CN114839536B - Lithium ion battery health state estimation method based on multiple health factors - Google Patents
Lithium ion battery health state estimation method based on multiple health factors Download PDFInfo
- Publication number
- CN114839536B CN114839536B CN202210352554.2A CN202210352554A CN114839536B CN 114839536 B CN114839536 B CN 114839536B CN 202210352554 A CN202210352554 A CN 202210352554A CN 114839536 B CN114839536 B CN 114839536B
- Authority
- CN
- China
- Prior art keywords
- battery
- health
- charging
- voltage
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 title claims abstract description 10
- 229910001416 lithium ion Inorganic materials 0.000 title claims abstract description 10
- 238000007600 charging Methods 0.000 claims abstract description 64
- 238000012549 training Methods 0.000 claims abstract description 11
- 239000013598 vector Substances 0.000 claims abstract description 6
- 230000000630 rising effect Effects 0.000 claims description 8
- 230000015556 catabolic process Effects 0.000 claims description 3
- 238000006731 degradation reaction Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 230000001174 ascending effect Effects 0.000 claims description 2
- 238000012795 verification Methods 0.000 claims description 2
- 238000012360 testing method Methods 0.000 abstract description 5
- 238000010277 constant-current charging Methods 0.000 abstract description 3
- 238000011156 evaluation Methods 0.000 abstract 1
- 238000002474 experimental method Methods 0.000 abstract 1
- 230000007547 defect Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- GELKBWJHTRAYNV-UHFFFAOYSA-K lithium iron phosphate Chemical compound [Li+].[Fe+2].[O-]P([O-])([O-])=O GELKBWJHTRAYNV-UHFFFAOYSA-K 0.000 description 2
- 208000032953 Device battery issue Diseases 0.000 description 1
- 238000010280 constant potential charging Methods 0.000 description 1
- 238000010281 constant-current constant-voltage charging Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000013021 overheating Methods 0.000 description 1
- 238000007086 side reaction Methods 0.000 description 1
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]
- G01R31/392—Determining battery ageing or deterioration, e.g. state of health
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/60—Other road transportation technologies with climate change mitigation effect
- Y02T10/70—Energy storage systems for electromobility, e.g. batteries
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Algebra (AREA)
- Evolutionary Biology (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
- Secondary Cells (AREA)
Abstract
The invention discloses a lithium ion battery health state estimation method based on multiple health factors, belongs to the technical field of battery management, and mainly solves the problem of low battery health state estimation precision under the condition of quick charge. Based on voltage and current test data in a battery rapid charge-discharge cycle experiment, extracting health factors from a constant current charging process to form a feature vector, wherein the feature vector comprises charging time, charging energy and information entropy in a local voltage interval in the charging process. And taking the feature vector as input, taking the battery SOH as output, establishing a Gaussian process regression prediction model, and training the Gaussian process regression model by using experimental data. In an on-line state, an input feature vector is obtained and is input into a trained Gaussian process regression model, so that the battery SOH can be predicted. The invention does not need to build a complex battery physical model, can realize the on-line evaluation of the battery SOH by a data driving method, and has very high accuracy and better universality.
Description
Technical Field
The invention relates to a lithium ion battery health state estimation method based on multiple health factors, belongs to the technical field of power battery management, and is used for estimating the health state of a vehicle-mounted power lithium ion battery under the condition of rapid charging.
Background
In the field of electric automobiles, lithium ion batteries are the primary energy storage devices. With the extension of the service time, the performance of the battery can decline, the available capacity, the output power and the like of the battery are affected, and the safety problem can be caused under certain conditions. The general battery state of health (SOH) of the battery industry characterizes the performance degradation degree of the battery, and the SOH of the new power battery is specified to be 1 or 100%; and when the battery performance cannot meet the use requirement, the battery is considered to be invalid, and the service life is finished. The SOH values of battery failures defined in different application occasions are different, and when the soh=70% of the power battery is considered to be the soh=70% of the pure electric vehicle mainly requiring energy, the battery cannot meet the normal requirement, namely the service life of the battery is finished, and when the soh=80% of the power battery is considered to be the end-of-use condition of the power battery for the hybrid electric vehicle mainly requiring power. Therefore, the lithium ion battery is properly managed and monitored, the battery health state can be accurately estimated, the performance of the electric automobile can be ensured, the abuse of the battery can be effectively prevented, and the occurrence of safety accidents is avoided.
