CN105137358B - The SOC/SOH Forecasting Methodologies of power battery based on big data self-study mechanism - Google Patents
The SOC/SOH Forecasting Methodologies of power battery based on big data self-study mechanism Download PDFInfo
- Publication number
- CN105137358B CN105137358B CN201510532492.3A CN201510532492A CN105137358B CN 105137358 B CN105137358 B CN 105137358B CN 201510532492 A CN201510532492 A CN 201510532492A CN 105137358 B CN105137358 B CN 105137358B
- Authority
- CN
- China
- Prior art keywords
- soh
- soc
- battery
- charge
- power battery
- 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
Landscapes
- Secondary Cells (AREA)
Abstract
The invention discloses a kind of SOC/SOH Forecasting Methodologies of the power battery based on big data self-study mechanism, including:S1, provide power battery SOC/SOH prediction model;Model, the measured value of V, I, T, σ up to the present measured after the charge and discharge cycles of current battery start after obtained amendment after S2, the charge and discharge cycles based on a upper battery pack, predicted from prediction model current SOC~/SOH~;After one S3, completion complete charge and discharge cycles, the SOC based on prediction~/SOH~and the SOC/SOH actually measured are modified the prediction model after upper one cycle;S4, the prediction for carrying out SOC/SOH using revised prediction model in next battery set charge/discharge cycle.The present invention can be monitored power battery real time execution and health status, and detection process is an automated procedure, without manual intervention.The present invention can carry out real-time alert processing to accident, such as lithium battery burning simultaneously, improve the security performance of power battery.
Description
Technical field
The present invention relates to power battery detection technique field, more particularly to a kind of dynamic based on big data self-study mechanism
The SOC/SOH Forecasting Methodologies of power battery.
Background technology
New-energy automobile and energy-storage system are the hot spots in one of our times various countries development priority direction and market.And
Dynamic lithium battery is one of core key technology of new-energy automobile and energy-storage system.The volume calculation SOC of dynamic lithium battery and
Health estimation SOH is world-famous puzzle again, therefore a series of dangerous accidents hinder the development of new energy.It is of the invention special
Profit is exactly to carry out operation, analysis, automatic modeling to the big data obtained from battery-end by a kind of self study, Self-organization Mechanism,
It is estimated so as to obtain more accurate SOC, SOH and safety.Promote the sound development of new energy battery.
Currently, to the estimation of SOC and SOH generally all in BMS (Battery Management System, battery management system
System) inside completion.The BMS of commercial batteries group is based on cost reason, often all by with basic digital signal processor DSP function
Microcontroller is realized to battery set charge/discharge management, battery balanced etc., includes the estimation to SOC and SOH.And based on same
Reason, usually without a large amount of storaging chip, historical events or performance data to battery pack almost or are not made for BMS inside
Retain.When estimating SOC and SOH, such as situation based on relative complex nonlinear model generally all first will be non-linear
Model simplifies processing and transformation to linearity approximate processing, this will introduce appreciable error to the estimation of SOC and SOH.Meanwhile one
As the measurement of the voltage to moment, electric current and temperature is all based on to the estimation of SOC and SOH to calculate instant internal resistance, then and electricity
It is compared and is obtained in the estimation to SOC and SOH when pond initially uses, ignore historical information, needless to say criticize with reference to using same
The operation or error message of other secondary batteries.Nowadays, people increasingly have found the ageing process of battery, history charge and discharge process,
Internal resistance change procedure all plays the performance of SOC and SOH sizable, it is necessary to monitor and these data is utilized to carry out SOC
With the estimation of SOH, with reference to using with the batch even operation or error message of different batches other batteries.
Therefore, for above-mentioned technical problem, it is necessary to provide a kind of power battery based on big data self-study mechanism
SOC/SOH Forecasting Methodologies.
Invention content
In order to overcome the deficiencies of the prior art, the purpose of the present invention is to provide a kind of dynamic based on big data self-study mechanism
The SOC/SOH Forecasting Methodologies of power battery.
