Abstract
Nonlinear fault responses are common in industrial systems yet cannot be effectively extracted by traditional feature extraction methods. In recent years, more techniques based on nonlinear dynamical system reconstruction are reported in the fault diagnosis and prognosis context. However, the key phrases researchers used vary from area to area, and it is difficult to locate the relevant papers. In this paper, we connect the related bearing fault diagnostics and prognostics literature in a short review. We propose a method for reconstructing dynamical system based on time-delay embedding and use it on bearing fault diagnostics. Based on one Wasserstein distance, the earth mover’s distance (EMD), we compare the reconstructed bearing vibration data with a baseline reconstruction from normal (healthy) bearing data to generate a severity index over time. Fault type assessment is performed by visualizing the distances between different reconstructed dynamical systems in a two-dimensional plot of the multidimensional scaling (MDS) results. We illustrate the proposed method with two laboratory bearing degradation datasets. We compare the trend with statistical features obtained from time and frequency domain, as well as the EMD trend without using phase space reconstruction. The EMD of reconstructions shows large difference between incipient faults and normal data, and then decreases to the normal bearing level. The EMD ratio is proposed as a fault severity indicator based on shape similarity information not available in the raw data features. The MDS results provide good visualization of the distances among time series for clustering and fault type diagnosis.
Similar content being viewed by others
References
Guo, F.W., Li, Y.B., Luo, Z.G.: Fault classification of rolling bearing based on reconstructed phase space and Gaussian mixture model. J. Sound Vib. 323(3), 1077–1089 (2009)
Farrar, C.R., Worden, K.: Structural Health Monitoring: A Machine Learning Perspective. Wiley, New York (2012)
Cabrera, J.: Applications of Dynamical Systems to the Statistical Analysis of Time Series. World Scientific, Singapore (1993)
Packard, N., Crutcheld, J., Farmer, J., Shaw, R.: Geometry from a time series. Phys. Rev. Lett. 45(9), 712 (1980)
Brock, W.A., Hommes, C.H.: Heterogeneous beliefs and routes to chaos in a simple asset pricing model. J. Econ. Dyn. Control 22(8–9), 1235–1274 (1998)
Muskulus, M., Verduyn-Lunel, S.: Wasserstein distances in the analysis of time series and dynamical systems. Phys. D Nonlinear Phenom. 240(1), 45–58 (2011)
West, B.J.: Fractal Physiology and Chaos in Medicine, vol. 16. World Scientific, Singapore (2013)
Whitney, H.: Differentiable manifolds. Ann. Math. 37(3), 645–680 (1936)
Takens, F.: Detecting strange attractors in turbulence. In: Takens, F. (ed.) Dynamical Systems and Turbulence, Warwick 1980, pp. 366–381. Springer, Berlin (1981)
Fraser, A.M., Swinney, H.L.: Independent coordinates for strange attractors from mutual information. Phys. Rev. A 33(2), 1134 (1986)
Kennel, M.B., Brown, R., Abarbanel, H.D.: Determining embedding dimension for phase-space reconstruction using a geometrical construction. Phys. Rev. A 45(6), 3403 (1992)
Logan, D., Mathew, J.: Using the correlation dimension for vibration fault diagnosis of rolling element bearings xi—basic concepts. Mech. Syst. Signal Process. 10(3), 241–250 (1996)
Logan, D.B., Mathew, J.: Using the correlation dimension for vibration fault diagnosis of rolling element bearings xii—selection of experimental parameters. Mech. Syst. Signal Process. 10(3), 251–264 (1996)
Jiang, J., Chen, J., Qu, L.: The application of correlation dimension in gearbox condition monitoring. J. Sound Vib. 223(4), 529–541 (1999)
Craig, C., Neilson, R., Penman, J.: The use of correlation dimension in condition monitoring of systems with clearance. J. Sound Vib. 231(1), 1–17 (2000)
