DETECTION OF HIGH IMPEDANCE FAULT USING A PROBABILISTIC NEURAL-NETWORK CLASSFIER

Sulaiman, Marizan and Ibrahim, Zulkifilie and Tawafan, Adnan (2013) DETECTION OF HIGH IMPEDANCE FAULT USING A PROBABILISTIC NEURAL-NETWORK CLASSFIER. Journal of Theoretical and Applied Information Technology, 53 (2). pp. 180-191. ISSN 1992-8645

[img] PDF
marizan#2.pdf

Download (421kB)

Abstract

In this paper, a simple and efficient method for detection high impedance fault (HIF) on power distribution systems using an intelligent approach the probabilistic neural network (PNN) combined with wavelet transform technique is proposed. A high impedance fault has impedance enough high so that conventional overcurrent devices, like overcurrent relays and fuses, cannot detect it. While low impedance faults, which include comparatively large fault currents are easily detected by conventional overcurrent devices. Both frequency and time data are needed to get the exact information to classify and detect no fault from HIF. In the proposed method, DWT is used to extract feature of the no fault and HIF signals. The features extracted which comprise the energy of detail and approximate coefficients of the voltage, current and power signals calculated at a chosen level frequency are utilized to train and test the probabilistic neural network (PNN) for a precise classification of no fault from HIFs.

Item Type: Article
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions: Faculty of Electrical Engineering > Department of Industrial Power
Depositing User: ENGR. PROFESOR DR. MARIZAN SULAIMAN
Date Deposited: 01 Aug 2013 07:28
Last Modified: 28 May 2015 03:43
URI: http://eprints.utem.edu.my/id/eprint/6552
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item