Data Dimension Reduction and Visualization with Application to Multi-Dimensional Gearbox Diagnostics Data: Comparison of Several Methods

Article Preview

Abstract:

In recent years we face the growing interest in building automated diagnosis systems detecting ‘normal’ or ‘abnormal’ functioning of a system. But little is known about the distribution and shape of the data describing 'normal' functioning. The shape of the data is of paramount importance in determining the mathematical model of the data serving for the diagnosis. We got real industrial data by gathering vibration signals of a gearbox working in a mine excavator operating in time-varying conditions. The main considered problems are: what is the shape of the recorded 15-dimensional data and what kind of outliers may be found there We have used for this purpose pseudo grand tour, PCA and simple auto-associative neural network. The methods used proved to be very effective in answering our questions.

You might also be interested in these eBooks

Info:

Periodical:

Solid State Phenomena (Volume 180)

Pages:

177-184

Citation:

Online since:

November 2011

Export:

Price:

[1] J. Antoni: Cyclostationarity by examples in Mechanical Systems and Signal Processing, 23/4, (2009), pp.987-1036

DOI: 10.1016/j.ymssp.2008.10.010

Google Scholar

[2] T. Barszcz, R.B. Randall: Application of spectral kurtosis for detection of a tooth crack in the planetary gear of a wind turbine in Mechanical Systems and Signal Processing, 23, (2009), pp.1352-1365

DOI: 10.1016/j.ymssp.2008.07.019

Google Scholar

[3] A. Grzadziela: An analysis of possible assessment of hazards to ship shaft line, resulting from impulse load, in Polish Maritime Research, 14/3, (2007), pp.12-20

DOI: 10.2478/v10012-007-0013-1

Google Scholar

[4] E.P. de Moura, C.R. Souto, A.A. Silva, M.A.S. Irmao: Evaluation of principal component analysis and neural network performance for bearing fault diagnosis from vibration signal processed by RS and DF analyses in Mechanical Systems and Signal Processing, 25, (2011), pp.1765-1772

DOI: 10.1016/j.ymssp.2010.11.021

Google Scholar

[5] W. Bartelmus, R. Zimroz: A new feature for monitoring the condition of gear- boxes in non-stationary operating systems in Mechanical Systems and Signal Processing, 23/5, (2009), pp.28-1534

DOI: 10.1016/j.ymssp.2009.01.014

Google Scholar

[6] Cz. Cempel: Multidimensional condition monitoring of mechanical systems in Operation, Mechanical Systems and Signal Processing, 17/6, (2003), pp.1291-1303

DOI: 10.1006/mssp.2002.1573

Google Scholar

[7] Cz. Cempel, M. Tabaszewski: Multidimensional condition monitoring of machines in nonstationary operation in Mechanical Systems and Signal Processing, 21/3, (2007), pp.1233-1241

DOI: 10.1016/j.ymssp.2006.04.001

Google Scholar

[8] W.J. Staszewski: Wavelet data compression and feature selection for vibration analysis Journal of Sound and Vibration, 211/5, (1998), pp.735-760

DOI: 10.1006/jsvi.1997.1380

Google Scholar

[9] P.D. Samuel, D.J. Pines: A review of vibration-based techniques for helicopter transmission diagnostics in Journal of Sound and Vibration, 282/1-2, (2005), pp.475-508

DOI: 10.1016/j.jsv.2004.02.058

Google Scholar

[10] R. Zimroz, W. Bartelmus: Gearbox condition estimation using cyclo-stationary properties of vibration signal in Key Engineering Materials, 413-414, (2009), pp.471-478

DOI: 10.4028/www.scientific.net/kem.413-414.471

Google Scholar

[11] J. Dybala, S. Radkowski: Geometrical method of selection of features of diagnostic signals in Mechanical Systems and Signal Processing, 21/2, (2007), pp.761-779

DOI: 10.1016/j.ymssp.2005.10.011

Google Scholar

[12] A. Bartkowiak, R. Zimroz: Outliers in vibration signals of two planetary gearboxes working in non-stationary operating conditions - a case study 9th Int. Conf. DAMAS 2011, Univ. of Oxford, UK, in Journal of Physics: Conference Series (JPCS), (2011), in press

Google Scholar

[13] D. Asimov: The grand tour: a tour for viewing multidimensional data in SIAM Journal of Scientific and Statistical Computing, 6, (1985), pp.128-143

DOI: 10.1137/0906011

Google Scholar

[14] E.J. Wegman, J. Shen: Three-dimensional Andrews plots and the grand tour, Proceedings of the 25th Symposium on the Interface, San Diego, Ca, in Computing Science and Statistcs, 25, (1993), pp.284-288

Google Scholar

[15] W. Martinez, A. Martinez: Exploratory Data Analysis with MATLAB. Chapman and Hall/CRC, Boca Raton, London (2004)

Google Scholar

[16] I.T. Jolliffe: Principal Component Analysis. 2nd Edition, Springer, New York (2002)

Google Scholar

[17] Q. He, R. Yan, F. Kong, R. Du: Machine condition monitoring using principal component representations in Mechanical Systems and Signal Processing, 23/2, (2009), pp.446-466

DOI: 10.1016/j.ymssp.2008.03.010

Google Scholar

[18] K. Worden, W.J. Staszewski, J.J. Hensman: Natural computing for mechanical system research: A tutorial overview in Mechanical Systems and Signal Processing, 25, (2011), pp.4-111

DOI: 10.1016/j.ymssp.2010.07.013

Google Scholar

[19] C.M. Bishop: Neural Networks for Pattern Recognition. Clarendon Press, Oxford UK (1995)

Google Scholar

[20] I.T. Nabney: Netlab, Algorithms for Pattern Recognition. 2nd printing, Springer, London (2003)

Google Scholar