MFETA-Net: Multi-Branch Frequency Enhancement and Temporal Attention for Small-Sample Rolling Bearing Fault Diagnosis
Machines · 20.08.2026 · 14 (8) · 952
DOI: 10.3390/machines14080952 ↗Kurz gefasst
Fachartikel in der Zeitschrift Machines, online erschienen am 20.08.2026. Verfasst von Chiming Wang und 7 weiteren Autor:innen. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Development and Application of Multi-Source Data Ship Intelligent Auxiliary Terminal Based on Large Model Technology.
Abstract (Originalsprache)
In practical industrial applications, rolling bearing fault samples are often scarce and costly to annotate, making small-sample fault diagnosis challenging. To address this issue, this paper proposes a frequency-aware time–frequency representation learning framework, named Multi-branch Frequency Enhancement Temporal Attention Network (MFETA-Net). In the proposed framework, dual-channel vibration signals are first transformed into time–frequency representations using the Short-Time Fourier Transform (STFT). Then, a multi-branch frequency enhancement encoder is used to extract local frequency-band patterns, cross-band correlations, and frequency variation features. A temporal-frequency dependency modeling mechanism preserves the correspondence between temporal positions and frequency distributions during sequential modeling, while a temporal attention aggregation module emphasizes diagnostically important regions. Extensive experiments on the CWRU and HUST bearing datasets show that MFETA-Net achieves accuracies of 77.26% and 79.60% under the smallest training setting, respectively, indicating its capability to learn discriminative fault representations from limited labeled samples. Ablation studies further verify the effectiveness of each proposed module, while noise experiments confirm the robustness of the proposed framework under controlled noisy conditions.
Förderung
- Development and Application of Multi-Source Data Ship Intelligent Auxiliary Terminal Based on Large Model Technology
Zitieren
APA
Wang, C., Zhou, Y., Zheng, D., Huang, C., Zhu, S., Li, Z., Wu, B., & Guan, L. (2026). MFETA-Net: Multi-Branch Frequency Enhancement and Temporal Attention for Small-Sample Rolling Bearing Fault Diagnosis. Machines, 14(8), 952. https://doi.org/10.3390/machines14080952
Vancouver
Wang C, Zhou Y, Zheng D, Huang C, Zhu S, Li Z, et al. MFETA-Net: Multi-Branch Frequency Enhancement and Temporal Attention for Small-Sample Rolling Bearing Fault Diagnosis. Machines. 2026;14(8):952. doi:10.3390/machines14080952
BibTeX
@article{Wang2026,
author = {Wang, Chiming and Zhou, Yiying and Zheng, Dongke and Huang, Chengming and Zhu, Shunzhi and Li, Zhenjun and Wu, Bingkun and Guan, Liangqing},
title = {MFETA-Net: Multi-Branch Frequency Enhancement and Temporal Attention for Small-Sample Rolling Bearing Fault Diagnosis},
journal = {Machines},
year = {2026},
volume = {14},
number = {8},
pages = {952},
doi = {10.3390/machines14080952}
}
EUVIMED