CN109884548A - A kind of lithium battery method for predicting residual useful life based on GASVM-AUKF algorithm - Google Patents
A kind of lithium battery method for predicting residual useful life based on GASVM-AUKF algorithm Download PDFInfo
- Publication number
- CN109884548A CN109884548A CN201910160991.2A CN201910160991A CN109884548A CN 109884548 A CN109884548 A CN 109884548A CN 201910160991 A CN201910160991 A CN 201910160991A CN 109884548 A CN109884548 A CN 109884548A
- Authority
- CN
- China
- Prior art keywords
- lithium battery
- algorithm
- residual error
- error data
- aukf
- 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
Abstract
The embodiment of the invention provides a kind of lithium battery method for predicting residual useful life based on GASVM-AUKF algorithm, comprising: obtains the capacity data of lithium battery, and establishes state space equation according to the capacity data；Based on the state space equation and adaptive Unscented kalman filtering AUKF algorithm, the corresponding residual error data of lithium battery is obtained；Based on support vector machines algorithm, the predicted value of the residual error data is calculated；Based on the predicted value of the AUKF algorithm and the residual error data, the remaining battery life of the lithium battery is predicted.Lithium battery method for predicting residual useful life provided in an embodiment of the present invention and system, using AUKF algorithm, the adaptive updates of process noise covariance and observation noise covariance may be implemented, reduce influence of the noise to whole filter effect, filtering accuracy is improved, realizes accurate predicting residual useful life result.
Description
Technical field
The present embodiments relate to battery technology field more particularly to a kind of lithium battery based on GASVM-AUKF algorithm are surplus
Remaining life-span prediction method.
Background technique
With the increase of countries in the world expanding economy and population, energy problem becomes focus concerned by people.Lithium battery
The advantages that due to its capacity density height, self-discharge rate is low, highly-safe, has extended cycle life is widely used in the daily life of people
In work.
However, in lithium battery use process, due to the effect of complexity and a variety of uncertain factors, function and performance
It can occur inevitably to degenerate, eventually lead to the failure of lithium battery.The failure of lithium battery is both likely to result in economic loss,
Great accident may be caused again.Currently, in the prior art have the thought realization lithium electricity combined using data model more
The mode of the estimation of pond RUL estimates the capacity prediction of battery and remaining life.
But the method noise that the prior art provides is larger, causes filter effect precision low, so that prediction result is inaccurate, because
This, needs a kind of lithium battery method for predicting residual useful life based on GASVM-AUKF algorithm now to solve the above problems.
Summary of the invention
To solve the above-mentioned problems, the embodiment of the present invention provides one kind and overcomes the above problem or at least be partially solved
State a kind of lithium battery method for predicting residual useful life based on GASVM-AUKF algorithm of problem.
The first aspect embodiment of the present invention provides a kind of lithium battery predicting residual useful life side based on GASVM-AUKF algorithm
Method, comprising:
The capacity data of lithium battery is obtained, and state space equation is established according to the capacity data；
Based on the state space equation and adaptive Unscented kalman filtering AUKF algorithm, it is corresponding residual to obtain lithium battery
Difference data；
Based on support vector machines algorithm, the predicted value of the residual error data is calculated；
Based on the predicted value of the AUKF algorithm and the residual error data, the remaining battery life of the lithium battery is predicted.
Lithium battery method for predicting residual useful life provided in an embodiment of the present invention based on GASVM-AUKF algorithm, using AUKF
The adaptive updates of process noise covariance and observation noise covariance may be implemented in algorithm, reduce noise to whole filtering effect
The influence of fruit improves filtering accuracy, realizes accurate predicting residual useful life result.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Bright some embodiments for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is a kind of lithium battery method for predicting residual useful life based on GASVM-AUKF algorithm provided in an embodiment of the present invention
Flow diagram.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical solution in the embodiment of the present invention is explicitly described, it is clear that described embodiment is the present invention
A part of the embodiment, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not having
Every other embodiment obtained under the premise of creative work is made, shall fall within the protection scope of the present invention.
