Open AccessMultiple features extraction and selection for detection and classification of stator winding faults
Author(s) -
Haroun Smail,
Seghir Amirouche Nait,
Touati Said
Publication year - 2018
Publication title -
iet electric power applications
Language(s) - English
Resource type - Journals
ISSN - 1751-8679
DOI - 10.1049/iet-epa.2017.0457
Subject(s) - stator , redundancy (engineering) , pattern recognition (psychology) , induction motor , classifier (uml) , feature extraction , computer science , feature selection , support vector machine , artificial neural network , artificial intelligence , fault detection and isolation , signal processing , engineering , electronic engineering , digital signal processing , mechanical engineering , electrical engineering , voltage , actuator , operating system
In this study, a new effective approach for detection and classification of stator winding faults in induction motors is presented. The approach is based on current analysis. It uses multiple features extraction techniques, where Park transform, zero crossing time signal, and the envelope are extracted from the three‐phase stator currents. Then, statistical features are calculated from time and frequency domains of each extracted signal. The Features selection techniques (ReliefF, minimum redundancy and max relevancy, and support vector machine approach based on recursive feature elimination) are used to select from the extracted features the most relevant ones. As a classifier, the self‐organising map neural network is used. The proposed procedure is experimentally studied using stator current signals obtained from various faulty cases and a healthy induction motor at different load variations. The experimental results verify that the proposed strategy is able to distinguish the faulty cases from the healthy ones. Also, it effectively identifies the faulty phase in addition to the extent of the fault.