time.
More specifically, in the step S2, the data sets of the different input feature parameters are five groups, including:
firstly, voltage, current and temperature; secondly, voltage, current and internal resistance; thirdly, voltage, temperature and internal resistance; fourthly, current, temperature and internal resistance; fifthly, voltage, current, temperature and internal resistance.
More specifically, in step S3, the training set and the test set are obtained by dividing the data set under each set of feature parameters, and the training set and the test set are divided by 70% and 30%.
More specifically, in step S4, the random forest prediction model belongs to an artificial intelligence algorithm, which has a three-layer structure including: input layer, intermediate layer, output layer. Wherein:
the input layer is different input characteristic parameter data set combinations in the step S2;
the middle layer is a corresponding mathematical relation between an input layer and an output layer found by machine learning of the random forest model;
the output layer is the SOC value of the lithium ion battery which is wanted.
The process of the constructed random forest prediction model is as follows:
generating a training set through sampling; constructing a decision tree; forest formation and algorithm execution.
More specifically:
(1) training sets are generated by sampling. M decision trees require the generation of M training sets. Obtaining new M training sets from the most original training set by sampling requires statistical sampling knowledge. The new training set is constructed by adopting a sampling mode of returning sampling, namely, the sampling mode of returning the extracted result to the original sample after the sample is extracted.
The sampling can be divided into two parts according to whether we set weight to the sample during sampling: bagging samples and Boosting samples. The idea of the Bagging sampling method is that a weak learning algorithm (a single weak learning algorithm is low in accuracy) and a training set are given, the learning algorithm is used for multiple times to obtain a prediction function sequence, voting or prediction is carried out, and finally the result accuracy is improved to a certain extent. The Boosting method is weighted sampling, which is also called updated weighted sampling. The Boosting method includes the steps that a group of training sets are obtained through random sampling, then weights (the weight is set to be 1/M, M is the number of samples in the training sets) are set for any training set in the group of training sets, after the weights are set for the group, all the training sets are tested, the weights of the training sets with poor performance are improved, a new weight series is obtained, after multiple times of training, each training set has own weight, and the weights influence voting during decision making, so that the final result is influenced.
(2) And (5) constructing a decision tree. One training set can establish one decision tree, and M training sets form a forest with M decision trees. The construction process involves two processes: and randomly selecting the random characteristic variable and splitting the node. Node splitting is the core of the algorithm, and only through node splitting can a decision tree be produced. The generation of each decision tree branch is according to a certain splitting rule, so as to obtain the optimal attribute. In the node splitting process, each attribute is sorted according to rules and indexes, then a certain attribute is selected to be set as a splitting attribute, and branch growth of the decision tree is determined through division. The random selection of the random characteristic variable refers to attributes participating in the comparison of node splitting attributes in the generation process of the algorithm.
(3) Forest formation and algorithm execution.
The basic idea diagram of the random forest model is shown in fig. 3.
The random forest prediction model comprises the following steps:
respectively putting the multiple groups of data sets in the step S2 into parallel random forest prediction models for training to obtain multiple different parallel random forest prediction models; putting test sets input by different data sets into parallel random forest prediction models for testing to obtain different SOC output values of the lithium ion battery; and carrying out error analysis on SOC output values of different lithium ion batteries and actual values of the test set.
More specifically, a random forest model-based vehicle-mounted lithium ion battery state of charge prediction model establishing step:
(1) and determining the growth of the regression tree by using the random parameter vector theta, wherein the leaf node of the corresponding decision tree marked as T (theta) and the decision tree T (theta) is L (x, theta). The training process of the single-course decision tree is shown in fig. 2.
(2) The method comprises the following steps of (1) resampling by adopting a Bootstrap method (Bootstrap is also called a self-expanding method, belongs to a bagging thought, and is a nonparametric method for estimating an overall value by using a small sample.
And constructing M forests. The construction algorithm of the random forest comprises the following steps:
firstly, resampling N samples from a training set D by adopting Bootstrap; then randomly selecting K attributes from all the attributes; then selecting the optimal segmentation attribute; and finally establishing a regression decision tree.
(3) And assuming that the feature vector is K-dimensional, randomly extracting K features from the K features to be used as a splitting feature set of the current node, and splitting the node in the best splitting mode of the K features.
