CN110346734A - A kind of lithium-ion-power cell health status evaluation method based on machine learning - Google Patents
A kind of lithium-ion-power cell health status evaluation method based on machine learning Download PDFInfo
- Publication number
- CN110346734A CN110346734A CN201910531963.7A CN201910531963A CN110346734A CN 110346734 A CN110346734 A CN 110346734A CN 201910531963 A CN201910531963 A CN 201910531963A CN 110346734 A CN110346734 A CN 110346734A
- Authority
- CN
- China
- Prior art keywords
- soc
- model
- parameter
- battery
- state
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
-
- 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
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
-
- 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
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Manufacturing & Machinery (AREA)
- Chemical & Material Sciences (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Electrochemistry (AREA)
- General Chemical & Material Sciences (AREA)
- Tests Of Electric Status Of Batteries (AREA)
- Secondary Cells (AREA)
Abstract
The invention discloses a kind of lithium-ion-power cell health status evaluation method based on machine learning, state-of-charge and health status for real-time estimation power battery.By establishing the equivalent-circuit model of lithium ion battery, parameter identification is carried out to it, resettles Uoc-SOC model, and estimate SOC.It is obtained using the training of a large amount of off-line datas with Uoc-SOC model parameter as input, maximum available is the neural network model of output.It carries out curve fitting to the Uoc and SOC of synchronization, obtain the parameter to be identified in model, it is entered into the neural network model that training obtains, obtain maximum available, and obtained Uoc-SOC model parameter and maximum available are returned into SOC estimation steps, update the parameter of its state equation and observational equation.The present invention proposes a kind of health state of lithium ion battery evaluation method, carries out estimation on line to cell health state, and carried out parameter update to SOC estimation, improves its estimation precision.
Description
Technical field
The present invention relates to electric automobile power battery management system state estimation technical fields, and in particular to power battery lotus
Electricity condition and health status joint estimate.
Background technique
As exhaustion, the environmental pollution increasingly of Global Oil resource are got worse, electric car is as a kind of energy conservation, ring
The vehicles of guarantor and sustainable development, have obtained the concern of people.Power resources of the power battery pack as electric car,
Its performance is always the emphasis studied.The battery of electric car when in use, need to make its work reasonable voltage, electric current,
In temperature range.Therefore, it is necessary to the uses to battery electronic on electric car effectively to be managed.To battery reality on electric car
The specific equipment for applying management is exactly battery management system (Battery Management System, BMS).It will not only guarantee electricity
Pond safely and reliably uses, and gives full play to the ability of battery and extend its service life, as battery entire car controller with
And the bridge linked up between driver, the charge and discharge of battery pack are controlled, and the base of electrokinetic cell system is reported to entire car controller
This parameter and fault message.The level of battery management system largely determines the performance of power battery pack.Therefore, one
A real-time, efficient battery management system is very important.
Battery management system (BMS) is the important ring of new-energy automobile dynamical system assembly and large-scale energy storage system exploitation
Section.Battery charge state (SOC) is used to characterize the remaining capacity of battery, the i.e. percentage of remaining capacity and rated capacity.Battery
State-of-charge (SOC) cannot be obtained directly from battery itself, can only pass through external characteristics parameter (such as voltage, electricity of measurement battery pack
Stream etc.) estimate to obtain indirectly.Electric automobile power battery in use, due to internal complicated electrochemical reaction, causes
Battery behavior embodies the non-linear of height, makes accurately to estimate that battery charge state (SOC) has great difficulty.It is non-for handling
The non-linear Kalman filtering (such as filtering of extension karr, Unscented kalman filtering) of linear problem is considered to be used to estimate SOC.
When using these algorithms, the relational expression of SOC and Uoc and the maximum available of battery, current method one can be related to
As do not consider its variation, default it for definite value.But in fact, with battery aging, the relationship of SOC and Uoc can become
Change, the maximum available of battery is also changing.If updating these variations not in time, the estimation error of SOC can become
It is increasing.
