IEEJ Transactions on Power and Energy
Online ISSN : 1348-8147
Print ISSN : 0385-4213
ISSN-L : 0385-4213
Development of an Expert System for Analyzing Faults in Power Systems Using Artificial Neural Network Based Waveform Recognition
Yoshikazu FukuyamaYoshiteru UekiKazuhiro Kaneko
Author information
JOURNAL FREE ACCESS

1991 Volume 111 Issue 7 Pages 735-742

Details
Abstract
For system restoration in a power system, appropriate steps need to be taken in early stages to avoid social damage caused by insufficient power supply. The first step to be taken for restoration is to analyze the fault encountered, which is very important to determine a restoration operation.
Today, a large number of data are going to be available at the occurrence of fault because of the advanced communication system using digital relays and optical fibers. This system is intended to obtain the data of relays and CBs under operation and the data of voltage and current during the operating time and during the time of prefault and postfault.
This paper presents a hybrid fault analyzing expert system using data based on protective devices and phasor measurement. This system is a combination of an artificial neutral network (ANN) and an expert system. ANN is used to simplify the analyses of current and voltage waveform which are considered difficult due to a fault resistance and a line impedance. Since a fault waveform contains various ambiguous factors because of the natures of fault resistance, load current and others, use of ANN is effective for judgements.
Content from these authors
© The Institute of Electrical Engineers of Japan
Previous article Next article
feedback
Top