Noise-robust multi-source domain adaptation for bearing fault diagnosis via hardness-aware noise injection and consistency learning
Journal of Vibration and Control · 08.05.2026
DOI: 10.1177/10775463261448167 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Vibration and Control, online erschienen am 08.05.2026. Verfasst von Shuo Mu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 23 Literaturangaben. Gefördert von: the Fundamental Research Funds of Beijing University of Civil Engineering and Architecture, the Beijing Natural Science Foundation, China Postdoctoral Science Foundation.
Abstract (Originalsprache)
To address the coupled effects of strong noise and operating-condition variations on cross-domain bearing fault diagnosis, this paper proposes a multi-source unsupervised domain adaptation framework with hardness-aware noise injection. Firstly, a dual-path training mechanism with shared parameters is constructed. The original path transforms raw time-domain vibration signals by FFT for classification and domain alignment, whereas the noisy path injects Gaussian white noise in the time domain according to sample hardness and uses the resulting spectra to learn noise-robust representations. Sample hardness, which reflects the learning difficulty of a sample, is estimated from predictive uncertainty or prediction inconsistency among multiple subnetworks. Secondly, a network architecture composed of a shared feature extractor and multiple source-domain-specific subnetworks is designed. Normalization, efficient attention aggregation, and deformable convolutions are combined to enhance feature stability and extract hierarchical features, while multi-level maximum mean discrepancy (MMD) alignment is imposed on original-path features to reduce domain discrepancy. Hierarchical feature consistency and prediction consistency constraints are introduced to jointly optimize the two paths at both the representation and output levels. Finally, experiments on the PU, HUST, and CWRU datasets under signal-to-noise ratios (SNRs) from −6 dB to 4 dB (extended to −8 dB on CWRU) demonstrate more robust target-domain performance, especially under low-SNR conditions. Ablation and visualization results further verify the effectiveness of hardness-aware noise allocation, consistency learning, and multi-level alignment.
Förderung
- the Fundamental Research Funds of Beijing University of Civil Engineering and Architecture
- the Beijing Natural Science Foundation
- China Postdoctoral Science Foundation
- National Natural Science Foundation of China
Zitieren
APA
Mu, S., Yao, D., Wang, N., Yang, J., Dai, F., & Zhou, T. (2026). Noise-robust multi-source domain adaptation for bearing fault diagnosis via hardness-aware noise injection and consistency learning. Journal of Vibration and Control. https://doi.org/10.1177/10775463261448167
Vancouver
Mu S, Yao D, Wang N, Yang J, Dai F, Zhou T. Noise-robust multi-source domain adaptation for bearing fault diagnosis via hardness-aware noise injection and consistency learning. Journal of Vibration and Control. 2026. doi:10.1177/10775463261448167
BibTeX
@article{Mu2026,
author = {Mu, Shuo and Yao, Dechen and Wang, Ning and Yang, Jianwei and Dai, Fangyi and Zhou, Tao},
title = {Noise-robust multi-source domain adaptation for bearing fault diagnosis via hardness-aware noise injection and consistency learning},
journal = {Journal of Vibration and Control},
year = {2026},
doi = {10.1177/10775463261448167}
}
EUVIMED