SOH refers to the health status of battery, i.e., the ratio of current maximum available and initial maximum active volume.With
Service time of battery increase, battery can gradually aging, occur internal resistance increase, battery capacity decaying phenomena such as.Battery capacity decaying
The reason of it is complicated, it is more to be related to factor, and change slow.Current still none accurate decline physical model.It is using
When model is established in machine learning, the selection of health factor has larger impact to its final precision, thus select suitable health because
Son is particularly significant.
Summary of the invention
To solve problems of the prior art, state-of-charge (SOC) and health status (SOH) of the present invention to battery
Joint estimate is carried out, by the coefficient and maximum possible capacity of real-time update Uoc and SOC relational expression, improves SOC estimation precision,
Reduce estimation error;And the input using Uoc and the coefficient of SOC relational expression as health factor, as BP neural network model.It should
Estimation and control of the invention for entire battery status, the capacity for improving the service life of battery and giving full play to battery have weight
Big meaning.
The present invention adopts the following technical solutions, realizes above-mentioned technical purpose.
A kind of lithium-ion-power cell health status evaluation method based on machine learning, comprising the following steps:
Step (1), establishes the equivalent-circuit model of lithium-ion-power cell, and recognizes the unknown parameter in model;
Step (2), establishes Uoc-SOC model:Wherein ai、bi、ciIt is
Parameter to be identified, U in modelOCIndicate the open-circuit voltage of battery, SOC is battery charge state;
Step (3), estimates state-of-charge SOC;
Step (4) obtains a by off-line data by curve matchingi、bi、ciValue;
Step (5), to ai、bi、ciAnd maximum available C is normalized, and obtains a'i、b'i、c'iAs defeated
Enter, C' conduct output, using machine learning algorithm to a'i、b'i、c'iAnd corresponding C' is trained, and is finally obtained with a'i、b
'i、c'iTo input the machine learning model for C' being output;
Step (6) carries out curve fitting to obtain input value a to the Uoc and SOC of synchronizationi、bi、ci, defeated after normalization
Enter to machine mould, obtains maximum available C;
Step (7), by a obtained in step (6)i、bi、ciAnd C value returns to step (3), updates state equation and observation
Corresponding parameter in equation.
Further, the equivalent-circuit model selects Thevenin equivalent-circuit model or Order RC equivalent-circuit model.
Further, the Uoc-SOC model UOC=K0+K1z+K2z2+K3z3+K4z4+K5z5+K6z6OrOrOrReplacement, wherein z is state-of-charge SOC, K0、K1、K2K3、
K4、K5、K6、α1、α2For parameter to be identified in model.
Further, the state-of-charge SOC is estimated using expanded Kalman filtration algorithm, the polarizing voltage of battery and
The state equation of state-of-charge isWherein
Up、Rp、CpIndicate that battery polarization voltage, resistance, capacitor, η are coulombic efficiency, Δ T is sampling time interval, ILFor battery charging and discharging stream,
ωkFor system noise;End voltage observational equation be
Wherein υkTo measure noise.
The beneficial effects of the present invention are: the lithium-ion-power cell health status proposed by the present invention based on machine learning is estimated
Calculation method, parameter and present battery when can estimate state-of-charge using modelling with real-time update in Uoc-SOC model are most
Big active volume improves the estimation precision of SOC.In addition, the present invention is strong using the parameter in Uoc-SOC model as data-driven
The health factor of health state estimating method has higher estimation precision;And in joint estimate, in updating estimation SOC
While Uoc-SOC Model Parameter, the input that the parameter of update is estimated as SOH, SOC estimation, SOH estimation share same
Group parameter, reduces calculation amount.
Detailed description of the invention
Fig. 1 is lithium-ion-power cell model equivalent circuit diagram;
Fig. 2 is the flow chart of the lithium-ion-power cell health status evaluation method the present invention is based on machine learning.