Wong, K.L.: Application of very-high-frequency (VHF) method to ceramic insulators. IEEE Trans. Dielectr. Electr. Insul. 11(6), 1057–1064 (2004)
Todd, M., Nichols, J., Pecora, L., Virgin, L.: Vibration-based damage assessment utilizing state space geometry changes: local attractor variance ratio. Smart Mater. Struct. 10(5), 1000 (2001)
Torkamani, S., Butcher, E.A., Todd, M.D., Park, G.: Hyperchaotic probe for damage identification using nonlinear prediction error. Mech. Syst. Signal Process. 29, 457–473 (2012)
Wang, W., Chen, J., Wu, X., Wu, Z.: The application of some non-linear methods in rotating machinery fault diagnosis. Mech. Syst. Signal Process. 15(4), 697–705 (2001)
Janjarasjitt, S., Ocak, H., Loparo, K.: Bearing condition diagnosis and prognosis using applied nonlinear dynamical analysis of machine vibration signal. J. Sound Vib. 317(1), 112–126 (2008)
Feng, Z.P., Zuo, M.J., Chu, F.L., Xiao, C.Y.: Gear crack assessment using correlation dimension. Appl. Mech. Mater. 29, 1627–1633 (2010)
Yan, R., Gao, R.X.: Approximate entropy as a diagnostic tool for machine health monitoring. Mech. Syst. Signal Process. 21(2), 824–839 (2007)
Li, M., Xu, J., Yang, J., Yang, D., Wang, D.: Multiple manifolds analysis and its application to fault diagnosis. Mech. Syst. Signal Process. 23(8), 2500–2509 (2009)
Lv, Y., Zhang, H., Li, Y., Xiao, H., Wang, Z., Hou, S.: Bearing fault diagnosis based on weighted phase space reconstruction. In: 2010 International Conference on Digital Manufacturing and Automation (ICDMA), vol. 1, pp. 315–318. IEEE (2010)
Fan, B., Hu, N., Hu, L., Gu, F.: Application of phase space warping on damage tracking for bearing fault. J. Phys. Conf. Ser. 364, 012025 (2012)
Yan, R., Liu, Y., Gao, R.X.: Permutation entropy: a nonlinear statistical measure for status characterization of rotary machines. Mech. Syst. Signal Process. 29, 474–484 (2012)
Aydin, I., Karakose, M., Akin, E.: An approach for automated fault diagnosis based on a fuzzy decision tree and boundary analysis of a reconstructed phase space. ISA Trans. 53, 220–229 (2014)
Choy, F., Wang, L., Zhou, J., Braun, M.: Vibration monitoring and damage quantification of faulty ball bearings. J. Tribol. 127(4), 776–783 (2005)
Rafsanjani, A., Abbasion, S., Farshidianfar, A., Moeenfard, H.: Nonlinear dynamic modeling of surface defects in rolling element bearing systems. J. Sound Vib. 319(3), 1150–1174 (2009)
Yang, J., Zhang, Y., Zhu, Y.: Intelligent fault diagnosis of rolling element bearing based on svms and fractal dimension. Mech. Syst. Signal Process. 21(5), 2012–2024 (2007)
Ghafari, S., Golnaraghi, F., Ismail, F.: Effect of localized faults on chaotic vibration of rolling element bearings. Nonlinear Dyn. 53(4), 287–301 (2008)
Ng, S.S.Y., Cabrera, J., Tsui, K.L.: An application of dynamical system reconstruction from vibrations for bearing diagnostics and prognostics. In: Spring Research Conference on Systems Engineering and Management Science, SRC-SEMS 2014, SRC-31 (2014)
Kruskal, J.B.: Nonmetric multidimensional scaling: a numerical method. Psychometrika 29(2), 115–129 (1964)
Acknowledgments
The work described in this paper was partly supported by grants from the Research Grants Council of the Hong Kong Special Administrative Region, China (Project No. CityU_122513 and GRF CityU 11216014); CityU SRG (Project No. 7004085); and the National Natural Science Foundation of China (No. 11471275).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Ng, S.S.Y., Cabrera, J., Tse, P.W.T. et al. Distance-based analysis of dynamical systems reconstructed from vibrations for bearing diagnostics. Nonlinear Dyn 80, 147–165 (2015). https://doi.org/10.1007/s11071-014-1857-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11071-014-1857-4