EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Denoising Diffusion Implicit Model Combined with TransNet for Rolling Bearing Fault Diagnosis Under Imbalanced Data

Chaobing Wang, Cong Huang iD, Long Zhang iD, Zhibin Xiang, Yiwen Xiao, Tongshuai Qian, Jiayang Liu iD

Sensors · 15.12.2024 · 24 (24) · 8009

DOI: 10.3390/s24248009 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 15.12.2024. Verfasst von Chaobing Wang und 6 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Performance Monitoring and Protecting of Rail Transit Infrastructure, East China Jiaotong University, Nanchang 330013, China. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Sciences of Jiangxi Province, Science and Technology Project of China State Railway Group Co., Ltd, National Key Laboratory Autonomous Projects.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Data imbalances present a serious problem for intelligent fault diagnosis. They can lead to reduced diagnostic precision, which can jeopardize equipment reliability and safety. Based on that, this paper proposes a novel fault diagnosis method combining the denoising diffusion implicit model (DDIM) with a new convolutional neural network framework. First, the Gramian angular difference field (GADF) is used to generate 2D images, which are then augmented using DDIM. Next, by utilizing the weight-sharing properties of a convolutional neural network and the self-attention mechanism along with the global data processing capabilities of Transformers, a TransNet model is constructed. The augmented data are input into the model for training to establish a fault diagnosis framework. Finally, the method is validated and analyzed using the CWRU bearing dataset and the Nanchang Railway Bureau dataset. The results show that the proposed method achieves over 99% recognition accuracy on the two datasets. Meanwhile, the proposed model provides better generalization performance and recognition accuracy than existing fault diagnosis methods.

Schlagwörter

Stichwörter der Autor:innen

data imbalancesdenoising diffusion implicit modelfault diagnosisrolling bearingtransformer

Autor:innen und Institutionen

  • State Key Laboratory of Performance Monitoring and Protecting of Rail Transit Infrastructure, East China Jiaotong University, Nanchang 330013, China.
  • School of Mechatronics and Vehicle Engineering, East China Jiaotong University, Nanchang 330013, China.

ORCID-Profile: Cong Huang, Long Zhang, Jiayang Liu

Förderung

  • Natural Sciences of Jiangxi Province
  • Science and Technology Project of China State Railway Group Co., Ltd
  • National Key Laboratory Autonomous Projects
  • Science and Technology Project of China State Railway Group Co, Ltd.

Zitieren

APA

Wang, C., Huang, C., Zhang, L., Xiang, Z., Xiao, Y., Qian, T., & Liu, J. (2024). Denoising Diffusion Implicit Model Combined with TransNet for Rolling Bearing Fault Diagnosis Under Imbalanced Data. Sensors, 24(24), 8009. https://doi.org/10.3390/s24248009

Vancouver

Wang C, Huang C, Zhang L, Xiang Z, Xiao Y, Qian T, et al. Denoising Diffusion Implicit Model Combined with TransNet for Rolling Bearing Fault Diagnosis Under Imbalanced Data. Sensors. 2024;24(24):8009. doi:10.3390/s24248009

BibTeX
@article{Wang2024,
  author = {Wang, Chaobing and Huang, Cong and Zhang, Long and Xiang, Zhibin and Xiao, Yiwen and Qian, Tongshuai and Liu, Jiayang},
  title = {Denoising Diffusion Implicit Model Combined with TransNet for Rolling Bearing Fault Diagnosis Under Imbalanced Data},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {24},
  pages = {8009},
  doi = {10.3390/s24248009}
}
Kostenlos starten →