Conformer-PhyFaultNet: Physics-Informed Spectral Attention Conformer for Generalizable Bearing Fault Diagnosis
IEEE Internet of Things Journal · 15.04.2026 · 13 (8) · 17538-17552
DOI: 10.1109/jiot.2026.3662413 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Internet of Things Journal, erschienen am 15.04.2026. Verfasst von Rizwan Ullah und 6 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 34 Literaturangaben. Gefördert von: Princess Nourah bint Abdulrahman University Researchers.
Abstract (Originalsprache)
Intelligent fault diagnosis of rotating machinery is essential for predictive maintenance, yet conventional deep learning models suffer from limited generalization under noisy and cross-domain conditions. Furthermore, their lack of interpretability restricts industrial trust and deployment. To address these challenges, we propose Conformer-PhyFaultNet, a novel physics-informed spectral attention conformer that seamlessly integrates domain knowledge with advanced sequence modeling. The method embeds characteristic fault frequencies [ball pass frequency outer race (BPFO), ball pass frequency inner race (BPFI), and fundamental train frequency (FTF)] directly into the spectral attention layer, guiding the network toward physically meaningful patterns rather than spurious features. A set of physics-guided tokens is introduced into the conformer encoder, which persist across layers and acts as stable descriptors of defect signatures. The hybrid spectral attention + physics tokens mechanism enables the model to simultaneously capture local fault harmonics and long-range dependencies across time–frequency representations. Unlike conventional CNN or transformers, proposed approach ensures interpretability by aligning attention distributions with analytic harmonics and providing layer-wise token activations as diagnostic evidence. This dual mechanism represents the key novelty, bridging analytic fault modeling with modern deep architectures for the first time in a unified framework. Extensive experiments on case western reserve university (CWRU), Paderborn, and huazhong university of science and technology (HUST) datasets demonstrate the superiority of the proposed method: in-domain accuracy reaches 93.75, cross-domain transfer achieves 86.75 (CWRU → Paderborn), and 84.3% (HUST → CWRU), while noise robustness remains above 87% at 10 dB and 81% at 0 dB, outperforming CNN, RNN, transformer, and physics-informed baselines by significant margins. The proposed Conformer-PhyFaultNet therefore offers a technically rigorous, interpretable, and noise-robust solution that can substantially enhance the reliability and adoption of intelligent predictive maintenance in industrial environments, while also enabling real-time monitoring and edge deployment in industrial IoT systems through low-latency inference (
Förderung
- Princess Nourah bint Abdulrahman University Researchers
Zitieren
APA
Ullah, R., Bilal, H., Aslam, M. S., Ayouni, S., Majid, A., Vasilakos, A. V., & Gadekallu, T. R. (2026). Conformer-PhyFaultNet: Physics-Informed Spectral Attention Conformer for Generalizable Bearing Fault Diagnosis. IEEE Internet of Things Journal, 13(8), 17538-17552. https://doi.org/10.1109/jiot.2026.3662413
Vancouver
Ullah R, Bilal H, Aslam MS, Ayouni S, Majid A, Vasilakos AV, et al. Conformer-PhyFaultNet: Physics-Informed Spectral Attention Conformer for Generalizable Bearing Fault Diagnosis. IEEE Internet of Things Journal. 2026;13(8):17538-17552. doi:10.1109/jiot.2026.3662413
BibTeX
@article{Ullah2026,
author = {Ullah, Rizwan and Bilal, Hazrat and Aslam, M. S. and Ayouni, Sarra and Majid, Abdul and Vasilakos, Athanasios V. and Gadekallu, Thippa Reddy},
title = {Conformer-PhyFaultNet: Physics-Informed Spectral Attention Conformer for Generalizable Bearing Fault Diagnosis},
journal = {IEEE Internet of Things Journal},
year = {2026},
volume = {13},
number = {8},
pages = {17538--17552},
doi = {10.1109/jiot.2026.3662413}
}
EUVIMED