Title :
Recognition on ultra-high-frequency signals of partial discharge by support vector machine
Author :
Jiang, Tianyan ; Li, Jian ; Chen, Mingying ; Grzybowski, Stanislaw
Author_Institution :
State Key Lab. of Power Transm. Equip., Chongqing Univ., Chongqing, China
Abstract :
This paper presented a novel approach to recognize ultra-high-frequency (UHF) signals of partial discharges (PDs). Four artificial insulation defect models were designed to generate PD UHF signals, which were detected by a Peano fractal antenna in experiments. Wavelet packet (WP) decomposition was used to decompose PD UHF signals into multiple scales. A group of energy parameters and fractal dimensions of PD UHF signals were computed and used as the input parameters of a support vector machine (SVM), which was used as the PD pattern classifier. For verifying the results of this approach, a back-propagation neural network (BPNN) was also used for pattern recognition of PD UHF signals. The recognition results showed that the SVM and the proposed parameters were qualified for PD pattern recognition and the SVM had advantages over the BPNN for the purpose.
Keywords :
UHF antennas; UHF detectors; backpropagation; fractal antennas; neural nets; partial discharges; pattern classification; signal detection; support vector machines; PD UHF signals; PD pattern recognition; artificial insulation defect models; backpropagation neural network; fractal dimensions; partial discharge; pattern classifier; peano fractal antenna; support vector machine; ultra high frequency signal recognition; wavelet packet decomposition; Atmospheric modeling; Fractal antennas; Fractals; Insulation; Partial discharges; Pattern recognition; Support vector machines;
Conference_Titel :
High Voltage Engineering and Application (ICHVE), 2010 International Conference on
Conference_Location :
New Orleans, LA
Print_ISBN :
978-1-4244-8283-2
DOI :
10.1109/ICHVE.2010.5640783