Currently, the think of still combined in the prior art using traditional data model for the prediction mode of remaining battery life
Think, but this mode of the prior art does not correct influence of the noise for total algorithm, causes filter effect precision lower.
Aiming at the problems existing in the prior art, Fig. 1 is provided in an embodiment of the present invention a kind of based on GASVM-AUKF calculation
The lithium battery method for predicting residual useful life flow diagram of method, as shown in Figure 1, comprising:
101, the capacity data of lithium battery is obtained, and state space equation is established according to the capacity data；
102, it is based on the state space equation and adaptive Unscented kalman filtering AUKF algorithm, it is corresponding to obtain lithium battery
Residual error data；
103, it is based on support vector machines algorithm, calculates the predicted value of the residual error data；
104, the predicted value based on the AUKF algorithm and the residual error data, predicts the remaining battery longevity of the lithium battery
Life.
Specifically, in a step 101, the embodiment of the present invention can obtain the battery capacity number in lithium battery use process first
According to, it should be noted that the battery capacity data is time storing data corresponding with capacity, then according to the battery capacity
Data can establish a state space equation on the basis of time state.Specifically, the embodiment of the present invention can be for difference
Battery data select different starting future positions, establish state sky using recorded battery capacity data before future position
Between equation.
Further, in a step 102, the embodiment of the present invention uses adaptive Unscented kalman filtering AUKF algorithm pair
Data are filtered, it is to be understood that AUKF algorithm is a kind of novel non-linearity filtering algorithm, and circulation is used to change
The form in generation goes out system parameter using the state estimation estimated according to known system parameters estimated state, has suitable well
Ying Xing.State space equation obtained in the AUKF algorithm combination step 101 provided through the embodiment of the present invention, can calculate
To the corresponding residual error data of lithium battery, residual error data refers to the difference between observation data and prediction data, to obtain originating
The residual error data at each moment before future position.
In step 103, according to obtained residual error data, the embodiment of the present invention uses SVM algorithm to the residual error data
Value predicted, it should be noted that the SVM algorithm be actually one utilize the trained mould of phase space reconfiguration method
Type can export corresponding predicted value after residual error data is inputted the model.Preferably, residual error data obtained in step 102
It needs to be predicted again after the removal of exceptional value by screening.
Finally, at step 104, for the embodiment of the present invention by the predicted value of residual error data in conjunction with AUKF algorithm, prediction is new
Model parameter, that is, predict the T+i moment state estimationT is starting prediction point moment, thus according to prediction result,
The battery predictive capacity at T+i (i=1,2 ..., n) moment can be obtained in conjunction with the calculation method of the measurement estimated value in AUKF algorithm.
Lithium battery method for predicting residual useful life provided in an embodiment of the present invention based on GASVM-AUKF algorithm, using AUKF
The adaptive updates of process noise covariance and observation noise covariance may be implemented in algorithm, reduce noise to whole filtering effect
The influence of fruit improves filtering accuracy, realizes accurate predicting residual useful life result.
On the basis of the above embodiments, the method also includes:
When calculating the predicted value of the residual error data, based on genetic algorithm to the algorithm parameter in the SVM algorithm into
Row optimization.
By the content of above-described embodiment it is found that method provided in an embodiment of the present invention uses SVM algorithm to residual error data
It is predicted.
Preferably, the embodiment of the present invention joined genetic algorithm (GeneticAlgorithm) to SVM algorithm in prediction
In kernel function K (xi,xt) and penalty coefficient C optimize, finally obtain more accurate residual error data
Specifically, genetic algorithm optimization SVM algorithm includes the following steps:
1, the residual error data obtained using AUKF algorithm is chosen a part and makees training set, and subsequent a part is as test
Collection, establishes training pattern.
2, then setting population number, maximum evolutionary generation, crossover probability, the bound of mutation probability and parameter pair, and
Initializaing variable is generated at random in time t=0.
3, the individual in current group is trained as hyper parameter, using validation data set training SVM to obtain mesh
Scalar functions, the position of target point and the best target value of current position.
4, it selects, intersects and variation group, use the position of SVM training more new solution, the position of target point and most
Good target value, setting evolution generation t=t+1.