The quick charging technology is a more approved access point for the electric automobile, and compared with a common charging mode, the high-current quick charging can save the charging time, and can be compared with the conventional automobile refueling time. However, the rapid charging is easier to cause side reactions and overheating phenomena in the battery, and has potential damage to the electrode structure of the battery, which may cause rapid changes in the state of health of the battery.
The estimation of the state of health of the lithium ion battery based on the conventional charging process is generally based on the health factor extracted from the battery charging experimental data to estimate the state of health of the battery, such as constant current charging time, constant voltage charging time, etc. The extraction of these factors depends on a conventional constant-current constant-voltage charging mode. Under high current charging conditions, the charging current is often stepped, with a very high current, and after reaching the limiting voltage, the current is reduced, charging continues to the limiting voltage, and the process is repeated. Thus, the charging is segmented, and the length of the charging time is closely related to the magnitude of the current used. Under such conditions, the state of health of the battery can no longer be effectively estimated by merely selecting the constant current charging time.
In the practice of estimating the state of health of the battery, the degree of degradation of the performance of the battery is not uniform, even with large differences, due to inconsistencies within the battery, even for the same lot of batteries. The battery state of health estimation by adopting a plurality of health factors can effectively solve the limitation of a single health factor, and the battery state of health can be estimated more accurately.
The patent provides an estimation method based on multiple health factors, which aims at estimating the health state of a battery under the current rapid charging condition, designs an extraction method based on partial voltage interval health factors, and can accurately estimate the health state of the battery without using a conventional charging method.
Disclosure of Invention
The invention aims to provide a lithium ion battery health state estimation method based on a rapid charging condition, which comprises the following steps: three health factors of charging time, charging energy and information entropy in a local voltage interval in a battery rapid charging process are extracted, and a Gaussian Process Regression (GPR) model is utilized to estimate the SOH of the battery. The method can realize the estimation of the battery health state of the battery under a high-current rapid charging strategy, and the estimation precision is greatly improved compared with a single health factor.
The specific implementation steps are as follows:
S1, extracting the charging time in a local voltage interval [ V a,Vb ] in the heavy current charging process as a first health factor, and obtaining the heavy current charging method by using a formula (1)
t＝tb-ta (1)
Wherein t a is the charging time corresponding to the charging voltage rising to V a, t b is the charging time corresponding to the charging voltage rising to V b, and t is the charging time corresponding to the voltage interval [ V a,Vb ]. The voltage interval may be selected according to the battery type, where the voltage corresponding to the lithium iron phosphate battery is V a＝3.15V,Vb =3.55v.
S2, extracting charging energy in a local voltage interval [ V a,Vb ] in the heavy current charging process as a second health factor, and obtaining the energy by using a formula (2)
Wherein t a is the charging time corresponding to the charging voltage rising to V a, t b is the charging time corresponding to the charging voltage rising to V b, I is the charging current, and V (t) is the time-varying voltage.
S3, extracting a third health factor by using the information entropy in the partial voltage interval [ V a,Vb ] in the large-current charging process, and obtaining the high-voltage energy-saving type charging device by using the formula (3)
The entropy index E k is represented by a charging voltage distribution within a certain voltage range, and the voltage range is determined by a minimum voltage value V a and a maximum voltage value V b. The voltage range is divided into a fixed number of intervals, i.e. every 0.1V the voltage range V a,Vb is divided into one cell, M is the number of cells, p (i) represents the frequency at which the voltage measurement occurs in each small voltage interval.
S4, using the three extracted health factors as input and the health state of the battery as output, and establishing a training data set and a prediction data set
S5, a Gaussian process regression algorithm is used for establishing a model, namely, a Gaussian process regression model y i＝f(HFi)+εi is established by taking HF i and y i as input and output respectively, wherein,For the health factors extracted in steps (1), (2) and (3), epsilon i is gaussian noise with mean value of 0 and variance of sigma n, expressed as formula (4), and y i is the state of health of the battery at i time. f (HF i) is a function of the health factor, belonging to the Gaussian process, expressed asThe process is determined by a mean function and a covariance function, expressed as equations (5) and (6), respectively
εi～N(0,σn 2) (4)
mHF＝E(f(HF)) (5)
The mean and covariance functions were chosen to be 0 and Matern/2, respectively, where Matern5/2 is expressed as equation (7)
Wherein,Σ f and σ l are hyper-parameters of the covariance function.