To achieve these goals, technical solution provided in an embodiment of the present invention is as follows:
A kind of SOC/SOH Forecasting Methodologies of the power battery based on big data self-study mechanism, the method includes:
S1, provide power battery SOC/SOH prediction model;
Model after obtained amendment after S2, the charge and discharge cycles based on a upper battery pack, in the charge and discharge of current battery
The measured value of V, I, T, σ up to the present that electricity cycle measures after starting, predict current SOC~/SOH from prediction model
~;
After one S3, completion complete charge and discharge cycles, the SOC based on prediction~/SOH~and the SOC/ actually measured
SOH is modified the prediction model after upper one cycle;
S4, the prediction for carrying out SOC/SOH using revised prediction model in next battery set charge/discharge cycle.
As a further improvement on the present invention, the step S2 is further included:
Periodically the electrical characteristics of battery pack are measured, and by measured data with a multigroup vector Xk nCarry out table
Show, Xk n∈Xn, and
Wherein Vk M、Ik M、Tk M、σk MVoltage, the electricity measured in the M times measurement that respectively battery pack k is carried out in n cycles
Stream, temperature and modifying factor.
As a further improvement on the present invention, the step S2 is further included:
The SOC/SOH of battery pack is predicted by the sample set measured, the X after n charge and discharge cycles are undergonek=
(Xk 1,Xk 2,....Xk n);
The all possible value for defining SOC and SOH is defined as state space S, and
After battery pack k completes n-th of cycle, the state of SOC/SOH is Sk。
As a further improvement on the present invention, the step S3 is specifically included:
S31, reward functions U is estimated, to each battery pack k, after n-th of cycle of experience, n=1,2....., N, I
Make one and estimate decision ak n∈ S define one and recurring number n relevant award factor rk n;
S32, a complete predicting strategy π is determined, and according to xkProbability-distribution function f (x) find out optimal predictor plan
Slightly πopt, wherein, πn:Xn→ S, π=(π1..., πn) completely estimate strategy for one, the sample set obtained to battery k
xk, its tactful π that estimates determines the correction that the need after each cycle is estimated are implemented, it and one and the relevant awards of n
Function is related, i.e. rn(x|π);
S33, in Xk nOn the basis of complete ak nDefinition is expected afterwards awards, and misses function by study definition expection.
As a further improvement on the present invention, in the step S31, reward functions U is specially:U(ak n, Sk,n)=θ
(ak n, Sk)+λ ψ (n), wherein, θ (ak n, Sk) precision estimated is depicted, ψ (n) expression is the timeliness estimated, and λ is more than 0
Coefficient, award factor rk n=U (ak n, Sk, n).
As a further improvement on the present invention, in the step S32, optimal predictor strategy π opt=argmaxV (π),
In, V (π)=∫z∈XR (x | π) f (x) dx, f (x) are xkProbability-distribution function.
As a further improvement on the present invention, in the step S33, strategy π is given-n=(π1..., πn-1, πn+1...,
πN), it is contemplated that award be:
As a further improvement on the present invention, in the step S33, it is contemplated that missing function is:
SOC/SOH Forecasting Methodologies the present invention is based on the power battery of big data self-study mechanism can be to power battery reality
Shi Yunhang and health status are monitored, and detection process is an automated procedure, without manual intervention.The present invention can be right simultaneously
Accident, such as lithium battery burning carry out real-time alert processing, improve the security performance of power battery.
Description of the drawings
Fig. 1 is the flow signal of the SOC/SOH Forecasting Methodologies of the power battery the present invention is based on big data self-study mechanism
Figure.
Fig. 2 is the module diagram the present invention is based on big data self-study mechanism.
Fig. 3 is the Modifying model schematic diagram of the present invention.
Fig. 4 is the state scattergram of SOC and SOH in the embodiment of the invention.
Specific embodiment
In order to which those skilled in the art is made to more fully understand the technical solution in the present invention, below in conjunction with of the invention real
The attached drawing in example is applied, the technical solution in the embodiment of the present invention is clearly and completely described, it is clear that described implementation
Example is only part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, this field is common
Technical staff's all other embodiments obtained without making creative work, should all belong to protection of the present invention
Range.
The invention discloses a kind of SOC/SOH Forecasting Methodologies of the power battery based on big data self-study mechanism, determine
Justice the two of one battery SOC (State of Charge, charged state) and SOH (State of Health, health status)
Dimension space, it is more next to the division of this two-dimensional space with the increase for the tested dynamic lithium battery group number for entering big data system
It is thinner therefore also higher and higher to the estimation precision of SOC and SOH.
