Open AccessVolterra bound interval type‐2 fuzzy logic‐based approach for multiple power quality events analysis
Author(s) -
Kapoor Rajiv,
Kumar Rahul,
Tripathi Madan Mohan
Publication year - 2018
Publication title -
iet electrical systems in transportation
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.588
H-Index - 26
ISSN - 2042-9746
DOI - 10.1049/iet-est.2017.0054
Subject(s) - fuzzy logic , probabilistic logic , volterra series , interval (graph theory) , pattern recognition (psychology) , noise (video) , computer science , series (stratigraphy) , artificial neural network , type (biology) , support vector machine , power (physics) , artificial intelligence , nonlinear system , mathematics , algorithm , paleontology , physics , quantum mechanics , combinatorics , ecology , image (mathematics) , biology
This study demonstrates detection and classification of power quality (PQ) events utilising Volterra series for feature extraction and interval type‐2 fuzzy logic system (IT2FLS) for classification of PQ events. The Volterra series represented in the form of infinite power series with memory which provides a convenient and strong platform for representation of input–output relationship for non‐linear systems. IT2FLS uses the concept of membership functions to perform classification of multiple PQ events. When supply power is distorted by additive noise where signal‐to‐noise ratio is low and uncertain, IT2FLS has shown improved performance over support vector machine, neural networks (NNs), probabilistic NN and type‐1 fuzzy logic system classifiers, which makes an IT2FLS favourable for real‐time applications.