Time-Frequency Multi-Domain 1D Convolutional Neural Network with Channel-Spatial Attention for Noise-Robust Bearing Fault Diagnosis
Sensors · 21.11.2023 · 23 (23) · 9311
DOI: 10.3390/s23239311 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 21.11.2023. Verfasst von Yejin Kim und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mechanical and Control Engineering, Handong Global University, Pohang 37554, Republic of Korea. Die Arbeit wurde bisher 37-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Korea Institute of Energy Technology Evaluation and Planning.
Abstract (Originalsprache)
This paper proposes a noise-robust and accurate bearing fault diagnosis model based on time-frequency multi-domain 1D convolutional neural networks (CNNs) with attention modules. The proposed model, referred to as the TF-MDA model, is designed for an accurate bearing fault classification model based on vibration sensor signals that can be implemented at industry sites under a high-noise environment. Previous 1D CNN-based bearing diagnosis models are mostly based on either time domain vibration signals or frequency domain spectral signals. In contrast, our model has parallel 1D CNN modules that simultaneously extract features from both the time and frequency domains. These multi-domain features are then fused to capture comprehensive information on bearing fault signals. Additionally, physics-informed preprocessings are incorporated into the frequency-spectral signals to further improve the classification accuracy. Furthermore, a channel and spatial attention module is added to effectively enhance the noise-robustness by focusing more on the fault characteristic features. Experiments were conducted using public bearing datasets, and the results indicated that the proposed model outperformed similar diagnosis models on a range of noise levels ranging from −6 to 6 dB signal-to-noise ratio (SNR).
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Mechanical and Control Engineering, Handong Global University, Pohang 37554, Republic of Korea.
- School of Mechanical and Control Engineering, Handong Global University, Pohang 37554, Republic of Korea.
ORCID-Profile: Yejin Kim, Young-Keun Kim
Förderung
- Korea Institute of Energy Technology Evaluation and Planning
Zitieren
APA
Kim, Y., & Kim, Y. K. (2023). Time-Frequency Multi-Domain 1D Convolutional Neural Network with Channel-Spatial Attention for Noise-Robust Bearing Fault Diagnosis. Sensors, 23(23), 9311. https://doi.org/10.3390/s23239311
Vancouver
Kim Y, Kim YK. Time-Frequency Multi-Domain 1D Convolutional Neural Network with Channel-Spatial Attention for Noise-Robust Bearing Fault Diagnosis. Sensors. 2023;23(23):9311. doi:10.3390/s23239311
BibTeX
@article{Kim2023,
author = {Kim, Yejin and Kim, Young-Keun},
title = {Time-Frequency Multi-Domain 1D Convolutional Neural Network with Channel-Spatial Attention for Noise-Robust Bearing Fault Diagnosis},
journal = {Sensors},
year = {2023},
volume = {23},
number = {23},
pages = {9311},
doi = {10.3390/s23239311}
}
EUVIMED