Using Multivariate Statistics & Multi-Scale Entropy to Monitor Gears Degradation and Signal Denoising Strategy using Wavelet Decomposition

Type : Article de conférence
Auteur(s) :  S. AOUABDI
Année :  2016
Domaine : Sciences des matériaux
Conférence: 7th African Conference on Non Destructive Testing (ACNDT) & the 5th International Conference on NDT and Materials Industry and Alloys (IC-WNDT-MI)
Lieu de la conférence:  Oran, Algeria
Résumé en PDF :  (résumé en pdf)
Fulltext en PDF :  (.pdf)
Mots clés :  gear Fault diagnosis, Multi-scale entropy, Induction machine, Wavelet decomposition and principal component analysis.

Résumé : 

This paper focuses on fault diagnosis in gears transmissions driven by induction machines. A new tool of anomaly detection based on multi-scale entropy (MSE) algorithm in conjunction with multivariate statistical approach of the motor current signature analysis (MCSA) is proposed. Simulation results show that the proposed methods are able to detect tooth surface decay in the permanent regime of MCSA.