One-shot battery degradation trajectory prediction with deep learning
The degradation of batteries is complex and dependent on several internal mechanisms. Variations arising from manufacturing uncertainties and real-world operating conditions make battery lifetime prediction challenging. Here, we introduce a deep learning-based battery health prognostics approach to...
| Main Authors: | , , , , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
Elsevier
2021
|
| _version_ | 1826256895610978304 |
|---|---|
| author | Li, W Sengupta, N Dechent, P Howey, D Annaswamy, A Sauer, DU |
| author_facet | Li, W Sengupta, N Dechent, P Howey, D Annaswamy, A Sauer, DU |
| author_sort | Li, W |
| collection | OXFORD |
| description | The degradation of batteries is complex and dependent on several internal mechanisms. Variations arising from manufacturing uncertainties and real-world operating conditions make battery lifetime prediction challenging. Here, we introduce a deep learning-based battery health prognostics approach to predict the future degradation trajectory in one shot without iteration or feature extraction. We also predict the end-of-life point and the knee-point. The model correctly learns about intrinsic variability caused by manufacturing differences, and is able to make accurate cell-specific predictions from just 100 cycles of data, and the performance improves over time as more data become available. Validation in an embedded device is demonstrated with the best-case median prediction error over the lifetime being 1.1% with normal data and 1.3% with noisy data. Compared to state-of-the-art approaches, the one-shot approach shows an increase in accuracy as well as in computing speed by up to 15 times. This work further highlights the effectiveness of data-driven approaches in the domain of health prognostics.
|
| first_indexed | 2024-03-06T18:09:32Z |
| format | Journal article |
| id | oxford-uuid:02894b61-c899-4127-bc36-bf32768a57f1 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-06T18:09:32Z |
| publishDate | 2021 |
| publisher | Elsevier |
| record_format | dspace |
| spelling | oxford-uuid:02894b61-c899-4127-bc36-bf32768a57f12022-03-26T08:41:17ZOne-shot battery degradation trajectory prediction with deep learningJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:02894b61-c899-4127-bc36-bf32768a57f1EnglishSymplectic ElementsElsevier2021Li, WSengupta, NDechent, PHowey, DAnnaswamy, ASauer, DUThe degradation of batteries is complex and dependent on several internal mechanisms. Variations arising from manufacturing uncertainties and real-world operating conditions make battery lifetime prediction challenging. Here, we introduce a deep learning-based battery health prognostics approach to predict the future degradation trajectory in one shot without iteration or feature extraction. We also predict the end-of-life point and the knee-point. The model correctly learns about intrinsic variability caused by manufacturing differences, and is able to make accurate cell-specific predictions from just 100 cycles of data, and the performance improves over time as more data become available. Validation in an embedded device is demonstrated with the best-case median prediction error over the lifetime being 1.1% with normal data and 1.3% with noisy data. Compared to state-of-the-art approaches, the one-shot approach shows an increase in accuracy as well as in computing speed by up to 15 times. This work further highlights the effectiveness of data-driven approaches in the domain of health prognostics. |
| spellingShingle | Li, W Sengupta, N Dechent, P Howey, D Annaswamy, A Sauer, DU One-shot battery degradation trajectory prediction with deep learning |
| title | One-shot battery degradation trajectory prediction with deep learning |
| title_full | One-shot battery degradation trajectory prediction with deep learning |
| title_fullStr | One-shot battery degradation trajectory prediction with deep learning |
| title_full_unstemmed | One-shot battery degradation trajectory prediction with deep learning |
| title_short | One-shot battery degradation trajectory prediction with deep learning |
| title_sort | one shot battery degradation trajectory prediction with deep learning |
| work_keys_str_mv | AT liw oneshotbatterydegradationtrajectorypredictionwithdeeplearning AT senguptan oneshotbatterydegradationtrajectorypredictionwithdeeplearning AT dechentp oneshotbatterydegradationtrajectorypredictionwithdeeplearning AT howeyd oneshotbatterydegradationtrajectorypredictionwithdeeplearning AT annaswamya oneshotbatterydegradationtrajectorypredictionwithdeeplearning AT sauerdu oneshotbatterydegradationtrajectorypredictionwithdeeplearning |