Specific embodiment
The specific technical solution of the present invention will be further described in conjunction with attached drawing below, but protection of the invention
Range is not limited to this.
A kind of lithium-ion-power cell health status evaluation method based on machine learning, comprising the following steps:
Step (1), establishes the equivalent-circuit model of lithium-ion-power cell, can select Thevenin equivalent circuit mould
Type or Order RC equivalent-circuit model, the present embodiment by taking Thevenin equivalent circuit as an example (such as Fig. 1), wherein UOCIndicate battery
Open-circuit voltage, UtIndicate the end voltage of battery, R0For the ohmic internal resistance of battery, Up、Rp、CpIndicate battery polarization voltage, resistance,
Capacitor;ILFor battery charging and discharging stream.According to circuit diagram in Fig. 1, using the above equivalent-circuit model of electrotechnics theory analysis,
Establish the continuous time equation of battery model:
Ut=Uoc-ILR0-Up (1)
Transmission function is obtained by Laplace transform:
Bilinear transformation enables?
It enables
Formula (4) can simplify are as follows:
UL, k=a1UL, k-1+UOC, k-a1UOC, k-1+a2IL, k+a3IL, k-1 (5)
Again because sampling time T is very short, then:
ΔUOC, k=UOC, k-UOC, k-1≈0 (6)
Then formula (6) can simplify are as follows:
UT, k=(1-a1)UOC, k+a1UT, k-1+a2IL, k+a3IL, k-1 (7)
Then parameter identification is carried out using least square method of recursion, formula (7) can be write as:
Wherein ΦLs, kIt is the data matrix of system, θLs, kIt is parameter matrix.
Step (2), establishes Uoc-SOC model:
Using battery testing cabinet, cycling life test is carried out to certain 18650 type lithium ion battery, obtains different cycle-indexes
Under corresponding SOC and Uoc value, carry out curve fitting to obtained data, obtain the relationship of Uoc-SOC: wherein ai、bi、ciFor
Parameter to be identified in model, these parameters to be identified change with the variation of cell health state, and then can be with
Health factor as characterization health status.
Uoc-SOC model can also be used with drag:
UOC=K0+K1z+K2z2+K3z3+K4z4+K5z5+K6z6 (11)
Wherein z is state-of-charge SOC, K0、K1、K2K3、K4、K5、K6、α1、α2For parameter to be identified in model, these are distinguished
The parameter of knowledge changes with the variation of cell health state, can also be used as the health factor of characterization health status.
Below by taking formula (9) as an example, n=3 is taken, it is fitted, the parameter obtained under different cycle-indexes is as follows:
Cycle-index | a1 | b1 | c1 | a2 | b2 | c2 | a3 | b3 | c3 |
1 | 3.936 | 1.242 | 0.8202 | 0.095 | 0.5856 | 0.1909 | 3.004 | -0.2176 | 0.7787 |
25 | 2.985 | 1.196 | 0.3515 | 2.863 | 0.7151 | 0.4342 | 3.12 | 0.04232 | 0.5155 |
50 | 3.51 | 1.196 | 0.4159 | 2.654 | 0.6447 | 0.4176 | 3.061 | 0.02453 | 0.482 |
75 | 3.471 | 1.219 | 0.6137 | 0.1646 | 0.6018 | 0.2187 | 3.353 | 0.1179 | 0.8297 |
As it can be seen that parameter to be identified converts, can be as health factor under different cycle-indexes.
Step (3) estimates that state-of-charge SOC, the present embodiment estimate SOC by taking expanded Kalman filtration algorithm as an example
It calculates, the polarizing voltage of lithium ion battery and state equation such as formula (10), the observational equation such as formula (11) of end voltage of state-of-charge.
Wherein: ωkFor system noise, it is assumed that it meets Gaussian Profile, υkTo measure noise, also assume that it meets Gauss point
Cloth, η are coulombic efficiency, and Δ T is sampling time interval.