The present invention obtains from each power battery of actual motion and stores real-time voltage, electric current, temperature parameter, group
Into a bivariate table, the modelling of this bivariate table is expressed by self study engine, is mapped to a unit of two-dimensional space.
Specifically, join shown in Fig. 1, method described above specifically includes:
S1, provide power battery SOC/SOH prediction model;
Model after obtained amendment after S2, the charge and discharge cycles based on a upper battery pack, in the charge and discharge of current battery
The measured value of V, I, T, σ up to the present that electricity cycle measures after starting, predict current SOC~/SOH from prediction model
~;
After one S3, completion complete charge and discharge cycles, the SOC based on prediction~/SOH~and the SOC/ actually measured
SOH is modified the prediction model after upper one cycle;
S4, the prediction for carrying out SOC/SOH using revised prediction model in next battery set charge/discharge cycle.
Join Fig. 2 shown in, V (t), I (t), T (t) be respectively t moment measure power battery voltage, discharge current, temperature,
SOC~(t) and SOH~(t) is respectively the power battery state parameter of t moment real-time estimation.
With reference to Fig. 3, based on model after obtained amendment after upper one cycle, surveyed with reference to rear since a new cycle
V, I, T, σ up to the present measured value, estimated from model current SOC~, SOH~, when complete one it is complete
After whole charge and discharge cycles, based on the SOC estimated~/SOH~and the practical SOC/SOH measured to upper one cycle after
Model is modified, for being used in next charge and discharge cycles SOC~and SOH~estimation.
We explain in detail for the self-study mechanism for the monitoring of power battery cloud proposed below.We are each battery
K ∈ { 1,2 ... .K } are numbered in group, each battery pack is considered as it and completes one following after a charge and discharge are undergone
Ring, n ∈ 1,2 ... }.
In charge and discharge cycles each time, periodically the electrical characteristics of battery pack (containing charge and discharge) are measured, and will
One multigroup vector X of measured datak nIt represents, Xk n∈Xn, it is preferable that X in a preferred embodiment of the inventionk nTable
It is shown as:
Wherein Vk M、Ik M、Tk M、σk MVoltage, the electricity measured in the M times measurement that respectively battery pack k is carried out in n cycles
Stream, temperature and modifying factor.Xk nIt is considered that coming from a very big space, it is unlimited that this space even may be considered.
As shown in figure 3, the present invention is that the SOC and SOH at battery pack end are estimated by the sample set measured, in n cycle of experience
Afterwards:Xk=(Xk 1,Xk 2,....Xk n)。
With reference to shown in Fig. 4, all possible value of SOC and SOH is defined as state space S in the present invention, andIt is a confined space.
After battery pack k completes n-th of cycle, it is assumed that the state of its SOC and SOH are Sk
The specific learning method of self study of the present invention is as follows:
S31, reward functions U is estimated;
S32, a complete predicting strategy π is determined, and according to xkProbability-distribution function f (x) find out optimal predictor plan
Slightly πopt;
S33, in Xk nOn the basis of complete ak nDefinition is expected afterwards awards, and misses function by study definition expection.
Estimate reward functions:
To each battery pack k, after n-th of cycle of experience, n=1,2....., n can make one and estimate decision
ak nAt this moment ∈ S define one and recurring number n relevant award factor rk n:
rk n=U (ak n, Sk, n).
U functions depend on the precision and timeliness estimated, and an example of the U functions of definition is
U(akn.Sk.n)=θ (akN, Sk)+λ ψ (n),
Wherein, θ (ak n, Sk) precision estimated is depicted, ψ (n) expression is the timeliness estimated, and λ is to be more than 0
Number.
Estimate the definition of strategy:
Estimating strategy and proceed to the measured of n-th cycle in predicting engine in self learning model proposed by the present invention
Sample set it is related.That is πn:Xn→S
π=(π1..., πn) completely estimate strategy for one
To the sample set xk that battery k is obtained, its tactful π that estimates is determined and is needed to implement after each cycle is estimated
Correction, it and one are related with the relevant reward functions of n.That is rn(x|π)。
Assuming that f (x) is xkProbability-distribution function, it contain (SOC, SOH) assessment rule information:
V (π)=∫x∈Xr(x|π)·f(x)dx;
It need to find out and optimal estimate strategyopt=argmaxV (π).
