Intelligent classification of three phase fault and voltage collapse for correct distance relay operation using support vector machine

Ahmad Farid Abidin, Azah Mohamed, Hussain Shareef

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

The conventional techniques used in distance relay operation are not fast enough in distinguishing between a three phase fault and voltage collapse and this may lead to unintended tripping of protection devices. Therefore, there is a need for fast detection of voltage collapse so as to improve the reliability of distance relay operation. This paper presents an intelligent approach to classify a voltage collapse and a three phase fault for distance relay operation by using the under impedance fault detector and support vector machine (SVM). To illustrate the proposed approach, simulations were carried out on the IEEE 39 bus test system using the PSS/E software. Test results shows that the proposed approach can accurately detect and classify fault and voltage collapse events for correct distance relay operation. To demonstrate the effectiveness of the SVM, a comparison is made with the results obtained from the application of the probabilistic neural network.

Original languageEnglish
Pages (from-to)623-631
Number of pages9
JournalInternational Review on Modelling and Simulations
Volume5
Issue number2
Publication statusPublished - 2012

Fingerprint

Relay
Support vector machines
Support Vector Machine
Fault
Voltage
Electric potential
Classify
Probabilistic Neural Network
Test System
Impedance
Detector
Detectors
Neural networks
Software
Demonstrate
Simulation

Keywords

  • Distance relay
  • Fault and voltage collapse
  • Support vector machine (SVM)
  • Under impedance fault detector

ASJC Scopus subject areas

  • Modelling and Simulation
  • Electrical and Electronic Engineering
  • Mechanical Engineering
  • Chemical Engineering(all)

Cite this

@article{c5a725cca999456899bf24a085072012,
title = "Intelligent classification of three phase fault and voltage collapse for correct distance relay operation using support vector machine",
abstract = "The conventional techniques used in distance relay operation are not fast enough in distinguishing between a three phase fault and voltage collapse and this may lead to unintended tripping of protection devices. Therefore, there is a need for fast detection of voltage collapse so as to improve the reliability of distance relay operation. This paper presents an intelligent approach to classify a voltage collapse and a three phase fault for distance relay operation by using the under impedance fault detector and support vector machine (SVM). To illustrate the proposed approach, simulations were carried out on the IEEE 39 bus test system using the PSS/E software. Test results shows that the proposed approach can accurately detect and classify fault and voltage collapse events for correct distance relay operation. To demonstrate the effectiveness of the SVM, a comparison is made with the results obtained from the application of the probabilistic neural network.",
keywords = "Distance relay, Fault and voltage collapse, Support vector machine (SVM), Under impedance fault detector",
author = "Abidin, {Ahmad Farid} and Azah Mohamed and Hussain Shareef",
year = "2012",
language = "English",
volume = "5",
pages = "623--631",
journal = "International Review on Modelling and Simulations",
issn = "1974-9821",
publisher = "Praise Worthy Prize",
number = "2",

}

TY - JOUR

T1 - Intelligent classification of three phase fault and voltage collapse for correct distance relay operation using support vector machine

AU - Abidin, Ahmad Farid

AU - Mohamed, Azah

AU - Shareef, Hussain

PY - 2012

Y1 - 2012

N2 - The conventional techniques used in distance relay operation are not fast enough in distinguishing between a three phase fault and voltage collapse and this may lead to unintended tripping of protection devices. Therefore, there is a need for fast detection of voltage collapse so as to improve the reliability of distance relay operation. This paper presents an intelligent approach to classify a voltage collapse and a three phase fault for distance relay operation by using the under impedance fault detector and support vector machine (SVM). To illustrate the proposed approach, simulations were carried out on the IEEE 39 bus test system using the PSS/E software. Test results shows that the proposed approach can accurately detect and classify fault and voltage collapse events for correct distance relay operation. To demonstrate the effectiveness of the SVM, a comparison is made with the results obtained from the application of the probabilistic neural network.

AB - The conventional techniques used in distance relay operation are not fast enough in distinguishing between a three phase fault and voltage collapse and this may lead to unintended tripping of protection devices. Therefore, there is a need for fast detection of voltage collapse so as to improve the reliability of distance relay operation. This paper presents an intelligent approach to classify a voltage collapse and a three phase fault for distance relay operation by using the under impedance fault detector and support vector machine (SVM). To illustrate the proposed approach, simulations were carried out on the IEEE 39 bus test system using the PSS/E software. Test results shows that the proposed approach can accurately detect and classify fault and voltage collapse events for correct distance relay operation. To demonstrate the effectiveness of the SVM, a comparison is made with the results obtained from the application of the probabilistic neural network.

KW - Distance relay

KW - Fault and voltage collapse

KW - Support vector machine (SVM)

KW - Under impedance fault detector

UR - http://www.scopus.com/inward/record.url?scp=84865584387&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84865584387&partnerID=8YFLogxK

M3 - Article

VL - 5

SP - 623

EP - 631

JO - International Review on Modelling and Simulations

JF - International Review on Modelling and Simulations

SN - 1974-9821

IS - 2

ER -