Step (4), obtains a large amount of off-line datas: test battery at different temperatures, under different health status with different
Uoc and SOC data when discharge-rate (such as 0.1C, 0.5C, 1C, 2C) discharges, and in various dynamic operation conditions (as new mark Europe is followed
Ring test-NEDC, Metro cycle-UDDS) under Uoc and SOC data;The Uoc-SOC model of formula (9) is selected, is considered
To model accuracy and computation complexity, n=3 is taken, then by the method for curve matching, obtains ai、bi、ciValue.
Step (5), due to (i.e. current maximum available C is different) a under different health statusi、bi、ciValue it is different, lead to
Cross correlation analysis, selection and the biggish a of SOH correlationi、bi、ciValue as input, using C as export;To improve training
Precision, using minimax normalization method to a of inputi、bi、ciIt is normalized with the C of output, obtains a'i、b'i、c'iWith
C';Neural network (by taking BP neural network as an example) algorithm is used, to a'i、b'i、c'i, C'(i=1,2,3;) learning training is carried out,
It finally obtains with a'i、b'i、c'iIt is the BP neural network model of output for input, C'.
Step (6) can be obtained real-time synchronization Uoc and SOC data by step (1), (3), choose 10%-90%
SOC and corresponding Uoc in range, are ordinate by abscissa, Uoc of SOC, obtain input value a by curve matchingi、bi、
ci, to ai、bi、ciIt evolves after normalizing, the BP neural network model that input step (5) obtains, and returned to the C' of output is counter
One changes, and obtains the current maximum available C of lithium battery.
Step (7), by a obtained in step (6)i、bi、ciAnd C value returns to step (3), updates state equation and observation
Corresponding parameter in equation.
Step (8) after step (7) has updated parameter, executes step (1), (3), (5), (6), (7), carries out one under battery
The health status of secondary circulation is estimated.
It should be noted that being explained although content disclosed in this invention is expounded through the foregoing embodiment
It states content and is not considered as limitation of the present invention.The modification that professional and technical personnel in the field make technical solution of the present invention
And equivalent replacement, it should all cover in scope of the invention as claimed.
Claims (4)
1. a kind of lithium-ion-power cell health status evaluation method based on machine learning, which is characterized in that including following step
It is rapid:
Step (1), establishes the equivalent-circuit model of lithium-ion-power cell, and recognizes the unknown parameter in model;
Step (2), establishes Uoc-SOC model:Wherein ai、bi、ciIt is model
In parameter to be identified, UOCIndicate the open-circuit voltage of battery, SOC is battery charge state;
Step (3), estimates state-of-charge SOC;
Step (4) obtains a by off-line data by curve matchingi、bi、ciValue;
Step (5), to ai、bi、ciAnd maximum available C is normalized, and obtains a 'i、b′i、c′iAs input, C'
As output, using machine learning algorithm to a 'i、b′i、c′iAnd corresponding C' is trained, and is finally obtained with a 'i、b′i、c′i
To input the machine learning model for C' being output;
Step (6) carries out curve fitting to obtain input value a to the Uoc and SOC of synchronizationi、bi、ci, it is input to after normalization
Machine mould obtains maximum available C;
Step (7), by a obtained in step (6)i、bi、ciAnd C value returns to step (3), updates state equation and observational equation
In corresponding parameter.
2. a kind of lithium-ion-power cell health status evaluation method based on machine learning according to claim 1,
It is characterized in that, the equivalent-circuit model selects Thevenin equivalent-circuit model or Order RC equivalent-circuit model.
3. a kind of lithium-ion-power cell health status evaluation method based on machine learning according to claim 1,
It is characterized in that, the Uoc-SOC model UOC=K0+K1z+K2z2+K3z3+K4z4+K5z5+K6z6OrOrOrReplacement, wherein z is state-of-charge SOC, K0、K1、K2 K3、
K4、K5、K6、α1、α2For parameter to be identified in model.
