Remaining Useful Life Prediction of Rolling Bearings Based on Multi-Scale Attention Residual Network
Entropy · 14.05.2023 · 25 (5) · 798
DOI: 10.3390/e25050798 ↗Kurz gefasst
Fachartikel in der Zeitschrift Entropy, online erschienen am 14.05.2023. Verfasst von Lin Song und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Engineering, Southwest University of Science and Technology, Mianyang 621010, China. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China, Panzhihua University Cultivation Program, National Key R&D Program of China.
Abstract (Originalsprache)
The remaining useful life (RUL) prediction of rolling bearings based on vibration signals has attracted widespread attention. It is not satisfactory to adopt information theory (such as information entropy) to realize RUL prediction for complex vibration signals. Recent research has used more deep learning methods based on the automatic extraction of feature information to replace traditional methods (such as information theory or signal processing) to obtain higher prediction accuracy. Convolutional neural networks (CNNs) based on multi-scale information extraction have demonstrated promising effectiveness. However, the existing multi-scale methods significantly increase the number of model parameters and lack efficient learning mechanisms to distinguish the importance of different scale information. To deal with the issue, the authors of this paper developed a novel feature reuse multi-scale attention residual network (FRMARNet) for the RUL prediction of rolling bearings. Firstly, a cross-channel maximum pooling layer was designed to automatically select the more important information. Secondly, a lightweight feature reuse multi-scale attention unit was developed to extract the multi-scale degradation information in the vibration signals and recalibrate the multi-scale information. Then, end-to-end mapping between the vibration signal and the RUL was established. Finally, extensive experiments were used to demonstrate that the proposed FRMARNet model can improve prediction accuracy while reducing the number of model parameters, and it outperformed other state-of-the-art methods.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Information Engineering, Southwest University of Science and Technology, Mianyang 621010, China.
- School of Intelligent Manufacturing, Panzhihua University, Panzhihua 617000, China.
- State Key Laboratory of Tribology, Institute of Manufacturing Engineering, Department of Mechanical Engineering, Tsinghua University, Beijing 100084, China.
- Strategic Technology and Equipment Development Center, China Academy of Engineering Physics, Mianyang 621010, China.
ORCID-Profile: Lin Song
Förderung
- National Key R&D Program of China
- Panzhihua University Cultivation Program
- National Key R&D Program of China
Zitieren
APA
Song, L., Wu, J., Wang, L., Chen, G., Shi, Y., & Liu, Z. (2023). Remaining Useful Life Prediction of Rolling Bearings Based on Multi-Scale Attention Residual Network. Entropy, 25(5), 798. https://doi.org/10.3390/e25050798
Vancouver
Song L, Wu J, Wang L, Chen G, Shi Y, Liu Z. Remaining Useful Life Prediction of Rolling Bearings Based on Multi-Scale Attention Residual Network. Entropy. 2023;25(5):798. doi:10.3390/e25050798
BibTeX
@article{Song2023,
author = {Song, Lin and Wu, Jun and Wang, Liping and Chen, Guo and Shi, Yile and Liu, Zhigui},
title = {Remaining Useful Life Prediction of Rolling Bearings Based on Multi-Scale Attention Residual Network},
journal = {Entropy},
year = {2023},
volume = {25},
number = {5},
pages = {798},
doi = {10.3390/e25050798}
}
EUVIMED