EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An improved multi-scale branching convolutional neural network for rolling bearing fault diagnosis

Meng Xu iD, Yaowei Shi, Minqiang Deng, Yang Liu, Xue Ding, Aidong Deng iD

PLOS ONE · 2023

DOI: 10.1371/journal.pone.0291353 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, 2023. Verfasst von Meng Xu und 5 weiteren Autor:innen. Beteiligte Einrichtung: National Engineering Research Center of Power Generation Control and Safety, School of Energy and Environment, Southeast University, Nanjing, China. Hauptthemen laut MEDLINE: Engineering, Industry. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Carbon Peak and Carbon Neutrality technology innova-tion of Jiangsu Province, Key Research and Development Program of Jiangsu Province, the Fundamental Research Funds for the Central Universities.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The vibration signals measured in practical engineering are usually complex and noisy, which brings challenges to fault diagnosis. In addition, industrial scenarios also put forward higher requirements for the accuracy and computational efficiency of diagnostic models. Aiming at these problems, an improved multiscale branching convolutional neural network is proposed for rolling bearing fault diagnosis. The proposed method first applies the multiscale feature learning strategy to extract rich and compelling fault information from diverse and complex vibration signals. Further, the lightweight dynamic separable convolution is elaborated and coupled into the feature extractor to "slim down" the model, reduce the computational loss on the one hand, and further improve the model’s adaptive learning ability for different inputs hand. Extensive experiments indicate that the proposed method is significantly improved compared with existing multi-scale neural networks.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

EngineeringIndustryIntelligenceLearningNeural Networks, Computer

Autor:innen und Institutionen

  • National Engineering Research Center of Power Generation Control and Safety, School of Energy and Environment, Southeast University, Nanjing, China.

ORCID-Profile: Meng Xu, Aidong Deng

Förderung

  • the Carbon Peak and Carbon Neutrality technology innova-tion of Jiangsu Province
  • Key Research and Development Program of Jiangsu Province
  • the Fundamental Research Funds for the Central Universities

Zitieren

APA

Xu, M., Shi, Y., Deng, M., Liu, Y., Ding, X., & Deng, A. (2023). An improved multi-scale branching convolutional neural network for rolling bearing fault diagnosis. PLOS ONE. https://doi.org/10.1371/journal.pone.0291353

Vancouver

Xu M, Shi Y, Deng M, Liu Y, Ding X, Deng A. An improved multi-scale branching convolutional neural network for rolling bearing fault diagnosis. PLOS ONE. 2023. doi:10.1371/journal.pone.0291353

BibTeX
@article{Xu2023,
  author = {Xu, Meng and Shi, Yaowei and Deng, Minqiang and Liu, Yang and Ding, Xue and Deng, Aidong},
  title = {An improved multi-scale branching convolutional neural network for rolling bearing fault diagnosis},
  journal = {PLOS ONE},
  year = {2023},
  doi = {10.1371/journal.pone.0291353}
}
Kostenlos starten →