And S6, importing the training data set into a Gaussian process regression model for training, and obtaining and optimizing the hyper-parameters of the model. In the model established in the step 5, there is a super parameter Θ= [ σ n,σl,σf ], and the super parameter of the model is optimized by using training data to obtain an optimal result. The maximized log-marginal likelihood function is used to optimize the super-parameters as shown in equation (8):
The function comprises three parts of contents, wherein the first part is a data fitting item and represents the fitting degree of the super parameter; the second part is a complexity penalty term, which is used for preventing overfitting; the third part is a constant term. Optimizing the super-parameters by adopting a gradient ascending method, and obtaining the partial derivative of the formula (8):
wherein β= (K HF,HF+σn 2In)-1 y).
After the optimized super parameters are obtained through formulas (8) and (9), new input HF 'is given to the model, and a predicted value y' of the battery health state is output.
And S7, importing the prediction data set into a trained model for verification, and judging the accuracy of the model by using root mean square error and average absolute error.
And S8, under the online condition, using the extracted three health factors as input vectors of a Gaussian process regression model, and outputting the health state of the battery by the model.
Drawings
FIG. 1 is SOH predicted by cell number 1 based on the GPR model for single health factor.
FIG. 2 is SOH predicted by cell number 1 based on the GPR model for multiple health factors.
FIG. 3 is SOH predicted by cell number 2 based on the GPR model for single health factor.
FIG. 4 is SOH predicted by cell number 2 based on the GPR model for multiple health factors.
FIG. 5 is SOH predicted by cell number 3 based on the GPR model for single health factor.
FIG. 6 is SOH predicted by cell number 3 based on the GPR model for multiple health factors.
FIG. 7 is SOH predicted by cell number 4 based on the GPR model for single health factor.
FIG. 8 is SOH predicted by cell number 4 based on the GPR model for multiple health factors.
FIG. 9 is SOH predicted by cell number 5 based on the GPR model for single health factor.
FIG. 10 is SOH predicted by cell number 5 based on the GPR model for multiple health factors.
FIG. 11 is SOH predicted by cell number 6 based on the GPR model for single health factor.
FIG. 12 is SOH predicted by cell number 6 based on the GPR model for multiple health factors.
FIG. 13 is a schematic flow chart of the method of the present invention.
Detailed Description
The technical scheme of the present invention is described in detail below with reference to the accompanying drawings and embodiments.
According to the method, the circulating charge and discharge data of the lithium iron phosphate battery in the laboratory are used for estimating and calculating SOH of 6 batteries under 3 different charging strategies, and the battery and the charge and discharge working conditions are shown in table 1.
Table 1 charge strategy and discharge test condition specification for test cells
Implementation case:
The number 1-6 batteries are respectively subjected to charge-discharge cycles under the working conditions shown in table 1, and the data set is divided into training data and test data based on voltage-current capacity data information obtained by the charge-discharge cycles. In the training data, t, E and 1/E k are extracted as inputs of the multivariate GPR model, SOH is taken as output, and the GPR model is trained. And in the test data set, obtaining a multi-health factor SOH estimation result of 6 batteries by using the established model. In addition, in order to compare the superiority of the multiple health factor estimation method, the battery state of health is estimated by using the charging time t of the battery in the same voltage range as the health factor, and compared with the multiple health factor as the input estimation method. Since the Mean Absolute Error (MAE) can better reflect the actual situation of the predicted value error, the Root Mean Square Error (RMSE) is very sensitive to the extra large or small error in a set of measurements, and thus can better reflect the accuracy of the prediction. The estimation accuracy of both methods is thus measured by Mean Absolute Error (MAE) and Root Mean Square Error (RMSE), as shown in table 2.
