About | Contact Us | Register | Login
ProceedingsSeriesJournalsSearchEAI
Proceedings of the 2nd International Conference on Machine Learning and Automation, CONF-MLA 2024, November 21, 2024, Adana, Turkey

Research Article

Research on Demagnetization Fault Diagnosis of Permanent Magnet Linear Synchronous Motor Based on SqueezeNet Neural Network

Download233 downloads
Cite
BibTeX Plain Text
  • @INPROCEEDINGS{10.4108/eai.21-11-2024.2354596,
        author={Tianye  Guo},
        title={Research on Demagnetization Fault Diagnosis of Permanent Magnet Linear Synchronous Motor Based on SqueezeNet Neural Network},
        proceedings={Proceedings of the 2nd International Conference on Machine Learning and Automation, CONF-MLA 2024, November 21, 2024, Adana, Turkey},
        publisher={EAI},
        proceedings_a={CONF-MLA},
        year={2025},
        month={3},
        keywords={permanent magnet linear synchronous motor demagnetization fault diagnosis squeezenet neural network recurrence plot algorithm},
        doi={10.4108/eai.21-11-2024.2354596}
    }
    
  • Tianye Guo
    Year: 2025
    Research on Demagnetization Fault Diagnosis of Permanent Magnet Linear Synchronous Motor Based on SqueezeNet Neural Network
    CONF-MLA
    EAI
    DOI: 10.4108/eai.21-11-2024.2354596
Tianye Guo1,*
  • 1: Anhui University, China
*Contact email: gty20040408@163.com

Abstract

This paper studies the demagnetization fault diagnosis method of Permanent Magnet Linear Synchronous Motor based on SqueezeNet neural network. A new demagnetization fault signal acquisition method is proposed to adapt to the spatial topological structure constraints of the double-stator coreless motor, and to obtain effective demagnetization fault signals without invasive measurement, so as to improve the accuracy of the fault signal source. At the same time, a simple linear motor demagnetization fault diagnosis device is designed. The one-dimensional demagnetization fault signal is converted into a two-dimensional image through the Recurrence Plot, and fault feature information is effectively extracted. In addition, this paper innovatively uses the lightweight SqueezeNet model for training. After continuous adjustment of the SqueezeNet network model, it can efficiently complete the classification of permanent magnet linear synchronous motor demagnetization faults.

Keywords
permanent magnet linear synchronous motor demagnetization fault diagnosis squeezenet neural network recurrence plot algorithm
Published
2025-03-11
Publisher
EAI
http://dx.doi.org/10.4108/eai.21-11-2024.2354596
Copyright © 2024–2025 EAI
EBSCOProQuestDBLPDOAJPortico
EAI Logo

About EAI

  • Who We Are
  • Leadership
  • Research Areas
  • Partners
  • Media Center

Community

  • Membership
  • Conference
  • Recognition
  • Sponsor Us

Publish with EAI

  • Publishing
  • Journals
  • Proceedings
  • Books
  • EUDL