A Topological Neural-Based Scheme for Classification of Faults in Induction Machines - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue IEEE Transactions on Industry Applications Année : 2021

A Topological Neural-Based Scheme for Classification of Faults in Induction Machines

, (1) , (2) , ,
1
2
Rahul R. Kumar
  • Fonction : Auteur
Andrea Tortella
  • Fonction : Auteur
Mauro Andriollo
  • Fonction : Auteur

Résumé

This article presents a data-driven approach for the classification of faults in induction machines. The designed scheme involves newly engineered features extracted from the line current signals, which provides an improved fault discrimination. For this purpose, a topological-based fast projection technique (curvilinear component analysis) is used as a tool to reduce the dimensionality of the data and interpret the feature behavior. Consequently, a shallow convolutional neural network has been designed to classify the three-phase stator current signals. Experimental tests at different operating conditions have assessed the procedure, confirming its effectiveness and suitability for online and real-time diagnostics.
Fichier non déposé

Dates et versions

hal-03631431 , version 1 (05-04-2022)

Identifiants

Citer

Rahul R. Kumar, Giansalvo Cirrincione, Maurizio Cirrincione, Andrea Tortella, Mauro Andriollo. A Topological Neural-Based Scheme for Classification of Faults in Induction Machines. IEEE Transactions on Industry Applications, 2021, 57 (1), pp.272-283. ⟨10.1109/TIA.2020.3032944⟩. ⟨hal-03631431⟩

Collections

U-PICARDIE LTI
4 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook Twitter LinkedIn More