Extreme value statistics for vibration spectra outlier detection

The issue of detecting abnormal vibrations from spectra is tackled in this article, when little is known about the mechanical behavior of the system, or the fault pattern. To do so, an original algorithm relying on the statistics of the maximum of log-periodograms is introduced. Receiver Operator Characteristic (ROC) curves are built and show good performance with bearing deterioration even when little wear is present.

[1]  S. Kay.  Fundamentals of statistical signal processing: estimation theory , 1993 .

[2]  Steven Kay,et al.  Fundamentals Of Statistical Signal Processing , 2001 .

[3]  David A. Clifton,et al.  Condition Monitoring of Gas-Turbine Engines , 2006 .

[4]  L. Tarassenko,et al.  Novelty detection in jet engines , 1999 .

[5]  E. Gumbel,et al.  Statistics of extremes , 1960 .

[6]  Sameer Singh,et al.  Novelty detection: a review - part 2: : neural network based approaches , 2003, Signal Process..

[7]  David A. Clifton,et al.  Novelty detection in jet engine vibration spectra , 2009 .

[8]  B Ng.  Survey of Anomaly Detection Methods , 2006 .

[9]  M. Farid Golnaraghi,et al.  Assessment of Gear Damage Monitoring Techniques Using Vibration Measurements , 2001 .

[10]  Robert P. W. Duin,et al.  Novelty Detection Using Self-Organizing Maps , 1997, ICONIP.

[11]  Peter W. Tse,et al.  Detection of the rubbing-caused impacts for rotor–stator fault diagnosis using reassigned scalogram , 2005 .

[12]  Michel Verleysen,et al.  Bayesian inference for outlier detection in vibration spectra with small learning dataset , 2011 .

[13]  Sameer Singh,et al.  Novelty detection: a review - part 1: statistical approaches , 2003, Signal Process..

[14]  L. Tarassenko,et al.  Bayesian Extreme Value Statistics for Novelty Detection in Gas-Turbine Engines , 2008, 2008 IEEE Aerospace Conference.

[15]  David A. Clifton,et al.  Novelty Detection with Multivariate Extreme Value Statistics , 2011, J. Signal Process. Syst..

[16]  Hai Qiu,et al.  Wavelet filter-based weak signature detection method and its application on rolling element bearing prognostics , 2006 .