Multirepresentation Signal Preprocessing for Bearing Fault Diagnosis Under Noise Using CNN–ResNeXt‐50
Shock and Vibration · 2026-01 · 2026 (1)
DOI: 10.1155/vib/1989522 ↗Kurz gefasst
Fachartikel in der Zeitschrift Shock and Vibration, online erschienen am 30.06.2026. Verfasst von Dongying Han und 4 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Hebei Province.
Abstract (Originalsprache)
Bearings are critical components in wind turbines, and their failure detection is vital for maintaining the reliability of these systems. However, traditional fault diagnosis methods often fail to perform adequately under noisy conditions, which are common in real‐world applications. This study introduces a robust multimodal diagnostic method based on convolutional neural network (CNN)–ResNeXt‐50 for rolling bearing fault diagnosis under noisy environments. The method combines the strengths of CNNs and ResNeXt‐50, utilizing two signal transformations—Fast Fourier Transform (FFT) and Synchrosqueezing Transform (SST)—to extract complementary features from vibration signals. The fused features are then used for fault classification, ensuring superior stability, and generalization ability. Experimental results on three publicly available datasets demonstrate that the proposed approach outperforms existing methods, achieving higher accuracy, faster convergence, and better robustness to varying noise levels, making it highly suitable for practical bearing fault diagnosis in noisy industrial environments.
Förderung
- Natural Science Foundation of Hebei Province
Zitieren
APA
Han, D., Cao, L., Zhang, Y., Ge, Z., & Shi, P. (2026). Multirepresentation Signal Preprocessing for Bearing Fault Diagnosis Under Noise Using CNN–ResNeXt‐50. Shock and Vibration, 2026(1). https://doi.org/10.1155/vib/1989522
Vancouver
Han D, Cao L, Zhang Y, Ge Z, Shi P. Multirepresentation Signal Preprocessing for Bearing Fault Diagnosis Under Noise Using CNN–ResNeXt‐50. Shock and Vibration. 2026;2026(1). doi:10.1155/vib/1989522
BibTeX
@article{Han2026,
author = {Han, Dongying and Cao, Lizhi and Zhang, Yu and Ge, Zixuan and Shi, Peiming},
title = {Multirepresentation Signal Preprocessing for Bearing Fault Diagnosis Under Noise Using CNN–ResNeXt‐50},
journal = {Shock and Vibration},
year = {2026},
volume = {2026},
number = {1},
doi = {10.1155/vib/1989522}
}
EUVIMED