![Student Publications [Scholarly]](../../assets/md5images/3a606fc6d4271534a4192eb383c1615a.jpg)
Student Publications [Scholarly]
Document Type
Article
Abstract
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. © 2026 Amin et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Publication Title
PLOS ONE
Publication Date
2-2026
Volume
21
Issue
2 February
ISSN
1932-6203
DOI
10.1371/journal.pone.0339239
Keywords
algorithms, humans, neural networks, computers, rotation, fault detection
Repository Citation
Amin, Md Al; Ahsan, Mohammad Shafat; Maua, Jannatul; Ahmed, Mumtahina; and Nur, Kamruddin, "Physics-informed self-supervised diagnosis of rotating machinery using latent ODEs and transformer encoders" (2026). Student Publications [Scholarly]. 83.
https://commons.clarku.edu/student_publications/83
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright Conditions
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, 21(2), e0339239.
