부분 방전의 안전도 평가를 위한 예측 모델 설계

A Study on the Design of Prediction Model for Safety Evaluation of Partial Discharge

  • 이수일 (목원대학교 지능정보융합학과) ;
  • 고대식 (목원대학교 전자공학과)
  • 투고 : 2020.08.28
  • 심사 : 2020.10.04
  • 발행 : 2020.10.05

초록

부분 방전 현상은 배전반, 트랜스포머, 스위치 기어 등 고압전력기기에서 많이 발생한다. 부분 방전은 절연체의 수명을 단축하고 절연파괴를 가져오게 되고 이로 인해 정전사고 등 대형피해가 발생하게 된다. 부분 방전 현상은 제품 내부에서 발생하는 경우와 표면에서 발생하는 여러 가지 유형을 가지고 있다. 본 논문에서는 부분 방전 현상에 대한 패턴 및 발생할 확률을 예측할 수 있는 예측 모델을 설계하는 것이다. 설계된 모델을 분석하기 위하여 부분 방전 현상을 발생시키는 시뮬레이터를 활용하여 각각의 부분 방전 유형에 대한 학습 데이터를 UHF 센서를 통하여 수집하였다. 본 논문에서 설계된 예측 모델은 딥 러닝 중 CNN을 기반으로 설계를 하였으며 학습을 통하여 모델을 검증하였다. 설계된 모델에 대한 학습을 위하여 5,000개의 훈련데이터를 만들었으며 훈련데이터의 형태는 UHF센서에서 입력되는 3차원의 원시데이터를 2차원 데이터로 전 처리하여 모델에 대한 입력데이터로 사용하였다. 실험결과, 학습을 통하여 설계된 모델에 대한 정확도는 0.9972의 정확도를 갖는 것을 알 수 있었으며 데이터를 2차원 이미지로 만들어 학습한 경우 보다 그레이 스케일 이미지 형태로 만들어 학습한 경우가 제안된 모델에 대해 정확도가 높음을 알 수 있었다.

Partial discharge occurs a lot in high-voltage power equipment such as switchgear, transformers, and switch gears. Partial discharge shortens the life of the insulator and causes insulation breakdown, resulting in large-scale damage such as a power outage. There are several types of partial discharge that occur inside the product and the surface. In this paper, we design a predictive model that can predict the pattern and probability of occurrence of partial discharge. In order to analyze the designed model, learning data for each type of partial discharge was collected through the UHF sensor by using a simulator that generates partial discharge. The predictive model designed in this paper was designed based on CNN during deep learning, and the model was verified through learning. To learn about the designed model, 5000 training data were created, and the form of training data was used as input data for the model by pre-processing the 3D raw data input from the UHF sensor as 2D data. As a result of the experiment, it was found that the accuracy of the model designed through learning has an accuracy of 0.9972. It was found that the accuracy of the proposed model was higher in the case of learning by making the data into a two-dimensional image and learning it in the form of a grayscale image.

키워드

참고문헌

  1. Mun-Gyu Choi, and Hanju Cha "The Noise Removal Methode of Partial Discharger Signal" The transactions of the Korean Institute of Electrical Engineers Vol 65. No. 8. pp. 1436~1441, 2016 https://doi.org/10.5370/KIEE.2016.65.8.1436
  2. T. TanaKa, "Internal Partial Discharge and Material Degradation" IEEE Transactions on Electrical Insulation, Vol. E1-21, pp. 899-905, 1986 https://doi.org/10.1109/TEI.1986.348999
  3. M.D. Judd, Li Yang, I.B.B. Hunter "Partial discharge monitoring of power transformers using UHF sensor. Part 1: sensor and signal interpretation" IEEE Insulation Magazine Vol. 21, pp.5-14, 2005
  4. Chang-Won Kang "Diagnosis of partial discharge of GIS and cubicle using electromagnetic waves", Instrumentation technology, pp 102-111, 2012
  5. Eun-Tae Ryu and Kyung-Rok Hwang, Jae-Ryong Jung, Hang-Jun Yang "Development of UHF sensor for partial discharger diagnosis of power transformer", KIEE Summer Conference 2011, pp20-22, 2011
  6. D. Aschenbrenner, H.-G. Kranz "On line PD measurements and diagnosis on power transformers" IEEE Transactions on Dielectrics and Electrical Insulation, Vol. 12, pp. 216-222, 2005 https://doi.org/10.1109/TDEI.2005.1430392
  7. Gyo-bum Chung and Sun-Geun Kwack "Comparison of Artificial Neural Network for Partial Discharge Diagnosis", Journal of the Korea Academia Industrial cooperation Society, Vol 14, No. 9, pp. 4455-4461, 2013 https://doi.org/10.5762/KAIS.2013.14.9.4455
  8. Eun-Sook Kang, Dae-Sik Ko "Automatic Classification Model of Electronic Documents Based on Machine Learning for Job Analysis", The Journal of Korean Institute of Information Technology, Vol. 17, No. 7, pp23-29, 2019 https://doi.org/10.14801/jkiit.2019.17.7.23
  9. Hui Song, Jiejie Dai, Gehao Sheng, Xiuchen Jiang "GIS partial discharge patten recognition via deep convolutional neural network under complex data source" IEEE Transactions on Dielectrics and Electrical Insulation, Vol. 25, pp. 678-685, 2018 https://doi.org/10.1109/TDEI.2018.006930
  10. Gwon-dong Lee, Juhyoung Maeng, Seokil Song "Mobility Mode Classification Method for Trajectory Data Using CNN" The Journal of Korean Institute of Information Technology, Vol 17,