(4) Each regression tree was grown to the maximum extent without pruning.
(5) For a new data X ═ X, the prediction of a single decision tree T (θ) can be obtained by averaging the observations of the leaf nodes L (X, θ). Let the weight vector omegai(x, θ) is:in the formula, observed value xiBelongs to a leaf node L (x, theta) and is not zero, weight omegaiThe sum of (x, θ) equals 1.
(6) Under X, the prediction of a single decision tree is by the observed value σ (X) of the dependent variable:
(7) by weighting ω against the regression treei(x, θ) (t ═ 1, 2.. times, k) is averaged, resulting in a weight ω for each observation i ∈ (1, 2.. times, n)i(x):
wherein, in the step S5, the performing precision analysis on the predicted value includes: mean Square Error (MSE), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE). The MSE can evaluate the change degree of data, and the smaller the MSE value is, the better the accuracy of the prediction model is. RMSE is the arithmetic square root of MSE. MAE can better reflect the actual situation of predicted value error. Wherein:
the specific calculation formula of the mean square error is as follows:
the specific calculation formula of the root mean square error is as follows:
the average absolute error is specifically calculated by the formula:
in summary, a model constructed from the algorithm steps of a random forest is shown in FIG. 4.
Claims (10)
1. A method for predicting the state of charge of a vehicle-mounted lithium ion battery based on a random forest model is characterized by comprising the following steps:
s1: in the discharging process of the lithium ion battery of the electric automobile, acquiring external characteristic parameters of the lithium ion battery for predicting the SOC of the battery;
s2: establishing random forest system models with different input characteristic parameters according to the collected data sets with different characteristic parameters;
s3: establishing a training set and a testing set of random forest models with different input parameters by using the random forest system model;
s4: establishing prediction models of estimation lithium ion battery SOC of different input parameters by utilizing the training set and the testing set of the random forest model;
s5: and according to the random forest prediction models with different parameters, carrying out precision analysis on the predicted value, determining an optimal solution, and obtaining a prediction result.
2. The method for predicting the state of charge of the vehicle-mounted lithium ion battery based on the random forest model according to claim 1, wherein the method comprises the following steps: in step S1, the external characteristic parameters of the battery including voltage (u), current (i), temperature (T), internal resistance (R), and true value of the battery SOC are collected in real time during the operation of the electric vehicle.
3. The method for predicting the state of charge of the vehicle-mounted lithium ion battery based on the random forest model according to claim 1, wherein the method comprises the following steps: in step S2, the data sets of different input feature parameters are five groups, including:
firstly, voltage, current and temperature; secondly, voltage, current and internal resistance; thirdly, voltage, temperature and internal resistance; fourthly, current, temperature and internal resistance; fifthly, voltage, current, temperature and internal resistance.
4. The method for predicting the state of charge of the vehicle-mounted lithium ion battery based on the random forest model according to claim 1, wherein the method comprises the following steps: in step S3, the training set and the test set are obtained by dividing the data set under each set of feature parameters, and dividing the training set and the test set by 70% and 30%.
5. The method for predicting the state of charge of the vehicle-mounted lithium ion battery based on the random forest model according to claim 1, wherein the method comprises the following steps: in step S4, the random forest prediction model belongs to an artificial intelligence algorithm, which has a three-layer structure including: input layer, intermediate layer, output layer.
6. The input layer of claim 5 is a different combination of input feature parameter data sets in step S2; the middle layer is a corresponding mathematical relation between an input layer and an output layer found by machine learning of the random forest model; the output layer is the SOC of the lithium ion battery which is thought to be obtained.
7. The random forest prediction model of claim 5 wherein: the process of the constructed random forest prediction model is as follows:
(1) training sets are generated by sampling.
(2) And (5) constructing a decision tree.
(3) Forest formation and algorithm execution.
8. The forest formation and algorithm execution of claim 7, wherein: the random forest prediction model comprises the following specific steps:
(1) and (5) respectively putting the multiple groups of data sets in the step (S2) into parallel random forest prediction models for training to obtain a plurality of different parallel random forest prediction models.
(2) And putting the test sets input by different data sets into parallel random forest prediction models for testing to obtain different SOC output values of the lithium ion battery.
