"

Cookies ussage consent

Our site saves small pieces of text information (cookies) on your device in order to deliver better content and for statistical purposes. You can disable the usage of cookies by changing the settings of your browser. By browsing our site without changing the browser settings you grant us permission to store that information on your device.

I agree, do not show this message again.

Application of learning vector quantization for estimating size and position of metallic particle adhering to spacer in GIS

YASIN KHAN1,*

Affiliation

  1. Department of Electrical Engineering, College of Engineering, King Saud University, P.O. Box. 800, Riyadh 11421, Kingdom of Saudi Arabia

Abstract

Metallic particle is the most harmful material in the perspective of Gas-Insulated Substation (GIS) reliability. It creates defects in GIS, especially in the weakest areas, i.e. the triple junction, by initializing partial discharges (PDs) which can lead to the failure of GIS. Therefore, the investigation of PD characteristics and particle size and position on the spacer surface are indispensable in the efforts of improving the reliability of GIS equipments. In this paper, learning vector quantization (LVQ) was employed to recognize various PD signal patterns provoked by different particle sizes and positions on the spacer surface and processed the PD patterns to estimate the particle size and position in simulated GIS arrangement. With its pattern recognition capability, the developed LVQ technique was able to perform such estimations with an accuracy of 76%. The proposed method is designated as a contribution towards reliability improvement of GIS systems..

Keywords

Learning vector quantization (LVQ), GIS, Partial discharge, Particle size and position estimation.

Submitted at: April 6, 2015
Accepted at: May 7, 2015

Citation

YASIN KHAN, Application of learning vector quantization for estimating size and position of metallic particle adhering to spacer in GIS, Journal of Optoelectronics and Advanced Materials Vol. 17, Iss. 5-6, pp. 780-784 (2015)