Comparison of BP and SOM as a Classification of PD Source

부분방전원의 분류에 있어서 BP와 SOM의 비교

  • 박성희 (충북대학교 전기전자컴퓨터공학부) ;
  • 강성화 (충청대학 산업안전과) ;
  • 임기조 (충북대학교 전기전자컴퓨터공학부)
  • Published : 2004.09.01


In this paper, neural networks is studied to apply as a PD source classification in XLPE power cable specimen. Two learning schemes are used to classification; BP(Back propagation algorithm), SOM(self organized map - kohonen network). As a PD source, using treeing discharge sources in the specimen, three defected models are made. And these data making use of a computer-aided discharge analyser, statistical and other discharge parameters is calculated to discrimination between different models of discharge sources. And a]so these distribution characteristics are applied to classify PD sources by two scheme of the neural networks. In conclusion, recognition efficiency of BP is superior to SOM.


  1. 전력기기 절연 진단 기술 한국전기연구원
  2. IEEE Trans. on EI v.28 no.6 Classification of partial discharge F. H. Kreuger;E. Gulski;A. Krivda
  3. IEEE Trans. on EI v.27 no.1 Computeraided recognition of discharge sources E. Gulski;F. H. Kreuger
  4. IEEE Trans. on EI v.27 no.1 The importance of statistial characteristics of partial discharge data B. Fruth;L. Niemer
  5. IEEE Trans. on EI v.27 no.3 pattern recognition of partial discharges in xlpe cables using a neural networks H. Suzuki;T. Endoh
  6. IEEE Trans. on NN v.13 no.2 Determination of neural network topology for partial discharge pulse pattern recognition M. M. A. Salama;R. Bartnikas
  7. IEEE Trans. on EI v.28 no.6 neural network as a tool for recognition of partial discharge E. Gulski;A. Krivda
  8. 전기전자재료학회논문지 v.17 no.1 STFT 및 통계적 처리에 의한 공기 중 부분방전원 식별 이강원;박성희;강성화;임기조
  9. 전기전자재료학회논문지 v.14 no.12 변압기 부분방전 상시 감시 기법에 관한 연구 권동진;박재준
  10. High Voltage Technology L. L. Alston
  11. IEEE Trans. on NN v.11 no.2 Partial Discharge ; Discharge in Air Part 1 : Physical Mechanisms N. G. Trich
  12. 高電壓工學 丁性桂;李德出
  13. 전기전자재료학회논문지 v.15 no.11 에폭시/고무 거시계면에서 장시간 절연파괴전압에 대한 연구 박우현;이기식