DOI QR코드

DOI QR Code

Fault diagnostic system for rotating machine based on Wavelet packet transform and Elman neural network

  • Youk, Yui-su (College of Engineering, School of Electronics & Information Engineering, Kunsan National University) ;
  • Zhang, Cong-Yi (College of Engineering, School of Electronics & Information Engineering, Kunsan National University) ;
  • Kim, Sung-Ho (College of Engineering, School of Electronics & Information Engineering, Kunsan National University)
  • Received : 2009.06.10
  • Accepted : 2009.09.10
  • Published : 2009.09.30

Abstract

An efficient fault diagnosis system is needed for industry because it can optimize the resources management and improve the performance of the system. In this study, a fault diagnostic system is proposed for rotating machine using wavelet packet transform (WPT) and elman neural network (ENN) techniques. In most fault diagnosis for mechanical systems, WPT is a well-known signal processing technique for fault detection and identification. In previous work, WPT can improve the continuous wavelet transform (CWT) used over a longer computing time and huge operand. It can also solve the frequency-band disagreement by discrete wavelet transform (DWT) only breaking up the approximation version. In the experimental work, the extracted features from the WPT are used as inputs in an Elman neural network. The results show that the scheme can reliably diagnose four different conditions and can be considered as an improvement of previous works in this field.

Keywords

Acknowledgement

Supported by : Korea Science and Engineering Foundation(KOSEF)

References

  1. F. Hlawatsch and G. F. Boudreaux-Bartels, "Linear and quadratic time frequency signal representations," lEEE Signal Processing Mag. vol. 9, pp. 21-67, Apr. 1992 https://doi.org/10.1109/79.127284
  2. O. Rioul and M. Vetterli, "Wavelets and signal processing," IEEE Signal Processing Mag. vol. 8, pp.14-38, Oct. 1991
  3. C.J. Li , & J. Ma,. "Wavelet decomposition of vibrations for detection of bearing-localized defects." NDT&E Inlernalional, vol. 30, pp. 143-149.1997 https://doi.org/10.1016/S0963-8695(96)00052-7
  4. C. K. Sung, H. M. Tai, & C. W. Chen, "Locating defects of a gear system by the technique of wavelet transform.", Mechanism and Machine Theory, vol. 35, pp. 1169-1182. 2000 https://doi.org/10.1016/S0094-114X(99)00045-2
  5. H. Zheng, Z, Li, & X, Chen, "Gear fault diagnosis based on continuous wavelet transfoml.", Mechanical Syslem and Signal Processing, vol. 16, pp. 447-457 2002 https://doi.org/10.1006/mssp.2002.1482
  6. C. Li , Z. Song & P. Li, "Bearing fault detection via wavelet packet transform and rough set ttheory." Proceedings of Fifth World Congress on lnlelligenl Control and Aulomalion, vol. 2, pp. 1663-1666, 2004
  7. E. Ortiz, & V. Syrmos, "Support vector machines and wavelet packet analysis for fau lt detection and identification", IJCNN 06. lnlernalional Joint Conference on Neural Networks, pp. 3449- 3456, 2006
  8. G. G. Yen & K. C. Lin, "Wavelet packet feature extraction for vibration monitoring", IEEE Transactions on Industrial Electronics, vol. 47, pp. 650-667, 2000 https://doi.org/10.1109/41.847906
  9. http ://www.bearcave.com/misVmisl_tech/wavelets/packfreq/index.html
  10. X. Z. Gao and S. J . Ovaska, "Genetic algorithm traning of Elman neural network in motor fault detection", Neural Compuling and Applicalions, vol. 11, no. 1, pp. 37-44, 2002 https://doi.org/10.1007/s005210200014