To achieve an effective feature extraction for power transformer vibration signals, the authors propose a method for signal feature extraction based on empirical wavelet transform (EWT) and multiscale entropy (MSE). First, transformer vibration signals are decomposed into several empirical wavelet functions (EWFs) with the method of EWT. Then, the frequency characteristics of signals are demonstrated in the time-frequency representation by applying a Hilbert transform to each EWF component. Finally, in order to quantify the extracted features, the MSEs of components being highly correlated with the original signals are calculated to construct the eigenvectors of transformer vibration signals. Several experiments are presented showing the effectiveness of this method compared with the classic empirical mode decomposition method.

References

1. 1)
  - 22. Ming, M., , Shaona, L., Haitao, M., et al: ‘Feature extraction method of motor imagery EEG based on DTCWT sample entropy’. Chinese Control Conf., Hangzhou, China, July 2015, pp. 3964–3968.
2. 2)
  - 21. Fu, L., He, Z.Y., Ro, Z.Q.: ‘Wavelet transform and approximate entropy based identification of faults in power swings’. IET 9th Int. Conf. on Developments in Power System Protection, Glasgow, UK, March 2008, pp. 590–594.
3. 3)
  - 12. Wang, J., Du, H., Guo, M.: ‘Feature extraction using HHT-based locally optimized short-time fractional Fourier transform for speaker recognition’. IEEE Int. Conf. on Imaging, Vision & Pattern Recognition (iclVPR), 2017, pp. 1–5.
4. 4)
  - 4. Ding, Q.L., Yuan, Y.M., Li, Z.: ‘A wavelet analysis of three-dimensional surface vibration signal of running power transformer’. 4th Int. Conf. on Intelligent System and Applied Material, Taiyuan, China, August 2014, pp. 634–637.
5. 5)
  - 15. Li, L., Zhu, Y., Song, Y.: ‘Feature extraction for vibration signal of transformer winding with multiple faults’, Electr. Power Autom. Equip., 2014, 34, (08), pp. 140–146.
6. 6)
  - 30. Wang, S., Huang, Y., Gong, L.: ‘Improved feature extraction using structured fisher discrimination sparse coding scheme for machinery fault diagnosis’, Adv. Mech. Eng., 2016, 8, (12), pp. 155–162.
7. 7)
  - 29. Yafei, J., Yongli, Z., Liuwang, W., et al: ‘Feature extraction and classification on partial discharge signals of power transformers based on VMD and multiscale entropy’, Trans. China Electrotech. Soc., 2016, 31, (19), pp. 208–216.
8. 8)
  - 25. Wu, S.-D., Wu, C.-W., Lin, S.-G., et al: ‘Feature extraction for bearing fault diagnosis using composite multiscale entropy’, IEEE/ASME Int. Conf. on Advanced Intelligent Mechatronics, Wollongong, NSW, Australia, 2013, pp. 1615–1618.
9. 9)
  - 18. Jerome, G.: ‘Empirical wavelet transform’, IEEE Trans. Signal Process., 2013, 61, (16), pp. 3999–4010.
10. 10)
  - 9. Wang, F., Cai, Y., Li, S.: ‘Fault feature extraction of diesel engine based on second generation wavelet and HHT’. 7th Int. Conf. on Mechatronics, Control and Materials (ICMCM), 2016, vol. 104, pp. 653–656.
11. 11)
  - 5. Evagoou, D., Kyprianou, A., Lewin, P.L., et al: ‘Feature extraction of partial discharge signals using the wavelet packet transform and classification with a probabilistic neural network’, IET Sci. Meas. Technol., 2010, 4, (3), pp. 177–192.
12. 12)
  - 2. Munir, B.S., Smit, J.J., Rinaldi, I.G.M.R.: ‘Diagnosing winding and core condition of power transformer by vibration signal analysis’. IEEE Int. Conf. on Condition Monitoring and Diagnosis, Bali, Indonesia, 2012, pp. 429–432.
13. 13)
  - 20. Pan, J., Chen, J., Zi, Y., et al: ‘Mono-component feature extraction for mechanical fault diagnosis using modified empirical wavelet transform via data-driven adaptive Fourier spectrum segment’, Mech. Syst. Signal Process., 2016, 72, (73), pp. 160–183.
14. 14)