(3) And carrying out error analysis on SOC output values of different lithium ion batteries and actual values of the test set.
9. The method for predicting the state of charge of the vehicle-mounted lithium ion battery based on the random forest model according to claim 1, wherein the method comprises the following steps: in step S5, the performing precision analysis on the predicted value includes: mean Square Error (MSE), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE). The MSE can evaluate the change degree of data, and the smaller the MSE value is, the better the accuracy of the prediction model is. RMSE is the arithmetic square root of MSE. MAE can better reflect the actual situation of predicted value error.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911402542.0A CN113125960A (en) | 2019-12-31 | 2019-12-31 | Vehicle-mounted lithium ion battery charge state prediction method based on random forest model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911402542.0A CN113125960A (en) | 2019-12-31 | 2019-12-31 | Vehicle-mounted lithium ion battery charge state prediction method based on random forest model |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113125960A true CN113125960A (en) | 2021-07-16 |
Family
ID=76768285
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911402542.0A Pending CN113125960A (en) | 2019-12-31 | 2019-12-31 | Vehicle-mounted lithium ion battery charge state prediction method based on random forest model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113125960A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113759263A (en) * | 2021-08-25 | 2021-12-07 | 电子科技大学长三角研究院(湖州) | Method for predicting charge state of lithium ion battery through artificial intelligence |
CN114580086A (en) * | 2022-05-05 | 2022-06-03 | 中汽研汽车检验中心(天津)有限公司 | Vehicle component modeling method based on supervised machine learning |
CN116500456A (en) * | 2023-06-25 | 2023-07-28 | 威胜信息技术股份有限公司 | Ternary lithium battery capacity detection method based on machine learning |
WO2023202098A1 (en) * | 2022-04-19 | 2023-10-26 | 深圳先进技术研究院 | Lithium battery formation stage product quality prediction method and system |
CN117310506A (en) * | 2023-11-23 | 2023-12-29 | 宁德时代新能源科技股份有限公司 | Method, apparatus and computer readable storage medium for monitoring energy storage power station |
CN117540879A (en) * | 2023-12-26 | 2024-02-09 | 淮阴工学院 | Method for predicting state of charge of lithium battery of new energy electric car |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105427194A (en) * | 2015-12-21 | 2016-03-23 | 西安美林数据技术股份有限公司 | Method and device for electricity sales amount prediction based on random forest regression |
CN105550374A (en) * | 2016-01-29 | 2016-05-04 | 湖南大学 | Random forest parallelization machine studying method for big data in Spark cloud service environment |
CN106021923A (en) * | 2016-05-19 | 2016-10-12 | 江苏理工学院 | Method and system for predicting state of charge of power battery of pure electric vehicle |
CN107843843A (en) * | 2017-09-30 | 2018-03-27 | 江苏理工学院 | A kind of on-vehicle battery SOC on-line prediction methods based on big data and extreme learning machine |
CN109190855A (en) * | 2018-10-26 | 2019-01-11 | 国网上海市电力公司 | A kind of Methods of electric load forecasting based on Spark platform and parallel random forest regression algorithm |
-
2019
- 2019-12-31 CN CN201911402542.0A patent/CN113125960A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105427194A (en) * | 2015-12-21 | 2016-03-23 | 西安美林数据技术股份有限公司 | Method and device for electricity sales amount prediction based on random forest regression |
CN105550374A (en) * | 2016-01-29 | 2016-05-04 | 湖南大学 | Random forest parallelization machine studying method for big data in Spark cloud service environment |
CN106021923A (en) * | 2016-05-19 | 2016-10-12 | 江苏理工学院 | Method and system for predicting state of charge of power battery of pure electric vehicle |
CN107843843A (en) * | 2017-09-30 | 2018-03-27 | 江苏理工学院 | A kind of on-vehicle battery SOC on-line prediction methods based on big data and extreme learning machine |
CN109190855A (en) * | 2018-10-26 | 2019-01-11 | 国网上海市电力公司 | A kind of Methods of electric load forecasting based on Spark platform and parallel random forest regression algorithm |
Non-Patent Citations (2)
Title |
---|
王惠杰等: "基于BP和RBF神经网络的机组能耗特性研究", 《汽轮机技术》 * |
