Leakage-Resistant Multi-Sensor Bearing Fault Diagnosis via Adaptive Time-Frequency Graph Learning and Sensor Reliability-Aware Fusion
Sensors · 17.04.2026 · 26 (8) · 2484
DOI: 10.3390/s26082484 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 17.04.2026. Verfasst von Yu Sun und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Technology, Changchun University, Changchun 130022, China. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the general project of National Natural Science Foundation, the general project of humanities and social sciences research of the ministry of education of the PRC, The key project of the Joint Fund for Free Exploration under Jilin Provincial Natural Science Foundation.
Abstract (Originalsprache)
Reliable multi-sensor bearing fault diagnosis is challenged by temporal leakage caused by window-level random splitting, limited modeling of cross-sensor dependencies, and inadequate integration of raw temporal dynamics with time-frequency representations. To address these issues, this study proposes a leakage-resistant multi-sensor diagnosis framework that combines a partition-before-windowing evaluation protocol with adaptive time-frequency graph learning and reliability-aware fusion. Continuous vibration records are first divided into disjoint temporal regions with guard intervals and overlap auditing to suppress time-neighbor leakage. The model then extracts complementary features from a raw-signal branch and a dual-resolution log-STFT branch, while adaptive graph learning captures sample-dependent inter-sensor couplings and sensor reliability weighting highlights informative channels. A cross-gated fusion module further integrates temporal and graph-domain representations in a sample-adaptive manner for final classification. Experiments on a reconstructed nine-class benchmark derived from the HUSTbearing dataset show that the proposed method achieves a Macro-Accuracy of 0.973, a Macro-Recall of 0.964, and a Macro-F1 of 0.954, outperforming representative raw-signal and STFT-based baselines under the same leakage-resistant protocol. These results demonstrate that jointly modeling multi-scale time-frequency structure, dynamic sensor relationships, and reliable evaluation yields an effective and interpretable solution for intelligent bearing fault diagnosis under complex operating conditions.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Computer Science and Technology, Changchun University, Changchun 130022, China.
ORCID-Profile: Yihang Qin, Wenhao Chen
Förderung
- the general project of National Natural Science Foundation
- the general project of humanities and social sciences research of the ministry of education of the PRC
- The key project of the Joint Fund for Free Exploration under Jilin Provincial Natural Science Foundation
Zitieren
APA
Sun, Y., Qin, Y., Chen, W., Zhao, W., & Sun, H. (2026). Leakage-Resistant Multi-Sensor Bearing Fault Diagnosis via Adaptive Time-Frequency Graph Learning and Sensor Reliability-Aware Fusion. Sensors, 26(8), 2484. https://doi.org/10.3390/s26082484
Vancouver
Sun Y, Qin Y, Chen W, Zhao W, Sun H. Leakage-Resistant Multi-Sensor Bearing Fault Diagnosis via Adaptive Time-Frequency Graph Learning and Sensor Reliability-Aware Fusion. Sensors. 2026;26(8):2484. doi:10.3390/s26082484
BibTeX
@article{Sun2026,
author = {Sun, Yu and Qin, Yihang and Chen, Wenhao and Zhao, Wenhui and Sun, Haoran},
title = {Leakage-Resistant Multi-Sensor Bearing Fault Diagnosis via Adaptive Time-Frequency Graph Learning and Sensor Reliability-Aware Fusion},
journal = {Sensors},
year = {2026},
volume = {26},
number = {8},
pages = {2484},
doi = {10.3390/s26082484}
}
EUVIMED