DOI QR코드

DOI QR Code

Partial Discharge Data Analysis with Unsupervised Classification

무감독분류 기법에 의한 부분방전 데이터 분석

  • 조경순 (서일대학교 컴퓨터응용전자과) ;
  • 홍선학 (서일대학교 컴퓨터응용전자과)
  • Received : 2018.11.20
  • Accepted : 2018.02.06
  • Published : 2018.12.30

Abstract

This study described partial discharge(PD) distribution analysis between the XLPE(Cross-Linked PolyEthylene)and EPDM(Ethylene Propylene Diene Monomer) interface with unsupervised classification. The ${\phi}-q-n$ patterns were analyzed using phase resolved partial discharge(PRPD). K-means cluster analysis forms a cluster based on similarities and distances among scattered individuals, and analyzes the characteristics of the formed clusters, dividing the multivariate data into several groups according to the similarity of each characteristic, Is a statistical analysis that makes it easier to navigate. It was confirmed that the phase angle of the cluster with the maximum discharge charge was concentrated around $0^{\circ}$ and $180^{\circ}$ at 30 kV after the initial phase distribution localized around $90^{\circ}$ and $300^{\circ}$ expanded to the whole phase angle according to the voltage rise. The Euclidean distance between the center of gravity and the discharge charge in the ${\Phi}-q$ cluster increased with increasing applied voltage.

Keywords

References

  1. N.C. Sahoo, M.M.A. Salama, R. Bartnikas, "Trends in partial discharge pattern classification: a survey," IEEE Trans DEIS, Vol.12, No.2, 2005, pp 248-264. https://doi.org/10.1109/TDEI.2005.1430395
  2. Suwarno, Y Suzuoki, F Komori, T Mizutani, "Partial discharges due to electrical treeing in polymers: phase-resolved and time-sequence observation and analysis," Journal of Physics D: Applied Physics, Vol.29, No.10, 1996, pp. 2922-2931. https://doi.org/10.1088/0022-3727/29/11/028
  3. P. Das, S. Chakravorti, "Studies on Partial Discharge Simulation Based on a Stochastic Model Considering the Variation of Discharge Area and Temperature of the Void Surface," International Journal for Computational Methods in Engineering Science and Mechanics, Vol.10, No.5, 2009, pp. 393-405. https://doi.org/10.1080/15502280903108008
  4. Min Wu, Hong Cao, Jianneng Cao, Hai-Long Nguyen, Joao Bartolo Gomes, Shonali Priyadarsini Krishnaswamy, "An overview of state-of-the-art partial discharge analysis techniques for condition monitoring," IEEE Electrical Insulation Magazine, Vol.31, No.6, 2015, pp. 22-35. https://doi.org/10.1109/MEI.2015.7303259
  5. Hong Seon Hack, Cho Kyung Soon, Yoon Jin Seob, "Embedded System Design with COS LoRa technology," Journal of the Korea Society of Digital Industry and Information Management, Vol.14, No.3, 2018, pp. 29-38. https://doi.org/10.17662/KSDIM.2018.14.3.029
  6. Raymond Wong Jee Keen, Illias Hazlee Azil, Bakar Ab Halim Abu, Mokhlis Hazlie, "Partial discharge classifications: Review of recent progress," Measurement, Vol.68, 2015, pp. 164-181. https://doi.org/10.1016/j.measurement.2015.02.032
  7. J.Z. Huang, M.K. Ng, Hongqiang Rong, Zichen Li, "Automated variable weighting in k-means type clustering," IEEE Trans PAMI, Vol.27, No.5, 2005, pp. 657-668. https://doi.org/10.1109/TPAMI.2005.95
  8. Hong Seon Hack, "Real Time Linux System Design," Journal of the Korea Society of Digital Industry and Information Management, Vol.10, No.2, 2014, pp. 13-20.
  9. Amin Mohebi, Saeed Aghabozorgi, Teh Ying Wah, Tutut Herawan, Ramin Yahyapour, "Iterative big data clustering algorithms," Software: Practice and Experience, Vol.46, No.1, 2015, pp. 107-129. https://doi.org/10.1002/spe.2341
  10. Hong Seon Hack, Cho Kyung Soon. "3D Scanning Embedded System Design," Journal of the Korea Society of Digital Industry and Information Management, Vol.13, No.4, 2017, pp. 49-56. https://doi.org/10.17662/ksdim.2017.13.1.049