A multi-band enhanced dynamic learning method for robust fault diagnosis under signal and label noise
ISA Transactions · 2026-11 · 178 · 171-195
DOI: 10.1016/j.isatra.2026.09.018 ↗Kurz gefasst
Fachartikel in der Zeitschrift ISA Transactions, 2026-11. Verfasst von Xin Li und 5 weiteren Autor:innen. Beteiligte Einrichtung: Key Lab of Industrial Computer Control Engineering of Hebei Province, Yanshan University, Qinhuangdao 066004, Hebei Province, China. Electronic addre…. Die Arbeit nennt 34 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Hebei Provincial Natural Science Foundation.
Abstract (Originalsprache)
Accurate fault diagnosis of rotating machinery from vibration measurements faces challenges from real-world data imperfections, especially the concurrent presence of measurement noise and label noise. Measurement noise corrupts vibration signals and blurs fault patterns, whereas label noise compromises supervision reliability and induces biased optimization in deep diagnostic models. To address this compound noise challenge, this paper proposes a robust framework named MSD-DCSFNet. The framework applies a multi-band signal decomposition module combining variational mode decomposition and the fast Fourier transform to construct a structured multi-channel spectral representation. This step enhances the visibility of harmonics, sidebands, and impact-related bands under low signal-to-noise conditions. A deep collaborative synergy feature network featuring a dual-branch architecture subsequently learns complementary spectral-structural cues and impact-transient cues, producing highly discriminative features. A dynamic asymmetric cross-entropy loss is also introduced to improve training robustness. It adaptively adjusts sample weights according to prediction confidence, suppressing high-risk supervision from corrupted labels and unstable measurements. Extensive experiments on the CWRU dataset, the SEU dataset, and a self-built dataset demonstrate that the proposed framework maintains over 90% diagnostic accuracy even under a 0 dB signal-to-noise ratio combined with a 60% label noise rate. These results validate its practical value for diagnosis using imperfect industrial data.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Key Lab of Industrial Computer Control Engineering of Hebei Province, Yanshan University, Qinhuangdao 066004, Hebei Province, China. Electronic address: lxin@ysu.edu.cn.
- Key Lab of Industrial Computer Control Engineering of Hebei Province, Yanshan University, Qinhuangdao 066004, Hebei Province, China. Electronic address: yman@stumail.ysu.edu.cn.
- Key Lab of Industrial Computer Control Engineering of Hebei Province, Yanshan University, Qinhuangdao 066004, Hebei Province, China; Tianjin Research Institute of Electric Science Co., Ltd, Tianjin, China. Electronic ad…
- School of Information and Control Engineering, Qingdao University of Technology, Qingdao 266520, Shandong Province, China. Electronic address: fanrui@qut.edu.cn.
- Key Lab of Industrial Computer Control Engineering of Hebei Province, Yanshan University, Qinhuangdao 066004, Hebei Province, China; Engineering Research Center of the Ministry of Education for Intelligent Control Syste…
- Key Lab of Industrial Computer Control Engineering of Hebei Province, Yanshan University, Qinhuangdao 066004, Hebei Province, China. Electronic address: kma@ysu.edu.cn.
Förderung
- National Natural Science Foundation of China
- Hebei Provincial Natural Science Foundation
Zitieren
APA
Li, X., Yang, M., Lv, J., Fan, R., Wei, L., & Ma, K. (2026). A multi-band enhanced dynamic learning method for robust fault diagnosis under signal and label noise. ISA Transactions, 178, 171-195. https://doi.org/10.1016/j.isatra.2026.09.018
Vancouver
Li X, Yang M, Lv J, Fan R, Wei L, Ma K. A multi-band enhanced dynamic learning method for robust fault diagnosis under signal and label noise. ISA Transactions. 2026;178:171-195. doi:10.1016/j.isatra.2026.09.018
BibTeX
@article{Li2026,
author = {Li, Xin and Yang, Man and Lv, Jin and Fan, Rui and Wei, Lixin and Ma, Kai},
title = {A multi-band enhanced dynamic learning method for robust fault diagnosis under signal and label noise},
journal = {ISA Transactions},
year = {2026},
volume = {178},
pages = {171--195},
doi = {10.1016/j.isatra.2026.09.018}
}
EUVIMED