CN107069122A - A kind of Forecasting Methodology of electrokinetic cell remaining life - Google Patents
A kind of Forecasting Methodology of electrokinetic cell remaining life Download PDFInfo
- Publication number
- CN107069122A CN107069122A CN201710214031.0A CN201710214031A CN107069122A CN 107069122 A CN107069122 A CN 107069122A CN 201710214031 A CN201710214031 A CN 201710214031A CN 107069122 A CN107069122 A CN 107069122A
- Authority
- CN
- China
- Prior art keywords
- electrokinetic cell
- remaining life
- neural network
- artificial
- input
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
Abstract
The present invention relates to a kind of Forecasting Methodology of electrokinetic cell remaining life, electrokinetic cell status data when electric automobile is driven a vehicle every time is specially obtained first, set up artificial nerve network model, using the electrokinetic cell status data as the input of artificial nerve network model, the training parameter of artificial nerve network model is trained；Obtain the electrokinetic cell status data in electric automobile to be measured, it is used as the input of the artificial neural network with training parameter, according to the input-output mappings relation of artificial neural network, predicting the outcome for the output of artificial neural network, i.e. electrokinetic cell remaining life is obtained.Present invention introduces remaining life（RUL）Concept, collection influence dynamic lithium battery remaining life six big influence factors, set up the Forecasting Methodology of dynamic lithium battery remaining life.By specifically testing, test result shows the reliability of artificial nerve network model.
Description
Technical field
The invention belongs to pure electric automobile field of battery management, and in particular to a kind of electrokinetic cell remaining life it is pre-
Survey method.
Background technology
At present, for the battery management system of new-energy automobile, we are mainly having focused on work to battery
On the supervisory function bit of guard system, accomplished security incident " early find, early prevention ", it is possible to increase the security of new-energy automobile and
Reliability.But but rarely have for the monitoring during new energy car battery use and refer to.
There is the remaining life (RUL, Remaining Useful Life) to an equipment or system in prior art
Estimated and predicted, academicly referred to as prognostics and health management technology (Prognostics and Health
Management,PHM).Wherein, prediction is core content and technological challenge in PHM.Predicting residual useful life is for system equipment
Maintenance is essential important information, and the analysis predicted the outcome according to RUL carries out good management, Ke Yiti to system equipment
High system or equipment availability and reliability, while reduction or the heavy losses for avoiding failure from causing.But at present for new energy
Dynamic lithium battery in automobile does not have systematic predicting residual useful life mechanism but.
The content of the invention
For the deficiencies in the prior art, remaining life (RUL) concept is introduced power lithium battery by the present invention
Pond field, by predicting the remaining life of dynamic lithium battery, to predict the security fault of dynamic lithium battery, makes electronic vapour
Car has higher reliability and security.
The present invention uses following technical scheme：
A kind of Forecasting Methodology of electrokinetic cell remaining life, obtains electrokinetic cell shape when electric automobile is driven a vehicle every time
State data, set up artificial nerve network model, using the electrokinetic cell status data as artificial nerve network model input,
Train the training parameter of artificial nerve network model；Obtain the electrokinetic cell status data in electric automobile to be measured, as with
The input of the artificial neural network of training parameter, according to the input-output mappings relation of artificial neural network, obtains artificial neuron
The output of network, i.e. electrokinetic cell remaining life predict the outcome.
Further, the electrokinetic cell status data includes electrokinetic cell total voltage, the mean temperature of electrokinetic cell, moved
Power battery charging and discharging electric current, the SOC of single-unit electrokinetic cell, the SOH of the battery core voltage of single-unit electrokinetic cell and single-unit electrokinetic cell.
Further, the foundation of the artificial nerve network model is specifically used：N layers of artificial neural network are set up, wherein
Only one layer hidden layer, the nodes of every layer of setting set up artificial nerve network model according to transfer function and training function.
Further, the N layers of artificial neural network has input layer and output layer, and the nodes of input layer are 6, output
The nodes of layer are 1；The nodes of hidden layer are determined according to following formula：
In formula：N is the nodes of hidden layer；niInput number of nodes；n0For output node number；A is the constant between 1-10.
