EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Bearing-Fault-Feature Enhancement and Diagnosis Based on Coarse-Grained Lattice Features

Xiaoyu Li, Baozhu Jia iD, Zhiqiang Liao, Xin Wang

Sensors · 30.05.2024 · 24 (11) · 3540

DOI: 10.3390/s24113540 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 30.05.2024. Verfasst von Xiaoyu Li und 3 weiteren Autor:innen. Beteiligte Einrichtung: Naval Architecture and Shipping College, Guangdong Ocean University, Zhanjiang 524088, China. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the National Natural Science Foundation 335 of China, the Program for Scientific Research Start-Up Funds of 336 Guangdong Ocean University, Guangdong Ocean Uni-337 versity Education Teaching Reform Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In view of the frequent failures occurring in rolling bearings, the strong background noise present in signals, weak features, and difficulties associated with extracting fault characteristics, a method of enhancing and diagnosing rolling bearing faults based on coarse-grained lattice features (CGLFs) is proposed. First, the vibrational signals of bearings are subjected to adaptive filtering to eliminate background noise. Second, frequency-domain transformation is performed, and a coarse-grained approach is used to continuously segment the spectrum. Within each segment, amplitude-enhancement operations are executed, transforming the data into a CGLF graph that enhances fault characteristics. This graph is then fed into a Swin Transformer-based pattern-recognition network. Third and finally, a high-precision fault diagnosis model is constructed using fully connected layers and Softmax, enabling the diagnosis of bearing faults. The fault recognition accuracy reaches 98.30% and 98.50% with public datasets and laboratory data, respectively, thereby validating the feasibility and effectiveness of the proposed method. This research offers an efficient and feasible fault diagnosis approach for rolling bearings.

Schlagwörter

Stichwörter der Autor:innen

Swin Transformercoarse-grained lattice featuresfault diagnosisfeature enhancementrolling bearings

Autor:innen und Institutionen

  • Naval Architecture and Shipping College, Guangdong Ocean University, Zhanjiang 524088, China.
  • Technical Research Center for Ship Intelligence and Safety Engineering of Guangdong Province, Zhanjiang 524088, China.
  • Guangdong Provincial Key Laboratory of Intelligent Equipment for South China Sea Marine Ranching, Guangdong Ocean University, Zhanjiang 524088, China.

ORCID-Profile: Baozhu Jia

Förderung

  • the National Natural Science Foundation 335 of China
  • the Program for Scientific Research Start-Up Funds of 336 Guangdong Ocean University
  • Guangdong Ocean Uni-337 versity Education Teaching Reform Program
  • National Natural Science Foundation of China
  • Program for Scientific Research Start-Up Funds of Guangdong Ocean University
  • Guangdong Ocean University Education Teaching Reform Program
  • Zhanjiang Non-funded Science and Technology Research Project

Zitieren

APA

Li, X., Jia, B., Liao, Z., & Wang, X. (2024). Bearing-Fault-Feature Enhancement and Diagnosis Based on Coarse-Grained Lattice Features. Sensors, 24(11), 3540. https://doi.org/10.3390/s24113540

Vancouver

Li X, Jia B, Liao Z, Wang X. Bearing-Fault-Feature Enhancement and Diagnosis Based on Coarse-Grained Lattice Features. Sensors. 2024;24(11):3540. doi:10.3390/s24113540

BibTeX
@article{Li2024,
  author = {Li, Xiaoyu and Jia, Baozhu and Liao, Zhiqiang and Wang, Xin},
  title = {Bearing-Fault-Feature Enhancement and Diagnosis Based on Coarse-Grained Lattice Features},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {11},
  pages = {3540},
  doi = {10.3390/s24113540}
}
Kostenlos starten →