4. a kind of lithium-ion-power cell health status evaluation method based on machine learning according to claim 1,
It is characterized in that, the state-of-charge SOC is estimated using expanded Kalman filtration algorithm, the polarizing voltage of battery and charged shape
The state equation of state isWherein Up、Rp、Cp
Indicate that battery polarization voltage, resistance, capacitor, η are coulombic efficiency, Δ T is sampling time interval, ILFor battery charging and discharging stream, ωk
For system noise;End voltage observational equation beWherein υk
To measure noise.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910531963.7A CN110346734B (en) | 2019-06-19 | 2019-06-19 | Machine learning-based lithium ion power battery health state estimation method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910531963.7A CN110346734B (en) | 2019-06-19 | 2019-06-19 | Machine learning-based lithium ion power battery health state estimation method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110346734A true CN110346734A (en) | 2019-10-18 |
CN110346734B CN110346734B (en) | 2021-07-20 |
Family
ID=68182393
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910531963.7A Active CN110346734B (en) | 2019-06-19 | 2019-06-19 | Machine learning-based lithium ion power battery health state estimation method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110346734B (en) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110888058A (en) * | 2019-12-02 | 2020-03-17 | 西安科技大学 | Algorithm based on power battery SOC and SOH joint estimation |
CN111308381A (en) * | 2020-04-07 | 2020-06-19 | 国网江苏省电力有限公司苏州供电分公司 | Health state evaluation method for power battery of pure electric bus |
CN111581904A (en) * | 2020-04-17 | 2020-08-25 | 西安理工大学 | Lithium battery SOC and SOH collaborative estimation method considering influence of cycle number |
CN111983467A (en) * | 2020-08-24 | 2020-11-24 | 哈尔滨理工大学 | Battery safety degree estimation method and estimation device based on second-order RC equivalent circuit model |
CN112595987A (en) * | 2020-11-28 | 2021-04-02 | 国网河南省电力公司电力科学研究院 | Lithium battery life estimation method based on mixed pulse voltage change |
CN112666473A (en) * | 2020-11-04 | 2021-04-16 | 深圳市科陆电子科技股份有限公司 | Battery detection method and battery detection system |
CN112946499A (en) * | 2021-02-04 | 2021-06-11 | 芜湖楚睿智能科技有限公司 | Lithium battery health state and charge state joint estimation method based on machine learning |
CN113075560A (en) * | 2021-04-19 | 2021-07-06 | 南京邮电大学 | Online estimation method for health state of power lithium ion battery |
CN113093014A (en) * | 2021-03-31 | 2021-07-09 | 山东建筑大学 | Online collaborative estimation method and system for SOH and SOC based on impedance parameters |
CN113866637A (en) * | 2020-06-30 | 2021-12-31 | 宁德时代新能源科技股份有限公司 | Method, device, equipment and medium for adjusting SOC of power battery |
CN114295987A (en) * | 2021-12-30 | 2022-04-08 | 浙江大学 | Battery SOC state estimation method based on nonlinear Kalman filtering |
US11422199B1 (en) * | 2021-06-17 | 2022-08-23 | Hong Kong Applied Science and Technology Research Institute Company Limited | State of health evaluation of retired lithium-ion batteries and battery modules |
CN117517980A (en) * | 2024-01-04 | 2024-02-06 | 烟台海博电气设备有限公司 | Method and system for monitoring health state of lithium battery in real time |
CN117706406A (en) * | 2024-02-05 | 2024-03-15 | 安徽布拉特智能科技有限公司 | Lithium battery health state monitoring model, method, system and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090210179A1 (en) * | 2008-02-19 | 2009-08-20 | Gm Global Technology Operations, Inc. | Model-based estimation of battery hysteresis |
US20130006455A1 (en) * | 2011-06-28 | 2013-01-03 | Ford Global Technologies, Llc | Nonlinear observer for battery state of charge estimation |
