Data Piecewise Linear Approximation for Bearings Degradation Monitoring

In this paper, we propose a method based on piecewise linear approximation (PLA) with segmented projection error (SPE) to reveal the underlying correlation structures and approximate multivariate time series. Based on this method we elaborate an indicator called vector of segmented projection error (VSPE) to characterize the bearings degradation using standard time domain standard features extracted from the vibration signal. The indicator VSPE monitors the evolution of the entire degradation process efficiently and provides real-time information on bearings degradation. We show the effectiveness of this new indicator using benchmark data. The results reveal the sensitive and monotonic character of the indicator VSPE according to the bearings degradation, which is promising for monitoring bearings on their lifespan.

[1]  D. E. Roberts,et al.  The Upper Tail Probabilities of Spearman's Rho , 1975 .

[2]  Takashi Hiyama,et al.  Predicting remaining useful life of rotating machinery based artificial neural network , 2010, Comput. Math. Appl..

[3]  W. Marsden.  I and J , 2012 .

[4]  Shaojiang Dong,et al.  Bearing degradation process prediction based on the PCA and optimized LS-SVM model , 2013 .

[5]  Kondo H. Adjallah,et al.  Bearings Degradation Monitoring Indicator Based on Segmented Hotelling T Square and Piecewise Linear Representation , 2018, 2018 IEEE International Conference on Mechatronics and Automation (ICMA).

[6]  Daming Lin,et al.  A review on machinery diagnostics and prognostics implementing condition-based maintenance , 2006 .

[7]  Brigitte Chebel-Morello,et al.  Accurate bearing remaining useful life prediction based on Weibull distribution and artificial neural network , 2015 .

[8]  Brigitte Chebel-Morello,et al.  PRONOSTIA : An experimental platform for bearings accelerated degradation tests. , 2012 .

[10]  Lin Ma,et al.  Machinery Condition Prognosis Using Multivariate Analysis , 2006 .

[11]  Jong-Myon Kim,et al.  Estimating the remaining useful life of bearings using a neuro-local linear estimator-based method. , 2017, The Journal of the Acoustical Society of America.

[12]  Noureddine Zerhouni,et al.  Remaining useful life estimation based on nonlinear feature reduction and support vector regression , 2013, Eng. Appl. Artif. Intell..

[13]  Eamonn J. Keogh,et al.  An online algorithm for segmenting time series , 2001, Proceedings 2001 IEEE International Conference on Data Mining.

[14]  A. P,et al.  Mechanical Vibrations , 1948, Nature.

[15]  S. Qin,et al.  Selection of the Number of Principal Components: The Variance of the Reconstruction Error Criterion with a Comparison to Other Methods† , 1999 .

[16]  A. C. Rencher.  Methods of multivariate analysis , 1995 .