DOI QR코드

DOI QR Code

Wavelet-like convolutional neural network structure for time-series data classification

  • Park, Seungtae (Department of Mechanical Engineering, Pohang University of Science and Technology) ;
  • Jeong, Haedong (Department of System Design and Control, Ulsan National Institute of Science and Technology) ;
  • Min, Hyungcheol (Korea Electric Power Corporation Research Institute) ;
  • Lee, Hojin (Department of Mechanical Engineering, Pohang University of Science and Technology) ;
  • Lee, Seungchul (Department of Mechanical Engineering, Pohang University of Science and Technology)
  • Received : 2017.05.08
  • Accepted : 2018.03.19
  • Published : 2018.08.25

Abstract

Time-series data often contain one of the most valuable pieces of information in many fields including manufacturing. Because time-series data are relatively cheap to acquire, they (e.g., vibration signals) have become a crucial part of big data even in manufacturing shop floors. Recently, deep-learning models have shown state-of-art performance for analyzing big data because of their sophisticated structures and considerable computational power. Traditional models for a machinery-monitoring system have highly relied on features selected by human experts. In addition, the representational power of such models fails as the data distribution becomes complicated. On the other hand, deep-learning models automatically select highly abstracted features during the optimization process, and their representational power is better than that of traditional neural network models. However, the applicability of deep-learning models to the field of prognostics and health management (PHM) has not been well investigated yet. This study integrates the "residual fitting" mechanism inherently embedded in the wavelet transform into the convolutional neural network deep-learning structure. As a result, the architecture combines a signal smoother and classification procedures into a single model. Validation results from rotor vibration data demonstrate that our model outperforms all other off-the-shelf feature-based models.

Keywords

Acknowledgement

Supported by : National Research Foundation of Korea, Small and Medium Business Administration, Korea Evaluation Institute of Industrial Technology