韦振汉等: "基于随机森林的锂离子电池荷电状态估算", 《广西师范大学学报(自然科学版)》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113759263A (en) * | 2021-08-25 | 2021-12-07 | 电子科技大学长三角研究院(湖州) | Method for predicting charge state of lithium ion battery through artificial intelligence |
CN113759263B (en) * | 2021-08-25 | 2023-10-17 | 电子科技大学长三角研究院(湖州) | Method for predicting lithium ion battery state of charge with respect to artificial intelligence |
WO2023202098A1 (en) * | 2022-04-19 | 2023-10-26 | 深圳先进技术研究院 | Lithium battery formation stage product quality prediction method and system |
CN114580086A (en) * | 2022-05-05 | 2022-06-03 | 中汽研汽车检验中心(天津)有限公司 | Vehicle component modeling method based on supervised machine learning |
CN116500456A (en) * | 2023-06-25 | 2023-07-28 | 威胜信息技术股份有限公司 | Ternary lithium battery capacity detection method based on machine learning |
CN116500456B (en) * | 2023-06-25 | 2023-10-10 | 威胜信息技术股份有限公司 | Ternary lithium battery capacity detection method based on machine learning |
CN117310506A (en) * | 2023-11-23 | 2023-12-29 | 宁德时代新能源科技股份有限公司 | Method, apparatus and computer readable storage medium for monitoring energy storage power station |
CN117310506B (en) * | 2023-11-23 | 2024-04-12 | 宁德时代新能源科技股份有限公司 | Method, apparatus and computer readable storage medium for monitoring energy storage power station |
CN117540879A (en) * | 2023-12-26 | 2024-02-09 | 淮阴工学院 | Method for predicting state of charge of lithium battery of new energy electric car |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113125960A (en) | Vehicle-mounted lithium ion battery charge state prediction method based on random forest model | |
CN113805064B (en) | Lithium ion battery pack health state prediction method based on deep learning | |
Mamo et al. | Long short-term memory with attention mechanism for state of charge estimation of lithium-ion batteries | |
CN112380630B (en) | New energy automobile battery thermal runaway risk prediction method based on Internet of vehicles data | |
CN108009585B (en) | Lead-acid battery health state prediction method based on local information fusion | |
CN113702843B (en) | Lithium battery parameter identification and SOC estimation method based on suburb optimization algorithm | |
CN110850298A (en) | Lithium battery SOH estimation method and system based on data driving | |
CN113109717B (en) | Lithium battery state of charge estimation method based on characteristic curve optimization | |
CN109239603A (en) | A kind of extreme learning machine under manifold regularization frame predicts power battery SOC method | |
CN114280479A (en) | Electrochemical impedance spectrum-based rapid sorting method for retired batteries | |
CN115856678A (en) | Lithium ion battery health state estimation method | |
CN115219906A (en) | Multi-model fusion battery state of charge prediction method and system based on GA-PSO optimization | |
CN114966436A (en) | Lithium battery state of charge prediction method, device, equipment and readable storage medium | |
CN117949832B (en) | Battery SOH analysis method based on optimized neural network | |
CN111400935A (en) | Lithium battery third-order model parameter identification method and system based on likelihood function | |
CN111707956A (en) | Method for predicting health state and residual life of multi-type lithium ion battery pack management system | |
CN115963407A (en) | ICGWO (intensive care unit) optimization ELM (element-based robust model) based lithium battery SOC estimation method | |
CN113484774A (en) | Lithium battery pack capacity estimation method based on temperature calibration and neural network | |
Yang et al. | A new self-learning TLBO algorithm for RBF neural modelling of batteries in electric vehicles | |
CN111337833B (en) | Lithium battery capacity integrated prediction method based on dynamic time-varying weight | |
CN117289167A (en) | Battery remaining life prediction method, device and medium based on multiple neural network | |
CN116930769A (en) | Lithium battery modeling method based on bidirectional generation type antagonistic neural network | |
Lyu et al. | State-of-charge estimation of lithium-ion batteries based on deep neural network | |
Song et al. | Capacity estimation method of lithium-ion batteries based on deep convolution neural network | |
CN116859259A (en) | Battery health state estimation method based on integrated learning and real vehicle big data |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210716 |
|
WD01 | Invention patent application deemed withdrawn after publication |