  - 1. Saponara, S., Fanucci, L., Bernardo, F.: ‘Predictive diagnosis of high-power transformer faults by networking vibration measuring nodes with integrated signal processing’, IEEE Trans. Instrum. Meas., 2016, 65, (8), pp. 1749–1760.
15. 15)
  - 13. Canxun, D., Weihua, G., Zhikun, H.: ‘Empirical mode decomposition and Hilbert spectrum analysis based bearing faults diagnosis’. IET Int. Conf. on Information Science and Control Engineering, 2012, pp. 1–5.
16. 16)
  - 17. Singh, J., Darpe, A.K, Singh, S.P.: ‘Bearing damage assessment using Jensen-Renyi divergence based on EEMD’, Mech. Syst. Signal Process., 2017, 87, pp. 307–339.
17. 17)
  - 7. Kim, J.: ‘Discrete wavelet transform-based feature extraction of experimental voltage signal for Li-ion cell consistency’, IEEE Trans. Veh. Technol., 2016, 65, (3), pp. 1150–1161.
18. 18)
  - 11. Abdenour, S., Kamal, M., Noureddine, Z.: ‘Bearing health monitoring based on Hilbert–Huang transform, support vector machine, and regression’, IEEE J. Mag., 2015, 64, (1), pp. 52–62.
19. 19)
  - 10. Wu, S., Huang, W., Kong, F.: ‘Vibration features extraction of power transformer using a time-scale-frequency analysis method based on WPT and HHT’. 6th IEEE Int. Power Electronics and Motion Control Conf., 2009, pp. 1977–1981.
20. 20)
  - 27. Haikun, S., Jinsha, Y., Yu, W., et al: ‘Feature extraction for partial discharge based on cross-wavelet transform and correlation coefficient matrix’, Trans. China Electrotech. Soc., 2014, 29, (4), pp. 274–281.
21. 21)
  - 28. Zhang, K., Zhao, B., Ding, Q., et al: ‘Intrinsic mode selection of transformer vibration signal based on correlation coefficient’. 2015 IEEE Int. Conf. on Information and Automation, Li Jiang, China, October 2015, pp. 1953–1956.
22. 22)
  - 6. Mota, H.d.O., Vasconcelos, F.H., de Castro, C.L.: ‘A comparison of cycle spinning versus stationary wavelet transform for the extraction of features of partial discharge signals’, IEEE Trans. Dielectr. Electr. Insul., 2016, 23, (02), pp. 1106–1118.
23. 23)
  - 8. Hidayat, R., Kristomo, D., Togarma, I.: ‘Feature extraction of the Indonesian phonemes using discrete wavelet and wavelet packet transform’. 8th Int. Conf. on Information Technology and Electrical Engineering (ICITEE), 2016, pp. 6–11.
24. 24)
  - 14. Hongshan, Z., Fanhao, X., Wenqi, X., et al: ‘Feature extraction method of transformer vibration based on ensemble empirical mode decomposition sub-band’. 2016 IEEE Int. Conf. on Power System Technology (POWERCON), 2016, pp. 1–6.
25. 25)
  - 23. Costa, M., Goldberger, A. L., Peng, C.-K.: ‘Multiscale entropy to distinguish physiologic and synthetic RR time series’, Comput. Cardiol., 2002, 29, 137–140.
26. 26)
  - 19. Gilles, J., Heal, K.: ‘A parameterless scale-space approach to find meaningful modes in histograms-application to image and spectrum segmentation’, Int. J. Wavelets, Multiresolution Inf. Process., 2014, 12, (6), pp. 1–13.
27. 27)
  - 16. Ling, T., Lv, H., Yu, L.: ‘An EEMD-based multi-scale fuzzy entropy approach for complexity analysis in clean energy markets’, Appl. Soft Comput., 2017, 56, pp. 124–133.
28. 28)
  - 24. Li, H., Pan, H., Ren, H.: ‘High-speed automaton fault detection and diagnosis based on multivariate multiscale entropy’. Int. Conf. on Ubiquitous Robots and Ambient Intelligence, Xi'an, China, 2016, pp. 252–255.
29. 29)
  - 3. Wu, Z.-L., Zhu, Y.-L.: ‘Features of vibration signal of power transformer using local wave method’. Proc. Int. Conf. Machine Learning and Cybernetics, USA, 2009, pp. 388–393.
30. 30)
  - 26. King, F.W.: ‘Hilbert transforms: Encyclopedia of Mathematics and Its Application’ (Cambridge Univ. Press, Cambridge, UK, 2009).

Feature extraction of power transformer vibration signals based on empirical wavelet transform and multiscale entropy

References

Related content