EUVIMEDEUVIMED entdecken
Crossref

Computation-Light AI Models for Robust Battery Capacity Estimation Based on Electrochemical Impedance Spectroscopy

Zhansheng Ning, Prasanth Venugopal, Thiago Batista Soeiro, Gert Rietveld

IEEE Transactions on Transportation Electrification · 2025-02 · 11 (1) · 3146-3158

DOI: 10.1109/tte.2024.3435455 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Transportation Electrification, 2025-02. Verfasst von Zhansheng Ning und 3 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: project SEANERGETIC of the Research Program Zero Emission and Circular Shipping (KIC) which is financed by the Dutch Research Council.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Electrochemical impedance spectroscopy (EIS) holds great promise for assessing battery degradation. Nevertheless, many present methods for extracting battery aging features from EIS data are unsuitable for cells that have very different aging behaviors. Another challenge is that the time complexity of machine learning (ML) models based on full-frequency EIS significantly increases. To tackle these issues, this article investigates two feature extraction methods together with suitable regression algorithms. First, manual feature extraction methods are studied that involve feature extraction via feature correlation and consistency analysis, enhancing the robustness of battery capacity estimation within Gaussian process regression (GPR) and support vector machine (SVM) algorithms. On the other hand, automatic feature extraction methods extract latent features using convolutional neural networks (CNNs) as inputs to the model. Best results are achieved with the CNN-based methods that achieve robust capacity estimation with 2.88% accuracy for different battery cells at varying temperatures while remaining insensitive to EIS measurement uncertainty. This is a factor of 2-3 more accurate than the existing published approaches on the same dataset. By combining the advantages of manual and automatic feature extraction approaches, a reduced EIS dataset is used to train a lightweight CNN model, resulting in an inference time of less than 21.48 ms on STM32L476RG, whereas the existing approaches take up to 50 ms for achieving a similar accuracy.

Förderung

  • project SEANERGETIC of the Research Program Zero Emission and Circular Shipping (KIC) which is financed by the Dutch Research Council

Zitieren

APA

Ning, Z., Venugopal, P., Soeiro, T. B., & Rietveld, G. (2025). Computation-Light AI Models for Robust Battery Capacity Estimation Based on Electrochemical Impedance Spectroscopy. IEEE Transactions on Transportation Electrification, 11(1), 3146-3158. https://doi.org/10.1109/tte.2024.3435455

Vancouver

Ning Z, Venugopal P, Soeiro TB, Rietveld G. Computation-Light AI Models for Robust Battery Capacity Estimation Based on Electrochemical Impedance Spectroscopy. IEEE Transactions on Transportation Electrification. 2025;11(1):3146-3158. doi:10.1109/tte.2024.3435455

BibTeX
@article{Ning2025,
  author = {Ning, Zhansheng and Venugopal, Prasanth and Soeiro, Thiago Batista and Rietveld, Gert},
  title = {Computation-Light AI Models for Robust Battery Capacity Estimation Based on Electrochemical Impedance Spectroscopy},
  journal = {IEEE Transactions on Transportation Electrification},
  year = {2025},
  volume = {11},
  number = {1},
  pages = {3146--3158},
  doi = {10.1109/tte.2024.3435455}
}
Kostenlos starten →