Further, the electrokinetic cell remaining life predict the outcome including：There is training parameter according to described
Neural network prediction obtain electrokinetic cell residual capacity and reach electrokinetic cell discharge and recharge number of times corresponding during failure, root
According to battery cycle life principle, predicting the outcome for electrokinetic cell remaining life is obtained.
Further, the SOC value of all single batteries of electrokinetic cell is obtained, handling averagely is done to it, using most
Cell SOC value close to average SOC value is used as one of electrokinetic cell status data.
Further, the battery core voltage of all single batteries of electrokinetic cell is obtained, handling averagely is done to it, is used
Cell battery core magnitude of voltage closest to average battery core magnitude of voltage is used as one of electrokinetic cell status data.
Further, the SOH value of all single batteries of electrokinetic cell is obtained, handling averagely is done to it, using most
Cell SOH value close to average SOH value is used as one of electrokinetic cell status data.
Further, the artificial nerve network model has transfer function, for data conversion between layers with
Transmission.
Further, the artificial nerve network model has training function, for based on dynamic as what is inputted and export
Power battery status data, electrokinetic cell remaining life, train the parameter of artificial nerve network model.
Beneficial effects of the present invention：
Present invention introduces remaining life (RUL) concept, the six of collection influence dynamic lithium battery remaining life
Big influence factor, sets up the artificial nerve network model of dynamic lithium battery remaining life, using above-mentioned six big influence factors
Parameter training is carried out, the Forecasting Methodology of dynamic lithium battery remaining life is set up.By specifically testing, test result is shown
The reliability of artificial nerve network model, its error within the scope of ideal illustrates the advance of this Forecasting Methodology.
Brief description of the drawings
Fig. 1 is flow chart of the method for the present invention；
Fig. 2 is artificial nerve network model schematic diagram of the invention；
Fig. 3 is the training process figure a of the present inventor's artificial neural networks；
Fig. 4 is the training process figure b of the present inventor's artificial neural networks；
Fig. 5 is the training process figure c of the present inventor's artificial neural networks；
Embodiment：
The invention will be further described with embodiment below in conjunction with the accompanying drawings：
It is noted that described further below is all exemplary, it is intended to provide further instruction to the application.Unless another
Indicate, all technologies used herein and scientific terminology are with usual with the application person of an ordinary skill in the technical field
The identical meanings of understanding.
It should be noted that term used herein above is merely to describe embodiment, and be not intended to restricted root
According to the illustrative embodiments of the application.As used herein, unless the context clearly indicates otherwise, otherwise singulative
It is also intended to include plural form, additionally, it should be understood that, when in this manual using term "comprising" and/or " bag
Include " when, it indicates existing characteristics, step, operation, device, component and/or combinations thereof.
A kind of exemplary embodiments of the present invention are a kind of Forecasting Methodologies of electrokinetic cell remaining life, as shown in figure 1,
The battery bag that the present embodiment chooses the battery core of Samsung 18650 is research object, and the battery bag is the battery core of 51 and 95 strings, rated capacity
For 112.2Ah.
The influence factor of dynamic lithium battery remaining life includes total voltage, temperature, charging and discharging currents, single battery
SOC, single battery battery core voltage, the big key elements of single battery SOH six.
(1) total voltage, is expressed as XV：The scope of total voltage is between 285V to 389.5V, and battery bag is 95 string ternary materials
Expect lithium battery, the height of total voltage represents the depth of battery bag discharge and recharge；
(2) temperature, is expressed as XT：Temperature range has been provided with 20 temperature acquisitions to the battery bag at -30 DEG C to 70 DEG C
In point, the battery core that this 51 and 95 string is evenly distributed on setpoint distance, we, which take, chooses the temperature T11 of battery bag middle for generation
Table；
(3) charging and discharging currents, are expressed as XI：Current range -0.2C arrive 2C, be charged as negative value, discharge on the occasion of；
(4) SOC of battery bag, is expressed as XS：Selection can represent the SOC of most of single-unit battery cores, and selection is the 20th
String；
(5) battery core voltage, is expressed as XC：Selection can represent the battery core voltage of most of single-unit battery cores, and selection is the
20 strings, it is consistent with SOC selections；
(6) SOH of battery, is expressed as XH：The 20th string is chosen, consistent, the present invention selection chosen with SOC, battery core voltage
Battery bag for 51 and 2.2Ah battery, capacity is 112.2Ah.
