Small Sample Fault Diagnosis Using Gap-Regularized Loss and Multiscale Attention CNN
IEEE Transactions on Reliability · 2026 · 75 · 1599-1610
DOI: 10.1109/tr.2026.3682327 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Reliability, 2026. Verfasst von Lihao Ye und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 36 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Jiangsu Province of China, Aeronautical Science Foundation of China.
Abstract (Originalsprache)
In aerospace engine systems, reliable fault diagnosis is essential for ensuring operational safety, yet the scarcity of labeled fault data remains a major obstacle. Although massive amounts of operational signals are routinely collected, expert annotation is costly and limited, leading to small-sample learning challenges, where only a limited number of labeled samples are available for model training. To address this issue, we propose a diagnostic framework tailored for such label-scarce scenarios. Specifically, a multiscale attentive convolutional neural network is constructed to enhance discriminative representation by integrating multiscale feature extraction with squeeze-and-excitation attention. More importantly, a Gap-regularized loss function is introduced to jointly enforce intraclass compactness and interclass separability, thereby improving generalization when only limited labeled data are available. Extensive experiments on two aerospace engine–related datasets demonstrate that the proposed method achieves superior diagnostic accuracy in limited-labeled-data settings, highlighting its potential for intelligent health monitoring in safety-critical aerospace applications.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Jiangsu Province of China
- Aeronautical Science Foundation of China
- Postgraduate Research and Practice Innovation Program of Jiangsu Province
Zitieren
APA
Ye, L., Zhang, K., Jiang, B., Simani, S., & Li, X. (2026). Small Sample Fault Diagnosis Using Gap-Regularized Loss and Multiscale Attention CNN. IEEE Transactions on Reliability, 75, 1599-1610. https://doi.org/10.1109/tr.2026.3682327
Vancouver
Ye L, Zhang K, Jiang B, Simani S, Li X. Small Sample Fault Diagnosis Using Gap-Regularized Loss and Multiscale Attention CNN. IEEE Transactions on Reliability. 2026;75:1599-1610. doi:10.1109/tr.2026.3682327
BibTeX
@article{Ye2026,
author = {Ye, Lihao and Zhang, Ke and Jiang, Bin and Simani, Silvio and Li, Xue},
title = {Small Sample Fault Diagnosis Using Gap-Regularized Loss and Multiscale Attention CNN},
journal = {IEEE Transactions on Reliability},
year = {2026},
volume = {75},
pages = {1599--1610},
doi = {10.1109/tr.2026.3682327}
}
EUVIMED