Open AccessPower quality disturbance classification employing S‐transform and three‐module artificial neural network
Author(s) -
Naik Chirag A.,
Kundu Prasanta
Publication year - 2014
Publication title -
international transactions on electrical energy systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.428
H-Index - 42
ISSN - 2050-7038
DOI - 10.1002/etep.1778
Subject(s) - harmonics , voltage sag , swell , power quality , artificial neural network , voltage , engineering , classifier (uml) , artificial intelligence , control theory (sociology) , pattern recognition (psychology) , computer science , electric power system , white noise , transient (computer programming) , electronic engineering , power (physics) , electrical engineering , telecommunications , physics , quantum mechanics , oceanography , control (management) , geology , operating system
SUMMARY A new technique employing S‐transform (ST)‐based features, a three‐module artificial neural network and a final rule‐based classifier is proposed in this paper for the identification and classification of power quality disturbances. To validate the proposed method, various short duration disturbances such as voltage sag, voltage swell, momentary interruption, harmonics, oscillatory transient and impulsive transient, defined in terms of their spectral content, duration and magnitude by IEEE 1159–2009 standards, are used. In addition, simultaneous disturbances such as voltage sag with harmonics, voltage swell with harmonics and voltage sag with impulsive transients are also used. Further, the performance of the proposed system is evaluated in the noisy environment with the addition of Gaussian white noise in the aforementioned signals. The proposed three‐module ANN structure has less training requirements, higher accuracy and enhanced ability to classify simultaneous disturbances. The distinct capabilities of extracted features from ST, the three‐module ANN and final rule base classifier enable the proposed system to identify and classify both single and simultaneous disturbances effectively. Copyright © 2013 John Wiley & Sons, Ltd.