USP Electronic Research Repository

A Topological and Neural Based Technique for Classification of Faults in Induction Machines

Kumar, Rahul R. and Cirrincione, Giansalvo and Cirrincione, Maurizio and Tortella, A. and Andriollo, M. (2018) A Topological and Neural Based Technique for Classification of Faults in Induction Machines. [Conference Proceedings]

[img] PDF - Accepted Version
Restricted to Repository staff only

Download (600kB)

Abstract

This paper presents a data driven approach where at first the most significant features of the three phase current signal are analyzed and then a Curvilinear Component based analysis (CCA), which is a nonlinear manifold learning technique, is performed to compress and interpret the feature behaviour. Finally, a multi-layer perceptron network is used to develop a classifier. The effectiveness of the developed model is verified experimentally with data provided on-line and in real-time.

Item Type: Conference Proceedings
Subjects: T Technology > TA Engineering (General). Civil engineering (General)
T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions: School of Information Technology, Engineering, Mathematics and Physics (STEMP)
Depositing User: Fulori Nainoca - Waqairagata
Date Deposited: 27 Jan 2021 00:03
Last Modified: 24 Nov 2022 22:04
URI: http://repository.usp.ac.fj/id/eprint/12579
UNSPECIFIED

Actions (login required)

View Item View Item

Document Downloads

More statistics for this item...