Feature Extraction and Classification of the Electric Current Signal of an Induction Motor for Condition Monitoring Purposes

Abstract:

A high availability of machines has always been important in production. One way to increase it is to avoid unscheduled production stops by detecting the onset of machine faults and to conduct preventative repairs. The detection part consists of the three steps signal acquisition, feature extraction and classification. This paper focuses on the last two steps through the example of an induction motor. Based on a publicly available motor current data set, features were extracted using the continuous wavelet transform. In the subsequent classification step eight different classification methods were compared with each other. It was found, that the accuracy of the classifiers varied significantly in a range from 20.6 % to 92.8 %. Moreover, the supportive vector machine, scoring an accuracy of 92.8 %, was the only classifier with an accuracy above 55.0 %.

• Periodical: Applied Mechanics and Materials (Volume 856)
• Pages: 244-251
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.856.244
• Online since: November 2016
• Authors: Christian Gebbe*, Christin Tran, Florian Lingenfelser, Johannes Glasschröder, Gunther Reinhart
• Keywords: Classification, Condition Monitoring, Machine Learning, Motor Current Signal Analysis

References

[1] A. K. Jardine, D. Lin, D. Banjevic (2006). A review on machinery diagnostics and prognostics implementing condition-based maintenance. Mechanical systems and signal processing, 20(7), 1483-1510.

DOI: 10.1016/j.ymssp.2005.09.012

[2] A. Siddique, G. S. Yadava, B. Singh, (2005). A review of stator fault monitoring techniques of induction motors. IEEE transactions on energy conversion, 20(1), 106-114.

DOI: 10.1109/tec.2004.837304

[3] S. Nandi, H. A. Toliyat, X. Li, (2005). Condition monitoring and fault diagnosis of electrical motors-a review. IEEE transactions on energy conversion, 20(4), 719-729.

DOI: 10.1109/tec.2005.847955

[4] W. T. Thomson, M.  Fenger, (2001). Current signature analysis to detect induction motor faults. IEEE Industry Applications Magazine, 7(4), 26-34.

DOI: 10.1109/2943.930988

[5] C. Lessmeier, O. Enge-Rosenblatt, C. Bayer, D. Zimmer, Data Acquisition and Signal Analysis from Measured Motor Currents for Defect Detection in Electromechanical Drive Systems.

[6] F. Gu, Y. Shao, N. Hu, A. Naid, A. D. Ball, (2011). Electrical motor current signal analysis using a modified bispectrum for fault diagnosis of downstream mechanical equipment. Mechanical Systems and Signal Processing, 25(1), 360-372.

DOI: 10.1016/j.ymssp.2010.07.004

[7] A. Soualhi, G. Clerc, H. Razik, (2013). Detection and diagnosis of faults in induction motor using an improved artificial ant clustering technique. IEEE Transactions on Industrial Electronics, 60(9), 4053-4062.

DOI: 10.1109/tie.2012.2230598

[8] M. Akar, I. Cankaya, (2012). Broken rotor bar fault detection in inverter-fed squirrel cage induction motors using stator current analysis and fuzzy logic. Turkish Journal of Electrical Engineering & Computer Sciences, 20(Sup. 1), 1077-1089.

DOI: 10.3906/elk-1102-1050

[9] R. J. Povinelli, M. T. Johnson, A. C. Lindgren, J. Ye, (2004). Time series classification using Gaussian mixture models of reconstructed phase spaces. IEEE Transactions on Knowledge and Data Engineering, 16(6), 779-783.

DOI: 10.1109/tkde.2004.17

[10] G. J. Janacek, A. J. Bagnall, M. Powell, (2005, May). A likelihood ratio distance measure for the similarity between the fourier transform of time series. In Pacific-Asia Conference on Knowledge Discovery and Data Mining (pp.737-743.

DOI: 10.1007/11430919_85

[11] M. Bator, A. Dicks, U. Mönks, V. Lohweg, (2014, October). Feature Extraction and Reduction Applied to Sensorless Drive Diagnosis. In Proceedings. 22. Workshop Computational Intelligence, Dortmund, 6. -7. Dezember 2012 (p.163.

[12] C. D. Avanzo, V. Tarantino, P. Bisiacchi, G. Sparacino, (2009). A wavelet methodology for EEG time-frequency analysis in a time discrimination task. International Journal of Bioelectromagnetism, 11(4), 185-188.

[13] D. Cvetkovic, E. D. Übeyli, I. Cosic, (2008). Wavelet transform feature extraction from human PPG, ECG, and EEG signal responses to ELF PEMF exposures: A pilot study. Digital signal processing, 18(5), 861-874.

DOI: 10.1016/j.dsp.2007.05.009

[14] P. Ghorbanian, D. M. Devilbiss, A. J. Simon, A. Bernstein, T. Hess, H. Ashrafiuon, (2012, October). Continuous wavelet transform EEG features of Alzheimer's disease. In ASME 2012 5th Annual Dynamic Systems and Control Conference joint with the JSME 2012 11th Motion and Vibration Conference (pp.567-572.

DOI: 10.1109/embc.2012.6346579

[15] E. Ayaz, A. Öztürk, S. Seker, B. R. Upadhyaya, (2009).

[16] C. J. Li, J. Ma, (1997). Wavelet decomposition of vibrations for detection of bearing-localized defects. Ndt & E International, 30(3), 143-149.

DOI: 10.1016/s0963-8695(96)00052-7

[17] S. Natarajan, P.G. Sreenath (2015). Wavelet analysis in fault diagnosis of spur bevel gearbox. International Research Journal of Coputer Science (2): 8-19.

[18] W. J. Wang, P. D. McFadden, (1996). Application of wavelets to gearbox vibration signals for fault detection. Journal of sound and vibration, 192(5), 927-939.

DOI: 10.1006/jsvi.1996.0226

[19] I. Ben-Gal, (2005). Outlier detection. In Data mining and knowledge discovery handbook (pp.131-146). Springer US.

DOI: 10.1007/0-387-25465-x_7

[20] H. P. Kriegel, P. Kröger, A. Zimek, (2010). Outlier detection techniques. In Tutorial at the 16th ACM international conference on knowledge discovery and data Mining (SIGKDD), Washington, DC.

DOI: 10.1145/1401890.1401946

[21] V. J. Hodge, J. Austin, (2004). A survey of outlier detection methodologies. Artificial intelligence review, 22(2), 85-126.

DOI: 10.1023/b:aire.0000045502.10941.a9

[22] C. C. Aggarwal, (2015). Outlier analysis. In Data Mining (pp.237-263). Springer International Publishing.

[23] K. L. Priddy, P. E.  Keller, (2005). Artificial neural networks: an introduction (Vol. 68). SPIE Press.