Comparison between sound perception and self-organizing maps in the monitoring of the bearing degradation
- PDF / 1,090,918 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 78 Downloads / 149 Views
ORIGINAL ARTICLE
Comparison between sound perception and self-organizing maps in the monitoring of the bearing degradation Saiefeddine Alia 1 & Rachid Nasri 1 & Ikhlas Meddour 2,3 & Ramdane Younes 3,4 Received: 6 May 2020 / Accepted: 27 August 2020 # Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract This study aims to monitor and detect bearing defects from measured signals on a wind turbine during 50 operating days using two methods. The first method involves a perceptual approach to classify the selected signals based on 50 measurements. The second method used is an unsupervised classification method called the Self-Organizing Map (SOM). Overall, the perceptive approach proved to be simple and effective compared to conventional methods of treatment and diagnosis of defects, as listeners were able to classify the selected sounds in the order of bearing degradation, allowing the severity of the bearing defect to be tracked. Furthermore, the neural classifier provided relevant information on the evolution of bearing degradation, as it could automatically cluster the vibration signal into four groups corresponding to the bearing life stages. Thus, these results can effectively contribute to well-timed maintenance decisions. In addition, the advantages and deficiencies of one method over the other are briefly discussed in this paper. Keywords Sound perception . Bearing defect . Self-organizing maps . Wind turbine . Defect diagnosis . Conditional monitoring
1 Introduction All operating systems generate vibratory and acoustic signals that have the same generating mechanism. The monitoring of a working machine is carried out by analyzing the vibration or acoustic signals. The combination of vibratory and acoustic methods allows to define a vibro-acoustic methods, including a variety of areas with very different approaches and techniques. As far as sound perception is concerned, an uncertainty appears as a consequence of individual variability. The sound perception is, therefore, a matter of physiological acoustics although all laws defining the psychological
* Ramdane Younes [email protected] 1
Laboratoire Mécanique Appliquée et Ingénierie MAI, Ecole Nationale d’Ingénieurs de Tunis- ENIT, BP 37, Le Belvedere, 1002 Tunis, Tunisia
2
Ecole Nationale Supérieure de Technologie, Dergana Bordj El Kiffan, Algiers, Algeria
3
Mechanics and Structures Laboratory, Université8 Mai 1945 Guelma, BP 401, 24000 Guelma, Algeria
4
Mechanical Engineering Department, Badji Mokhtar University, P.O. Box 12, 23000 Annaba, Algeria
relationships between physical quantities and sensations are statistical, and the limits of validity appear as soon as the uncertainty becomes greater than the measured phenomenon. During operation, electromechanical equipment and machines generate vibrations and noise that human beings perceive and interpret. People who listen to a working machine associate, necessarily, the generated noise with the object that transmits it. This property, thanks to the evolution of new techniques, has
Data Loading...