Table 2 SOH estimation error for single and multiple health factors
From Table 2, the accuracy of the estimation of multiple health factors is very high, MAE in [0.0039,0.0058] range and RMSE in [0.00480.0076] range. For cell number 2, the MAE error was reduced from 0.0193 to 0.0039 and RMSE was reduced from 0.0244 to 0.0048. For cell number 6, the MAE error was reduced from 0.0149 to 0.0053 and the RMSE was reduced from 0.0187 to 0.0061. The SOH estimation precision of the multi-health factors of the 6 batteries is improved by at least 37% relative to the estimation precision of the single health factor, and the estimation precision of the rest batteries except the No. 1 and No. 5 batteries is improved by more than 50%, and error analysis shows that compared with the single health factor, the estimation precision of the multi-health factors is obviously improved.
In view of the above application, the estimation method adopting single characteristics can realize the SOH estimation of the battery, but because the single health characteristics have limitations in reflecting the health state of the battery, the SOH estimation precision of the battery is lower, and unlike the single characteristic estimation method, the multi-health characteristic estimation method can well compensate the defect of the limitation of the single characteristics, and the estimation precision is greatly improved. Furthermore, since the health features are extracted based on partial voltage intervals, an estimation of the state of health of the battery in case of incomplete charging can be achieved.
The above examples can effectively demonstrate the superiority of the method of the present invention: the method has the advantages that the SOH estimation of the battery under the condition of quick charge is realized by adopting the quick charge experimental data to extract the health factors, the state of health of the battery can be accurately estimated under the condition of incomplete charge of the battery, and compared with a single factor estimation method, the method can make up the defect of a single characteristic estimation method, and the estimation precision is greatly improved. In addition, the method of the invention is verified under 6 different batteries and 3 different heavy current charging working conditions, and has good universality.
Claims (1)
1. A lithium ion battery health state estimation method based on multiple health factors is characterized in that: the method takes charging time t, charging energy E and information entropy E k in a local voltage interval in a rapid charging process as health factors, a battery capacity degradation model is established by utilizing a Gaussian process regression algorithm, and finally the health state SOH of the battery is determined;
The specific implementation steps are as follows:
Step (1): extracting the charging time in a local voltage interval [ V a,Vb ] in the high-current charging process as a first health factor, and obtaining by using a formula (1):
t＝tb-ta (1)
Wherein t a is the charging time corresponding to the charging voltage rising to V a, t b is the charging time corresponding to the charging voltage rising to V b, and t is the charging time corresponding to the voltage interval [ V a,Vb ];
step (2): extracting the charging energy in a local voltage interval [ V a,Vb ] in the high-current charging process as a second health factor, and obtaining by using a formula (2):
Wherein t a is the charging time corresponding to the charging voltage rising to V a, t b is the charging time corresponding to the charging voltage rising to V b, I is the charging current, and V (t) is the time-varying voltage;
Step (3): extracting a third health factor by using the information entropy in a partial voltage interval [ V a,Vb ] in the high-current charging process, and obtaining by using a formula (3):
The entropy index E k is represented by a charging voltage distribution in a certain voltage range, and the voltage range is determined by a minimum voltage value V a and a maximum voltage value V b; dividing the voltage range into a fixed number of intervals, namely dividing the voltage range [ V a,Vb ] into a small voltage interval every 0.1V, wherein M is the number of the small voltage intervals, p (ii) represents the frequency of occurrence of the voltage measurement value in each small voltage interval, and ii is the sequence number of the voltage intervals;
step (4): using the extracted three health factors as input and the health state of the battery as output to establish a training data set and a prediction data set;