Dynamic lithium battery remaining life, is designated YC, the circulating battery service life of selection is theoretical to be followed for 800 times
Ring, each discharge and recharge is reduced once, YC=(800- cycle-indexes)/800.
This method that the present embodiment is proposed is verified below by experiment：
Sampled data is that real vehicle runs away data, according to mentioned above principle, screens to be formed by the later stage, partial data is shown in Table 1.
The dynamic lithium battery remaining life data acquisition table of table 1
The present embodiment can be learnt and be stored substantial amounts of defeated using artificial neural network structure's figure such as Fig. 2, artificial neural network
Enter-output mode mapping relations, the math equation of this mapping relations is described without disclosing in advance.
The input value Input of artificial neural network：X={ XV, XT, XI, XS, XC, XH}；
The output valve Output of artificial neural network：Prediction battery life with prediction battery residual capacity be it is of equal value,
Battery remaining power reaches that discharge and recharge number of times corresponding during stale value is the cycle life of battery, and output valve is designated as YC.
The step of artificial neural network is set up：
1) the network number of plies：Neutral net is set up, first has to predefine the number of plies of network, is not limiting node in hidden layer
In the case of, this implementation uses the neutral net of two layers (only one layer of hidden layer), you can to realize arbitrary nonlinear mapping.
2) input for determining artificial neural network in the nodes of input layer, the present embodiment is total voltage, temperature, discharge and recharge
The big key element of electric current, SOC, battery core voltage, SOH etc. six, so nodes are 6.
3) determine in the nodes of output layer, the present embodiment that artificial neural network is output as dynamic lithium battery residue and used
Life-span, nodes are 1.
4) nodes of hidden layer are determined：For the neutral net of pattern-recognition, the nodes of hidden layer are with reference to following public affairs
Formula is designed：
In formula：N is the nodes of hidden layer；niInput number of nodes；n0For output node number；A is the constant between 1~10,
The node in hidden layer of selection is 5.
5) transfer function：As needed from functions such as S (sigmoid) type function, purely linear (Pureline) functions.
6) function is trained：By needing, from Bp neutral nets choosing even function, or other training functions, to optimize data,
Reach training goal.
The input value and corresponding output valve collected according to charge and discharge cycles, trains the parameter of neutral net, is reaching
The training of setting terminates after parameter, and deconditioning obtains training parameter.Parameter Map in artificial neural network training process, is shown in
Fig. 3 to Fig. 5.
Fig. 3 terminates parameter for the training in the training process of artificial neural network；Fig. 4 is the training of artificial neural network
Physical training condition in journey；Fig. 5 is the regression figure in the training process of artificial neural network.
Run away by real vehicle, then gather 10 groups of data, using freshly harvested 10 groups of data, as test input variable, entered
Row checking, obtains the results are shown in Table 2.
As can be seen from Table 2, according to electrokinetic cell total voltage, the mean temperature of electrokinetic cell, electrokinetic cell discharge and recharge electricity
This six big influence factor of the SOH of stream, the battery core voltage of the SOC of single-unit electrokinetic cell, single-unit electrokinetic cell and single-unit electrokinetic cell
Data, obtain test result, are compared with the data collected, and error rate can be substantially controlled within ± 3%, it is achieved thereby that
By gathering the big factor data of total voltage, temperature, charging and discharging currents, SOC, battery core voltage, SOH etc. six, dynamic lithium battery is predicted
The purpose of remaining life, the safety and reliability for raising dynamic lithium battery provides foundation.
The dynamic lithium battery remaining life simulating, verifying table of table 2
Present invention introduces remaining life (RUL) concept, the six of collection influence dynamic lithium battery remaining life
Big influence factor, sets up the artificial nerve network model of dynamic lithium battery remaining life, using above-mentioned six big influence factors
Parameter training is carried out, the Forecasting Methodology of dynamic lithium battery remaining life is set up.By specifically testing, test result is shown
The reliability of artificial nerve network model, its error within the scope of ideal illustrates the advance of this Forecasting Methodology.
