EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Physics-informed self-supervised diagnosis of rotating machinery using latent ODEs and transformer encoders

Md Al Amin iD, Mohammad Shafat Ahsan iD, Jannatul Maua, Mumtahina Ahmed iD, Kamruddin Nur iD

PLOS One · 2026

DOI: 10.1371/journal.pone.0339239 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2026. Verfasst von Md Al Amin und 4 weiteren Autor:innen. Beteiligte Einrichtung: MS in Information Technology, St. Francis College, Brooklyn, New York, United States of America. Hauptthemen laut MEDLINE: Physics. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper proposes a novel Physics-Informed Self-Supervised Diagnosis (PI-SSD) framework for rotating machinery fault detection, combining physical modeling, self-supervised representation learning, and uncertainty-aware classification. The architecture integrates a multi-resolution convolutional encoder, a windowed Transformer for temporal context modeling, and a latent neural ordinary differential equation (ODE) module that embeds mechanical priors, such as Jeffcott rotor dynamics, directly into the learning process. A masked segment reconstruction objective enables self-supervised pretraining using unlabeled healthy signals, while an evidential classifier head produces fault probabilities with calibrated uncertainty. We evaluate PI-SSD on two publicly available datasets, the NASA PHM’09 Gearbox dataset and the Aalto Rotor dataset, covering 6 fault types and over 5,500 multichannel vibration recordings. Compared to seven strong baselines, PI-SSD achieves the highest Macro-F1 score (0.91) and lowest Expected Calibration Error (ECE = 0.022) on the NASA dataset, while maintaining strong domain transfer performance on Aalto (Macro-F1 = 0.81, PR-MSE = 0.067) without fine-tuning. Ablation studies confirm the contribution of each component, and physics consistency analysis demonstrates low violation rates under varying speeds. These results highlight the potential of embedding physics knowledge into self-supervised neural systems for robust, interpretable, and transferable fault diagnosis in industrial applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

PhysicsSupervised Machine LearningRepresentation Machine LearningAlgorithmsRotation

Autor:innen und Institutionen

  • MS in Information Technology, St. Francis College, Brooklyn, New York, United States of America.
  • MSc in IT Project Management, School of Professional Studies, Clark University, Worcester, Massachusetts, United States of America.
  • Department of Computer Science and Engineering, Bangladesh University of Business and Technology, Dhaka, Bangladesh.
  • Department of Computer Science, American International University-Bangladesh, Dhaka, Bangladesh.

ORCID-Profile: Md Al Amin, Mohammad Shafat Ahsan, Mumtahina Ahmed, Kamruddin Nur

Zitieren

APA

Amin, M. A., Ahsan, M. S., Maua, J., Ahmed, M., & Nur, K. (2026). Physics-informed self-supervised diagnosis of rotating machinery using latent ODEs and transformer encoders. PLOS One. https://doi.org/10.1371/journal.pone.0339239

Vancouver

Amin MA, Ahsan MS, Maua J, Ahmed M, Nur K. Physics-informed self-supervised diagnosis of rotating machinery using latent ODEs and transformer encoders. PLOS One. 2026. doi:10.1371/journal.pone.0339239

BibTeX
@article{Amin2026,
  author = {Amin, Md Al and Ahsan, Mohammad Shafat and Maua, Jannatul and Ahmed, Mumtahina and Nur, Kamruddin},
  title = {Physics-informed self-supervised diagnosis of rotating machinery using latent ODEs and transformer encoders},
  journal = {PLOS One},
  year = {2026},
  doi = {10.1371/journal.pone.0339239}
}
Kostenlos starten →