A fault diagnosis method based on an improved diffusion model under limited sample conditions
PLOS ONE · 03.09.2024 · 19 (9) · e0309714
DOI: 10.1371/journal.pone.0309714 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 03.09.2024. Verfasst von Qiushi Wang und 4 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Networked Control Systems, Chinese Academy of Sciences, Shenyang, China. Hauptthemen laut MEDLINE: Neural Networks, Computer. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Applied Basic Research Project of Liaoning Province.
Abstract (Originalsprache)
As a critical component in mechanical systems, the operational status of rolling bearings plays a pivotal role in ensuring the stability and safety of the entire system. However, in practical applications, the fault diagnosis of rolling bearings often encounters limitations due to the constraint of sample size, leading to suboptimal diagnostic accuracy. This article proposes a rolling bearing fault diagnosis method based on an improved denoising diffusion probability model (DDPM) to address this issue. The practical value of this research lies in its ability to address the limitation of small sample sizes in rolling bearing fault diagnosis. By leveraging DDPM to generate one-dimensional vibration data, the proposed method significantly enriches the datasets and consequently enhances the generalization capability of the diagnostic model. During the model training process, we innovatively introduce the feature differences between the original vibration data and the predicted vibration data generated based on prediction noise into the loss function, making the generated data more directional and targeted. In addition, this article adopts a one-dimensional convolutional neural network (1D-CNN) to construct a fault diagnosis model to more accurately extract and focus on key feature information related to faults. The experimental results show that this method can effectively improve the accuracy and reliability of rolling bearing fault diagnosis, providing new ideas and methods for fault detection and prevention in industrial applications. This advancement in diagnostic technology has the potential to significantly reduce the risk of system failures, enhance operational efficiency, and lower maintenance costs, thus contributing significantly to the safety and efficiency of mechanical systems.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Key Laboratory of Networked Control Systems, Chinese Academy of Sciences, Shenyang, China.
- Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China.
- State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, Liaoning Province, China.
- PipeChina Institute of Science and Technology, Langfang, China.
ORCID-Profile: Zhicheng Sun
Förderung
- Applied Basic Research Project of Liaoning Province
Zitieren
APA
Wang, Q., Sun, Z., Zhu, Y., Li, D., & Ma, Y. (2024). A fault diagnosis method based on an improved diffusion model under limited sample conditions. PLOS ONE, 19(9), e0309714. https://doi.org/10.1371/journal.pone.0309714
Vancouver
Wang Q, Sun Z, Zhu Y, Li D, Ma Y. A fault diagnosis method based on an improved diffusion model under limited sample conditions. PLOS ONE. 2024;19(9):e0309714. doi:10.1371/journal.pone.0309714
BibTeX
@article{Wang2024,
author = {Wang, Qiushi and Sun, Zhicheng and Zhu, Yueming and Li, Dong and Ma, Yunbin},
title = {A fault diagnosis method based on an improved diffusion model under limited sample conditions},
journal = {PLOS ONE},
year = {2024},
volume = {19},
number = {9},
pages = {e0309714},
doi = {10.1371/journal.pone.0309714}
}
EUVIMED