EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Data Augmentation for Lithium-Ion Battery State-of-Charge Estimation Across Methods and Models

Alexey A. Druzhinin, Daniel Lisnovetski

Energies · 05.11.2026 · 19 (21) · 5310

DOI: 10.3390/en19215310 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Energies, online erschienen am 05.11.2026. Verfasst von Alexey A. Druzhinin und 1 weiteren Autor:innen. Die Arbeit nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Science and Higher Education of the Russian Federation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate state-of-charge (SoC) estimation from voltage, current, and temperature is required for lithium-ion pack energy management. Learning-based estimators need labeled field traces that are costly on a deployed sensing chain, and data augmentation is used to enlarge those sets. Published studies almost always train one synthesizer for one learner, so it remains unknown which operators help which estimator classes, at what intensity, and after how much real labeled volume. In this paper, a factorial of classical, physics-informed, and generative operators is evaluated on twelve SoC estimators (dose L=1–10, labeled volume n=1–5; >5000 configurations) using dual stand–logger unmanned aerial vehicle (UAV) pack flights as the labeled corpus, with root-mean-square error (RMSE) scored on a locked acceptance trajectory. RMSE change versus the matched unaugmented baseline is class-conditional: sequential and convolutional estimators improve by +18% to +32%, LightGBM and XGBoost average ≈−2.4% and −4.9%, and a physics-informed network degrades by ≈22%. Labeled volume accounts for ≈53% of logRMSE variance versus ≈2% for synthesizer identity. Operators that preserve the empirical training distribution (thermo-voltage coupling and point shuffle) outrank mean-shift and TimeGAN. Dose L is a process parameter: thermo-voltage is optimal at L=8 for all eleven classical estimators, and selecting L on the acceptance set inflates reported gain by a factor of ≈2.5 relative to averaging over L. Admissible operators therefore depend on estimator class and on labeled volume n.

Förderung

  • Ministry of Science and Higher Education of the Russian Federation

Zitieren

APA

Druzhinin, A. A., & Lisnovetski, D. (2026). Data Augmentation for Lithium-Ion Battery State-of-Charge Estimation Across Methods and Models. Energies, 19(21), 5310. https://doi.org/10.3390/en19215310

Vancouver

Druzhinin AA, Lisnovetski D. Data Augmentation for Lithium-Ion Battery State-of-Charge Estimation Across Methods and Models. Energies. 2026;19(21):5310. doi:10.3390/en19215310

BibTeX
@article{Druzhinin2026,
  author = {Druzhinin, Alexey A. and Lisnovetski, Daniel},
  title = {Data Augmentation for Lithium-Ion Battery State-of-Charge Estimation Across Methods and Models},
  journal = {Energies},
  year = {2026},
  volume = {19},
  number = {21},
  pages = {5310},
  doi = {10.3390/en19215310}
}
Kostenlos starten →