DOI QR코드

DOI QR Code

Comparison of Artificial Neural Network for Partial Discharge Diagnosis

부분방전 진단을 위한 인공신경망 기법의 비교

  • Received : 2013.06.04
  • Accepted : 2013.09.06
  • Published : 2013.09.30

Abstract

This paper investigates the diagnosis performance of Artificial Neural Network (ANN) depending on the structure and the input vector type of ANN, which has been used to detect the partial discharge to lead to the electric machinery deterioration. The diagnosis performance of one hidden layer and two hidden layer in ANN are compared. The performance using the 2048 time-series data and the performance using the feature input vector are compared. For measuring the partial discharge signal, the tip-to-plate, the sphere-to-sphere, the tip-to-tip, the tip-to-sphere and the sphere-to-plate electrodes are used respectively. For ANN's learning, Matlab and C-code program are used. For evaluating the diagnosis performance of ANNs, the simulation studies are performed.

본 논문은 전력기기 열화의 주요한 원인으로 알려진 부분방전의 진단을 위해 널리 사용되는 인공신경망의 계층 구조 및 입력벡터의 구성 요소의 변화에 대한 진단 성능을 검토한다. 은닉층이 1개 또는 2개인 인공신경망의 계층구조 변화에 대한 진단 성능을 비교하였으며, 입력벡터는 세라믹 커플러를 이용하여 한주기에 2048번 샘플링한 시계열 신호를 직접 사용하는 경우와 특성벡터를 추출하여 사용하는 경우를 비교하였다. 침${\leftrightarrow}$평판, 구${\leftrightarrow}$구, 침${\leftrightarrow}$침, 평판${\leftrightarrow}$평판, 구${\leftrightarrow}$평판 형태의 5가지 전극조합의 부분방전 실험으로 학습데이타를 수집하고, 시뮬레이션 연구를 수행하여 인공신경망의 진단 성능을 평가하였다.

Keywords

References

  1. Hyun-Jin Lee, Jung-Il Jeong, Chang-Su Huh, Han-Goo Cho, "Analysis on Thermal Transfer Characteristics of 50 kVA Mold-Transformer," Journal of the Korea institute of Illuminating and Electrical Installation Engineers Vol.16, No.3 pp.47-54 May, 2002 DOI: http://dx.doi.org/10.5207/JIEIE.2002.16.3.047
  2. M. Darveniza, T.K. Saha, D.J.T. Hill, T.T. Le, "Investigations into effective methods for assessing the condition of insulation in aged power transformers," IEEE Trans. on Power Delivery, Vol. 13, No. 4, pp. 1214-1223, October, 1998. DOI: http://dx.doi.org/10.1109/61.714487
  3. Tapan K. Saha, "Review of Modern Diagnostic Techniques for Assessing Insulation Condition in Aged Transformers," IEEE trans on Dielectrics and Electrical Insulation, Vol. 10, No. 5, pp. 903-917, October 2003. DOI: http://dx.doi.org/10.1109/TDEI.2003.1237337
  4. Dong-Jin Kweon, Kyo-Sun Koo, Joo-Sik Kwak, Jung-Wook Woo, Yeon-Woog Kang, "Establishment of Diagnostic Criteria in the Preventive Diagnostic System for the Power Transformer" The Trans. of KIEE ,Vol. 54A. No 9. pp 449-456. SEP 2005
  5. Kim Doyoon, Jung Hosung, Park Young, Han Seokyoun, Lee Sang Bin, "A case study of condition monitoring for mold transformers on urban railway transit," The Korean Society for Railway, Proceedings of Autumn Annual Conference,, pp. 235-240, Novemver, 2008.
  6. Bong-Keun Oh, Hyun-Il Kim, Seong-Hwa Kang, Hee-Joe Lim, "Analysis and Test of On-line and Off-line PD Testing for High Voltage Ritating Machines Stator Windings using Ceramic Coupler," Journal of the Korea Institute of Electrical & Electronic Material Engineers, Vol.20, No.10 pp.895-900 October 2007 DOI: http://dx.doi.org/10.4313/JKEM.2007.20.10.895
  7. Young-Ki Chung, Jong-Wook Jung, Jae-Chul Kim, Hee-Ro Kwak, "FFT and AR Coefficient Analysis of Vibration Signal in Mold Transformer,' Journal of the Korea institute of Illuminating and Electrical Installation Engineers , Vol. 12, No. 4, pp.136-145, 1998.11.
  8. Jong-Fil Moon, Jae-Chul Kim, Tae-Hoon Im, "Development of the Expert System for Diagnosing Silicone Oil-filled Transformer," Journal of the korean institute of llluminating and Electrical installation Engineers Vol, 18.No 2,pp. 55-62 March 2004 https://doi.org/10.5207/JIEIE.2004.18.2.055
  9. Dae-Jong Lee, Jong-Pil Lee, Pyeong-Shik Ji, Jae-Yoon Lim, "Fault Diagnosis of Power Transformer Using Support Vector Machine," Journal of the korean institute of llluminating and Electrical installation Engineers Vol, 23. No 2, pp. 62-69, February 2009 https://doi.org/10.5207/JIEIE.2009.23.2.062
  10. E. Howells, E. T. Norton "Detection of Partial Discharges in Transformers using Acoustic Emission Techniques" IEEE Transformers on Power Apparatus and Systems, Vol. PAS-97 No 5, Sept/Oct 1978 DOI: http://dx.doi.org/10.1109/TPAS.1978.354646
  11. D.S. Kang, J.H. Sun, K.H. Cho.....S.M. Lee, Y.H. Yun., " Development of Partial Discharge Measuring Sensor and System for Mold Transformer," KIEE Proceedings of Fall Conference for Electrical Installation Committee, pp. 99-102, Novemberm 2005.
  12. Chan-Yong Park, Sung-Wook Kim, Jae-Sung Choi, Dae-Won Park, Gyung-Suk Kil, "Comparison Analysis of Partial Discharge Detection Methods in Cast Resin Dry Type Transformers," KIIEE Proceedings of Autumn Annual Conference, pp 301-306, Octorber 2008.
  13. June-Ho Lee, Chin-Woo Yi, "Recognition of Partial Discharge Patterns," Journal of the Korea institute of Illuminating and Electrical Installation Engineers Vol.14, No.2 pp.8-17 March, 2000.
  14. Ho-Keun Lee, Jeong-Tae Kim, "Comparative Study on Neural Network Algorithms for Partial Discharge Pattern Recognition," KIEE Proceedings of Spring Conference for Electrical Installation Committee, pp.109-112, May, 2005.
  15. Martin T. Hagan , Howard B. Bemuth , Mark H. Beale (translated by Byun Younshik et al.), " Neural Network Design,", ISBN 9788956674452, Intervision Publishing, Korea, 2008.
  16. Hyeong-Taek Jang, Sun-Geun Kwack, Pan-Seok Shin, Chang-Eob Kim, Gyo-Bum Chung, "Investigation of Simulation and Measuring Algorithm of Partial Discharge for Diagnosis of Electric Machinery Deterioration," Journal of the Korean Institute of IIIuminating and Electrical Installation Engineers, Vol.25 Np.8, pp. 30-38, August, 2011. DOI: http://dx.doi.org/10.5207/JIEIE.2011.25.8.030