The fusion of classifier outputs to improve partial discharge classification

Abstract

The detection of partial discharge signals and classifying its patterns is an area of interest in the analysis of defects in high voltage cables. This paper investigates a filter-bank based approach to extract frequency domain based features to represent partial discharge signals. By applying the fast Fourier transform, the sampled partial discharge data are mapped into equivalent discrete frequency bins, which are then grouped into N equal sub-bands and also octave sub-bands, each providing N-dimensional features for partial discharge pattern classification. Two classifiers, namely, the support vector machine and the sparse representation classifier, are implemented and their outputs are fused, in order to improve the accuracy of classifying partial discharge. Classification accuracy is also compared with wavelet domain based octave frequency sub-band features.

Keywords

partial discharge / features / fusion / classification

References

[1] Hao L, Lewin P L. Partial discharge source discrimination using a support vector machine. IEEE Transactions on Dielectrics and Electrical Insulation, 2010, 17(1): 189-197

[2] Sriram S, Nitin S, Prabhu K M M, Bastiaans M J. Signal denoising techniques for partial discharge measurements. IEEE Transactions on Dielectrics and Electrical Insulation, 2005, 12(6): 1182-1191

[3] Kyprianou A, Lewin P L, Efthymiou V, Stavrou A, Georghiou G E. Wavelet packet de-noising for online partial discharge detection in cables and its application to experimental field results. Measurement Science and Technology, 2006, 17(9): 2367-2379

[4] Ambikairajah R, Phung B T, Ravishankar J, Blackburn T R, Liu Z. Smart sensors and online condition monitoring of high voltage cables for the smart grid. In: Proceedings of the Fourteenth International Middle East Power Systems Conference (MEPCON). 2010, 807-811

[5] Ambikairajah R, Phung B T, Ravishankar J, Blackburn T R, Liu Z. Novel frequency domain features for the pattern classification of partial discharge signals. In: Proceedings of the XVII International Symposium on High Voltage Engineering. 2011, Paper F-044

[6] Kuncheva L, Bezdek J C, Duin R P W. Decision templates for multiple classifier fusion: an experimental comparison. Pattern Recognition, 2001, 34(2): 299-314

[7] Evagorou D, Kyprianou A, Lewin P L, Stavrou A, Efthymiou V, Metaxas A C, Georghiou G E. Feature extraction of partial discharge signals using the wavelet packet transform and classification with a probabilistic neural network. IET Science, Measurement and Technology, 2010, 4(3): 177-192

[8] Ma X, Zhou C, Kemp I J. Interpretation of wavelet analysis and its application in partial discharge detection. IEEE Transactions on Dielectrics and Electrical Insulation, 2002, 9(3): 446-457

[9] Wright J, Yang A Y, Ganesh A, Sastry S S, Ma Y. Robust face recognition via sparse representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(2): 210-227

[10] Elad M. Sparse and Redundant Representations. New York, NY: Springer, 2009

[11] Mohimani G H, Babaie-Zadeh M, Jutten C. Fast sparse representation based on smoothed L0 norm. In: Proceedings of the Seventh International Conference on Independent Component Analysis and Signal Separation. 2007, 389-396

[12] Kanevsky D, Sainath T N, Ramabhadran B, Nahamoo D. An analysis of sparseness and regularization in exemplar-based methods for speech classification. In: Proceedings of Interspeech 2010. 2010, 2842-2845

RIGHTS & PERMISSIONS

Higher Education Press and Springer-Verlag Berlin Heidelberg