EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Interpretable Multi-Band Spectral Learning for In-Cabin Magnetic-Field Prediction and Equivalent-Source Attribution

Zeju Liu, Jinbao Zhang, Deping Wang, Dan Zhang, Yingda Fu

Signals · 02.11.2026 · 7 (6) · 110

DOI: 10.3390/signals7060110 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Signals, online erschienen am 02.11.2026. Verfasst von Zeju Liu und 4 weiteren Autor:innen. Die Arbeit nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Jilin Province Science and Technology Development Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Magnetic fields generated by electromagnetic radiation sources in electric vehicle cabins may affect passenger exposure and the reliable operation of onboard electronics. Physical measurement campaigns are time-consuming and spatially limited, motivating rapid field-prediction methods. Based on measured frequency-domain data, this study proposes the Multi-band Equivalent-Source Attribution Network (MESA-Net) that uses the S01 (Static background) spectrum to anchor a spatial background branch and learns condition- and frequency-dependent effective source strengths for powered and dynamic operating states. This static-background-conditioned decomposition is introduced because each cabin probe records an aggregate amplitude-only signal rather than an isolated source spectrum. Five predefined cuboid equivalent-source regions are coupled with normalized distance kernels and an optional diagnostic residual through incoherent power-domain superposition. The dataset comprises 12 passenger measurement points, two near-source auxiliary points, five operating conditions, and four independently acquired bands spanning 1 Hz–400 kHz. Under leakage-free nested spatial holdout, the model achieved a mean absolute amplitude error of 3.528 dB. Learning band-dependent attenuation improved balanced multi-band performance relative to fixed attenuation. MESA-Net therefore links broadband signal prediction with model-constrained candidate-source attribution, rather than unique physical source-power recovery, and provides an engineering reference for rapid cabin-field assessment and diagnostic prioritization.

Förderung

  • Jilin Province Science and Technology Development Program

Zitieren

APA

Liu, Z., Zhang, J., Wang, D., Zhang, D., & Fu, Y. (2026). Interpretable Multi-Band Spectral Learning for In-Cabin Magnetic-Field Prediction and Equivalent-Source Attribution. Signals, 7(6), 110. https://doi.org/10.3390/signals7060110

Vancouver

Liu Z, Zhang J, Wang D, Zhang D, Fu Y. Interpretable Multi-Band Spectral Learning for In-Cabin Magnetic-Field Prediction and Equivalent-Source Attribution. Signals. 2026;7(6):110. doi:10.3390/signals7060110

BibTeX
@article{Liu2026,
  author = {Liu, Zeju and Zhang, Jinbao and Wang, Deping and Zhang, Dan and Fu, Yingda},
  title = {Interpretable Multi-Band Spectral Learning for In-Cabin Magnetic-Field Prediction and Equivalent-Source Attribution},
  journal = {Signals},
  year = {2026},
  volume = {7},
  number = {6},
  pages = {110},
  doi = {10.3390/signals7060110}
}
Kostenlos starten →