A Topological and Neural Based Technique for Classification of Faults in Induction Machines - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

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

, (1) , , , (2)
1
2
R. R. Kumar
  • Fonction : Auteur
M. Cirrincione
  • Fonction : Auteur
A. Tortella
  • Fonction : Auteur
M. Andriollo
  • Fonction : Auteur

Résumé

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.
Fichier non déposé

Dates et versions

hal-03631448 , version 1 (05-04-2022)

Identifiants

  • HAL Id : hal-03631448 , version 1

Citer

R. R. Kumar, G. Cirrincione, M. Cirrincione, A. Tortella, M. Andriollo. A Topological and Neural Based Technique for Classification of Faults in Induction Machines. 2018 21ST INTERNATIONAL CONFERENCE ON ELECTRICAL MACHINES AND SYSTEMS (ICEMS), Oct 2018, Jeju, South Korea. pp.653-658. ⟨hal-03631448⟩

Collections

U-PICARDIE LTI
5 Consultations
0 Téléchargements

Partager

Gmail Facebook Twitter LinkedIn More