If 5, reaching maximum algebra, by σ, the optimized parameter of C, γ are obtained as hyper parameter by training dataset
Optimal models, it is no to then follow the steps 3 continuation iteration.
6, the new residual error data of the model training obtained using step 5.
What genetic algorithm and SVM algorithm obtained is the residual error data of a prediction, and n can be obtained using n one-step prediction
Walk prediction effect:
It is on the basis of the above embodiments, described that state space equation is established according to the capacity data, comprising:
Starting future position is determined in the capacity data；
According to the capacity data and least square method before the starting future position, the state space equation is established.
By the content of above-described embodiment it is found that the embodiment of the present invention can establish state space equation according to capacity data,
In actual mechanical process, the embodiment of the present invention can select different starting future positions, utilize prediction according to different battery datas
Experimental data and combination least square method before putting establish corresponding state space equation, and the data after future position are as survey
Sample sheet, the accuracy of verifying prediction of the embodiment of the present invention.
Specifically during emulation experiment, the embodiment of the present invention has selected B0005, B0006, B0007, B0018 in NASA
Four groups of battery datas carry out emulation experiment, the state space equation established are as follows:
Wherein, xk=[ak,bk,ck,dk], k indicates cycle-index, xkIndicate state model parameter, QkIndicate the sight of capacity
Measured value, in addition, wkWith vkRespectively indicate state white Gaussian noise and observation white Gaussian noise.
On the basis of the above embodiments, described to be based on the state space equation and adaptive Unscented kalman filtering
AUKF algorithm obtains the corresponding residual error data of lithium battery, comprising:
Non-loss transformation is carried out to the state space equation；
Prediction of result based on non-loss transformation simultaneously updates noise covariance matrix, to obtain the corresponding residual error number of lithium battery
According to.
The embodiment of the present invention on the basis of state space equation, using AUKF algorithm obtained starting future position before
T residual error data, detailed process are as follows:
1) it, is based on state space equation, carries out lossless UT transformation, detailed process is as follows:
State space equation is as follows:
2n+1 sigma point is calculated, i.e. sampled point, n here refers to the dimension of state.Preferably, of the invention real
It applies in example because state vector dimension is 4, n=4.
Wherein, I-th column of representing matrix root.
Then it calculates the corresponding weight of sampled point and obtains the result of UT transformation:
2) predicted portions:
One group of sampled point (referred to as Sigma point set) and its corresponding weight are obtained using above-mentioned two groups of formula:
The one-step prediction of 2n+1 Sigma point set is calculated, i=1,2 ..., 2n+1:
X(i)(k+1 | k)=f [k, X(i)(k|k)]；
The one-step prediction and covariance matrix of computing system quantity of state, it is obtained by the predicted value weighted sum of Sigma point set
It arrives:
3) part, is updated:
According to one-step prediction value, UT transformation is reused, new Sigma point set is generated:
By the prediction Sigma point set obtained by above-mentioned steps substitution observational equation, the observed quantity predicted, i=1,
2 ..., 2n+1:
Z(i)(k+1 | k)=h [X(i)(k+1|k)]；
The observation predicted value that will be obtained obtains the mean value and covariance of system prediction by weighted sum:
Then kalman gain is calculated:
The state of computing system updates and covariance updates:
Calculate measurement estimated value:
Finally, carrying out process noise covariance and observation noise covariance update:
Wherein, ZkThe capability value for indicating lithium battery, corresponding to the Q in state space equationk, when obtaining T by AUKF algorithm
Residual error data e before quarter1:T, i.e., state updating section is corresponding in AUKF algorithmIt is each
The corresponding residual error data of a k value.
On the basis of the above embodiments, described to be based on support vector machines algorithm, calculate the prediction of the residual error data
Value, comprising:
According to the support vector machines and Radial basis kernel function of ε-SVR, the predicted value of the residual error data is calculated.
