KIEE International Transactions on Electrophysics and Applications

The Korean Institute of Electrical Engineers (대한전기학회)
권호 표지

Artificial Neural Network Discrimination of Multi-PD Sources Detected by UHF Sensor

  • Lee, Kang-Won (Dept. of Electrical Engineering, Chungbuk National University) ;
  • Jang, Dong-Uk (Dept. of Electrical Engineering, Chungbuk National University) ;
  • Park, Jae-Yeol (Dept. of Electrical Engineering, Chungbuk National University) ;
  • Kang, Seong-Hwa (Dept. of Electrical Engineering, Chungbuk National University) ;
  • Lim, Kee-Joe (Dept. of Electrical Engineering, Chungbuk National University)
  • Published : 2003.01.01
Download PDF
⟨ Previous Next ⟩

Abstract

The waveforms of partial discharges (PDs) imply physical and structural properties of PD sources, so analyzing them give us information on the kind of PD sources and the location. Waveforms of PD as a time series function have variable amplitudes but sustain a certain uniform shape, which shows well the characteristics of the waveforms and frequency region. They can also be used as parameters having time and frequency information of PD signals and applied to classification of multiple PDs sources via Artificial Neural Network with back propagation (BP) learning.

Keywords

References

  1. H. S. Park, J. D. Park, Y. K. Chung, and H. R. Kwak, 'Characteristics of Ultrasonic Signals by Partial Dis charge Types', Conference of KlEE, pp.1897-1899, 2000
  2. S. H. Lee, K. S. Park, H. D. Lee, Ch. N. Kim, H. J. Song, K. C. Kim, K. S. Lee, and D. I. Lee, 'The Fundamental Study About Partial Discharge Detection With The Radiated Electromagnetic Wave Characteristics', Journal of KlEE, pp412-417, 2000
  3. Y. N. Kim, J. C. Kim, I. C. Seo, Y. J. Jeon, K. H. Kim, 'The Detection of Partial Discharge Signal by the Measurement of an Electromagnetic Wave and Pattern Recognition Technique', Journal of KlEE, pp.276-283, 2002
  4. F. H. Kreuger, E. Gulski and A. Krivda, 'Classification of Partial Discharge', IEEE Trans, Electrical Insulation, Vol. 28, No.6, pp917-931, 1993
  5. M. Hoof, and R. Patsch, . 'Pulse-Sequence Analysis: A New Method for Investigating the Physics of PD-Induced Ageing', lEE Proceedings on Science, Measurement and Technology, Vol. 142,No .1 ,pp95 -101, Jan. 1995
  6. E. Gulski, and A. Krivda, 'Neural Networks as a Tool for Recognition of Partial Discharges', IEEE Trans. on Electrical Insulation. Vol.28 No. 6, pp.984-1001 Dec. 1993 https://doi.org/10.1109/14.249372