USP Electronic Research Repository

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

Kumar, R. 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 (586Kb)

    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 12:03
    Last Modified: 27 Jan 2021 12:03
    URI: http://repository.usp.ac.fj/id/eprint/12579
    UNSPECIFIED

    Actions (login required)

    View Item

    Document Downloads

    More statistics for this item...