EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Research on Open-Set Recognition Methods for Rolling Bearing Fault Diagnosis

Jia Xu iD, Yan Wang iD, Renyi Xu iD, Hailin Wang iD, Xinzhi Zhou iD

Sensors · 10.05.2025 · 25 (10) · 3019

DOI: 10.3390/s25103019 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 10.05.2025. Verfasst von Jia Xu und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic Information, Sichuan University, Chengdu 610065, China. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: China Nuclear Power Research and Design Institute Joint Fund, Nuclear Grade Instrumentation Project 2024, the Nuclear Grade Instrumentation Project Grant 2024.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In rolling bearing fault diagnosis, when an unknown fault is present, the Closed-Set Recognition (CSR) method tends to misclassify it as a known fault. To address this issue, an Open-Set Recognition (OSR) framework is proposed for rolling bearing fault diagnosis in this study. The framework is built upon a serial multi-scale convolutional prototype learning (SMCPL) network, enhanced with an efficient channel attention (ECA) mechanism to extract the most critical fault features. The extracted features are fed into the Density Peak Clustering (DPC) module, which identifies known and unknown classes based on the computed local densities and relative distances. Finally, validation is performed on the Case Western Reserve University (CWRU) dataset, the Xi’an Jiaotong University rolling bearing accelerated life test dataset (XJTU-SY), and the Paderborn University bearing dataset (PU), Germany, and the framework is comprehensively evaluated in terms of several evaluation metrics, such as normalization accuracy and feature visualization. The experimental results show that SMCPL-ECA-DPC outperforms the comparative methods of SMCPL, CPL, ANEDL, CNN, and OpenMax and has high diagnostic performance in the identification of unknown faults.

Schlagwörter

Stichwörter der Autor:innen

Open-Set Recognitionmulti-scalerolling bearingsunknown fault diagnosis

Autor:innen und Institutionen

  • School of Electronic Information, Sichuan University, Chengdu 610065, China.
  • National Key Laboratory of Science and Technology on Reactor System Design Technology, Nuclear Power Institute of China, Chengdu 610213, China.

ORCID-Profile: Jia Xu, Yan Wang, Renyi Xu, Hailin Wang, Xinzhi Zhou

Förderung

  • China Nuclear Power Research and Design Institute Joint Fund
  • Nuclear Grade Instrumentation Project 2024
  • the Nuclear Grade Instrumentation Project Grant 2024
  • the China Nuclear Power Research and Design Institute Joint Fund

Zitieren

APA

Xu, J., Wang, Y., Xu, R., Wang, H., & Zhou, X. (2025). Research on Open-Set Recognition Methods for Rolling Bearing Fault Diagnosis. Sensors, 25(10), 3019. https://doi.org/10.3390/s25103019

Vancouver

Xu J, Wang Y, Xu R, Wang H, Zhou X. Research on Open-Set Recognition Methods for Rolling Bearing Fault Diagnosis. Sensors. 2025;25(10):3019. doi:10.3390/s25103019

BibTeX
@article{Xu2025,
  author = {Xu, Jia and Wang, Yan and Xu, Renyi and Wang, Hailin and Zhou, Xinzhi},
  title = {Research on Open-Set Recognition Methods for Rolling Bearing Fault Diagnosis},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {10},
  pages = {3019},
  doi = {10.3390/s25103019}
}
Kostenlos starten →