EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Phase-Aware Complex-Spectrogram Autoencoder for Vibration Preprocessing: Fault-Component Separation via Input-Phasor Orthogonality Regularization

Seung-yeol Yoo, Ye-na Lee, Jae-chul Lee, Se-yun Hwang, Jae-yun Lee, Soon-sup Lee

Machines · 13.10.2025 · 13 (10) · 945

DOI: 10.3390/machines13100945 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machines, online erschienen am 13.10.2025. Verfasst von Seung-yeol Yoo und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We propose a phase-aware complex-spectrogram autoencoder (AE) for preprocessing raw vibration signals of rotating electrical machines. The AE reconstructs normal components and separates fault components as residuals, guided by an input-phasor phase-orthogonality regularization that defines parallel/orthogonal residuals with respect to the local signal phase. We use a U-Net-based AE with a mask-bias head to refine local magnitude and phase. Decisions are based on residual features—magnitude/shape, frequency distribution, and projections onto the normal manifold. Using the AI Hub open dataset from field ventilation motors, we evaluate eight representative motor cases (2.2–5.5 kW: misalignment, unbalance, bearing fault, belt looseness). The preprocessing yielded clear residual patterns (low-frequency floor rise, resonance-band peaks, harmonic-neighbor spikes), and achieved an area under the receiver operating characteristic curve (ROC-AUC) = 0.998–1.000 across eight cases, with strong leave-one-file-out generalization and good calibration (expected calibration error (ECE) ≤ 0.023). The results indicate that learning to remove normal structure while enforcing phase consistency provides an unsupervised front-end that enhances fault evidence while preserving interpretability on field data.

Zitieren

APA

Yoo, S., Lee, Y., Lee, J., Hwang, S., Lee, J., & Lee, S. (2025). Phase-Aware Complex-Spectrogram Autoencoder for Vibration Preprocessing: Fault-Component Separation via Input-Phasor Orthogonality Regularization. Machines, 13(10), 945. https://doi.org/10.3390/machines13100945

Vancouver

Yoo S, Lee Y, Lee J, Hwang S, Lee J, Lee S. Phase-Aware Complex-Spectrogram Autoencoder for Vibration Preprocessing: Fault-Component Separation via Input-Phasor Orthogonality Regularization. Machines. 2025;13(10):945. doi:10.3390/machines13100945

BibTeX
@article{Yoo2025,
  author = {Yoo, Seung-yeol and Lee, Ye-na and Lee, Jae-chul and Hwang, Se-yun and Lee, Jae-yun and Lee, Soon-sup},
  title = {Phase-Aware Complex-Spectrogram Autoencoder for Vibration Preprocessing: Fault-Component Separation via Input-Phasor Orthogonality Regularization},
  journal = {Machines},
  year = {2025},
  volume = {13},
  number = {10},
  pages = {945},
  doi = {10.3390/machines13100945}
}
Kostenlos starten →