Condition Monitoring of Rotating MachinesUsing Artificial Neural Networks andWavelet Transform

Type : Article de conférence
Auteur(s) :  A. Boudiaf, A. K. Moussaoui and S. E. A. Seddiki
Année :  2011
Domaine : Génie électrique
Conférence: International Conference on Signal, Image, Vision and their Applications SIVA’11
Résumé en PDF :  (résumé en pdf)
Fulltext en PDF :  (.pdf)
Mots clés :  Condition monitoring, Fault Diagnosis, ANN, wavelet, Vibration analysis, unbalance.

Résumé : 

This paper deals with the application ofArtificial Neural Network (ANN) and Wavelet Transform(WT) for the prediction of the effect of unbalance fault onthe frequency components of vibration signature ofrotating machines. The suggested Technique is applied to realvibratory signals resulting from sensors placed on a test riginterfaced to a multi-channel data acquisition system OROS 25.The characteristic features of frequency domain vibrationsignals have been used as inputs to the ANN. Thesuggested ANN prediction model was implemented usingBayesian Evidence based training algorithm. It is foundthat the Bayesian Evidence based approach is much moreefficient than other techniques, which results in anaccurate detection of unbalance fault signals in theconsidered rotating machine.