By the content of above-described embodiment it is found that the embodiment of the present invention utilizes SVM algorithm, residual error data is trained,
In preferably select the ε-SVM method more sensitive to residual error data, by resulting residual error data by screening, remove exceptional value
Later, the input as ε-SVM, training obtain new prediction residual data, wherein the SVM kernel function of selection is radial base core
Function, expression are as follows:
On the basis of the above embodiments, the predicted value based on the AUKF algorithm and the residual error data, prediction
The remaining battery life of the lithium battery, comprising:
Based on the predicted value of the AUKF algorithm and the residual error data, calculates lithium battery and predict capacity；
If the lithium battery prediction capacity is greater than preset capacity threshold value, determine that prediction is accurate, to obtain the lithium battery
Remaining battery life.
It is understood that obtained new residual values are updated to again in AUKF algorithm, at this point, not needing to add
New measured value, the defect of one-step prediction can only be carried out by changing AUKF algorithm, to achieve the purpose that multi-step prediction.Utilize AUKF
It after algorithm obtains new estimated value, is compared with capacity threshold, after reaching the capacity threshold defined before, then at this time
RUL is prediction starting point to the time between failure threshold point, and will predict that estimation all between starting point and failpoint is held
Magnitude and test set, i.e. true capacity value carry out root-mean-square error, the index analysis such as absolute error percentage comparison, to verify
The accuracy of prediction.
So pass through the accurate estimation to following instant capability value, so that it may obtain the remaining battery life of lithium battery.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It realizes by means of software and necessary general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be embodied in the form of software products in other words, should
Computer software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
Method described in certain parts of example or embodiment.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
Present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: it still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features；
And these are modified or replaceed, technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (6)
1. a kind of lithium battery method for predicting residual useful life based on GASVM-AUKF algorithm characterized by comprising
The capacity data of lithium battery is obtained, and state space equation is established according to the capacity data；
Based on the state space equation and adaptive Unscented kalman filtering AUKF algorithm, the corresponding residual error number of lithium battery is obtained
According to；
Based on support vector machines algorithm, the predicted value of the residual error data is calculated；
Based on the predicted value of the AUKF algorithm and the residual error data, the remaining battery life of the lithium battery is predicted.
2. the method according to claim 1, wherein the method also includes:
When calculating the predicted value of the residual error data, the algorithm parameter in the SVM algorithm is carried out based on genetic algorithm excellent
Change.
3. the method according to claim 1, wherein described establish state space side according to the capacity data
Journey, comprising:
Starting future position is determined in the capacity data；
According to the capacity data and least square method before the starting future position, the state space equation is established.
4. the method according to claim 1, wherein described based on the state space equation and adaptively without mark
Kalman filtering AUKF algorithm obtains the corresponding residual error data of lithium battery, comprising:
Non-loss transformation is carried out to the state space equation；
Prediction of result based on non-loss transformation simultaneously updates noise covariance matrix, to obtain the corresponding residual error data of lithium battery.
5. being calculated described residual the method according to claim 1, wherein described be based on support vector machines algorithm
The predicted value of difference data, comprising:
According to the support vector machines and Radial basis kernel function of ε-SVR, the predicted value of the residual error data is calculated.