The preferred embodiment of the application is the foregoing is only, the application is not limited to, for the skill of this area
For art personnel, the application can have various modifications and variations.It is all within spirit herein and principle, made any repair
Change, equivalent substitution, improvement etc., should be included within the protection domain of the application.
Claims (10)
1. a kind of Forecasting Methodology of electrokinetic cell remaining life, it is characterised in that：Obtain when electric automobile is driven a vehicle every time
Electrokinetic cell status data, sets up artificial nerve network model, regard the electrokinetic cell status data as artificial neural network
The input of model, trains the training parameter of artificial nerve network model；Obtain the electrokinetic cell status number in electric automobile to be measured
According to as the input of the artificial neural network with training parameter, according to the input-output mappings relation of artificial neural network, obtaining
To predicting the outcome for the output of artificial neural network, i.e. electrokinetic cell remaining life.
2. according to the method described in claim 1, it is characterised in that：It is always electric that the electrokinetic cell status data includes electrokinetic cell
Pressure, the mean temperature of electrokinetic cell, electrokinetic cell charging and discharging currents, the SOC of single-unit electrokinetic cell, the battery core of single-unit electrokinetic cell
The SOH of voltage and single-unit electrokinetic cell.
3. according to the method described in claim 1, it is characterised in that：The foundation of the artificial nerve network model is specifically used：
N layers of artificial neural network are set up, wherein only one layer hidden layer, the nodes of every layer of setting, according to transfer function and training letter
Number sets up artificial nerve network model.
4. method according to claim 3, it is characterised in that：The N layers of artificial neural network has input layer and output
Layer, the nodes of input layer are 6, and the nodes of output layer are 1；The nodes of hidden layer are determined according to following formula：
<mrow>
<mi>n</mi>
<mo>=</mo>
<msqrt>
<mrow>
<msub>
<mi>n</mi>
<mi>i</mi>
</msub>
<mo>+</mo>
<msub>
<mi>n</mi>
<mn>0</mn>
</msub>
</mrow>
</msqrt>
<mo>+</mo>
<mi>a</mi>
</mrow>
In formula：N is the nodes of hidden layer；niInput number of nodes；n0For output node number；A is the constant between 1-10.
5. according to the method described in claim 1, it is characterised in that：The bag that predicts the outcome of the electrokinetic cell remaining life
Include：Obtain corresponding when electrokinetic cell residual capacity reaches failure according to the neural network prediction with training parameter
Electrokinetic cell discharge and recharge number of times, according to battery cycle life principle, obtain predicting the outcome for electrokinetic cell remaining life.
6. according to the method described in claim 1, it is characterised in that：The SOC value of all single batteries of the electrokinetic cell is obtained,
Handling averagely is done to it, one of electrokinetic cell status data is used as using the cell SOC value closest to average SOC value.
7. according to the method described in claim 1, it is characterised in that：Obtain the battery core electricity of all single batteries of the electrokinetic cell
Pressure, handling averagely is done to it, and electrokinetic cell is used as using the cell battery core magnitude of voltage closest to average battery core magnitude of voltage
One of status data.
8. according to the method described in claim 1, it is characterised in that：The SOH value of all single batteries of the electrokinetic cell is obtained,
Handling averagely is done to it, one of electrokinetic cell status data is used as using the cell SOH value closest to average SOH value.
9. according to the method described in claim 1, it is characterised in that：The artificial nerve network model has transfer function, uses
In data conversion between layers and transmission.