Step (5): a gaussian process regression algorithm is used to build the model, i.e., a gaussian process regression model y i＝f(HFi)+εi is built with HF i and y i as inputs and outputs, respectively, wherein, For the health factors extracted in the steps (1), (2) and (3), epsilon i is Gaussian noise with the mean value of 0 and variance sigma n, and is expressed as a formula (4), and y i is the health state of the battery at the moment i; f (HF i) is a function of the health factor, belonging to the Gaussian process, expressed asThe Gaussian process is determined by a mean function and a covariance function, expressed as equations (5) and (6), respectively
εi～N(0,σn 2) (4)
mHF＝E(f(HF)) (5)
The mean and covariance functions were chosen to be 0 and Matem/2, respectively, where Matern5/2 is expressed as equation (7)
Wherein,Σ f and σ l are hyper-parameters of the covariance function;
Step (6): the training data set is imported into a Gaussian process regression model for training, and super parameters of the model are obtained and optimized; in the Gaussian process regression model established in the step (5), super parameters theta= [ sigma n,σl,σf ] exist, and the super parameters of the Gaussian process regression model are optimized by utilizing training data so as to obtain an optimal result; the maximized log-marginal likelihood function is used to optimize the super-parameters as shown in equation (8):
The maximized log-marginal likelihood function comprises three parts of contents, wherein the first part is a data fitting item and represents the fitting degree of the super-parameters; the second part is a complexity penalty term, which is used for preventing overfitting; the third part is a constant term; optimizing the super-parameters by adopting a gradient ascending method, and obtaining the partial derivative of the formula (8):
wherein β= (K HF,HF+σn 2In)-1 y;
after obtaining optimized super parameters through formulas (8) and (9), giving new input HF 'to the model, and outputting a predicted value y' of the state of health of the battery;
Step (7): leading the predicted data set into a trained model for verification, and judging the accuracy of the model by using root mean square error and average absolute error;
Step (8): under the on-line condition, the three extracted health factors are used as input vectors of a Gaussian process regression model, and the model can output the health state of the battery.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210352554.2A CN114839536B (en) | 2022-04-05 | 2022-04-05 | Lithium ion battery health state estimation method based on multiple health factors |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210352554.2A CN114839536B (en) | 2022-04-05 | 2022-04-05 | Lithium ion battery health state estimation method based on multiple health factors |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114839536A CN114839536A (en) | 2022-08-02 |
| CN114839536B true CN114839536B (en) | 2024-06-04 |
Family
ID=82564193
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210352554.2A Active CN114839536B (en) | 2022-04-05 | 2022-04-05 | Lithium ion battery health state estimation method based on multiple health factors |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114839536B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116256648A (en) * | 2023-05-16 | 2023-06-13 | 合肥力高动力科技有限公司 | Lithium battery SOH estimation method based on charging data |
| CN116381540B (en) * | 2023-06-05 | 2023-08-22 | 石家庄学院 | Battery health monitoring system under computer running state |
| CN116953554A (en) * | 2023-07-25 | 2023-10-27 | 国网江苏省电力有限公司镇江供电分公司 | Multi-fragment data-based method and device for estimating SOH of lithium battery of energy storage power station |
| CN116736141A (en) * | 2023-08-10 | 2023-09-12 | 锦浪科技股份有限公司 | Lithium battery energy storage safety management system and method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019162749A1 (en) * | 2017-12-07 | 2019-08-29 | Yazami Ip Pte. Ltd. | Method and system for online assessing state of health of a battery |
| 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 |
| CN111398837A (en) * | 2020-04-01 | 2020-07-10 | 重庆大学 | Vehicle battery health state estimation method based on data driving |
| WO2020191800A1 (en) * | 2019-03-27 | 2020-10-01 | 东北大学 | Method for predicting remaining service life of lithium-ion battery employing wde-optimized lstm network |
| CN113030744A (en) * | 2021-02-24 | 2021-06-25 | 上海交通大学 | Battery health condition prediction method, system and medium based on health factor extraction |
| CN113189490A (en) * | 2021-05-17 | 2021-07-30 | 武汉理工大学 | Lithium battery health state estimation method based on feature screening and Gaussian process regression |
