CN112100902A - Lithium ion battery service life prediction method based on stream data - Google Patents
Lithium ion battery service life prediction method based on stream data Download PDFInfo
- Publication number
- CN112100902A CN112100902A CN202010797577.5A CN202010797577A CN112100902A CN 112100902 A CN112100902 A CN 112100902A CN 202010797577 A CN202010797577 A CN 202010797577A CN 112100902 A CN112100902 A CN 112100902A
- Authority
- CN
- China
- Prior art keywords
- battery
- data
- random forest
- life prediction
- 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
- 238000000034 method Methods 0.000 title claims abstract description 30
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 title claims abstract description 26
- 229910001416 lithium ion Inorganic materials 0.000 title claims abstract description 26
- 238000007637 random forest analysis Methods 0.000 claims abstract description 29
- 238000012549 training Methods 0.000 claims abstract description 19
- 238000012935 Averaging Methods 0.000 claims abstract description 4
- 238000003066 decision tree Methods 0.000 claims description 16
- 239000000126 substance Substances 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 239000002245 particle Substances 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 238000000342 Monte Carlo simulation Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012805 post-processing Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013501 data transformation Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/04—Ageing analysis or optimisation against ageing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Tests Of Electric Status Of Batteries (AREA)
- Secondary Cells (AREA)
Abstract
The invention discloses a lithium ion battery service life prediction method based on stream data, which comprises the following steps: acquiring flow data of battery characteristics, constructing a plurality of random forest models at the same time, and then training the random forest models by using the flow data of the battery characteristics; the method comprises the steps of obtaining a plurality of time sequence data of battery features to be predicted, wherein one time sequence data corresponds to one random forest model, inputting each time sequence data into the corresponding random forest model for life prediction, averaging life prediction results output by each random forest model, and taking the averaged result as a final battery life prediction result.
Description
Technical Field
The invention relates to a lithium ion battery life prediction method, in particular to a lithium ion battery life prediction method based on stream data.
Background
From the production to the use of lithium ion batteries, the Remaining Useful Life (RUL) of the battery has been a problem throughout. After the lithium ion battery is produced, unqualified batteries with too low expected life need to be screened out, and the batteries meeting the standard can be classified according to the expected life. Therefore, early classification of lithium ion battery life predicts a major focus of RUL prediction.
Currently, there are many studies on the prediction of the lifetime of lithium ion batteries. Some studies have focused on methods of data transformation. For example, Zhang Yongzhi et al, in "lithium ion based remaining using function prediction with Box-cox transformation and monte carlo simulation. IEEE transformations on Industrial Electronics,66(2): 1585. sup. 1597,2018," predict RUL using the Box-cox transformation and Monte Carlo simulation. Some studies are predicted by building models of lithium ion batteries. Dong Guangzhong et al in "Battery health characterization using a brown motion model and particle filters on Industrial Electronics,65(11): 8646-. Guha arij and Path Amit used characteristics of capacity attenuation and internal resistance in the context of "State of health estimation of lithium-ion batteries using capacity and internal resistance growth models, 4(1): 135-146, 2017". Ma Yan et al, "Yang Ma, Yang Chen, Xiuwen Zhou, and Hong Chen. remaining using the prediction of lithium-ion based on gaps-human particulate filter. IEEE Transactions on Control Systems Technology,27(4):1788 and 1795,2018," use the extended Kalman filter to construct the prediction model and update the parameters of the filter with the Gauss-human particulate filter. Other studies have used machine learning methods. Wei Jingwen et al use a support vector machine and particle filter to predict battery life in the context of "Remaining useful life prediction and state for lithium-ion batteries using a particle filter and a sub-vector regression, IEEE Transactions on Industrial Electronics,65(7): 565656565643, 2017". Khumpurom Phatta and Yodo Nita used deep neural networks to predict battery life in "Adata-driven predictive model for lithium-ion batteries based on a deep learning algorithm, Energies,12(4):660,2019. Severson et al, Data-driven prediction of basic cycle life before capacity prediction. Nature Energy,4(5): 383-.
However, in the above prior art, when training a model, it is necessary to extract features from data and then train the model using the features, so the prediction complexity is high and the prediction accuracy is low.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a lithium ion battery service life prediction method based on stream data, which can reduce the complexity of prediction and improve the prediction precision.
