EUVIMEDEUVIMED entdecken
Crossref

Co-Estimation of SOH and RUL for Second-Life Battery Based on Self-Supervised Auxiliary Learning

Rong Zhu, Weiwen Peng, Qiqi Wang, Min Xie

IEEE Transactions on Transportation Electrification · 2026-08 · 12 (4) · 6276-6287

DOI: 10.1109/tte.2026.3683068 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Transportation Electrification, 2026-08. Verfasst von Rong Zhu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 44 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Shenzhen Sustainable Development Science and Technology Special Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate estimation of the state of health (SOH) and remaining useful life (RUL) of second-life lithium-ion batteries (SL-LIBs) retired from electric vehicles (EVs) is critical for their safe reuse in energy storage systems (ESSs). Existing methods often face challenges such as limited labeled data and poor generalization across diverse working conditions. To address these limitations, we propose a co-estimation framework for SL-LIBs that integrates self-supervised auxiliary learning (SAL), gradient adversarial training (GAT), and uncertainty calibration within a multitask learning (MTL) architecture. The framework introduces the discharge capacity change rate (DCCR) as an auxiliary label to enrich degradation information, while GAT mitigates gradient interference between tasks. Additionally, predictive uncertainty is quantified using Monte Carlo (MC) Dropout and further calibrated through isotonic regression to enhance reliability. Extensive experiments on a self-tested dataset of 84 SL-LIBs demonstrate that the proposed method achieves a mean absolute error (MAE) of 0.0089 for SOH and 67 cycles for RUL, reducing the best published baseline by 41% and 39%, respectively.

Förderung

  • National Natural Science Foundation of China
  • Shenzhen Sustainable Development Science and Technology Special Project

Zitieren

APA

Zhu, R., Peng, W., Wang, Q., & Xie, M. (2026). Co-Estimation of SOH and RUL for Second-Life Battery Based on Self-Supervised Auxiliary Learning. IEEE Transactions on Transportation Electrification, 12(4), 6276-6287. https://doi.org/10.1109/tte.2026.3683068

Vancouver

Zhu R, Peng W, Wang Q, Xie M. Co-Estimation of SOH and RUL for Second-Life Battery Based on Self-Supervised Auxiliary Learning. IEEE Transactions on Transportation Electrification. 2026;12(4):6276-6287. doi:10.1109/tte.2026.3683068

BibTeX
@article{Zhu2026,
  author = {Zhu, Rong and Peng, Weiwen and Wang, Qiqi and Xie, Min},
  title = {Co-Estimation of SOH and RUL for Second-Life Battery Based on Self-Supervised Auxiliary Learning},
  journal = {IEEE Transactions on Transportation Electrification},
  year = {2026},
  volume = {12},
  number = {4},
  pages = {6276--6287},
  doi = {10.1109/tte.2026.3683068}
}
Kostenlos starten →