A Dimension Reduction Method and its Application in GIS Partial Discharge Pattern Recognition Research

Abstract:

GIS partial discharge pattern recognition is an important part of its state evaluation, authors have set up 252kV GIS partial discharge detection simulation experiment platform based on UHF detection method, and designed four kinds of typical partial discharge models in laboratory, then established corresponding UHF signal mapping database through the experimental method, and also extracted the original feature parameters; because the original characteristic dimension is high, which is bad for pattern recognition, based on this, the article uses a species mean kernel principal component analysis method, it mapped the partial discharge original data samples to high-dimensional feature space, at first, it calculate all kinds of class mean vector data, and then do principal component analysis based on class mean vector space, build the class average kernel matrix, at last, the class kernel mean principal component analysis algorithm is established. Results show that characteristic of this method contained all the information of the original data, and dimension is less than GIS insulation defect category numbers, and it can realize data dimension reduction without information loss, which improve the pattern recognition rate.

• Periodical: Applied Mechanics and Materials (Volumes 602-605)
• Pages: 2105-2109
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.602-605.2105
• Online since: August 2014
• Authors: Fang Cheng Lv*, Hu Jin, Zi Jian Wang, Bo Zhang
• Keywords: Feature Extraction, Gas Insulated Switchgear (GIS), Non-Information Loss Dimension Reduction, Partial Discharge (PD)

References

[1] Si Wenrong, Li Junhao, Yuan Peng, et al. Detection and Identification Techniques for Multi-PD Sources in GIS. Proceedings of the CSEE, 2009, 29 (16): 119-125, in Chinese.

[2] JOLLIFFE I T. Principal Component Analysis. New York: Springer, (2002).

[3] G. Banfai, G. Philippovich. Experiences Gained in the Installation and Operation of Gas Insulated Substations for the 420 kV Grid. CIGRE Proceedings of the 32nd Session, Paris, France: CIGRE, 1988. 1~6.

[4] Masayuki Hikita, Shinya Ohtsuka, Junichi Wada, et al. Study of Partial Discharge Radiated Electromagnetic Wave Propagation Characteristics in an Actual 154 kV Model GIS. IEEE Transactions on Dielectrics and Electrical Insulation, 2012, 19 (1): 8-16.

DOI: 10.1109/tdei.2012.6148497

[5] WEI Yashi. Matrix-based Kernel Method for Large-scale Data Set. International Jourmal of Image. Graphics and Signal Processing, 2010, 2: 1-10.

DOI: 10.5815/ijigsp.2010.02.01

[6] XU Yong, DAVID Zhang, SONG Fengxi, et al. Amethod for Speeding Up Feature Extraction Based on KPCA. Neurocomputing, 2007, 70(4-6): 1056-1061.

DOI: 10.1016/j.neucom.2006.09.005

[7] ŽVOKELJ M, ZUPAN S, PREBIL I. Non-linear Multivariate and Multiscale Monitoring and Signal Denoising Strategy Using Kernel Principal Component Analysis Combined with Ensemble Empirical Mode Decomposition Method. Mechanical Systems and Signal Processing, 2011, 25(7): 2631-2653.

DOI: 10.1016/j.ymssp.2011.03.002