Feature Analysis and Identification of Low-voltage Series Arc Fault
ID:336 View Protection:ATTENDEE Updated Time:2022-08-29 15:56:29 Hits:281 Poster Presentation

Start Time:Pending(Asia/Shanghai)

Duration:Pending

Session:No Session »

No files

Abstract
Fires caused by arc faults are increasing every year, but low-voltage AC series arc faults are tricky to be detected by traditional methods because of its concealment. A detection algorithm based on multi-feature fusion to analyze arc faults is proposed in this paper. Furthermore, different loads, including motor loads and the power electronic loads, are selected to extract arc characteristics by combining various methods, especially Empirical Wavelet Transform (EWT). In contrast with some traditional modal decomposition algorithms, EWT can overcome modal aliasing and end-point effects, and improve the quality of the frequency band. Then, the change in signal complexity is calculated by introducing the Shannon entropy of the frequency band signal. In order to make the results more accurate, several classical features are integrated as the input elements of the neural network in this paper. Finally, the Scaled Conjugate Gradient Backpropagation algorithm is used to identify arc faults. The detection results with detection accuracy of over 99.8% by training the existing features, prove that the multi-feature fusion algorithm can detect AC arc faults effectively and accurately.
 
Keywords
Energy Feature Extraction,waveform,time domain
Speaker
Xiaoxue Chang
Nanjing University of Aeronautics and Astronautics

Submission Author
Xiaoxue Chang Nanjing University of Aeronautics and Astronautics
Xu Zhang Nanjing University of Aeronautics and Astronautics
Yanbo Tao Nanjing University of Aeronautics and Astronautics
Wenqian Zhang Nanjing University of Aeronautics and Astronautics
Jun Jiang Nanjing University of Aeronautics and Astronautics
Chaohai Zhang China;Wuhan NARI Limited Company of State Grid Electric Power Research Institute
Submit Comment
Verify Code Change Another
All Comments
Important Date
  • Conference Date

    Sep 25

    2022

    to

    Sep 29

    2022

  • Aug 15 2022

    Early Bird Registration

  • Sep 10 2022

    Contribution Submission Deadline

  • Nov 10 2022

    Registration deadline

  • Nov 30 2022

    Draft paper submission deadline

  • Nov 30 2022

    Final Paper Deadline

Sponsored By
IEEE DEIS
Organized By
Chongqing University
Contact Information