10. according to the method described in claim 1, it is characterised in that：The artificial nerve network model has training function, uses
In based on the electrokinetic cell status data as input and output, electrokinetic cell remaining life, artificial neural network is trained
The parameter of model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710214031.0A CN107069122A (en) | 2017-04-01 | 2017-04-01 | A kind of Forecasting Methodology of electrokinetic cell remaining life |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710214031.0A CN107069122A (en) | 2017-04-01 | 2017-04-01 | A kind of Forecasting Methodology of electrokinetic cell remaining life |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107069122A true CN107069122A (en) | 2017-08-18 |
Family
ID=59602089
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710214031.0A Pending CN107069122A (en) | 2017-04-01 | 2017-04-01 | A kind of Forecasting Methodology of electrokinetic cell remaining life |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107069122A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108490365A (en) * | 2018-04-18 | 2018-09-04 | 北京理工大学 | A method of the remaining life of the power battery of estimation electric vehicle |
| CN108680861A (en) * | 2018-03-05 | 2018-10-19 | 北京航空航天大学 | The construction method and device of lithium battery cycles left Life Prediction Model |
| CN108961460A (en) * | 2018-07-18 | 2018-12-07 | 清华大学 | Failure prediction method and device based on sparse ESGP and multiple-objection optimization |
| CN110555226A (en) * | 2019-04-03 | 2019-12-10 | 太原理工大学 | method for predicting residual life of lithium iron phosphate battery based on EMD and MLP |
| CN111142026A (en) * | 2019-12-31 | 2020-05-12 | 联想(北京)有限公司 | Data processing method and device and electronic equipment |
| CN112327170A (en) * | 2020-11-13 | 2021-02-05 | 中汽研（天津）汽车工程研究院有限公司 | Power battery full-period residual life estimation method based on neural network |
| CN113173104A (en) * | 2021-04-29 | 2021-07-27 | 浙江吉利控股集团有限公司 | New energy vehicle power battery early warning method and system |
| CN113466706A (en) * | 2021-07-26 | 2021-10-01 | 上海伟翔众翼新能源科技有限公司 | Lithium battery echelon utilization residual life prediction method based on convolutional neural network |
| CN113614554A (en) * | 2021-06-17 | 2021-11-05 | 香港应用科技研究院有限公司 | State of health assessment of decommissioned lithium ion batteries and battery modules |
| CN113619447A (en) * | 2021-07-16 | 2021-11-09 | 张立佳 | Method for predicting state of charge of battery of electric vehicle |
| CN114019380A (en) * | 2021-10-29 | 2022-02-08 | 天津市捷威动力工业有限公司 | Calendar life extension prediction method for battery cell |
| CN114089206A (en) * | 2021-10-24 | 2022-02-25 | 郑州云海信息技术有限公司 | Method, system, medium and device for predicting service life of battery redundancy module |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101067644A (en) * | 2007-04-20 | 2007-11-07 | 杭州高特电子设备有限公司 | Storage battery performance analytical expert diagnosing method |
| CN101809456A (en) * | 2007-08-23 | 2010-08-18 | 株式会社Lg化学 | System and method for estimating long term characteristics of battery |
| CN105789716A (en) * | 2016-03-03 | 2016-07-20 | 北京交通大学 | Generalized battery management system |
| CN106526494A (en) * | 2016-11-18 | 2017-03-22 | 普天新能源车辆技术有限公司 | Method and device for predicting service life of power cell |
-
2017
- 2017-04-01 CN CN201710214031.0A patent/CN107069122A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101067644A (en) * | 2007-04-20 | 2007-11-07 | 杭州高特电子设备有限公司 | Storage battery performance analytical expert diagnosing method |
| CN101809456A (en) * | 2007-08-23 | 2010-08-18 | 株式会社Lg化学 | System and method for estimating long term characteristics of battery |
| CN105789716A (en) * | 2016-03-03 | 2016-07-20 | 北京交通大学 | Generalized battery management system |
| CN106526494A (en) * | 2016-11-18 | 2017-03-22 | 普天新能源车辆技术有限公司 | Method and device for predicting service life of power cell |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108680861A (en) * | 2018-03-05 | 2018-10-19 | 北京航空航天大学 | The construction method and device of lithium battery cycles left Life Prediction Model |
| CN108490365A (en) * | 2018-04-18 | 2018-09-04 | 北京理工大学 | A method of the remaining life of the power battery of estimation electric vehicle |
| CN108961460A (en) * | 2018-07-18 | 2018-12-07 | 清华大学 | Failure prediction method and device based on sparse ESGP and multiple-objection optimization |
