EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep Reconstruction Transfer Convolutional Neural Network for Rolling Bearing Fault Diagnosis

Ziwei Feng, Qingbin Tong iD, Xuedong Jiang, Feiyu Lu, Xin Du, Jianjun Xu, Jingyi Huo

Sensors · 24.03.2024 · 24 (7) · 2079

DOI: 10.3390/s24072079 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 24.03.2024. Verfasst von Ziwei Feng und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Electrical Engineering, Beijing Jiaotong University, Beijing 100044, China. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Fundamental Research Funds for the Central Universities, the Beijing Natural Science Foundation, Fundamental Research Funds for the Central Universities.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep transfer learning has been widely used to improve the versatility of models. In the problem of cross-domain fault diagnosis in rolling bearings, most models require that the given data have a similar distribution, which limits the diagnostic effect and generalization of the model. This paper proposes a deep reconstruction transfer convolutional neural network (DRTCNN), which satisfies the domain adaptability of the model under cross-domain conditions. Firstly, the model uses a deep reconstruction convolutional automatic encoder for feature extraction and data reconstruction. Through sharing parameters and unsupervised training, the structural information of target domain samples is effectively used to extract domain-invariant features. Secondly, a new subdomain alignment loss function is introduced to align the subdomain distribution of the source domain and the target domain, which can improve the classification accuracy by reducing the intra-class distance and increasing the inter-class distance. In addition, a label smoothing algorithm considering the credibility of the sample is introduced to train the model classifier to avoid the impact of wrong labels on the training process. Three datasets are used to verify the versatility of the model, and the results show that the model has a high accuracy and stability.

Schlagwörter

Stichwörter der Autor:innen

autoencoderdomain adaptationintelligent fault diagnosislabel smoothingtransfer learning

Autor:innen und Institutionen

  • School of Electrical Engineering, Beijing Jiaotong University, Beijing 100044, China.

ORCID-Profile: Qingbin Tong

Förderung

  • the Fundamental Research Funds for the Central Universities
  • the Beijing Natural Science Foundation
  • Fundamental Research Funds for the Central Universities
  • Beijing Natural Science Foundation

Zitieren

APA

Feng, Z., Tong, Q., Jiang, X., Lu, F., Du, X., Xu, J., & Huo, J. (2024). Deep Reconstruction Transfer Convolutional Neural Network for Rolling Bearing Fault Diagnosis. Sensors, 24(7), 2079. https://doi.org/10.3390/s24072079

Vancouver

Feng Z, Tong Q, Jiang X, Lu F, Du X, Xu J, et al. Deep Reconstruction Transfer Convolutional Neural Network for Rolling Bearing Fault Diagnosis. Sensors. 2024;24(7):2079. doi:10.3390/s24072079

BibTeX
@article{Feng2024,
  author = {Feng, Ziwei and Tong, Qingbin and Jiang, Xuedong and Lu, Feiyu and Du, Xin and Xu, Jianjun and Huo, Jingyi},
  title = {Deep Reconstruction Transfer Convolutional Neural Network for Rolling Bearing Fault Diagnosis},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {7},
  pages = {2079},
  doi = {10.3390/s24072079}
}
Kostenlos starten →