High Voltage Equipment PD Pattern Recognition Based on BP Classifier

Article Preview

Abstract:

The corresponding discharge waveforms were detected by ultrasonic sensor. The dimension of feature vectors extracted from discharge waveforms were reduced by local linear embedding algorithm. The processed vectors were used as input to train and test BP_Adaboost classifier. Recognition results show that, high voltage reactor insulating defects recognition with this method can reduce the calculation and maintain a high recognition rate at the same time. This shows its effectiveness in the application of partial discharge pattern recognition.

You might also be interested in these eBooks

Info:

Periodical:

Pages:

99-103

Citation:

Online since:

February 2015

Export:

Price:

Permissions CCC:

Permissions PLS:

Сopyright:

© 2015 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

* - Corresponding Author

[1] Yan Yongl, i Yan Jun. Calculation and adjustment of pa-rameter coordination for field testwith power frequency se-ries resonance equipment [J]. High Voltage Apparatus, 2004, 40 (5): 391-393.

Google Scholar

[2] Quan Zhaochun, GuanGenzh, i YuanYongwu, eta. l Application of frequency tuned series resonance in dielectrictesting ofGIS [J]. High Voltage Apparatus, 2006, 42(3): 199-200.

Google Scholar

[3] Zhao Yanzhen, Ma Xiku. i Calculation of the reactancecharacteristic ofdry-type hal-f iron-core reactors [J]. Ad-vanced Technology ofElectricalEngineering and Energy, 2004, 23 (1): 68-71.

Google Scholar

[4] QiuYu, StephenA Sebo. Accurate evaluation of themag-netic field strength of large substation air-core reactor coils[J]. IEEE Trans. on Power Delivery, 1998, 13 (4): 1114-1119.

DOI: 10.1109/61.714470

Google Scholar

[5] Morisue T. Magnetic vector potential and electric scalarpotential in three dimensional eddy currentproblem [J]. IEEE Trans. onMagnetics, 1982, 18 (2): 531-535.

DOI: 10.1109/tmag.1982.1061856

Google Scholar

[6] WU Xiao-ting. Research on Data Dimensionality Reduction Algorithms Based on Manifold Learning[D]. Dalian: Liaoning Normal University, (2010).

Google Scholar