Prior-guided dual stream time–frequency meta learning network for few-shot cross-domain fault diagnosis
Measurement Science and Technology · 13.11.2026 · 37 (45) · 456202
DOI: 10.1088/1361-6501/aebab2 ↗Kurz gefasst
Fachartikel in der Zeitschrift Measurement Science and Technology, online erschienen am 12.11.2026. Verfasst von Zishan Xie und 3 weiteren Autor:innen. Die Arbeit nennt 54 Literaturangaben. Gefördert von: Natural Science Fund of Fujian Province.
Abstract (Originalsprache)
Drastic fluctuations in fault feature distributions under large-span variable speeds, compounded by target domain label scarcity, severely degrade the generalization performance of diagnostic models. To address these challenges, a prior-guided time–frequency dual-stream meta-learning network (PR-TFML) is proposed in this paper. By leveraging the deeply decoupled synergy between mechanistic knowledge and data-driven learning, PR-TFML constructs a multimodal feature extraction architecture composed of complementary time-domain and time–frequency branches. The time-domain branch employs large-receptive-field convolutions to capture nonstationary transient impact characteristics, while the time–frequency branch extracts high-dimensional evolutionary features through an embedded short-time Fourier transform layer. Building upon this, a physical prior mapping branch is introduced to construct a compact hybrid prior by combining macroscopic operating conditions (e.g. rotational speed) with intrinsic statistical and energy-based descriptors (e.g. kurtosis, envelope energy, and wavelet energy). This prior is transformed into domain-invariant semantic anchors, enabling adaptive calibration against distribution shifts. Furthermore, guided by physical priors, an explicit alignment-enhanced meta-optimization strategy couples Model-Agnostic Meta-Learning with Correlation Alignment constraints to facilitate rapid cross-domain adaptation and feature distribution alignment under extreme few-shot conditions. Extensive experiments conducted on the Huazhong University of Science and Technology bearing and Beijing Jiaotong University Wind Turbine-Planetary gearbox datasets demonstrate that PR-TFML maintains a high degree of feature consistency and diagnostic robustness under extreme few-shot and large-span variable operating conditions. This method effectively mitigates the feature degradation inherent in purely data-driven models under domain shifts, providing a reliable physics-guided paradigm with strong generalization capability for the cross-domain predictive maintenance of complex rotating machinery.
Förderung
- Natural Science Fund of Fujian Province
Zitieren
APA
Xie, Z., Cheng, J., Yang, C., & Zou, T. (2026). Prior-guided dual stream time–frequency meta learning network for few-shot cross-domain fault diagnosis. Measurement Science and Technology, 37(45), 456202. https://doi.org/10.1088/1361-6501/aebab2
Vancouver
Xie Z, Cheng J, Yang C, Zou T. Prior-guided dual stream time–frequency meta learning network for few-shot cross-domain fault diagnosis. Measurement Science and Technology. 2026;37(45):456202. doi:10.1088/1361-6501/aebab2
BibTeX
@article{Xie2026,
author = {Xie, Zishan and Cheng, Jun and Yang, Changcai and Zou, Tengyue},
title = {Prior-guided dual stream time–frequency meta learning network for few-shot cross-domain fault diagnosis},
journal = {Measurement Science and Technology},
year = {2026},
volume = {37},
number = {45},
pages = {456202},
doi = {10.1088/1361-6501/aebab2}
}
EUVIMED