EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Padé Approximant Neural Networks as Feature Extractors for Unsupervised Domain Adaptation in Bearing Fault Diagnosis

Sertac Kilickaya, Cansu Celebioglu, Murat Askar, Turker Ince, Levent Eren

Machines · 05.07.2026 · 14 (7) · 755

DOI: 10.3390/machines14070755 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machines, online erschienen am 05.07.2026. Verfasst von Sertac Kilickaya und 4 weiteren Autor:innen. Die Arbeit nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The Scientific and Technological Research Council of Türkiye.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Variations in mechanical load constitute a dominant source of domain shift in data-driven fault diagnosis of rotating machinery, causing models trained under one operating condition to degrade sharply when deployed under another. This work addresses the problem through unsupervised domain adaptation (UDA)—which transfers diagnostic knowledge from a labeled source condition to an unlabeled target condition by aligning their feature distributions—and introduces Padé Approximant Neural Networks (PadéNets) as compact yet highly expressive feature extractors. One-dimensional PadéNet encoders are embedded into three established adaptation frameworks—Deep CORAL, Domain-Adversarial Neural Networks (DANNs), and Conditional Domain-Adversarial Networks (CDANs)—to learn load-invariant representations without any labeled target data. On the Case Western Reserve University benchmark, where the models operate directly on raw time-domain vibration signals, replacing conventional convolutional encoders with PadéNets consistently improves cross-load diagnostic accuracy, reaching up to 99.28% average target-domain accuracy at a low parameter count. To assess generalization to a more demanding setting, the CDAN–PadéNet configuration is further evaluated on frequency-domain representations of the Paderborn University dataset, where domain shift arises from simultaneous variation of load torque and radial force on bearings with real accelerated-lifetime damage, attaining 99.84% average accuracy across six cross-condition transfer tasks while requiring fewer parameters than competing methods. These results establish PadéNet-enhanced UDA as an accurate, broadly applicable approach for robust bearing fault diagnosis under varying operating conditions, with a reduced parameter count suited to resource-constrained embedded platforms.

Förderung

  • The Scientific and Technological Research Council of Türkiye

Zitieren

APA

Kilickaya, S., Celebioglu, C., Askar, M., Ince, T., & Eren, L. (2026). Padé Approximant Neural Networks as Feature Extractors for Unsupervised Domain Adaptation in Bearing Fault Diagnosis. Machines, 14(7), 755. https://doi.org/10.3390/machines14070755

Vancouver

Kilickaya S, Celebioglu C, Askar M, Ince T, Eren L. Padé Approximant Neural Networks as Feature Extractors for Unsupervised Domain Adaptation in Bearing Fault Diagnosis. Machines. 2026;14(7):755. doi:10.3390/machines14070755

BibTeX
@article{Kilickaya2026,
  author = {Kilickaya, Sertac and Celebioglu, Cansu and Askar, Murat and Ince, Turker and Eren, Levent},
  title = {Padé Approximant Neural Networks as Feature Extractors for Unsupervised Domain Adaptation in Bearing Fault Diagnosis},
  journal = {Machines},
  year = {2026},
  volume = {14},
  number = {7},
  pages = {755},
  doi = {10.3390/machines14070755}
}
Kostenlos starten →