References

  1. Borghetti, A., Bosetti, M., Di Silvestro, M., Nucci, C.A. and Paolone, M. (2008), "Continuous-wavelet transform for fault location in distribution power networks: Definition of mother wavelets inferred from fault originated transients", IEEE T. Power Syst., 23(2), 380-388. https://doi.org/10.1109/TPWRS.2008.919249
  2. Chase Lipton, Z., Elkan, C. and Narayanaswamy, B. (2014), "Thresholding Classifiers to Maximize F1 Score", arXiv preprint arXiv:1402.1892.
  3. Chen, Z., Li, C. and Sanchez, R.V. (2015), "Gearbox fault identification and classification with convolutional neural networks", J. Shock Vib., 2015.
  4. Cui, Z., Chen, W. and Chen, Y. (2016), "Multi-scale convolutional neural networks for time series classification", arXiv preprint arXiv:1603.06995.
  5. Donoho, D.L. (1993), "Nonlinear wavelet methods for recovery of signals, densities, and spectra from indirect and noisy data", In Proceedings of Symposia in Applied Mathematics.
  6. Donoho, D L. (1993), "Unconditional bases are optimal bases for data compression and for statistical estimation", Appl. Comput. Harmon. A., 1(1), 100-115. https://doi.org/10.1006/acha.1993.1008
  7. Donoho, D.L. and Johnstone, I.M. (1994), "Ideal spatial adaptation by wavelet shrinkage", Biometrika, 425-455.
  8. Donoho, D.L. and Johnstone, I.M. (1995), "Adapting to unknown smoothness via wavelet shrinkage", J. Am. Statist. Sssociation, 90(432), 1200-1224. https://doi.org/10.1080/01621459.1995.10476626
  9. Donoho, D.L. and Johnstone, J.M. (1994), "Ideal spatial adaptation by wavelet shrinkage", Biometrika, 81(3), 425-455. https://doi.org/10.1093/biomet/81.3.425
  10. Gelman, L., Patel, T.H., Persin, G., Murray, B. and Thomson, A. (2013), "Novel technology based on the spectral kurtosis and wavelet transform for rolling bearing diagnosis", Int. J. Prognost. Health Management, 2153-2648.
  11. Gelman, L., Petrunin, I., Jennions, I.K. and Walters, M. (2012), "Diagnostics of local tooth damage in gears by the wavelet technology", Int. J. Prognost. Health Management, 3(52).
  12. He, K., Zhang, X., Ren, S. and Sun, J. (2016), "Deep residual learning for image recognition", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.
  13. Jaber, A.A. and Bicker, R. (2016), "Industrial robot backlash fault diagnosis based on discrete wavelet transform and artificial neural network", Am. J. Mech. Eng., 4(1), 21-31.
  14. Janssens, O., Slavkovikj, V., Vervisch, B., Stockman, K., Loccufier, M., Verstockt, S. and Van Hoecke, S. (2016), "Convolutional neural network based fault detection for rotating machinery", J. Sound Vib., 377, 331-345. https://doi.org/10.1016/j.jsv.2016.05.027
  15. Jeong, H., Park, S., Woo, S. and Lee, S. (2016), "Rotating machinery diagnostics u sing deep learning on orbit plot images", Procedia Manufact., 5, 1107-1118. https://doi.org/10.1016/j.promfg.2016.08.083
  16. Jung, U., and Koh, B. (2014), "Bearing fault detection through multiscale wavelet scalogram-based SPC", Smart Struct. Syst., 14(3), 377-395. https://doi.org/10.12989/sss.2014.14.3.377
  17. Korekado, K., Morie, T., Nomura, O., Ando, H., Nakano, T., Matsugu, M. and Iwata, A. (2003), "A convolutional neural network VLSI for image recognition using merged/mixed analog-digital architecture", In Knowledge-Based Intelligent Information and Engineering Systems, 169-176. Springer Berlin/Heidelberg.
  18. LeCun, Y., Boser, B., Denker, J.S., Henderson, D., Howard, R E., Hubbard, W. and Jackel, L.D. (1989), "Backpropagation applied to handwritten zip code recognition", Neural Comput., 1(4), 541-551. https://doi.org/10.1162/neco.1989.1.4.541
  19. Lipton, Z.C., Kale, D.C., Elkan, C. and Wetzell, R. (2015), "Learning to diagnose with LSTM recurrent neural networks", arXiv preprint arXiv:1511.03677.
  20. Matsugu, M., Mori, K., Mitari, Y. and Kaneda, Y. (2003), "Subject independent facial expression recognition with robust face detection using a convolutional neural network", Neural Networks, 16(5), 555-559. https://doi.org/10.1016/S0893-6080(03)00115-1
  21. Rafiee, J., Rafiee, M.A. and Tse, P.W. (2010), "Application of mother wavelet functions for automatic gear and bearing fault diagnosis", Exp. Syst. Appl., 37(6), 4568-4579. https://doi.org/10.1016/j.eswa.2009.12.051
  22. Rafiee, J., Tse, P.W., Harifi, A. and Sadeghi, M.H. (2009), "A novel technique for selecting mother wavelet function using an intelligent fault diagnosis system", Exp. Syst. Appl., 36(3), 4862-4875. https://doi.org/10.1016/j.eswa.2008.05.052
  23. Sawicki, J.T., Sen, A.K. and Litak, G. (2009), "Multiresolution wavelet analysis of the dynamics of a cracked rotor", Int. J. Rotat. Machinery, 2009.
  24. Williams, D.R.G.H.R. and Hinton, G.E. (1986), "Learning representations by back-propagating errors", Nature, 323(6088), 533-538. https://doi.org/10.1038/323533a0
  25. Zeiler, M.D. and Fergus, R. (2014), "Visualizing and understanding convolutional networks", In European conference on computer vision, 818-833.
  26. Zhang, L., Zhou, W. and Jiao, L. (2004), "Wavelet support vector machine", IEEE T. Syst. Man. Cy. B, 34(1), 34-39. https://doi.org/10.1109/TSMCB.2003.811113
  27. Zhou, C., Li, H., Li, D., Lin, Y. and Yi, T. (2013), "Online damage detection using pair cointegration method of time-varying displacement", Smart Struct. Syst., 12(3), 309-325. https://doi.org/10.12989/sss.2013.12.3_4.309