| CN108961460B (en) * | 2018-07-18 | 2020-05-08 | 清华大学 | Fault prediction method and device based on sparse ESGP (Enterprise service gateway) and multi-objective optimization |
| CN110555226A (en) * | 2019-04-03 | 2019-12-10 | 太原理工大学 | method for predicting residual life of lithium iron phosphate battery based on EMD and MLP |
| CN111142026A (en) * | 2019-12-31 | 2020-05-12 | 联想(北京)有限公司 | Data processing method and device and electronic equipment |
| CN112327170A (en) * | 2020-11-13 | 2021-02-05 | 中汽研（天津）汽车工程研究院有限公司 | Power battery full-period residual life estimation method based on neural network |
| CN113173104A (en) * | 2021-04-29 | 2021-07-27 | 浙江吉利控股集团有限公司 | New energy vehicle power battery early warning method and system |
| CN113614554A (en) * | 2021-06-17 | 2021-11-05 | 香港应用科技研究院有限公司 | State of health assessment of decommissioned lithium ion batteries and battery modules |
| CN113619447A (en) * | 2021-07-16 | 2021-11-09 | 张立佳 | Method for predicting state of charge of battery of electric vehicle |
| CN113466706A (en) * | 2021-07-26 | 2021-10-01 | 上海伟翔众翼新能源科技有限公司 | Lithium battery echelon utilization residual life prediction method based on convolutional neural network |
| CN113466706B (en) * | 2021-07-26 | 2022-07-29 | 上海伟翔众翼新能源科技有限公司 | Lithium battery echelon utilization residual life prediction method based on convolutional neural network |
| CN114089206A (en) * | 2021-10-24 | 2022-02-25 | 郑州云海信息技术有限公司 | Method, system, medium and device for predicting service life of battery redundancy module |
| CN114019380A (en) * | 2021-10-29 | 2022-02-08 | 天津市捷威动力工业有限公司 | Calendar life extension prediction method for battery cell |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107069122A (en) | A kind of Forecasting Methodology of electrokinetic cell remaining life | |
| CN104538999B (en) | Photovoltaic generating energy storage system and energy scheduling method thereof | |
| CN102324582B (en) | Intelligent maintenance device of multifunctional lead-acid battery and capacity prediction method | |
| Jiaqiang et al. | Effects analysis on active equalization control of lithium-ion batteries based on intelligent estimation of the state-of-charge | |
| CN103675707B (en) | Lithium ion battery peak power online evaluation method | |
| Shen et al. | A new battery available capacity indicator for electric vehicles using neural network | |
| CN104332666B (en) | Availability evaluation method on retired dynamic lithium battery | |
| Wang et al. | A LiFePO4 battery pack capacity estimation approach considering in-parallel cell safety in electric vehicles | |
| CN105811500B (en) | A kind of Li-ion batteries piles balance control method | |
| CN107870306A (en) | A kind of lithium battery charge state prediction algorithm based under deep neural network | |
| Wu et al. | Dynamic battery equalization with energy and time efficiency for electric vehicles | |
| CN104485681B (en) | A kind of monitoring method of wind energy turbine set energy-storage system | |
| CN108872869B (en) | Lithium ion battery degradation classification method based on BP neural network | |
| CN107015158B (en) | Lithium battery remaining life on-line quick detection method based on constant-current discharge segment | |
| CN205693405U (en) | Set of cells or capacitor group management system | |
| CN111680848A (en) | Battery life prediction method based on prediction model fusion and storage medium | |
| CN106154165A (en) | The appraisal procedure of a kind of high capacity cell energy-storage system performance and assessment system | |
| CN106383316A (en) | Echelon utilization lithium battery performance evaluation method | |
| CN106526493A (en) | Power battery external short circuit fault diagnosing and temperature rise prediction method and system based on BP neural networks | |
| CN111366848A (en) | Battery health state prediction method based on PSO-ELM algorithm | |
| CN103941191A (en) | Energy storing device integrated management method and energy storing device | |
| Zhang et al. | An adaptive battery capacity estimation method suitable for random charging voltage range in electric vehicles | |
| CN105183994A (en) | Method and device for predicting powder battery SOC on basis of improved I-ELM | |
| Zhang et al. | Prior-knowledge-independent equalization to improve battery uniformity with energy efficiency and time efficiency for lithium-ion battery | |
| CN106777786A (en) | A kind of lithium ion battery SOC 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170818 |
|
| RJ01 | Rejection of invention patent application after publication |