Robust Transfer Learning for Battery Lifetime Prediction Using Early Cycle Data

Journal Article (2025)
Author(s)

W. Kang (TU Delft - Statistics)

Dianpeng Wang (Beijing Institute of Technology)

Geurt Jongbloed (TU Delft - Statistics)

Jiawen Hu (University of Electronic Science and Technology of China)

P. Chen (Zhejiang University, TU Delft - Statistics)

Research Group
Statistics
DOI related publication
https://doi.org/10.1109/TII.2025.3545079
More Info
expand_more
Publication Year
2025
Language
English
Related content
Research Group
Statistics
Bibliographical Note
Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. @en
Issue number
6
Volume number
21
Pages (from-to)
4639-4648
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Battery lifetime prediction is crucial in industrial applications. However, the lack of diversity in training data often poses challenges regarding the robustness and generalization of lifetime predictions for batteries from different batches. Motivated by the early cycle data from lithium-ion batteries, this article proposes a robust transfer learning method by employing a model average framework, where the weights are determined based on the distance between the source domain and the target domain. Kernel regression is used to build the prediction of battery lifetime using early cycle data, and transfer component analysis is utilized to transfer knowledge between different domains. The case study on lithium-ion phosphate/graphite cells demonstrates that the proposed method can mitigate the impact of negative transfer and has superior performance compared to traditional methods.

Files

License info not available
warning

File under embargo until 15-09-2025