EUVIMEDEUVIMED entdecken
Crossref

Current Density Distribution Estimation of REBCO Coated Conductors Using Machine Learning

Junichiro Takei, Takanobu Mato, Atsushi Ishiyama, So Noguchi

IEEE Transactions on Applied Superconductivity · 2026-08 · 36 (5) · 1-5

DOI: 10.1109/tasc.2026.3670249 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Applied Superconductivity, 2026-08. Verfasst von Junichiro Takei und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 15 Literaturangaben. Gefördert von: JSPS KAKENHI.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

High-temperature superconducting (HTS) rare-earth barium copper oxide (REBCO) coated conductors (CCs) are promising for high-field applications; however, their critical current often exhibits non-uniformity along the tape length due to fabrication-induced defects such as edge cracks or low critical current region. To ensure the reliability of REBCO magnets, non-destructive and high-resolution evaluation of the local critical current distribution is essential. The Hall array measurement (HAM) method enables two-dimensional mapping of the critical current density distribution through the inverse analysis using the measured field distribution. The performance of the conventional methods is limited with the number of sample points in HAM. In this study, a convolutional neural network (CNN)-based inverse analysis method is proposed to reconstruct the current density distribution from the measured field. The CNN-based estimator is trained with 5,000 pairs of field and current density distributions artificially generated considering the current conservation law. Experimental validation demonstrated that the CNN-based method can estimate a more realistic current density distribution than the conventional FFT-based approach, even with a limited number of measurement points. Although the CNN results showed slight noise effects, they remained consistent with the expected Bean's model behavior. The proposed approach offers a promising framework for fast and accurate non-destructive evaluation of REBCO tapes, contributing to improved reliability of HTS magnet systems.

Förderung

  • JSPS KAKENHI

Zitieren

APA

Takei, J., Mato, T., Ishiyama, A., & Noguchi, S. (2026). Current Density Distribution Estimation of REBCO Coated Conductors Using Machine Learning. IEEE Transactions on Applied Superconductivity, 36(5), 1-5. https://doi.org/10.1109/tasc.2026.3670249

Vancouver

Takei J, Mato T, Ishiyama A, Noguchi S. Current Density Distribution Estimation of REBCO Coated Conductors Using Machine Learning. IEEE Transactions on Applied Superconductivity. 2026;36(5):1-5. doi:10.1109/tasc.2026.3670249

BibTeX
@article{Takei2026,
  author = {Takei, Junichiro and Mato, Takanobu and Ishiyama, Atsushi and Noguchi, So},
  title = {Current Density Distribution Estimation of REBCO Coated Conductors Using Machine Learning},
  journal = {IEEE Transactions on Applied Superconductivity},
  year = {2026},
  volume = {36},
  number = {5},
  pages = {1--5},
  doi = {10.1109/tasc.2026.3670249}
}
Kostenlos starten →