CN106324523A (en) * | 2016-09-26 | 2017-01-11 | 合肥工业大学 | Discrete variable structure observer-based lithium battery SOC (state of charge) estimation method |
CN106872899A (en) * | 2017-02-10 | 2017-06-20 | 泉州装备制造研究所 | A kind of electrokinetic cell SOC methods of estimation based on reduced dimension observer |
CN108398652A (en) * | 2017-05-26 | 2018-08-14 | 北京航空航天大学 | A kind of lithium battery health state evaluation method merging deep learning based on multilayer feature |
-
2019
- 2019-06-19 CN CN201910531963.7A patent/CN110346734B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090210179A1 (en) * | 2008-02-19 | 2009-08-20 | Gm Global Technology Operations, Inc. | Model-based estimation of battery hysteresis |
US20130006455A1 (en) * | 2011-06-28 | 2013-01-03 | Ford Global Technologies, Llc | Nonlinear observer for battery state of charge estimation |
CN106324523A (en) * | 2016-09-26 | 2017-01-11 | 合肥工业大学 | Discrete variable structure observer-based lithium battery SOC (state of charge) estimation method |
CN106872899A (en) * | 2017-02-10 | 2017-06-20 | 泉州装备制造研究所 | A kind of electrokinetic cell SOC methods of estimation based on reduced dimension observer |
CN108398652A (en) * | 2017-05-26 | 2018-08-14 | 北京航空航天大学 | A kind of lithium battery health state evaluation method merging deep learning based on multilayer feature |
Cited By (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110888058A (en) * | 2019-12-02 | 2020-03-17 | 西安科技大学 | Algorithm based on power battery SOC and SOH joint estimation |
CN111308381A (en) * | 2020-04-07 | 2020-06-19 | 国网江苏省电力有限公司苏州供电分公司 | Health state evaluation method for power battery of pure electric bus |
CN111581904A (en) * | 2020-04-17 | 2020-08-25 | 西安理工大学 | Lithium battery SOC and SOH collaborative estimation method considering influence of cycle number |
CN111581904B (en) * | 2020-04-17 | 2024-03-22 | 西安理工大学 | Lithium battery SOC and SOH collaborative estimation method considering cycle number influence |
CN113866637B (en) * | 2020-06-30 | 2024-04-26 | 宁德时代新能源科技股份有限公司 | Method, device, equipment and medium for adjusting SOC of power battery |
CN113866637A (en) * | 2020-06-30 | 2021-12-31 | 宁德时代新能源科技股份有限公司 | Method, device, equipment and medium for adjusting SOC of power battery |
CN111983467B (en) * | 2020-08-24 | 2023-02-03 | 哈尔滨理工大学 | Battery safety degree estimation method and estimation device based on second-order RC equivalent circuit model |
CN111983467A (en) * | 2020-08-24 | 2020-11-24 | 哈尔滨理工大学 | Battery safety degree estimation method and estimation device based on second-order RC equivalent circuit model |
CN112666473A (en) * | 2020-11-04 | 2021-04-16 | 深圳市科陆电子科技股份有限公司 | Battery detection method and battery detection system |
CN112595987A (en) * | 2020-11-28 | 2021-04-02 | 国网河南省电力公司电力科学研究院 | Lithium battery life estimation method based on mixed pulse voltage change |
CN112946499B (en) * | 2021-02-04 | 2024-02-02 | 芜湖楚睿智能科技有限公司 | Lithium battery health state and state of charge joint estimation method based on machine learning |
CN112946499A (en) * | 2021-02-04 | 2021-06-11 | 芜湖楚睿智能科技有限公司 | Lithium battery health state and charge state joint estimation method based on machine learning |
CN113093014B (en) * | 2021-03-31 | 2022-05-27 | 山东建筑大学 | Online collaborative estimation method and system for SOH and SOC based on impedance parameters |
CN113093014A (en) * | 2021-03-31 | 2021-07-09 | 山东建筑大学 | Online collaborative estimation method and system for SOH and SOC based on impedance parameters |
CN113075560B (en) * | 2021-04-19 | 2022-11-18 | 南京邮电大学 | Online estimation method for health state of power lithium ion battery |
CN113075560A (en) * | 2021-04-19 | 2021-07-06 | 南京邮电大学 | Online estimation method for health state of power lithium ion battery |
