A Method for Anomaly Detection for Non-stationary Vibration Signatures



Published Oct 14, 2013
Renata Klein


Vibration signatures contain information regarding the health status of the machine components. One approach to assess the health of the components is to search systematically for a list of specific failure patterns, based on the physical specifications of the known components (e.g. the physical specifications of the bearings, the gearwheels or the shafts). It is possible to do so, since the manifestation of the possible failures in the vibration signature is known a priory. The problem is that such a list is not comprehensive, and may not cover all possible failures. The manifestation of some failure modes in the vibration signature may be less investigated or even unknown. In addition, when more than one component is malfunctioning, unexpected patterns may be generated. Anomaly detection tackles the more general problem: How can one determine that the vibration signatures indicate abnormal functioning when the specifics of the abnormal functioning or its manifestation in the vibration signatures are not known a priori? In essence, anomaly detection completes the diagnostics of the predefined failure modes. In many complex machines (e.g. turbofan engines), the task of anomaly detection is further complicated by the fact that changes in operating conditions influence the vibration sources and change the frequency and amplitude characteristics of the signals, making them non-stationary. Because of that, joint time-frequency representations of the signals are desired. This is different from other vibration based diagnostic techniques, which are designated for stationary signals, and often focus on either the time domain or the frequency domain.

For the purpose of this article, we will refer as TFR (time- frequency representation) to all 3D representations which employ on one axis either time, or cycles, or RPM, and on the other axis either frequency, or order. The proposed method suggests a solution for anomaly detection by analysis of various TFRs of the vibration signals (primarily

the RPM-order domain).In the first stage, TFRs of healthy machines are used to create a baseline. The TFRs can be obtained using various methods (Wigner-Ville, wavelets, STFT, etc). In the next stage, the distance TFR between the inspected recording and the baseline is computed. In the third stage, the distance TFR is analyzed and the exceptional regions in the TFR are found and characterized. A basic classification of the anomaly type is suggested. The different stages of analysis: creating baselines, computing the distance TFR, identifying the exception regions, are illustrated with actual data.

How to Cite

Klein, R. . (2013). A Method for Anomaly Detection for Non-stationary Vibration Signatures. Annual Conference of the PHM Society, 5(1). https://doi.org/10.36001/phmconf.2013.v5i1.2250
Abstract 214 | PDF Downloads 200



anomaly detection, health monitoring, TFR

Antoni, J. & Randall, R. B., (2002). Differential Diagnosis of Gear and Bearing Faults, Journal of Vibration and Acoustics, Vol. 124 pp165-171, April 2002.
Polyshchuk, V. V., Choy, F. K. & Braun, M. J., (2002). Gear Fault Detection with Time-Frequency Based Parameter NP4, International Journal of Rotating Machinery, 8(1), 57-70, 2002.
Juluri, N. & Swarnamani, S., (2003). Improved accuracy of Fault Diagnosis of Rotating Machinery using Wavelet De-noising and Feature Selection, Proceedings of ASME Turbo Expo 2003, Power for Land, Sea and Air, June 16-19, 2003, Atlanta, Georgia, USA.
Antoni, J., Bonnardot, F., Raad, A. & El Badaoui, M., (2004). Cyclostationary modeling of rotating machine vibration signals, Mechanical Systems and Signal Processing 18 (6), pp. 1285-1314, 2004.
Yang, W. X. & Ren, X. M., (2004)., Detecting Impulses in Mechanical Signals by Wavelets, EURASIP journal on Applied Signal Processing, pp 1156-1162, 2004.
Bradford, S. C., (2006). Time-Frequency Analysis of Systems with Changing Dynamic Properties, Ph.D. Thesis, California Institute of Technology, Pasadena, California, 2006.
Huillery, J., Millioz, F. & Martin, N., (2008). On the description of spectrogram Probabilities with a Chi- Squared Law, IEEE Transactions on Signal Processing 56, 6 (2008) pp. 2249-2258.
Sawalhi, N. & Randall, R. B., (2008). Localised fault diagnosis in rolling element bearings in gearboxes, Proceedings of The Fifth International Conference on Condition Monitoring and Machinery Failure Prevention Technologies – CM/MFPT, 2008.
Clifton, D. A. & Tarassenko, L., (2009). Novelty detection in jet engine vibration spectra, Proceedings of the 6th International Conference on Condition Monitoring and Machine Failure Prevention Technologies, 2009.
Klein, R., Rudyk, E., Masad, E. & Issacharoff, M., (2009). Emphasizing bearing tones for prognostics, The Sixth International Conference on Condition Monitoring and Machinery Failure Prevention Technologies, pp. 578- 587, 2009.
Bechhoefer, E., He, D. & Dempsey, P., (2011). Gear health threshold setting based on probability of false alarm, Proceedings of the Annual Conference of the Prognostics and Health Management Society, 2011.
Klein, R., Masad, E., Rudyk, E. & Winkler, I. (2011). Bearing diagnostics using image processing methods, Proceedings of Surveillance 6, Compiegne, October 2011.
Klein, R., Rudyk, E. & Masad, E. (2012). Bearing diagnostics in non-stationary environment, International Journal of Condition Monitoring, March 2012.
Hazan, A., Verleysen, M., Cottrell, M., Lacaille, J. & Madani, K. (2012). Probabilistic outlier detection in vibration spectra with small learning dataset, Mechanical Systems and Signal Processing, 2012.
Hazan, A. & Madani, K., (2013). Frequency-Dependent Peak-Over-Threshold algorithm for fault detection in the spectral domain, ESANN 2013, Bruges: Belgium, 2013.
Technical Research Papers

Most read articles by the same author(s)