analiza aiqbench
This research introduces Spectral Aliasing Pretext (SAP), a self-supervised learning technique designed to overcome the scarcity of labeled data in industrial machinery fault diagnosis. By training Transformers on deliberately undersampled vibration signals, the method forces models to learn robust frequency-domain features without relying on destructive augmentations or extensive supervision. The approach demonstrates superior stability and classification performance compared to fully supervised fine-tuning when only limited labeled datasets are available for testing.
Spectral Aliasing Pretext: A novel task for Self-Supervised fault diagnosis in rotating machinery
arXiv:2608.05705v1 Announce Type: new Abstract: Deep learning is a new way for machinery fault diagnosis but requires extensive labeled data, a scarce resource in industrial settings. We propose Spectral Aliasing Pretext (SAP), a self-supervised learning method that pretrains models on unlabeled vibration data by exploiting spectral aliasing. We deliberately undersample signals to create folded spectrum, then train a Transformer to reconstruct the original unfolded spectrum. This pretext task forces the model to learn frequency-domain invariants characteristic of mechanical faults, without potentially destructive augmentations. Experiments on the CWRU dataset show that SAP learns stable and highly discriminative representations. In a linear probing setting, SAP quickly achieves very high classification performance with only a small fraction of labeled data and low variance. In contrast, full fine-tuning, including fully supervised training, does not lead to more stable or better results. Overall, these findings suggest that SAP combined with linear probing can be more effective and reliable than fully supervised training for fault diagnosis with limited labeled data.
Abstract:Deep learning is a new way for machinery fault diagnosis but requires extensive labeled data, a scarce resource in industrial settings. We propose Spectral Aliasing Pretext (SAP), a self-supervised learning method that pretrains models on unlabeled vibration data by exploiting spectral aliasing. We deliberately undersample signals to create folded spectrum, then train a Transformer to reconstruct the original unfolded spectrum. This pretext task forces the model to learn frequency-domain invariants characteristic of mechanical faults, without potentially destructive augmentations. Experiments on the CWRU dataset show that SAP learns stable and highly discriminative representations. In a linear probing setting, SAP quickly achieves very high classification performance with only a small fraction of labeled data and low variance. In contrast, full fine-tuning, including fully supervised training, does not lead to more stable or better results. Overall, these findings suggest that SAP combined with linear probing can be more effective and reliable than fully supervised training for fault diagnosis with limited labeled data.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2608.05705 [cs.LG]
(or arXiv:2608.05705v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2608.05705 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 256 cuvinte
Subiecte conexe
Neonatal Hypoxic-ischaemic Encephalopathy Classification from the EEG and HRV Signals Using a Conformer based Masked Autoencoder
arXiv · 28 iul. 2026
Combining General and Domain-Specific Pretext Tasks for Brain MR Image Segmentation
arXiv · 28 sept. 2026
Catching the Imposter: Self-Supervised Learning of Physical Coherence with Cross-Entity Feature Permutations
arXiv · 17 aug. 2026
Which Tasks Survive Self-Supervised Learning?
arXiv · 1 oct. 2026