In order to achieve the above purpose, the method for predicting the service life of the lithium ion battery based on the streaming data comprises the following steps:
acquiring flow data of battery characteristics, constructing a plurality of random forest models at the same time, and then training the random forest models by using the flow data of the battery characteristics;
the method comprises the steps of obtaining a plurality of time sequence data of battery features to be predicted, wherein one time sequence data corresponds to one random forest model, inputting each time sequence data into the corresponding random forest model for life prediction, averaging life prediction results output by each random forest model, and taking the averaged result as a final battery life prediction result.
Random forest model RFiRandom forest model RF composed of several different decision treesiThe input of (a) is stream data of the ith characteristic of the battery;
for a single decision tree, all nodes except leaf nodes are provided with an SVM classifier, on the basis of input data with the size of Q x t of the decision tree, data of t' time nodes are randomly extracted to serve as input data of the SVM classifier, the SVM classifier divides a battery into two types, each node is analogized until the node is divided into the leaf nodes, and at the moment, the leaf nodes have a label which is the average value of battery lives in the leaf nodes.
The training process of the SVM classifier is as follows:
1) selecting penalty parameter C as 1, kernel function K (x)i,xj) Constructing and solving a convex quadratic regression problem for the rbf function
s.t.
Get the optimal solution
2) Selection of alpha*A component of
Wherein the content of the first and second substances,
computing
3) The final classification decision function is obtained as:
the characteristics of the battery include the voltage and temperature of the battery.
The invention has the following beneficial effects:
when the method for predicting the service life of the lithium ion battery based on the streaming data is specifically operated, time series data of the battery such as voltage and temperature are directly used as input of a random forest model to train the random forest model, the training is not based on characteristics extracted from data traditionally, the method is easy to implement due to no need of characteristic engineering, only simple measurement is needed, no complex data post-processing is needed, the method can be used as input of an SVM classifier, the number of parameters needing to be adjusted is small, and compared with a method for extracting the characteristics and then performing machine learning, the method for predicting the service life of the lithium ion battery based on the streaming data is easier to adjust and more accurate in prediction.
Drawings
FIG. 1 is a schematic diagram of the RUL prediction algorithm;
FIG. 2 is a block diagram of a random forest;
FIG. 3 is a schematic diagram of a decision tree training and prediction process;
fig. 4 is a schematic diagram of a tag dynamic update process.
Detailed Description
The invention is described in further detail below with reference to the accompanying drawings:
the lithium ion battery life prediction algorithm comprises the following steps:
establishing a plurality of random forest models, wherein each random forest model carries out life prediction according to input time sequence data (such as voltage working condition data), then averaging the life prediction results output by each random forest model to obtain a final battery life prediction result, meanwhile, a decision tree in the random forest models utilizes a support vector machine to process the splitting of decision tree nodes so as to ensure that the depth of the decision tree can be controlled even if the time sequence data is longer, the specific principle is shown in figure 1, a q axis represents different battery data, an f axis represents different battery characteristics, the battery characteristics are voltages and temperatures of different cycles, and a t axis is a time axis1，RF2……RFf) Training is carried out, and results are summarized.
Random forest model RFiRandom forest model RF composed of several different decision treesiThe input of (a) is the flow data of the ith feature, and the size is Q x t, and the input of each decision tree is obtained by a put-back sampling mode, and the size is Q x t, and the structure of the random forest is shown in fig. 2.
For a single decision tree, each node except a leaf node has an SVM classifier, based on input data of the size of decision tree Q × t, data of t' time nodes are randomly extracted as input data of the SVM classifier, the SVM classifier divides a battery into two types, each node is analogized until the node is divided into the leaf nodes, at this time, the leaf nodes have a label, the label is an average value of battery lives in the leaf nodes, when a model is applied, the label is used as a life prediction value of the decision tree, a process of training and predicting the decision tree is shown in fig. 3, specifically, a training process of the SVM classifier is as follows:
1) selecting penalty parameter C as 1, kernel function K (x)i,xj) Constructing and solving a convex quadratic regression problem for the rbf function
s.t.
Get the optimal solution
2) Selection of alpha*A component of
Wherein the content of the first and second substances,
computing
3) The final classification decision function is obtained as:
the SVM classifier is used as an algorithm with supervised learning, training data needs to have a-1/1 label when the SVM classifier is trained, the existing training data label is battery life, and therefore the numerical label of the battery life needs to be dynamically converted into a classification label. For the batteries included in the input data of the Q SVM classifiers, the median of all the battery lives is found first, the battery below the median is marked as-1, the rest batteries are marked as 1, and the battery needs to be marked again before the SVM classifier is trained each time, and the specific process is shown in fig. 4.
Compared with the traditional algorithm for training the model based on the battery characteristics, the method directly utilizes the time series data of the battery such as the voltage, the temperature and the like as the input of the model for training, is easy to implement due to no need of characteristic engineering, only needs simple measurement and no complex data post-processing, and can be used as the input of the SVM classifier.
Meanwhile, the selection of the features by the traditional battery feature-based algorithm results in data requiring many cycles, which brings great influence on the efficiency of model training. Meanwhile, the service life of the finished lithium ion battery is also reduced due to excessive cycles during testing, but the requirement on the data cycle number is low, and rapid and effective prediction is facilitated during practical application.
At present, the invention has obtained excellent effects in the lithium ion battery working condition database established by Kristen A.Severson and Peter M.Attia, and the like, and the specific indexes are as follows:
for the problem of predicting lithium ion battery life, the Mean Absolute Percent Error (MAPE) of the training set was 18.00% and the MAPE of the test set was 15.16%. For comparison, under the same data set, the training set MAPE of the prediction model based on the LSTM algorithm is 32.44%, and the test set MAPE is 24.87%; the training set MAPE of the prediction model based on the CNN algorithm is 18.56%, and the test set MAPE is 20.13%, so that the prediction precision of the method is high.
Claims (4)
1. A lithium ion battery life prediction method based on stream data is characterized by comprising the following steps:
acquiring flow data of battery characteristics, constructing a plurality of random forest models at the same time, and then training the random forest models by using the flow data of the battery characteristics;
the method comprises the steps of obtaining a plurality of time sequence data of battery features to be predicted, wherein one time sequence data corresponds to one random forest model, inputting each time sequence data into the corresponding random forest model for life prediction, averaging life prediction results output by each random forest model, and taking the averaged result as a final battery life prediction result.
2. The method for predicting the life of a lithium ion battery based on stream data as claimed in claim 1, wherein a random forest model RFiRandom forest model RF composed of several different decision treesiThe input of (a) is stream data of the ith characteristic of the battery;
for a single decision tree, all nodes except leaf nodes are provided with an SVM classifier, on the basis of input data with the size of Q x t of the decision tree, data of t' time nodes are randomly extracted to serve as input data of the SVM classifier, the SVM classifier divides a battery into two types, each node is analogized until the node is divided into the leaf nodes, and at the moment, the leaf nodes have a label which is the average value of battery lives in the leaf nodes.
3. The method for predicting the service life of the lithium ion battery based on the streaming data as claimed in claim 1, wherein the training process of the SVM classifier is as follows:
1) selecting penalty parameter C as 1, kernel function K (x)i,xj) Constructing and solving a convex quadratic regression problem for the rbf function
Get the optimal solution
2) Selection of alpha*A component of
Wherein the content of the first and second substances,
computing
3) The final classification decision function is obtained as:
4. the method of claim 1, wherein the characteristics of the battery include a voltage and a temperature of the battery.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010797577.5A CN112100902B (en) | 2020-08-10 | 2020-08-10 | Lithium ion battery life prediction method based on flow data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010797577.5A CN112100902B (en) | 2020-08-10 | 2020-08-10 | Lithium ion battery life prediction method based on flow data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112100902A true CN112100902A (en) | 2020-12-18 |
| CN112100902B CN112100902B (en) | 2023-12-22 |
Family
ID=73753191
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010797577.5A Active CN112100902B (en) | 2020-08-10 | 2020-08-10 | Lithium ion battery life prediction method based on flow data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112100902B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113589175A (en) * | 2021-08-23 | 2021-11-02 | 上海智能新能源汽车科创功能平台有限公司 | Fuel cell service life prediction method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108846227A (en) * | 2017-12-05 | 2018-11-20 | 北京航空航天大学 | A kind of capacity of lithium ion battery degradation prediction appraisal procedure based on random forest and capacity self- recoverage effect analysis |
| CN110888059A (en) * | 2019-12-03 | 2020-03-17 | 西安科技大学 | Algorithm based on improved random forest combined cubature Kalman power battery state of charge estimation |
| US20200164763A1 (en) * | 2017-07-21 | 2020-05-28 | Quantumscape Corporation | Predictive model for estimating battery states |
| AU2020100709A4 (en) * | 2020-05-05 | 2020-06-11 | Bao, Yuhang Mr | A method of prediction model based on random forest algorithm |
-
2020
- 2020-08-10 CN CN202010797577.5A patent/CN112100902B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200164763A1 (en) * | 2017-07-21 | 2020-05-28 | Quantumscape Corporation | Predictive model for estimating battery states |
| CN108846227A (en) * | 2017-12-05 | 2018-11-20 | 北京航空航天大学 | A kind of capacity of lithium ion battery degradation prediction appraisal procedure based on random forest and capacity self- recoverage effect analysis |
| CN110888059A (en) * | 2019-12-03 | 2020-03-17 | 西安科技大学 | Algorithm based on improved random forest combined cubature Kalman power battery state of charge estimation |
| AU2020100709A4 (en) * | 2020-05-05 | 2020-06-11 | Bao, Yuhang Mr | A method of prediction model based on random forest algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 韦振汉;宋树祥;夏海英;: "基于随机森林的锂离子电池荷电状态估算", 广西师范大学学报(自然科学版), no. 04 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113589175A (en) * | 2021-08-23 | 2021-11-02 | 上海智能新能源汽车科创功能平台有限公司 | Fuel cell service life prediction method and system |
| CN113589175B (en) * | 2021-08-23 | 2024-04-12 | 上海智能新能源汽车科创功能平台有限公司 | Fuel cell life prediction method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112100902B (en) | 2023-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Luo et al. | A review of deep learning approach to predicting the state of health and state of charge of lithium-ion batteries | |
| Can et al. | A new model for software defect prediction using particle swarm optimization and support vector machine | |
| Liu et al. | Transfer learning for battery smarter state estimation and ageing prognostics: Recent progress, challenges, and prospects | |
| CN113361197B (en) | Method and system for predicting remaining service life of lithium battery | |
| CN109740859A (en) | Transformer condition evaluation and system based on Principal Component Analysis and support vector machines | |
| CN110571792A (en) | Analysis and evaluation method and system for operation state of power grid regulation and control system | |
| Zheng et al. | Long-short term echo state network for time series prediction | |
| CN111999649A (en) | XGboost algorithm-based lithium battery residual life prediction method | |
| CN114580706A (en) | Power financial service wind control method and system based on GRU-LSTM neural network | |
| Kamada et al. | An adaptive learning method of restricted Boltzmann machine by neuron generation and annihilation algorithm | |
| CN114047452B (en) | Method and device for determining cycle life of battery | |
| CN115469227B (en) | Aggregation variation self-encoder and dynamic regular lithium battery abnormality detection method | |
| CN110598902A (en) | Water quality prediction method based on combination of support vector machine and KNN | |
| Li et al. | An optimal stacking ensemble for remaining useful life estimation of systems under multi-operating conditions | |
| CN115204038A (en) | Energy storage lithium battery life prediction method based on data decomposition and integration model | |
| Li et al. | Structure optimization for echo state network based on contribution | |
| Du et al. | Remaining useful performance estimation for complex analog circuit based on maximal information coefficient and bidirectional gate recurrent unit | |
| Li et al. | A hybrid framework for predicting the remaining useful life of battery using Gaussian process regression | |
| CN111652478A (en) | Electric power system voltage stability evaluation misclassification constraint method based on umbrella algorithm | |
| CN112100902B (en) | Lithium ion battery life prediction method based on flow data | |
| Liu et al. | Multiple optimized online support vector regression for adaptive time series prediction | |
| Wang et al. | Continual deep residual reservoir computing for remaining useful life prediction | |
| Li et al. | An ensemble hybrid model with outlier detection for prediction of lithium-ion battery remaining useful life | |
| Zhou et al. | Combined sparse Bayesian learning strategy for remaining useful life forecasting of lithium-ion battery | |
| CN114021465A (en) | Electric power system robust state estimation method and system based on deep learning |
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 |