Adaptive Transfer Learning Strategy for Predicting Battery Aging in Electric Vehicles
This work presents an adaptive transfer learning approach for predicting the aging of lithium-ion batteries (LiBs) in electric vehicles using capacity fade as the metric for the battery state of health. The proposed approach includes a similarity-based and adaptive strategy in which selected data fr...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Batteries |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-0105/11/1/21 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589094149947392 |
|---|---|
| author | Daniela Galatro Manav Shroff Cristina H. Amon |
| author_facet | Daniela Galatro Manav Shroff Cristina H. Amon |
| author_sort | Daniela Galatro |
| collection | DOAJ |
| description | This work presents an adaptive transfer learning approach for predicting the aging of lithium-ion batteries (LiBs) in electric vehicles using capacity fade as the metric for the battery state of health. The proposed approach includes a similarity-based and adaptive strategy in which selected data from an original dataset are transferred to a clean dataset based on the combined/weighted similarity contribution of feature and stress factor similarities and times series similarities. Transfer learning (TL) is then performed by pre-training a model with clean data, with frozen weights and biases to the hidden layer. At the same time, weights and biases toward the output node are recalculated with the target data. The error reduction lies between −0.4% and −8.3% for 20 computational experiments, attesting to the effectiveness and robustness of our adaptive TL approach. Considerations for data structure and representation learning are presented, as well as a workflow to enhance the application of transfer learning for predicting aging in LiBs. |
| format | Article |
| id | doaj-art-08bc3571a9504ab3b479220475fc4c26 |
| institution | Kabale University |
| issn | 2313-0105 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Batteries |
| spelling | doaj-art-08bc3571a9504ab3b479220475fc4c262025-01-24T13:22:26ZengMDPI AGBatteries2313-01052025-01-011112110.3390/batteries11010021Adaptive Transfer Learning Strategy for Predicting Battery Aging in Electric VehiclesDaniela Galatro0Manav Shroff1Cristina H. Amon2Department of Chemical Engineering and Applied Chemistry, University of Toronto, Toronto, ON M5S 3E5, CanadaDepartment of Chemical Engineering and Applied Chemistry, University of Toronto, Toronto, ON M5S 3E5, CanadaDepartment of Chemical Engineering and Applied Chemistry, University of Toronto, Toronto, ON M5S 3E5, CanadaThis work presents an adaptive transfer learning approach for predicting the aging of lithium-ion batteries (LiBs) in electric vehicles using capacity fade as the metric for the battery state of health. The proposed approach includes a similarity-based and adaptive strategy in which selected data from an original dataset are transferred to a clean dataset based on the combined/weighted similarity contribution of feature and stress factor similarities and times series similarities. Transfer learning (TL) is then performed by pre-training a model with clean data, with frozen weights and biases to the hidden layer. At the same time, weights and biases toward the output node are recalculated with the target data. The error reduction lies between −0.4% and −8.3% for 20 computational experiments, attesting to the effectiveness and robustness of our adaptive TL approach. Considerations for data structure and representation learning are presented, as well as a workflow to enhance the application of transfer learning for predicting aging in LiBs.https://www.mdpi.com/2313-0105/11/1/21adaptive transfer learningelectric vehiclebattery agingtime series similarities |
| spellingShingle | Daniela Galatro Manav Shroff Cristina H. Amon Adaptive Transfer Learning Strategy for Predicting Battery Aging in Electric Vehicles Batteries adaptive transfer learning electric vehicle battery aging time series similarities |
| title | Adaptive Transfer Learning Strategy for Predicting Battery Aging in Electric Vehicles |
| title_full | Adaptive Transfer Learning Strategy for Predicting Battery Aging in Electric Vehicles |
| title_fullStr | Adaptive Transfer Learning Strategy for Predicting Battery Aging in Electric Vehicles |
| title_full_unstemmed | Adaptive Transfer Learning Strategy for Predicting Battery Aging in Electric Vehicles |
| title_short | Adaptive Transfer Learning Strategy for Predicting Battery Aging in Electric Vehicles |
| title_sort | adaptive transfer learning strategy for predicting battery aging in electric vehicles |
| topic | adaptive transfer learning electric vehicle battery aging time series similarities |
| url | https://www.mdpi.com/2313-0105/11/1/21 |
| work_keys_str_mv | AT danielagalatro adaptivetransferlearningstrategyforpredictingbatteryaginginelectricvehicles AT manavshroff adaptivetransferlearningstrategyforpredictingbatteryaginginelectricvehicles AT cristinahamon adaptivetransferlearningstrategyforpredictingbatteryaginginelectricvehicles |