Although Ensemble empirical mode decomposition (EEMD) method has been successfully applied to various applications, features extracted using EEMD could not detect anomalies for roller bearings, especially when anomalies includes small defects. In this study a novel feature extraction method is proposed to detect the state of roller bearings. Performance improved EEMD, which is a reliable adaptive method to calculate an appropriate noise amplitude is applied to decompose the acceleration signals into zero-mean components called intrinsic mode functions (IMFs). Then, three dimensional feature vectors are created by applying the Teager-Kaiser energy operator (TKEO) to the first three IMFs. The novel features obtained from the healthy bearing signals are utilized to construct the separating hyperplane using one-class support vector machine (SVM). In order to validate the method proposed, a number of operating conditions (shaft speed and load) are considered to generate the data (vibration signals) by means of an assembled test rig. It is shown that the proposed method can successfully identify the states of the new samples (healthy and faulty). The uncertainty of the model prediction is investigated computing Margin and the number of support vectors. It create less complex (less fraction of support vectors) and more reliable (higher Margin) hyperplane than the EEMD method.
anomaly detection, feature extraction, One-Class SVM, Roller bearing, ensemble empirical mode decomposition (EEMD), Teager-Kaiser energy operator (TKEO)
Feng, Z., Wang, T., Zuo, M., Chu, F., & Yan, S. (2011).
Teager energy spectrum for fault diagnosis of rolling element bearings, Journal of Physics: Conference Series, vol. 305, 012129.
Huang, N., et al. (1998). The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis, Proceedings of the Royal Society of London, vol. 454, pp. 903-995.
Junsheng, C., Dejie, Y., & Yu, Y. (2007). The application of energy operator demodulation approach based on EMD in machinery fault diagnosis, Mechanical systems and signal processing, vol. 21, pp. 668-677.
Kaiser, J. (1990). On a simple algorithm to calculate the energy of a signal, Proceedings of international Conference on Acoustics, speech and signal processing, April 3-6.
Kwak, D., Lee, D., Ahn, J., & Koh, B. (2014), Fault detection of roller-bearings using signal processing and optimization algorithms, Sensors: SA Transactions, vol. 14(1), pp. 283-298.
Lei, Y., Lin, J., He, Z., & Zuo, M. (2013). A review on empirical mode decomposition in fault diagnosis of rotating machinery, Mechanical Systems and Signal Processing, vol. 35, pp. 108-126.
Li, H., Fu, L., & Zhang, Y. (2009). Bearing fault diagnosis based on Teager energy operator demodulation technique, Proceedings of Measuring technology and mechatronics automation Conference, April 11-12.
Li, H., Zheng, H., & Tang, L. (2009). Bearing fault detection and diagnosis based on Teager-Huang transform, International Journal of wavelets multiresolution and information Processing, vol. 7 (5), pp. 643-663.
Liu, H., Wang, J., & Lu, C. (2013), Rolling bearing fault detection based on the Teager energy operator and Elman neural network, Mathematical problems in engineering, vol. 10, Article ID 498385.
Maragos, P., Kaiser, J.F., & Quatieri, T.F. (1993A), On amplitude and frequency demodulation using energy operators, IEEE Transactions on Signal Processing, vol. 41, pp. 1532-1550.
Maragos, P., Kaiser, J.F., & Quatieri, T.F. (1993B), Energy separation in signal modulations with application to speech analysis, IEEE Transactions on Signal Processing, vol. 41(10), pp. 3024-3051.
Randall, R.B., & Antoni, J. (2011). Rolling element bearing diagnostics – A tutorial, Mechanical Systems and Signal Processing, vol. 25, pp. 485-520.
Rodriguez, P., Alonso, J., Ferrer, M., & Travieso, C. (2013), Application of the Teager-Kaiser energy operator in bearing fault diagnosis, ISA Transactions, vol. 52, pp. 278-284.
Scholkopf, B., Williamson, R., Smola, A., Taylor, J.S., & Platt, J. (2000), Support vector method for novelty detection, Advances in Neural Information Processing Systems, vol. 12, pp. 582-586.
Shin, H.J., Eom, D-H., & Kim, S-S. (2005), One-class support vector machines - an application in machine fault detection and classification, Computer and Industrial Engineering, vol. 48, pp. 395-408.
Tabrizi, A., Garibaldi, L., Fasana, A., & Marchesiello, S. (2014), Influence of stopping criterion for sifting process of Empirical Mode Decomposition technique (EMD) on roller bearing fault diagnosis, Advances in Condition Monitoring of Machinery in Non-Stationary Operations, Springer-Verlag (DEU), pp. 389-398, doi: 10.1007/978-3-642-39348-8_33.
Tabrizi, A., Garibaldi, L., Fasana, A., & Marchesiello, S. (2015A), Performance improvement of ensemble empirical mode decomposition for roller bearings damage detection, Shock and vibration, Article ID 964805, In Press.
Tabrizi, A., Garibaldi, L., Fasana, A., & Marchesiello, S. (2015B). Early damage detection of roller bearings using wavelet packet decomposition, ensemble empirical mode decomposition and support vector machine, Meccanica, vol. 50 (30), pp. 865-874, doi: 10.1007/s11012-014-9968-z.
Teager, H. (1980). Some observations on oral air flow during phonation. Acoustics, speech and signal processing, vol. 28 (5), pp. 599-601.
Vapnik, A.V.N. (1995), The nature of statistical learning theory, Springer, Berlin.
Widodo, A., & Yang, B. (2007), Support vector machine in machine condition monitoring and fault and diagnosis, Mechanical Systems and Signal Processing, vol. 21, pp.2560-2574.
Wu, Z. & Huang, N. (2009). Ensemble Empirical Mode Decomposition: A noise-assisted data analysis method, Advances in Adaptive Data Analysis, vol. 1(1), pp. 1-41.