A Novel Multi-Task Self-Supervised Transfer Learning Framework for Cross-Machine Rolling Bearing Fault Diagnosis
Electronics · 23.11.2024 · 13 (23) · 4622
DOI: 10.3390/electronics13234622 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 23.11.2024. Verfasst von Lujia Zhao und 5 weiteren Autor:innen. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Hebei Provincial Natural Science Foundation, Chinese Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
In recent years, intelligent methods based on transfer learning have achieved significant research results in the field of rolling bearing fault diagnosis. However, most studies focus on the transfer diagnosis scenario under different working conditions of the same machine. The transfer fault diagnosis methods used for different machines have problems such as low recognition accuracy and unstable performance. Therefore, a novel multi-task self-supervised transfer learning framework (MTSTLF) is proposed for cross-machine rolling bearing fault diagnosis. The proposed method is trained using a multi-task learning paradigm, which includes three self-supervised learning tasks and one fault diagnosis task. First, three different scales of masking methods are designed to generate masked vibration data based on the periodicity and intrinsic information of the rolling bearing vibration signals. Through self-supervised learning, the attention to the intrinsic features of data in different health conditions is enhanced, thereby improving the model’s feature expression capability. Secondly, a multi-perspective feature transfer method is proposed for completing cross-machine fault diagnosis tasks. By integrating two types of metrics, probability distribution and geometric similarity, the method focuses on transferable fault diagnosis knowledge from different perspectives, thereby enhancing the transfer learning ability and accomplishing cross-machine fault diagnosis of rolling bearings. Two experimental cases are carried out to evaluate the effectiveness of the proposed method. Results suggest that the proposed method is effective for cross-machine rolling bearing fault diagnosis.
Förderung
- National Natural Science Foundation of China
- Hebei Provincial Natural Science Foundation
- Chinese Fundamental Research Funds for the Central Universities
- Top Youth Talent Support Program of Hebei Province
- Hebei Provincial High-Level Talent Funding Project
- South Taihu Innovative Talent Team Project
Zitieren
APA
Zhao, L., He, Y., Dai, D., Wang, X., Bai, H., & Huang, W. (2024). A Novel Multi-Task Self-Supervised Transfer Learning Framework for Cross-Machine Rolling Bearing Fault Diagnosis. Electronics, 13(23), 4622. https://doi.org/10.3390/electronics13234622
Vancouver
Zhao L, He Y, Dai D, Wang X, Bai H, Huang W. A Novel Multi-Task Self-Supervised Transfer Learning Framework for Cross-Machine Rolling Bearing Fault Diagnosis. Electronics. 2024;13(23):4622. doi:10.3390/electronics13234622
BibTeX
@article{Zhao2024,
author = {Zhao, Lujia and He, Yuling and Dai, Derui and Wang, Xiaolong and Bai, Honghua and Huang, Weiling},
title = {A Novel Multi-Task Self-Supervised Transfer Learning Framework for Cross-Machine Rolling Bearing Fault Diagnosis},
journal = {Electronics},
year = {2024},
volume = {13},
number = {23},
pages = {4622},
doi = {10.3390/electronics13234622}
}
EUVIMED