Predicting battery lifetime under varying usage conditions from early aging data
Accurate battery lifetime prediction is important for maintenance, warranties, and cell design. However, manufacturing variability and usage-dependent degradation make life prediction challenging. Here, we investigate new features derived from capacity-voltage data in early life to predict the lifet...
| Автори: | , , , , |
|---|---|
| Формат: | Journal article |
| Мова: | English |
| Опубліковано: |
Cell Press
2024
|
| _version_ | 1826313138608275456 |
|---|---|
| author | Li, T Zhou, Z Thelen, A Howey, DA Hu, C |
| author_facet | Li, T Zhou, Z Thelen, A Howey, DA Hu, C |
| author_sort | Li, T |
| collection | OXFORD |
| description | Accurate battery lifetime prediction is important for maintenance, warranties, and cell design. However, manufacturing variability and usage-dependent degradation make life prediction challenging. Here, we investigate new features derived from capacity-voltage data in early life to predict the lifetime of cells cycled under varying charge rates, discharge rates, and depths of discharge. The early-life features capture a cell’s state of health and the change rate of component-level degradation modes. Using a newly generated dataset from 225 nickel-manganese-cobalt/graphite lithium-ion cells aged under a wide range of conditions, we demonstrate a lifetime prediction of in-distribution cells with 15.1% mean absolute percentage error (MAPE). A hierarchical Bayesian model shows improved performance on extrapolation, achieving 21.8% MAPE for out-of-distribution cells. Our approach highlights the importance of using domain knowledge of battery degradation to inform feature engineering and model construction. Further, a new publicly available battery lifelong aging dataset is provided. |
| first_indexed | 2024-09-25T04:08:25Z |
| format | Journal article |
| id | oxford-uuid:1540819a-a436-45f8-b6cb-af45afbc3c17 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-09-25T04:08:25Z |
| publishDate | 2024 |
| publisher | Cell Press |
| record_format | dspace |
| spelling | oxford-uuid:1540819a-a436-45f8-b6cb-af45afbc3c172024-06-10T19:15:14ZPredicting battery lifetime under varying usage conditions from early aging dataJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:1540819a-a436-45f8-b6cb-af45afbc3c17EnglishSymplectic ElementsCell Press2024Li, TZhou, ZThelen, AHowey, DAHu, CAccurate battery lifetime prediction is important for maintenance, warranties, and cell design. However, manufacturing variability and usage-dependent degradation make life prediction challenging. Here, we investigate new features derived from capacity-voltage data in early life to predict the lifetime of cells cycled under varying charge rates, discharge rates, and depths of discharge. The early-life features capture a cell’s state of health and the change rate of component-level degradation modes. Using a newly generated dataset from 225 nickel-manganese-cobalt/graphite lithium-ion cells aged under a wide range of conditions, we demonstrate a lifetime prediction of in-distribution cells with 15.1% mean absolute percentage error (MAPE). A hierarchical Bayesian model shows improved performance on extrapolation, achieving 21.8% MAPE for out-of-distribution cells. Our approach highlights the importance of using domain knowledge of battery degradation to inform feature engineering and model construction. Further, a new publicly available battery lifelong aging dataset is provided. |
| spellingShingle | Li, T Zhou, Z Thelen, A Howey, DA Hu, C Predicting battery lifetime under varying usage conditions from early aging data |
| title | Predicting battery lifetime under varying usage conditions from early aging data |
| title_full | Predicting battery lifetime under varying usage conditions from early aging data |
| title_fullStr | Predicting battery lifetime under varying usage conditions from early aging data |
| title_full_unstemmed | Predicting battery lifetime under varying usage conditions from early aging data |
| title_short | Predicting battery lifetime under varying usage conditions from early aging data |
| title_sort | predicting battery lifetime under varying usage conditions from early aging data |
| work_keys_str_mv | AT lit predictingbatterylifetimeundervaryingusageconditionsfromearlyagingdata AT zhouz predictingbatterylifetimeundervaryingusageconditionsfromearlyagingdata AT thelena predictingbatterylifetimeundervaryingusageconditionsfromearlyagingdata AT howeyda predictingbatterylifetimeundervaryingusageconditionsfromearlyagingdata AT huc predictingbatterylifetimeundervaryingusageconditionsfromearlyagingdata |