Comparison between sound perception and self-organizing maps in the monitoring of the bearing degradation

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.

[1]  Ying Wei,et al.  Data-driven bearing fault identification using improved hidden Markov model and self-organizing map , 2018, Comput. Ind. Eng..

[2]  Hamzaoui Nacer,et al.  Subjective evaluations of sound radiated by impacted plates, using the design of experiments method , 2010 .

[3]  Zhi-li Zhao,et al.  Vibration control of a pneumatic driven piezoelectric flexible manipulator using self-organizing map based multiple models , 2016 .

[4]  John Vanderkooy,et al.  The Great Debate: Subjective Evaluation , 1980 .

[5]  Anas Sakout,et al.  Evaluation of the acoustic comfort of air-treatment systems with a multi-task procedure , 2012 .

[6]  S. Winsberg,et al.  A multidimentional technique for sound quality assessment , 1999 .

[7]  Wolfgang Ellermeier,et al.  Using probabilistic choice models to investigate auditory unpleasantness , 2004 .

[8]  Teuvo Kohonen,et al.  Self-organized formation of topologically correct feature maps , 2004, Biological Cybernetics.

[9]  Wei Liang,et al.  Dynamic degradation observer for bearing fault by MTS–SOM system , 2013 .

[10]  Sanjay H Upadhyay,et al.  Bearing performance degradation assessment based on a combination of empirical mode decomposition and k-medoids clustering , 2017 .

[11]  B J McDermott,et al.  Multidimensional analyses of circuit quality judgments. , 1969, The Journal of the Acoustical Society of America.

[12]  M.N.S. Swamy,et al.  Neural Networks and Statistical Learning , 2013 .

[13]  T. Kohonen.  Self-organized formation of topographically correct feature maps , 1982 .

[14]  Ville-Veikko Mattila.  Ideal Point Modelling of Speech Quality in Mobile Communications Based on Multidimensional Scaling (MDS) , 2002 .

[15]  Tomomichi Suzuki,et al.  Evaluating adaptive paired comparison experiments , 2010 .

[16]  Jay Lee,et al.  Robust performance degradation assessment methods for enhanced rolling element bearing prognostics , 2003, Adv. Eng. Informatics.

[17]  Etienne Parizet,et al.  Noise assessment in a high-speed train , 2002 .

[18]  Sebastian Möller,et al.  An instrumental measure for end-to-end speech transmission quality based on perceptual dimensions: framework and realization , 2008, INTERSPEECH.

[19]  Gérard Dreyfus,et al.  Neural networks - methodology and applications , 2005 .

[20]  Dimitrios Moshou,et al.  Dynamic muscle fatigue detection using self-organizing maps , 2005, Appl. Soft Comput..

[21]  Yannis Papanikolaou,et al.  Denoising Autoencoder Self-Organizing Map (DASOM) , 2018, Neural Networks.

[22]  Nacer Hamzaoui,et al.  Experimental study of real gear transmission defects using sound perception , 2015 .