Neural network architectures for fault diagnosis and parameter recognition in induction machines

Author

Filippetti, F. ; Uncini, A. ; Piazza, C. ; Campolucci, P. ; Tassoni, C. ; Franceschin, G.

Author_Institution

Dipartimento di Ingegneria Elettrica, Bologna Univ., Italy

Volume

1

fYear

1996

fDate

13-16 May 1996

Firstpage

289

Abstract

This paper presents a neural network that is able to give, together with the rotor fault diagnosis, the combined rotor-load inertia momentum of an induction machine. The inputs of the network are the spectral components of machine input currents, speed and torque. A specific neural network architecture containing new fast spline-based neurons with improved generalisation capabilities has been used. The training set is obtained by a faulted machine dynamical model as simulator

Keywords

digital simulation; electric machine analysis computing; fault diagnosis; generalisation (artificial intelligence); induction motors; learning (artificial intelligence); neural nets; rotors; splines (mathematics); faulted machine dynamical model; generalisation capabilities; machine input currents; machine speed; machine torque; neural network architectures; parameter recognition; rotor fault diagnosis; rotor-load inertia momentum; spline-based neurons; training set; Artificial neural networks; Electrical fault detection; Fault diagnosis; Frequency; Induction machines; Intelligent networks; Neural networks; Spline; Stators; Torque;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrotechnical Conference, 1996. MELECON '96., 8th Mediterranean

Conference_Location

Bari

Print_ISBN

0-7803-3109-5

Type

conf

DOI

10.1109/MELCON.1996.551542

Filename

551542