| WO2021185308A1 (en) * | 2020-03-18 | 2021-09-23 | 北京理工大学 | Online determination method and system for state of health of power battery pack of electric vehicle |
-
2022
- 2022-04-05 CN CN202210352554.2A patent/CN114839536B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019162749A1 (en) * | 2017-12-07 | 2019-08-29 | Yazami Ip Pte. Ltd. | Method and system for online assessing state of health of a battery |
| WO2020191800A1 (en) * | 2019-03-27 | 2020-10-01 | 东北大学 | Method for predicting remaining service life of lithium-ion battery employing wde-optimized lstm network |
| 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 |
| WO2021185308A1 (en) * | 2020-03-18 | 2021-09-23 | 北京理工大学 | Online determination method and system for state of health of power battery pack of electric vehicle |
| CN111398837A (en) * | 2020-04-01 | 2020-07-10 | 重庆大学 | Vehicle battery health state estimation method based on data driving |
| CN113030744A (en) * | 2021-02-24 | 2021-06-25 | 上海交通大学 | Battery health condition prediction method, system and medium based on health factor extraction |
| CN113189490A (en) * | 2021-05-17 | 2021-07-30 | 武汉理工大学 | Lithium battery health state estimation method based on feature screening and Gaussian process regression |
Non-Patent Citations (5)
| Title |
|---|
| Yanqin Zhang ; Huafeng Zhang ; Zhiwei Tian.The Application Of Gaussian Process Regression In State Of Health Prediction Of Lithium Ion Batteries.PROCEEDINGS OF 2018 IEEE 3RD ADVANCED INFORMATION TECHNOLOGY, ELECTRONIC AND AUTOMATION CONTROL CONFERENCE (IAEAC 2018).2019,全文. * |
| 动力电池动态模型参数辨识的研究;张彦琴;郭凯;刘汉雨;吴斌;李怡霞;;电池工业;20130425(第Z1期);全文 * |
| 基于能量加权高斯过程回归的锂离子电池健康状态预测;郑雪莹;邓晓刚;曹玉苹;;电子测量与仪器学报;20200615(第06期);全文 * |
| 基于高斯过程回归的锂离子电池SOC估计;李嘉波;魏孟;叶敏;焦生杰;徐信芯;;储能科学与技术(第01期);全文 * |
| 锂离子电池健康评估和寿命预测综述;刘大同;周建宝;郭力萌;彭宇;;仪器仪表学报;20150115(第01期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114839536A (en) | 2022-08-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114839536B (en) | Lithium ion battery health state estimation method based on multiple health factors | |
| CN112034356B (en) | GP-UKF-based online SOH estimation method for electric vehicle power battery | |
| Tian et al. | Consistency evaluation and cluster analysis for lithium-ion battery pack in electric vehicles | |
| Zhou et al. | A low-complexity state of charge estimation method for series-connected lithium-ion battery pack used in electric vehicles | |
| CN112526348B (en) | Battery model parameter identification method based on multi-innovation recursive Bayesian algorithm | |
| CN107741568B (en) | Lithium battery SOC estimation method based on state transition optimization RBF neural network | |
| CN110632528B (en) | Lithium battery SOH estimation method based on internal resistance detection | |
| CN110346734A (en) | A kind of lithium-ion-power cell health status evaluation method based on machine learning | |
| CN111352032A (en) | Lithium battery dynamic peak power prediction method | |
| Huang et al. | Soc estimation of li-ion battery based on improved ekf algorithm | |
| CN111965560B (en) | Battery health state estimation method oriented to general discharge working condition | |
| CN113064089B (en) | Internal resistance detection method, device, medium and system of power battery | |
| Lee et al. | Enhanced coulomb counting method for SoC and SoH estimation based on coulombic efficiency | |
| CN112163372B (en) | SOC estimation method of power battery | |
| Xu et al. | A vehicle-cloud collaborative method for multi-type fault diagnosis of lithium-ion batteries | |
| CN103983920A (en) | Method for establishing model of power battery of electric vehicle | |
| CN103529397A (en) | Method for estimating electric quantity of battery and system for managing electric quantity of battery | |
| CN114781176B (en) | Equivalent circuit parameter identification method for lumped parameters of lithium ion battery energy storage system | |
| CN117719345B (en) | Battery micro-short circuit quantification method considering aging based on IC curve | |
| CN114646888A (en) | Assessment method and system for capacity attenuation of power battery | |
| CN114545275A (en) | Indirect prediction method for remaining service life of lithium ion battery | |
| CN112946480B (en) | Lithium battery circuit model simplification method for improving SOC estimation real-time performance | |
| CN110297185A (en) | A kind of new energy car battery dynamic state of parameters monitoring system | |
| CN117709396A (en) | Lithium ion battery energy state prediction method | |
| CN116466250A (en) | Dynamic working condition model error characteristic-based power battery health state estimation method |
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 |