Proceedings of the KIEE Conference (대한전기학회:학술대회논문집)

The Korean Institute of Electrical Engineers (대한전기학회)
권호 표지

A Study on High Impedance Fault Detection using Wavelet Transform and Neural-Network

웨이브릿 변환과 신경망 학습을 이용한 고저항 지락사고 검출에 관한 연구

  • Hong, Dae-Seung (Dept. of Control and Instrumentation Eng. Kwangwoon University) ;
  • Ryu, Chang-Wan (Dept. of Control and Instrumentation Eng. Kwangwoon University) ;
  • Ko, Jae-Ho (Dept. of Control and Instrumentation Eng. Kwangwoon University) ;
  • Yim, Wha-Yeong (Dept. of Control and Instrumentation Eng. Kwangwoon University)
  • 홍대승 (광운대학교 제어계측공학과) ;
  • 유창완 (광운대학교 제어계측공학과) ;
  • 고재호 (광운대학교 제어계측공학과) ;
  • 임화영 (광운대학교 제어계측공학과)
  • Published : 1999.07.19
Download PDF
⟨ Previous Next ⟩

Abstract

The analysis of distribution line faults is essential to the proper protection of power system. A high impedance fault(HIF) dose not make enough current to cause conventional protective device. It is well known that undesirable operating conditions and certain types of faults on electric distribution feeders cannot be detected by using conventional Protection system. This paper describes an algorithm using neural network for pattern recognition and detection of high impedance faults. Wavelet transform analysis gives the time-scale information. Time-scale representation of high impedance faults can detect easily and localize correctly the fault waveform.

Keywords