CN110095731A - Remaining life DIRECT FORECASTING METHOD applied to long-life space lithium ion battery - Google Patents
Remaining life DIRECT FORECASTING METHOD applied to long-life space lithium ion battery Download PDFInfo
- Publication number
- CN110095731A CN110095731A CN201910372667.7A CN201910372667A CN110095731A CN 110095731 A CN110095731 A CN 110095731A CN 201910372667 A CN201910372667 A CN 201910372667A CN 110095731 A CN110095731 A CN 110095731A
- Authority
- CN
- China
- Prior art keywords
- life
- remaining life
- remaining
- battery
- lithium ion
- 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]
- G01R31/392—Determining battery ageing or deterioration, e.g. state of health
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Secondary Cells (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
- Tests Of Electric Status Of Batteries (AREA)
Abstract
Applied to the remaining life DIRECT FORECASTING METHOD of long-life space lithium ion battery, it is related to lithium ion battery life-span prediction method technical field.The present invention is to solve for cycle life was up to 5~8 years space lithium ion batteries, and traditional method for predicting residual useful life based on Degradation path modeling is difficult to be suitable for such prediction level length, the problems in slow application scenarios of degenerating.The battery capacity data building data set in every section lithium ion battery each period is acquired, according to the remaining life for setting every batteries under every batteries service life maximum value and periodicity acquisition different cycles；It is inputted data set as training data, using remaining battery life as output data, data will be output and input brings Method Using Relevance Vector Machine model into and obtain the mapping model of trained capacity sequence and remaining life；Battery capacity to be predicted under each period is input in mapping model, the estimated value of remaining battery life to be predicted is obtained.For predicting the remaining life of lithium ion battery.
Description
Technical field
The present invention relates to the remaining life DIRECT FORECASTING METHODs for being applied to long-life space lithium ion battery.Belong to lithium ion
Battery life predicting method and technology field.
Background technique
Lithium ion battery has become third generation space energy-storage battery and is widely used in all kinds of spacecrafts.With spacecraft
In-orbit operation, lithium ion battery constantly carry out charge and discharge cycles, inside a series of irreversible electrochemical reactions can occur
The performance of battery is caused to be degenerated.The remaining life of Accurate Prediction lithium ion battery is to guarantee spacecraft safe and stable operation
One of premise, and realize the premise of flexible, the autonomous mission planning of spacecraft cluster.But traditional lithium ion battery service life is pre-
Survey method pays close attention to the modeling problem of performance of lithium ion battery degradation trend, i.e., first to the performance degradation rail of lithium ion battery
Mark is predicted, and then the remaining life of lithium ion battery is inferred based on defined failure threshold in advance.But with battery material,
The continuous development of technique and the continuous promotion of spacecraft requirements for life, existing space lithium ion battery service life are reachable
5~8 years, about 48000 orbital periods.For life prediction problem, such long-term prediction scene can directly result in tradition
Based on degenerative character prediction Life Prediction Model mismatch, it is difficult to obtain accurate, stable prediction result.
Summary of the invention
The present invention be in order to solve for cycle life was up to 5~8 years space lithium ion batteries, it is traditional based on
The method for predicting residual useful life of Degradation path modeling is difficult to, slow application scenarios of degenerating long suitable for such prediction level
Problem.The remaining life DIRECT FORECASTING METHOD for being applied to long-life space lithium ion battery is now provided.
Applied to the remaining life DIRECT FORECASTING METHOD of long-life space lithium ion battery, the method includes following steps
It is rapid:
Step 1: acquiring the battery capacity data in every each service life of section lithium ion battery, data set is constructed,
According to the every batteries service life maximum value and periodicity of setting, the remaining longevity of every batteries under different cycles is obtained
Life；
Step 2: using the data set in step 1 as the input data of training data, by under the corresponding period battery it is surplus
Output data of the remaining service life as training data, by the input data and output data bring into Method Using Relevance Vector Machine model into
Row training, obtains the mapping model of trained capacity sequence and remaining life；
Step 3: being input to step 2 using the battery capacity to be predicted under each period as the input data of training data
In mapping model in, obtain the output data of mapping model, the estimated value as the remaining battery life to be predicted；
Step 4: being filtered using kalman filter method to the remaining life estimated value, obtain to be predicted
The remaining life estimated result of battery.
