Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.24475 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918408459649024 |
|---|---|
| author | da Silva, Samuel Filgueira Ozkan, Mehmet Fatih Idrissi, Faissal El Canova, Marcello |
| author_facet | da Silva, Samuel Filgueira Ozkan, Mehmet Fatih Idrissi, Faissal El Canova, Marcello |
| contents | Accurate forecasting of state-of-health (SOH) is essential for ensuring safe and reliable operation of lithium-ion cells. However, existing models calibrated on laboratory tests at specific conditions often fail to generalize to new cells that differ due to small manufacturing variations or operate under different conditions. To address this challenge, an uncertainty-aware transfer learning framework is proposed, combining a Long Short-Term Memory (LSTM) model with domain adaptation via Maximum Mean Discrepancy (MMD) and uncertainty quantification through Conformal Prediction (CP). The LSTM model is trained on a virtual battery dataset designed to capture real-world variability in electrode manufacturing and operating conditions. MMD aligns latent feature distributions between simulated and target domains to mitigate domain shift, while CP provides calibrated, distribution-free prediction intervals. This framework improves both the generalization and trustworthiness of SOH forecasts across heterogeneous cells. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_24475 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Conformalized Transfer Learning for Li-ion Battery State of Health Forecasting under Manufacturing and Usage Variability da Silva, Samuel Filgueira Ozkan, Mehmet Fatih Idrissi, Faissal El Canova, Marcello Machine Learning Systems and Control Accurate forecasting of state-of-health (SOH) is essential for ensuring safe and reliable operation of lithium-ion cells. However, existing models calibrated on laboratory tests at specific conditions often fail to generalize to new cells that differ due to small manufacturing variations or operate under different conditions. To address this challenge, an uncertainty-aware transfer learning framework is proposed, combining a Long Short-Term Memory (LSTM) model with domain adaptation via Maximum Mean Discrepancy (MMD) and uncertainty quantification through Conformal Prediction (CP). The LSTM model is trained on a virtual battery dataset designed to capture real-world variability in electrode manufacturing and operating conditions. MMD aligns latent feature distributions between simulated and target domains to mitigate domain shift, while CP provides calibrated, distribution-free prediction intervals. This framework improves both the generalization and trustworthiness of SOH forecasts across heterogeneous cells. |
| title | Conformalized Transfer Learning for Li-ion Battery State of Health Forecasting under Manufacturing and Usage Variability |
| topic | Machine Learning Systems and Control |
| url | https://arxiv.org/abs/2603.24475 |