조명전기설비학회논문지 (Journal of the Korean Institute of Illuminating and Electrical Installation Engineers)

  • 제23권2호
  • /
  • Pages.62-69
  • /
  • 2009
  • /
  • 1229-4691(pISSN)
  • /
  • 2287-5034(eISSN)
한국조명전기설비학회 (The Korean Institute of IIIuminating and Electrical Installation Engineers)
권호 표지
DOI QR코드

DOI QR Code

써포트 벡터머신을 이용한 전력용 변압기 고장진단

Fault Diagnosis of Power Transformer Using Support Vector Machine

  • 발행 : 2009.02.28
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 논문에서는 전력용 변압기의 고장진단을 위해 써포트 백터머신에 기반을 둔 고장진단 알고리즘을 제안한다. 제안된 기법은 데이터 취득부, 정상/고장판별부, 고장원인판별부로 구성된다. 제안한 고장진단과정을 보면, 데이터 취득부에서는 변압기에서 가스성분을 취득한다. 정상/고장 판별부에서는 취득된 가스성분들을 KEPCO 규정과 비교하여 정상/고장 여부를 판단한다. 고장원인 판별부에서는 입력 데이터가 고장으로 판정이 난 경우에 다중-클래스 써포트 백터머신에 의해 고장원인을 판정한다. 제안된 방법은 사례연구를 통해 우수성을 입증하였다.

For the fault diagnosis of power transformer, we develop a diagnosis algorithm based on support vector machine. The proposed fault diagnosis system consists of data acquisition, fault/normal diagnosis, and identification of fault. In data acquisition part, concentrated gases are extracted from transformer for data gas analysis. In fault/normal diagnosis part, KEPCO based decision rule is performed to separate normal state from fault types. The determination of fault type is executed by multi-class SVM in identification part. As the simulation results to verify the effectiveness, the proposed method showed more improved classification results than conventional methods.

키워드

참고문헌

  1. H. Tsukioka, K. Sugawara, E. Mori and H. Yamaguchi, "New apparatus for detecting transformer faults," IEEE Trans.Electrical Insulation, vol. EI-21, no. 2, pp. 221-229, 1986 https://doi.org/10.1109/TEI.1986.348948
  2. M. Duval, "Dissolved gas analysis : It can save your transformer," IEEE Electrical Insulation Magazine, vol. 5, no. 6, pp. 22-26, 1989 https://doi.org/10.1109/57.44605
  3. H. Yoshida, Y. Ishioka, T. Suzuki, T. Yanariand T.Teranishi, "Degradation of insulating materials oftransformers," IEEE Trans. Electrical Insulation, vol. EI-22,No. 6, pp. 795-800, 1987 https://doi.org/10.1109/TEI.1987.298942
  4. Y. Kamata, "Diagnostic methods for power transformer insulation," IEEE Trans.Electrical Insulation, vol EI-21, no.6, pp.1045-1048, 1986 https://doi.org/10.1109/TEI.1986.349022
  5. Pyeong Shik Ji,Jae Yoon Lim; Jong Pil Lee, "Aging characteristics of power transformer oil and development of its analysis using KSOM," TENCON 99, Proceedings of the IEEE Region, vol. 2,pp. 1026- 029, Sept. 1999 https://doi.org/10.1109/TENCON.1999.818596
  6. Adriana R.C., Vladimiro Miranda, "Knowledge Discovery in Nerual Networks with Application to Transformer Failure Diagnosis", IEEE trans. Power Systems, VOL. 20, NO. 2, pp.717-724, 2005 https://doi.org/10.1109/TPWRS.2005.846074
  7. Magn_Hui Wang, Hong-Chan Chang, "Novel clustering method for coherency identification using an artificial neural network," IEEE Trans., Power Systems, vol. 9,Nov. pp. 2056-2062, 1994 https://doi.org/10.1109/59.331469
  8. J.L.Naredo, P. Moreno, C.R. Fuerte, "A comparative study of neural network efficiency in power transformers diagnosis using dissolved gas analysis," IEEE Trans. Power Delivery, vol.16, pp. 643 – 647, Oct. 2001 https://doi.org/10.1109/61.956751
  9. V. Miranda, A.R.G. Castro, "Improving the IEC table for transformer failure diagnosis with knowledge extraction from neural networks," IEEE Trans. Power Delivery, vol. 20,pp. 2509-2516, Oct. 2005 https://doi.org/10.1109/TPWRD.2005.855423
  10. Vapnik, V.N. The nature of statistical learning theory,New York. Springer, 1999
  11. Ganyun LV, Haozhong Cheng, Haibao Zhai, Lixin Dong, "Fault diagnosis of power transformer based on multi-layer SVM classifier", Electrical Power Systems Research Vol. 75, pp9-15. 2005 https://doi.org/10.1016/j.epsr.2004.07.013
  12. Achmad Widodo, Bo-Suk Yang and Tian Han, "Combination of independent component analysis and support vector machines for intelligent faults diagnosisof induction motors", Expert Systems with Applications, In Press, Corrected Proof, Available online 4, Jan. 2006
  13. 문종필, 김재철, 임태훈, 실리콘 유입변압기 진단을 위한 전문가시스템 개발, 한국조명전기설비학회논문지, 제 18권 제1호, pp. 55-62, 2004 https://doi.org/10.5207/JIEIE.2004.18.2.055
  14. Bezdec, J.C., Pattern Recognition with Fuzzy Objective Function Algorithms, Plenum Press, New York, 1981. - 삭제요망
  15. Chin-Chang, Chih-Jen Lin, (2001), LIBSVM a library for support vector machines, Software available: http://www.csie.ntu.edu.tw/ ~cjlin/libsvm