The invention has the benefit that
This method is a kind of direct method of remaining battery life prediction.This method by using capacity sequence as input,
It can be obtained remaining battery life prediction result.Battery capacity when this method is predicted for lithium ion battery residual life simultaneously
The influence that non-linear degradation and apparatus for battery capacity measurement noise generate prediction result, uses RVM (Relevance Vector
Machine, RVM) battery capacity space reflection to linear remaining life space reduces non-linear degradation effects by model, together
When combine Kalman filtering algorithm (Kalman Filter, KF) algorithm remaining battery life prediction result is filtered, reduce
The influence of the measurement noise of battery capacity, has obtained high-precision prediction result.This method is tested on 4 groups of batteries
Card, there is good prediction effect on different batteries.Less than 72 periods of remaining battery life prediction result worst error, in advance
Result is surveyed gradually to be promoted as periodicity increases precision of prediction.Prediction result precision is higher than conventional method.
Detailed description of the invention
Fig. 1 is that the remaining life described in specific embodiment one applied to long-life space lithium ion battery is directly predicted
The flow chart of method；
Fig. 2 is the curve graph that lithium ion battery residual life is obtained using the present processes.
Specific embodiment
Specific embodiment 1: illustrating present embodiment referring to Figures 1 and 2, it is applied to described in present embodiment
The remaining life DIRECT FORECASTING METHOD of long-life space lithium ion battery, the described method comprises the following steps:
Step 1: acquiring the battery capacity data in every each service life of section lithium ion battery, data set is constructed,
According to the every batteries service life maximum value and periodicity of setting, the remaining longevity of every batteries under different cycles is obtained
Life；
Step 2: using the data set in step 1 as the input data of training data, by under the corresponding period battery it is surplus
Output data of the remaining service life as training data, by the input data and output data bring into Method Using Relevance Vector Machine model into
Row training, obtains the mapping model of trained capacity sequence and remaining life；
Step 3: being input to step 2 using the battery capacity to be predicted under each period as the input data of training data
In mapping model in, obtain the output data of mapping model, the estimated value as the remaining battery life to be predicted；
Step 4: being filtered using kalman filter method to the remaining life estimated value, obtain to be predicted
The remaining life estimated result of battery.
In present embodiment, the present invention establishes the direct prediction mould between lithium ion battery degenerative character and remaining life
Type is realized between capacity sequence and remaining life using Method Using Relevance Vector Machine (Relevance Vector Machine, RVM) algorithm
Direct mapping will be counted by Kalman filtering (Kalman Filter, KF) algorithm and using this estimated result as observation
It is blended according to the result and physical model of driving model, reduces influence of the measurement noise to prediction result, realize lithium ion battery
The optimal estimation of remaining life.
Embodiment 1:
The predicting residual useful life result of three groups of batteries is as shown in the table, and specific evaluation index is as shown in table 1.
Table 1:
Step 1: the battery data collection using University of Maryland is tested, there are CX2-26, CX2- in the battery data collection
The data configuration data set of each periodic battery capacity of every batteries is denoted as Cap by 37, CX2-38 battery datasi(k), wherein
K is periodicity, and i is battery number；Set the i-th batteries service life maximum valueFor battery capacity degeneration most rated capacity
80% when corresponding periodicity, (1) calculates the corresponding remaining life RUL of the kth period battery as the following formulai(k)；
Step 2: the data of two batteries of CX2-38 construct the training set of RVM model as training data by CX2-37
[xtrain, ytrain]:
Wherein
Training set [xtrain, ytrain] is brought into RVM model, xtrain is training input, and ytrain is that training is defeated
Out；RVM is trained, RVM equation can write following formula (2):
Wherein, xtrainiIndicate that the i-th column data of xtrain, σ indicate bandwidth, RVM () indicates the output of RVM model
Value, ω=(ω0,...ωn)TFor weight vectors；
To ω=(ω in RVM model0,...ωn)TParameter is trained；
Step 3: the battery capacity data construction for predicting battery CX2-26 is as follows:
Xtest={ Captest(k-n+1),Captest(k-n+2),...,Captest(k)}；
Wherein, k is periodicity and k ∈ Z, n≤k.
Xtest is brought into trained RVM model, as shown in following formula (3).
Wherein,Result is exported for RVM model；
Step 4: being filtered by kalman filter method to prediction result: firstly, setting initialization association side
Poor P (k-1) withValue, setting covariance be training set in l monomer remaining life variance, state initial value
For the mean value of l monomer remaining life；
It is as follows to establish state transition equation:
Wherein,For the quantity of state of k-th of periodic battery RUL, ω (k) is the system noise in k-th of period；
Predictive estimation covariance matrix P (k):
P (k)=P (k-1)+Q (k) (6)
Wherein, Q (k) is the system noise variance in k-th of period；
It calculates Kalman filtering gain kg (k):
Wherein, R (k) is the measurement noise variance in k-th of period；
Calculate final predicted value
Specific embodiment 2: present embodiment be to described in specific embodiment one be applied to long-life space lithium from
The remaining life DIRECT FORECASTING METHOD of sub- battery is described further, and in present embodiment, in step 1, data set is denoted as:
Capi(k), wherein k is periodicity, and i is battery number, altogether includes the data of l batteries；
The remaining life RUL of every batteries under different cyclesi(k) are as follows:
In formula,For the i-th batteries service life maximum value.
In present embodiment,In period be the battery capacity degenerate to corresponding period when the 80% of rated capacity
Number.
Specific embodiment 3: present embodiment be to described in specific embodiment one be applied to long-life space lithium from
The remaining life DIRECT FORECASTING METHOD of sub- battery is described further, defeated in training data in step 2 in present embodiment
Enter data xtrain are as follows:
In formula,
Output data ytrain in training data are as follows:
Specific embodiment 4: present embodiment be to described in specific embodiment one be applied to long-life space lithium from
The remaining life DIRECT FORECASTING METHOD of sub- battery is described further, in present embodiment, by the input data and output
Data are brought into Method Using Relevance Vector Machine model and are trained, and the mapping model of trained capacity sequence and remaining life is obtained are as follows:
In formula, xtrainiIndicate that the i-th column data of xtrain, σ indicate that gaussian kernel function width, RVM () indicate related
The output valve of vector machine model, ω=(ω0,...ωn)TFor weight vectors.
In present embodiment, training set [xtrain, ytrain] is brought into formula 4 and is trained.To ω in RVM model
=(ω0,...ωn)TParameter is trained.
Specific embodiment 5: present embodiment be to described in specific embodiment one be applied to long-life space lithium from
The remaining life DIRECT FORECASTING METHOD of sub- battery is described further, in present embodiment, in step 3, by under each period to
Survey battery capacity CaptestAs the input data xtest of training data, are as follows:
Xtest={ Captest(k-n+1),Captest(k-n+2),...,Captest(k) } formula 5,
In formula, k ∈ Z, n≤k.
Specific embodiment 6: present embodiment be to described in specific embodiment five be applied to long-life space lithium from
The remaining life DIRECT FORECASTING METHOD of sub- battery is described further, and in present embodiment, in step 3, obtains battery to be predicted
The process of the estimated value of remaining life are as follows:
Xtest is brought into trained Method Using Relevance Vector Machine model:
In formula,Result is exported for Method Using Relevance Vector Machine model.
Specific embodiment 7: present embodiment be to described in specific embodiment one be applied to long-life space lithium from
The remaining life DIRECT FORECASTING METHOD of sub- battery is described further, and in present embodiment, in step 4, obtains battery to be predicted
Remaining life detailed process are as follows:
In step 4 one, the current training set of setting the covariance of l monomer remaining life and average life span be filter at the beginning of
Beginningization covariance and initialization remaining life estimated value；
Step 4 two, the association side that monomer remaining life to be predicted of next period is obtained using the covariance in step 4 one
Difference obtains next period monomer remaining life estimated value to be predicted using the initialization remaining life estimated value in step 4 one；
Step 4 three obtains Kalman filtering gain according to the covariance of the monomer remaining life to be predicted in next period；
Step 4 four, using kalman filter method, according to the estimated value of remaining battery life to be predicted, covariance, on
A period this monomer remaining life estimated value, initialization remaining life estimated value and Kalman filtering gain, obtain electricity to be predicted
The remaining life in pond.
Specific embodiment 8: present embodiment be to described in specific embodiment seven be applied to long-life space lithium from
The remaining life DIRECT FORECASTING METHOD of sub- battery is described further, and in present embodiment, in step 4 two, obtains the next period
Remaining life estimated value to be predicted are as follows:
State transition equation is established according to the initialization covariance of l monomer remaining life in current training set:
In formula,For the quantity of state of k-th of periodic battery RUL,For -1 periodic battery of kth
The quantity of state of RUL, W (k) are the system noise in k-th of period；
Obtain the covariance of k-th of l monomer remaining life are as follows:
P (k)=P (k-1)+Q (k) formula 9,
In formula, Q (k) is the system noise variance in k-th of period, and P (k) is the association side of the monomer remaining life in k period
Poor R (k) is the measurement noise variance in k-th of period, and P (k-1) is the covariance of the monomer remaining life in k-1 period.
In present embodiment, setting covariance is the variance of l monomer remaining life in training set, and state initial value is l
The mean value of monomer remaining life.
Specific embodiment 9: present embodiment be to described in specific embodiment eight be applied to long-life space lithium from
The remaining life DIRECT FORECASTING METHOD of sub- battery is described further, and in present embodiment, in step 4 three, obtains Kalman's filter
Wave gain kg (k) are as follows:
In formula, R (k) is the measurement noise variance in k-th of period.
Specific embodiment 10: present embodiment be to described in specific embodiment nine be applied to long-life space lithium from
The remaining life DIRECT FORECASTING METHOD of sub- battery is described further, and in present embodiment, in step 4 four, obtains electricity to be predicted
The remaining life in pondAre as follows:
Claims (10)
1. being applied to the remaining life DIRECT FORECASTING METHOD of long-life space lithium ion battery, which is characterized in that the method packet
Include following steps:
Step 1: acquiring the battery capacity data in every each service life of section lithium ion battery, data set is constructed,
According to the every batteries service life maximum value and periodicity of setting, the remaining life of every batteries under different cycles is obtained；
Step 2: using the data set in step 1 as the input data of training data, by the remaining longevity of battery under the corresponding period
The output data as training data is ordered, the input data and output data are brought into Method Using Relevance Vector Machine model and instructed
Practice, obtains the mapping model of trained capacity sequence and remaining life；
Step 3: being input in step 2 using the battery capacity to be predicted under each period as the input data of training data
In mapping model, the output data of mapping model is obtained, the estimated value as the remaining battery life to be predicted；
Step 4: being filtered using kalman filter method to the remaining life estimated value, battery to be predicted is obtained
Remaining life estimated result.
2. it is applied to the remaining life DIRECT FORECASTING METHOD of long-life space lithium ion battery according to claim 1, it is special
Sign is, in step 1, data set is denoted as: Capi(k), wherein k is periodicity, and i is battery number, altogether includes the number of l batteries
According to；
The remaining life RUL of every batteries under different cyclesi(k) are as follows:
In formula,For the i-th batteries service life maximum value.
3. it is applied to the remaining life DIRECT FORECASTING METHOD of long-life space lithium ion battery according to claim 1, it is special
Sign is, the input data xtrain in step 2, in training data are as follows:
In formula,
Output data ytrain in training data are as follows:
4. it is applied to the remaining life DIRECT FORECASTING METHOD of long-life space lithium ion battery according to claim 1, it is special
Sign is, the input data and output data are brought into Method Using Relevance Vector Machine model and are trained, trained appearance is obtained
Measure the mapping model of sequence and remaining life are as follows:
In formula, xtrainiIndicate that the i-th column data of xtrain, σ indicate that gaussian kernel function width, RVM (g) indicate Method Using Relevance Vector Machine
The output valve of model, ω=(ω0,Kωn)TFor weight vectors.
5. it is applied to the remaining life DIRECT FORECASTING METHOD of long-life space lithium ion battery according to claim 1, it is special
Sign is, in step 3, by the mesuring battary capacity C ap under each periodtestAs the input data xtest of training data, are as follows:
Xtest={ Captest(k-n+1),Captest(k-n+2),...,Captest(k) } formula 5,
In formula, k ∈ Z, n≤k.
6. it is applied to the remaining life DIRECT FORECASTING METHOD of long-life space lithium ion battery according to claim 5, it is special
Sign is, in step 3, obtains the process of the estimated value of remaining battery life to be predicted are as follows:
Xtest is brought into trained Method Using Relevance Vector Machine model:
In formula,Result is exported for Method Using Relevance Vector Machine model.
7. it is applied to the remaining life DIRECT FORECASTING METHOD of long-life space lithium ion battery according to claim 1, it is special
Sign is, in step 4, obtains the detailed process of the remaining life of battery to be predicted are as follows:
The covariance of l monomer remaining life and average life span are the initialization filtered in step 4 one, the current training set of setting
Covariance and initialization remaining life estimated value；
Step 4 two, the covariance that monomer remaining life to be predicted of next period is obtained using the covariance in step 4 one, benefit
Next period monomer remaining life estimated value to be predicted is obtained with the initialization remaining life estimated value in step 4 one；
Step 4 three obtains Kalman filtering gain according to the covariance of the monomer remaining life to be predicted in next period；
Step 4 four, using kalman filter method, according to the estimated value of remaining battery life to be predicted, covariance, last week
Phase this monomer remaining life estimated value, initialization remaining life estimated value and Kalman filtering gain, obtain battery to be predicted
Remaining life.
8. it is applied to the remaining life DIRECT FORECASTING METHOD of long-life space lithium ion battery according to claim 7, it is special
Sign is, in step 4 two, obtains the remaining life estimated value to be predicted in next period are as follows:
State transition equation is established according to the initialization covariance of l monomer remaining life in current training set:
In formula,For the quantity of state of k-th of periodic battery RUL,For the shape of -1 periodic battery RUL of kth
State amount, W (k) are the system noise in k-th of period；
Obtain the covariance of the monomer remaining life in k-th of period are as follows:
P (k)=P (k-1)+Q (k) formula 9,
In formula, Q (k) is the system noise variance in k-th of period, and P (k) is the covariance R of the monomer remaining life in k period
It (k) is the measurement noise variance in k-th of period, P (k-1) is the covariance of the monomer remaining life in k-1 period.
9. it is applied to the remaining life DIRECT FORECASTING METHOD of long-life space lithium ion battery according to claim 8, it is special
Sign is, in step 4 three, obtains Kalman filtering gain kg (k) are as follows:
In formula, R (k) is the measurement noise variance in k-th of period.
10. it is applied to the remaining life DIRECT FORECASTING METHOD of long-life space lithium ion battery according to claim 9, it is special
Sign is, in step 4 four, obtains the remaining life of battery to be predictedAre as follows:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910372667.7A CN110095731B (en) | 2019-05-06 | 2019-05-06 | Method for directly predicting residual life of lithium ion battery applied to long-life space |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910372667.7A CN110095731B (en) | 2019-05-06 | 2019-05-06 | Method for directly predicting residual life of lithium ion battery applied to long-life space |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110095731A true CN110095731A (en) | 2019-08-06 |
| CN110095731B CN110095731B (en) | 2021-06-22 |
Family
ID=67447007
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910372667.7A Active CN110095731B (en) | 2019-05-06 | 2019-05-06 | Method for directly predicting residual life of lithium ion battery applied to long-life space |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110095731B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111783242A (en) * | 2020-06-17 | 2020-10-16 | 河南科技大学 | RVM-KF-based rolling bearing residual life prediction method and device |
| CN111856298A (en) * | 2020-07-23 | 2020-10-30 | 上海空间电源研究所 | On-orbit residual capacity prediction method for lithium ion storage battery for spacecraft |
| CN111880099A (en) * | 2020-06-30 | 2020-11-03 | 国网浙江省电力有限公司电力科学研究院 | Method and system for predicting service life of battery monomer in energy storage power station |
| CN112114268A (en) * | 2020-08-26 | 2020-12-22 | 昆山贝思泰智能科技有限公司 | Batch battery core external characteristic fault prediction method based on embedded AI algorithm |
| CN113064091A (en) * | 2021-03-10 | 2021-07-02 | 北京理工新源信息科技有限公司 | Method and system for predicting remaining life of battery |
| CN114216558A (en) * | 2022-02-24 | 2022-03-22 | 西安因联信息科技有限公司 | Method and system for predicting remaining life of battery of wireless vibration sensor |
| CN116205379A (en) * | 2023-05-04 | 2023-06-02 | 上海叁零肆零科技有限公司 | Method, system, equipment and medium for establishing lithium-ion battery survival day prediction model |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103336877A (en) * | 2013-07-25 | 2013-10-02 | 哈尔滨工业大学 | Satellite lithium ion battery residual life prediction system and method based on RVM (relevance vector machine) dynamic reconfiguration |
| CN103399276A (en) * | 2013-07-25 | 2013-11-20 | 哈尔滨工业大学 | Lithium-ion battery capacity estimation and residual cycling life prediction method |
| CN104156791A (en) * | 2014-08-29 | 2014-11-19 | 哈尔滨工业大学 | Lithium ion battery residual life predicting method based on LS-SVM probability ensemble learning |
| CN106908736A (en) * | 2017-03-17 | 2017-06-30 | 哈尔滨工业大学 | Based on the lithium battery method for predicting residual useful life that depth confidence net and Method Using Relevance Vector Machine are merged |
| CN107957562A (en) * | 2018-01-05 | 2018-04-24 | 广西大学 | A kind of lithium ion battery residual life on-line prediction method |
| CN109633474A (en) * | 2018-11-14 | 2019-04-16 | 江苏大学 | A kind of lithium ion battery residual life prediction technique |
-
2019
- 2019-05-06 CN CN201910372667.7A patent/CN110095731B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103336877A (en) * | 2013-07-25 | 2013-10-02 | 哈尔滨工业大学 | Satellite lithium ion battery residual life prediction system and method based on RVM (relevance vector machine) dynamic reconfiguration |
| CN103399276A (en) * | 2013-07-25 | 2013-11-20 | 哈尔滨工业大学 | Lithium-ion battery capacity estimation and residual cycling life prediction method |
| CN104156791A (en) * | 2014-08-29 | 2014-11-19 | 哈尔滨工业大学 | Lithium ion battery residual life predicting method based on LS-SVM probability ensemble learning |
| CN106908736A (en) * | 2017-03-17 | 2017-06-30 | 哈尔滨工业大学 | Based on the lithium battery method for predicting residual useful life that depth confidence net and Method Using Relevance Vector Machine are merged |
| CN107957562A (en) * | 2018-01-05 | 2018-04-24 | 广西大学 | A kind of lithium ion battery residual life on-line prediction method |
| CN109633474A (en) * | 2018-11-14 | 2019-04-16 | 江苏大学 | A kind of lithium ion battery residual life prediction technique |
Non-Patent Citations (2)
| Title |
|---|
| 周建宝等: "可重构卫星锂离子电池剩余寿命预测系统研究", 《仪器仪表学报》 * |
| 庞景月等: "锂离子电池剩余寿命间接预测方法", 《中国科技论文》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111783242A (en) * | 2020-06-17 | 2020-10-16 | 河南科技大学 | RVM-KF-based rolling bearing residual life prediction method and device |
| CN111783242B (en) * | 2020-06-17 | 2024-05-28 | 河南科技大学 | RVM-KF-based rolling bearing residual life prediction method and device |
| CN111880099A (en) * | 2020-06-30 | 2020-11-03 | 国网浙江省电力有限公司电力科学研究院 | Method and system for predicting service life of battery monomer in energy storage power station |
| CN111880099B (en) * | 2020-06-30 | 2023-03-24 | 国网浙江省电力有限公司电力科学研究院 | Method and system for predicting service life of battery monomer in energy storage power station |
| CN111856298A (en) * | 2020-07-23 | 2020-10-30 | 上海空间电源研究所 | On-orbit residual capacity prediction method for lithium ion storage battery for spacecraft |
| CN112114268A (en) * | 2020-08-26 | 2020-12-22 | 昆山贝思泰智能科技有限公司 | Batch battery core external characteristic fault prediction method based on embedded AI algorithm |
| CN113064091A (en) * | 2021-03-10 | 2021-07-02 | 北京理工新源信息科技有限公司 | Method and system for predicting remaining life of battery |
| CN113064091B (en) * | 2021-03-10 | 2023-02-10 | 北京理工新源信息科技有限公司 | Method and system for predicting remaining life of battery |
| CN114216558A (en) * | 2022-02-24 | 2022-03-22 | 西安因联信息科技有限公司 | Method and system for predicting remaining life of battery of wireless vibration sensor |
| CN116205379A (en) * | 2023-05-04 | 2023-06-02 | 上海叁零肆零科技有限公司 | Method, system, equipment and medium for establishing lithium-ion battery survival day prediction model |
| CN116205379B (en) * | 2023-05-04 | 2023-07-07 | 上海叁零肆零科技有限公司 | Method, system, equipment and medium for establishing lithium-ion battery survival day prediction model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110095731B (en) | 2021-06-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110095731A (en) | Remaining life DIRECT FORECASTING METHOD applied to long-life space lithium ion battery | |
| EP3542173B1 (en) | Determining a state of health of a battery and providing an alert | |
| CN110568359B (en) | Lithium battery residual life prediction method | |
| CN111007400A (en) | Lithium battery SOC estimation method based on self-adaptive double-extended Kalman filtering method | |
| CN110596593A (en) | Lithium ion battery SOC estimation method based on intelligent adaptive extended Kalman filtering | |
| CN113917337A (en) | Battery health state estimation method based on charging data and LSTM neural network | |
| CN111142036A (en) | Lithium ion battery online rapid capacity estimation method based on capacity increment analysis | |
| CN108490361B (en) | Cloud feedback-based SOC (state of charge) calculation method | |
| CN111753416A (en) | Lithium ion battery RUL prediction method based on two-stage Wiener process | |
| CN111812515A (en) | XGboost model-based lithium ion battery state of charge estimation | |
| CN106154168B (en) | The method for estimating charge state of power cell of data-driven | |
| CN114035098A (en) | Lithium battery health state prediction method integrating future working condition information and historical state information | |
| CN112433170B (en) | Method for identifying parameter difference of single batteries of series battery pack | |
| CN109633470B (en) | Estimation method for battery real-time full charge time based on EKF-GPR and daily segment data | |
| CN110196395A (en) | Battery SOC estimation method | |
| CN114705990A (en) | Battery cluster state of charge estimation method and system, electronic equipment and storage medium | |
| CN115980588A (en) | Lithium ion battery health state estimation method based on self-encoder extraction features | |
| CN113406503A (en) | Lithium battery SOH online estimation method based on deep neural network | |
| CN114035095B (en) | Lithium battery SOH estimation method, medium and equipment based on voltage curve inflection point identification | |
| CN113312807B (en) | Electrolyte formula recommendation method based on lithium battery performance simulation environment | |
| CN110441702A (en) | A method of lithium ion battery charge capacity is estimated with Extended Kalman filter | |
| CN117471320A (en) | Battery state of health estimation method and system based on charging fragments | |
| US20230349977A1 (en) | Method and apparatus for estimating state of health of battery | |
| CN112327169A (en) | Lithium battery residual life prediction method | |
| CN116953547A (en) | Energy storage battery health evaluation method, system, equipment and storage medium |
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 |