Induction machine faults detection based on a constant false alarm rate detector - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

Induction machine faults detection based on a constant false alarm rate detector

Résumé

This paper proposes a new method for fault detection in three-phase induction machines based on the stator current measurements. The proposed detection method is based on the hypothesis testing. Specifically, this paper investigates a binary detection problem: the machine is healthy or faulty. The Generalized Likelihood Ratio Test (GLRT) is used to address this statistical detection problem with unknown signal and noise parameters. This proposed detector is a Constant False Alarm Rate (CFAR) detector. The decision is obtained according to a threshold, which is set to reach a desired false alarm probability. To implement this detector, four estimations based one the Maximum-Likelihood-Estimator (MLE) are required: model order, frequency, phase and amplitude estimations. Frequencies are estimated by Total Least Squares-Estimation of Signal Parameters via Rotational Invariance Techniques (TLS-ESPRIT). Two types of faults are considered: bearing and broken rotor bars faults. Experimental tests clearly show the effectiveness of the proposed detector.
Fichier principal
Vignette du fichier
IECON2016_Trachi.pdf (546.42 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01449096 , version 1 (30-01-2017)

Identifiants

Citer

Youness Trachi, Elhoussin Elbouchikhi, Vincent V. Choqueuse, Tianzhen Wang, Mohamed Benbouzid. Induction machine faults detection based on a constant false alarm rate detector. IECON, Oct 2016, Florence, Italy. pp.6359 - 6363, ⟨10.1109/IECON.2016.7793928⟩. ⟨hal-01449096⟩
174 Consultations
289 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More