On-line study:
Given strategy π-n=(π1..., πn-1, πn+1..., πn)
In XnOn the basis of complete anDefinition is expected afterwards awards:
After acting on learning algorithm σ n, function is missed in definition expection:
The SOC and SOH of power battery can be more accurately predicted according to revised model.
Wherein, the present invention can be there are two source for the primary sample of study, and first source is that the factory of battery carries
The battery raw measurement data of confession, second source are to produce enough raw sample datas using existing instant model, are supplied
Self learning model training is used.
Compared with prior art, the present invention is based on the SOC/SOH Forecasting Methodologies of the power battery of big data self-study mechanism
Power battery real time execution and health status can be monitored, and detection process is an automated procedure, without manually doing
In advance.The present invention can carry out real-time alert processing to accident, such as lithium battery burning simultaneously, improve the safety of power battery
Performance.
It is obvious to a person skilled in the art that the present invention is not limited to the details of above-mentioned exemplary embodiment, Er Qie
In the case of without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the present invention is by appended power
Profit requirement rather than above description limit, it is intended that all by what is fallen within the meaning and scope of the equivalent requirements of the claims
Variation is included within the present invention.Any reference numeral in claim should not be considered as to the involved claim of limitation.
In addition, it should be understood that although this specification is described in terms of embodiments, but not each embodiment is only wrapped
Containing an independent technical solution, this description of the specification is merely for the sake of clarity, and those skilled in the art should
It considers the specification as a whole, the technical solutions in each embodiment can also be properly combined, forms those skilled in the art
The other embodiment being appreciated that.
Claims (8)
- A kind of 1. SOC/SOH Forecasting Methodologies of the power battery based on big data self-study mechanism, which is characterized in that the method Including:S1, provide power battery SOC/SOH prediction model;Model after obtained amendment, is followed in the charge and discharge of current battery after S2, the charge and discharge cycles based on a upper battery pack The measured value of V, I, T, σ up to the present that ring measures after starting, predicted from prediction model current SOC~/SOH~;S3, after completing a complete charge and discharge cycles, the SOC based on prediction~/SOH~with actually measure SOC/SOH pairs Prediction model after a upper cycle is modified;S4, the prediction for carrying out SOC/SOH using revised prediction model in next battery set charge/discharge cycle.
- 2. according to the method described in claim 1, it is characterized in that, the step S2 is further included:Periodically the electrical characteristics of battery pack are measured, and by measured data with a multigroup vector Xk nIt represents, Xk n∈Xn, andWherein Vk M、Ik M、Tk M、σk MVoltage that respectively battery pack k is measured in n cycles in carry out the M time measurement, electric current, temperature Degree and modifying factor.
- 3. according to the method described in claim 2, it is characterized in that, the step S2 is further included:The SOC/SOH of battery pack is predicted by the sample set measured, the X after n charge and discharge cycles are undergonek=(Xk 1, Xk 2,....Xk n);The all possible value for defining SOC and SOH is defined as state space S, andAfter battery pack k completes n-th of cycle, the state of SOC/SOH is Sk。
- 4. according to the method described in claim 3, it is characterized in that, the step S3 is specifically included:S31, reward functions U is estimated, to each battery pack k, after n-th of cycle of experience, n=1,2....., N, Wo Menzuo Go out one and estimate decision ak n∈ S define one and recurring number n relevant award factor rk n;S32, a complete prediction is determined Tactful π, and according to xkProbability-distribution function f (x) find out optimal predictor strategy πopt, wherein, πn:Xn→ S, π=(π1..., πn) completely estimate strategy for one, the sample set x obtained to battery kk, its tactful π that estimates determines and followed at each Ring estimate after the correction implemented of need, it and, an i.e. r related with the relevant reward functions of nn(x|π);S33, in Xk nOn the basis of complete ak nDefinition is expected afterwards awards, and misses function by study definition expection.
- 5. according to the method described in claim 4, it is characterized in that, in the step S31, reward functions U is specially:U(ak n, Sk,n)=θ (ak n, Sk)+λ ψ (n), wherein, θ (ak n, Sk) depicting the precision estimated, ψ (n) expression is the timeliness estimated, λ To be more than 0 coefficient, award factor rk n=U (ak n, Sk, n).
- 6. according to the method described in claim 4, it is characterized in that, in the step S32, optimal predictor strategy πopt= ArgmaxV (π), wherein,F (x) is xkProbability-distribution function.
- 7. according to the method described in claim 6, it is characterized in that, in the step S33, strategy π is given-n=(π1..., πn-1, πn+1..., πN), it is contemplated that award be:
- 8. the method according to the description of claim 7 is characterized in that in the step S33, it is contemplated that missing function is:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510532492.3A CN105137358B (en) | 2015-08-27 | 2015-08-27 | The SOC/SOH Forecasting Methodologies of power battery based on big data self-study mechanism |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510532492.3A CN105137358B (en) | 2015-08-27 | 2015-08-27 | The SOC/SOH Forecasting Methodologies of power battery based on big data self-study mechanism |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105137358A CN105137358A (en) | 2015-12-09 |
CN105137358B true CN105137358B (en) | 2018-06-26 |
Family
ID=54722765
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510532492.3A Active CN105137358B (en) | 2015-08-27 | 2015-08-27 | The SOC/SOH Forecasting Methodologies of power battery based on big data self-study mechanism |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105137358B (en) |
Families Citing this family (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN106528951B (en) * | 2016-10-18 | 2019-10-25 | 上海博强微电子有限公司 | A kind of method and apparatus of power battery life prediction and safe early warning |
CN106918789B (en) * | 2017-05-10 | 2019-05-14 | 成都理工大学 | A kind of SOC-SOH combines online real-time estimation and on-line amending method |
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 |
CN108549035A (en) * | 2018-04-20 | 2018-09-18 | 成都雅骏新能源汽车科技股份有限公司 | A method of SOH is estimated based on big data |
CN108614219A (en) * | 2018-04-27 | 2018-10-02 | 联华聚能科技股份有限公司 | Double self-teaching formula battery estimating systems and method |
CN108872861B (en) * | 2018-04-27 | 2020-07-21 | 温州大学 | Method for evaluating health state of battery on line |
JP7298114B2 (en) * | 2018-06-25 | 2023-06-27 | 株式会社Gsユアサ | State estimation method and state estimation device |
US11065978B2 (en) | 2019-02-25 | 2021-07-20 | Toyota Research Institute, Inc. | Systems, methods, and storage media for adapting machine learning models for optimizing performance of a battery pack |
CN109991541A (en) * | 2019-03-06 | 2019-07-09 | 重庆雅讯电源技术有限公司 | The chip architecture that lead-acid accumulator parameter calculates |
CN111190112B (en) * | 2020-02-10 | 2020-10-09 | 宜宾职业技术学院 | Battery charging and discharging prediction method and system based on big data analysis |
CN111953034A (en) * | 2020-06-24 | 2020-11-17 | 地上铁租车(深圳)有限公司 | Battery equalization method and battery equalization equipment |
CN111722139B (en) * | 2020-06-29 | 2022-08-09 | 重庆邮电大学 | Lithium battery health monitoring model self-learning method based on micro-continuous mapping |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103267950A (en) * | 2012-12-14 | 2013-08-28 | 惠州市亿能电子有限公司 | SOH (State Of Health) value evaluation method of electric car battery pack |
CN103620432A (en) * | 2012-03-16 | 2014-03-05 | 株式会社Lg化学 | Battery state estimation device and method |
CN103744030A (en) * | 2014-01-12 | 2014-04-23 | 中国科学院电工研究所 | Device and method for estimating health status and state of charge of battery pack on line |
WO2014061238A1 (en) * | 2012-10-16 | 2014-04-24 | 国立大学法人新潟大学 | Secondary cell tester |
WO2014083856A1 (en) * | 2012-11-30 | 2014-06-05 | 三洋電機株式会社 | Battery management device, power supply, and soc estimation method |
CN104698382A (en) * | 2013-12-04 | 2015-06-10 | 东莞钜威新能源有限公司 | Method for predicting the SOC and SOH of battery pack |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE10210516B4 (en) * | 2002-03-09 | 2004-02-26 | Vb Autobatterie Gmbh | Method and device for determining the functionality of a storage battery |
-
2015
- 2015-08-27 CN CN201510532492.3A patent/CN105137358B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103620432A (en) * | 2012-03-16 | 2014-03-05 | 株式会社Lg化学 | Battery state estimation device and method |
WO2014061238A1 (en) * | 2012-10-16 | 2014-04-24 | 国立大学法人新潟大学 | Secondary cell tester |
WO2014083856A1 (en) * | 2012-11-30 | 2014-06-05 | 三洋電機株式会社 | Battery management device, power supply, and soc estimation method |
CN103267950A (en) * | 2012-12-14 | 2013-08-28 | 惠州市亿能电子有限公司 | SOH (State Of Health) value evaluation method of electric car battery pack |
CN104698382A (en) * | 2013-12-04 | 2015-06-10 | 东莞钜威新能源有限公司 | Method for predicting the SOC and SOH of battery pack |
CN103744030A (en) * | 2014-01-12 | 2014-04-23 | 中国科学院电工研究所 | Device and method for estimating health status and state of charge of battery pack on line |
Non-Patent Citations (2)
Title |
---|
锂离子电池健康评估和寿命预测综述;刘大同 等;《仪器仪表学报》;20150131;第36卷(第1期);第1-16页 * |
锂离子电池容量的预测建模及其仿真研究;李欣然 等;《系统仿真学报》;20140831;第26卷(第8期);第1733-1740、1746页 * |
Also Published As
Publication number | Publication date |
---|---|
CN105137358A (en) | 2015-12-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105137358B (en) | The SOC/SOH Forecasting Methodologies of power battery based on big data self-study mechanism | |
Xiong et al. | An electrochemical model based degradation state identification method of Lithium-ion battery for all-climate electric vehicles application | |
Xu et al. | Remaining useful life prediction of lithium-ion batteries based on wiener process under time-varying temperature condition | |
Xuan et al. | Real-time estimation of state-of-charge in lithium-ion batteries using improved central difference transform method | |
Baba et al. | Numerical simulation of thermal behavior of lithium-ion secondary batteries using the enhanced single particle model | |
CN106055775B (en) | A kind of service life of secondary cell prediction technique that particle filter is combined with mechanism model | |
Rajabloo et al. | An inverse method for estimating the electrochemical parameters of lithium-ion batteries | |
CN109073710A (en) | The system and method for generating with using for electric heating battery model | |
CN105334462A (en) | Online estimation method for battery capacity loss | |
Cheng et al. | Development of a lifetime prediction model for lithium thionyl chloride batteries based on an accelerated degradation test | |
CN103529400A (en) | Battery capacity forecasting method with self-adaptive temperature compensating function | |
Feng et al. | A graphical model for evaluating the status of series‐connected lithium‐ion battery pack | |
JP2011122951A (en) | Charged state estimation device and deterioration state estimation device of secondary battery | |
CN108205114A (en) | The Forecasting Methodology and system of battery life | |
Luo et al. | A simple feature extraction method for estimating the whole life cycle state of health of lithium-ion batteries using transformer-based neural network | |
Pozzi et al. | Stochastic model predictive control for optimal charging of electric vehicles battery packs | |
WO2013082955A1 (en) | Analysis system for evaluating operation state of lithium ion battery | |
Wu et al. | A collaborative estimation scheme for lithium-ion battery state of charge and state of health based on electrochemical model | |
Luo et al. | An SVM-based health classifier for offline Li-ion batteries by using EIS technology | |
Pang et al. | A Review on the Prediction of Health State and Serving Life of Lithium‐Ion Batteries | |
Huang et al. | State of health estimation of lithium-ion batteries based on fine-tuning or rebuilding transfer learning strategies combined with new features mining | |
Cui et al. | Ultra-early prediction of lithium-ion battery performance using mechanism and data-driven fusion model | |
Madani et al. | Thermal behavior modeling of lithium-ion batteries: A comprehensive review | |
Huang et al. | A multi-variable multi-step Seq2seq networks for the state of charge estimation of lithium-ion battery | |
Zhao et al. | Robust Online State of Charge Estimation of Lithium‐Ion Battery Pack Based on Error Sensitivity Analysis |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |