Ensemble Model Based on Stacked Long Short-Term Memory Model for Cycle Life Prediction of Lithium–Ion Batteries
To meet the target value of cycle life, it is necessary to accurately assess the lithium–ion capacity degradation in the battery management system. We present an ensemble model based on the stacked long short-term memory (SLSTM), which is used to predict the capacity cycle life of lithium–ion batter...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-05-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/10/3549 |
| _version_ | 1827716440693669888 |
|---|---|
| author | Fu-Kwun Wang Chang-Yi Huang Tadele Mamo |
| author_facet | Fu-Kwun Wang Chang-Yi Huang Tadele Mamo |
| author_sort | Fu-Kwun Wang |
| collection | DOAJ |
| description | To meet the target value of cycle life, it is necessary to accurately assess the lithium–ion capacity degradation in the battery management system. We present an ensemble model based on the stacked long short-term memory (SLSTM), which is used to predict the capacity cycle life of lithium–ion batteries. The ensemble model combines LSTM with attention and gradient boosted regression (GBR) models to improve prediction accuracy, where these individual prediction values are used as input to the SLSTM model. Among 13 cells, single and multiple cells were used as the training set to verify the performance of the proposed model. In seven single-cell experiments, 70% of the data were used for model training, and the rest of the data were used for model validation. In the second experiment, one cell or two cells were used for model training, and other cells were used as test data. The results show that the proposed method is superior to individual and traditional integrated learning models. We used Monte Carlo dropout techniques to estimate variance and obtain prediction intervals. In the second experiment, the average absolute percentage errors for GBR, LSTM with attention, and the proposed model are 28.6580, 1.7813, and 1.5789, respectively. |
| first_indexed | 2024-03-10T19:41:40Z |
| format | Article |
| id | doaj.art-519a8e62ca3c43eab6b273a436f6877e |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T19:41:40Z |
| publishDate | 2020-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-519a8e62ca3c43eab6b273a436f6877e2023-11-20T01:09:46ZengMDPI AGApplied Sciences2076-34172020-05-011010354910.3390/app10103549Ensemble Model Based on Stacked Long Short-Term Memory Model for Cycle Life Prediction of Lithium–Ion BatteriesFu-Kwun Wang0Chang-Yi Huang1Tadele Mamo2Department of Industrial Management, National Taiwan University of Science and Technology, Taipei 10607, TaiwanDepartment of Industrial Management, National Taiwan University of Science and Technology, Taipei 10607, TaiwanDepartment of Industrial Management, National Taiwan University of Science and Technology, Taipei 10607, TaiwanTo meet the target value of cycle life, it is necessary to accurately assess the lithium–ion capacity degradation in the battery management system. We present an ensemble model based on the stacked long short-term memory (SLSTM), which is used to predict the capacity cycle life of lithium–ion batteries. The ensemble model combines LSTM with attention and gradient boosted regression (GBR) models to improve prediction accuracy, where these individual prediction values are used as input to the SLSTM model. Among 13 cells, single and multiple cells were used as the training set to verify the performance of the proposed model. In seven single-cell experiments, 70% of the data were used for model training, and the rest of the data were used for model validation. In the second experiment, one cell or two cells were used for model training, and other cells were used as test data. The results show that the proposed method is superior to individual and traditional integrated learning models. We used Monte Carlo dropout techniques to estimate variance and obtain prediction intervals. In the second experiment, the average absolute percentage errors for GBR, LSTM with attention, and the proposed model are 28.6580, 1.7813, and 1.5789, respectively.https://www.mdpi.com/2076-3417/10/10/3549lithium–ion batteryensemble modelgradient boosted regressionlong short-term memoryattention mechanism |
| spellingShingle | Fu-Kwun Wang Chang-Yi Huang Tadele Mamo Ensemble Model Based on Stacked Long Short-Term Memory Model for Cycle Life Prediction of Lithium–Ion Batteries Applied Sciences lithium–ion battery ensemble model gradient boosted regression long short-term memory attention mechanism |
| title | Ensemble Model Based on Stacked Long Short-Term Memory Model for Cycle Life Prediction of Lithium–Ion Batteries |
| title_full | Ensemble Model Based on Stacked Long Short-Term Memory Model for Cycle Life Prediction of Lithium–Ion Batteries |
| title_fullStr | Ensemble Model Based on Stacked Long Short-Term Memory Model for Cycle Life Prediction of Lithium–Ion Batteries |
| title_full_unstemmed | Ensemble Model Based on Stacked Long Short-Term Memory Model for Cycle Life Prediction of Lithium–Ion Batteries |
| title_short | Ensemble Model Based on Stacked Long Short-Term Memory Model for Cycle Life Prediction of Lithium–Ion Batteries |
| title_sort | ensemble model based on stacked long short term memory model for cycle life prediction of lithium ion batteries |
| topic | lithium–ion battery ensemble model gradient boosted regression long short-term memory attention mechanism |
| url | https://www.mdpi.com/2076-3417/10/10/3549 |
| work_keys_str_mv | AT fukwunwang ensemblemodelbasedonstackedlongshorttermmemorymodelforcyclelifepredictionoflithiumionbatteries AT changyihuang ensemblemodelbasedonstackedlongshorttermmemorymodelforcyclelifepredictionoflithiumionbatteries AT tadelemamo ensemblemodelbasedonstackedlongshorttermmemorymodelforcyclelifepredictionoflithiumionbatteries |