US11422199B1 (en) * | 2021-06-17 | 2022-08-23 | Hong Kong Applied Science and Technology Research Institute Company Limited | State of health evaluation of retired lithium-ion batteries and battery modules |
CN114295987A (en) * | 2021-12-30 | 2022-04-08 | 浙江大学 | Battery SOC state estimation method based on nonlinear Kalman filtering |
CN114295987B (en) * | 2021-12-30 | 2024-04-02 | 浙江大学 | Battery SOC state estimation method based on nonlinear Kalman filtering |
CN117517980A (en) * | 2024-01-04 | 2024-02-06 | 烟台海博电气设备有限公司 | Method and system for monitoring health state of lithium battery in real time |
CN117517980B (en) * | 2024-01-04 | 2024-03-22 | 烟台海博电气设备有限公司 | Method and system for monitoring health state of lithium battery in real time |
CN117706406A (en) * | 2024-02-05 | 2024-03-15 | 安徽布拉特智能科技有限公司 | Lithium battery health state monitoring model, method, system and storage medium |
CN117706406B (en) * | 2024-02-05 | 2024-04-16 | 安徽布拉特智能科技有限公司 | Lithium battery health state monitoring model, method, system and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN110346734B (en) | 2021-07-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110346734A (en) | A kind of lithium-ion-power cell health status evaluation method based on machine learning | |
CN107368619B (en) | Extended Kalman filtering SOC estimation method | |
Tang et al. | Model migration based battery power capability evaluation considering uncertainties of temperature and aging | |
CN107576919A (en) | Power battery charged state estimating system and method based on ARMAX models | |
Sun et al. | Overview of the types of battery models | |
CN104535934B (en) | The electrokinetic cell state of charge method of estimation and system of online feedforward compensation | |
CN107741568B (en) | Lithium battery SOC estimation method based on state transition optimization RBF neural network | |
CN104617623B (en) | A kind of electric automobile power battery group balance control method | |
CN109061520A (en) | A kind of power battery health and power rating estimation on line method and system | |
CN105425153B (en) | A kind of method of the state-of-charge for the electrokinetic cell for estimating electric vehicle | |
CN111060834A (en) | Power battery state of health estimation method | |
CN110888064B (en) | Algorithm for evaluating battery cell capacity distribution interval of battery system | |
Huang et al. | Soc estimation of li-ion battery based on improved ekf algorithm | |
CN111352032A (en) | Lithium battery dynamic peak power prediction method | |
CN111581904A (en) | Lithium battery SOC and SOH collaborative estimation method considering influence of cycle number | |
CN108445422B (en) | Battery state of charge estimation method based on polarization voltage recovery characteristics | |
CN105319515A (en) | A combined estimation method for the state of charge and the state of health of lithium ion batteries | |
CN103983920B (en) | A kind of method of the model of the electrokinetic cell setting up electric vehicle | |
CN109633473B (en) | Distributed battery pack state of charge estimation algorithm | |
Xiong et al. | Data-driven state-of-charge estimator for electric vehicles battery using robust extended Kalman filter | |
CN109901072B (en) | Retired battery parameter detection method based on historical data and laboratory test data | |
CN110632520A (en) | Estimation device and estimation method for SOC of power battery | |
CN112098849A (en) | Lithium battery residual capacity estimation method based on integral Kalman filtering | |
US20210325467A1 (en) | Method and system for identifying third-order model parameters of lithium battery based on likelihood function | |
Yang et al. | SOC estimation of lithium-ion battery based on new adaptive fading extended Kalman filter |
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 |