6. the method according to claim 1, wherein described based on the AUKF algorithm and the residual error data
Predicted value predicts the remaining battery life of the lithium battery, comprising:
Based on the predicted value of the AUKF algorithm and the residual error data, calculates lithium battery and predict capacity；
If the lithium battery prediction capacity is greater than preset capacity threshold value, determine that prediction is accurate, to obtain the electricity of the lithium battery
Pond remaining life.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910160991.2A CN109884548B (en) | 2019-03-04 | 2019-03-04 | Method for predicting remaining life of lithium battery based on GASVM-AUKF algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910160991.2A CN109884548B (en) | 2019-03-04 | 2019-03-04 | Method for predicting remaining life of lithium battery based on GASVM-AUKF algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109884548A true CN109884548A (en) | 2019-06-14 |
| CN109884548B CN109884548B (en) | 2021-07-20 |
Family
ID=66930441
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910160991.2A Active CN109884548B (en) | 2019-03-04 | 2019-03-04 | Method for predicting remaining life of lithium battery based on GASVM-AUKF algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109884548B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113125969A (en) * | 2020-01-14 | 2021-07-16 | 比亚迪股份有限公司 | Battery data processing method, device and medium based on AUKF |
| CN116466244A (en) * | 2023-06-20 | 2023-07-21 | 中国华能集团清洁能源技术研究院有限公司 | Battery state of charge anomaly detection method based on support vector machine |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008533486A (en) * | 2005-03-16 | 2008-08-21 | エルジー・ケム・リミテッド | Apparatus and method for estimating state of charge of battery |
| CN102680907A (en) * | 2012-05-31 | 2012-09-19 | 浙江大学 | Battery charging stress optical coefficient (SOC) detection method in photovoltaic system |
| CN103744026A (en) * | 2013-12-19 | 2014-04-23 | 广西科技大学 | Storage battery state of charge estimation method based on self-adaptive unscented Kalman filtering |
| CN104502851A (en) * | 2014-12-12 | 2015-04-08 | 广西科技大学 | SOC (Stress Optical Coefficient) estimation method based on AUKF (Adaptive Unscented Kalman Filter) algorithm |
| DE102013018405A1 (en) * | 2013-11-02 | 2015-05-07 | Daimler Ag | Determination of the condition of a battery characteristic estimation parameters |
| CN104714188A (en) * | 2015-03-31 | 2015-06-17 | 桂林电子科技大学 | Method and system for estimating measured noise variance matrix matched battery state of charge (SOC) |
| CN106093783A (en) * | 2016-06-03 | 2016-11-09 | 哈尔滨工业大学 | The battery SOC method of estimation that Kalman filtering merges with data-driven |
| CN106291376A (en) * | 2016-07-29 | 2017-01-04 | 华晨汽车集团控股有限公司 | Lithium battery SOC method of estimation based on supporting vector machine model and Kalman filtering |
| CN107064811A (en) * | 2017-03-01 | 2017-08-18 | 华南理工大学 | A kind of lithium battery SOC On-line Estimation methods |
| CN108872790A (en) * | 2018-07-10 | 2018-11-23 | 武汉科技大学 | A kind of MMC method for diagnosing faults based on Kalman filtering and support vector machines |
-
2019
- 2019-03-04 CN CN201910160991.2A patent/CN109884548B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008533486A (en) * | 2005-03-16 | 2008-08-21 | エルジー・ケム・リミテッド | Apparatus and method for estimating state of charge of battery |
| CN102680907A (en) * | 2012-05-31 | 2012-09-19 | 浙江大学 | Battery charging stress optical coefficient (SOC) detection method in photovoltaic system |
| DE102013018405A1 (en) * | 2013-11-02 | 2015-05-07 | Daimler Ag | Determination of the condition of a battery characteristic estimation parameters |
| CN103744026A (en) * | 2013-12-19 | 2014-04-23 | 广西科技大学 | Storage battery state of charge estimation method based on self-adaptive unscented Kalman filtering |
| CN104502851A (en) * | 2014-12-12 | 2015-04-08 | 广西科技大学 | SOC (Stress Optical Coefficient) estimation method based on AUKF (Adaptive Unscented Kalman Filter) algorithm |
| CN104714188A (en) * | 2015-03-31 | 2015-06-17 | 桂林电子科技大学 | Method and system for estimating measured noise variance matrix matched battery state of charge (SOC) |
| CN106093783A (en) * | 2016-06-03 | 2016-11-09 | 哈尔滨工业大学 | The battery SOC method of estimation that Kalman filtering merges with data-driven |
| CN106291376A (en) * | 2016-07-29 | 2017-01-04 | 华晨汽车集团控股有限公司 | Lithium battery SOC method of estimation based on supporting vector machine model and Kalman filtering |
| CN107064811A (en) * | 2017-03-01 | 2017-08-18 | 华南理工大学 | A kind of lithium battery SOC On-line Estimation methods |
| CN108872790A (en) * | 2018-07-10 | 2018-11-23 | 武汉科技大学 | A kind of MMC method for diagnosing faults based on Kalman filtering and support vector machines |
Non-Patent Citations (6)
| Title |
|---|
| XIUJUAN ZHENG 等: "An integrated unscented kalman filter and relevance vector regression approach for lithium-ion battery remaining useful life and short-term capacity prediction", 《RELIABILITY ENGINEERING AND SYSTEM SAFETY》 * |
| YANG CHANG 第: "A new hybrid method for the prediction of the remaining useful life of a lithium-ion battery", 《APPLIED ENERGY》 * |
| YINJIAO XING 等: "An ensemble model for predicting the remaining useful performance of lithium-ion batteries", 《MICROELECTRONICS RELIABILITY》 * |
| 刘伟龙 等: "基于模型融合与自适应无迹卡尔曼滤波算法的锂离子电池SOC估计", 《汽车工程》 * |
| 李昌 等: "结合支持向量机的卡尔曼预测算法在VRLA蓄电池状态监测中的应用", 《电工技术学报》 * |
| 李正国 等: "SVM和Kalman滤波大功率动力电池SOC预估方法的研究", 《中国测试》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113125969A (en) * | 2020-01-14 | 2021-07-16 | 比亚迪股份有限公司 | Battery data processing method, device and medium based on AUKF |
| CN113125969B (en) * | 2020-01-14 | 2022-07-15 | 比亚迪股份有限公司 | Battery data processing method, device and medium based on AUKF |
| CN116466244A (en) * | 2023-06-20 | 2023-07-21 | 中国华能集团清洁能源技术研究院有限公司 | Battery state of charge anomaly detection method based on support vector machine |
| CN116466244B (en) * | 2023-06-20 | 2023-08-29 | 中国华能集团清洁能源技术研究院有限公司 | Battery state of charge anomaly detection method based on support vector machine |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109884548B (en) | 2021-07-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112487702B (en) | Method for predicting residual service life of lithium ion battery | |
| CN109993270A (en) | Lithium ion battery residual life prediction technique based on grey wolf pack optimization LSTM network | |
| CN108986470A (en) | The Travel Time Estimation Method of particle swarm algorithm optimization LSTM neural network | |
| CN113537600B (en) | Medium-long-term precipitation prediction modeling method for whole-process coupling machine learning | |
| CN104331635B (en) | The method of power optical fiber Communication ray power prediction | |
| CN107316099A (en) | Ammunition Storage Reliability Forecasting Methodology based on particle group optimizing BP neural network | |
| CN109800898A (en) | A kind of intelligence short-term load forecasting method and system | |
| CN109215344B (en) | Method and system for urban road short-time traffic flow prediction | |
| CN109001640A (en) | A kind of data processing method and device of power battery | |
| CN111859733B (en) | Method for optimizing reliability of automobile exhaust system based on ant colony algorithm | |
| CN110442941A (en) | It is a kind of to be tracked and RUL prediction technique based on the battery status for improving particle filter and process noise features fusion algorithm | |
| CN110082682A (en) | A kind of lithium battery charge state estimation method | |
| CN109884548A (en) | A kind of lithium battery method for predicting residual useful life based on GASVM-AUKF algorithm | |
| CN109492748A (en) | A kind of Mid-long term load forecasting method for establishing model of the electric system based on convolutional neural networks | |
| CN116345578B (en) | Micro-grid operation optimization scheduling method based on depth deterministic strategy gradient | |
| CN106296434A (en) | A kind of Grain Crop Yield Prediction method based on PSO LSSVM algorithm | |
| CN114609994A (en) | Fault diagnosis method and device based on multi-granularity regularization rebalance incremental learning | |
| CN116244647A (en) | Unmanned aerial vehicle cluster running state estimation method | |
| CN114648170A (en) | Reservoir water level prediction early warning method and system based on hybrid deep learning model | |
| Xu et al. | A novel Drosophila‐back propagation method for the lithium‐ion battery state of charge estimation adaptive to complex working conditions | |
| CN112257348B (en) | Method for predicting long-term degradation trend of lithium battery | |
| CN116449218B (en) | Lithium battery health state estimation method | |
| CN117007974A (en) | Solid-state battery SOC estimation method based on model fusion | |
| CN112381315A (en) | LS-SVM intelligent platform area load prediction method and system based on PSO optimization | |
| CN114755586B (en) | Lithium ion battery residual life prediction method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |