Home // INTELLI 2013, The Second International Conference on Intelligent Systems and Applications // View article
Authors:
Leandro H. S. Silva
Sergio C Oliveira
Eduardo Fontana
Keywords: Partial discharges; rain detection; pattern recognition; leakage current; insulators
Abstract:
Partial discharges (PD) on high voltage insulator surfaces are directly related with the deposition of pollution over the insulators. A complete partial discharge sensor network was previously developed and has been in operation for approximately three years. This system records the PD activity classifying it into four levels. As the PD activity is influenced by the weather conditions the sensor network measures the one hour average temperature and relative humidity. Also a fuzzy inference system was developed to extract the flashover occurrence risk level based on the partial discharge activity recorded. However, a strong rain event can wash the insulators strings almost instantaneously decreasing the risk level. To a correct result interpretation it is important to properly analyze the weather data to detect the rain occurrence. This paper presents a comparison among three approaches for rain detection from humidity and temperature data. The three approaches, Naïve Bayes Classifier, Support Vector Machines and Multilayer Perceptron Neural Network are trained on data gathered by meteorological stations located nearby the PD sensors and used in conjunction with the data obtained by those. Promising preliminary results are presented.
Pages: 176 to 183
Copyright: Copyright (c) IARIA, 2013
Publication date: April 21, 2013
Published in: conference
ISSN: 2308-4065
ISBN: 978-1-61208-269-1
Location: Venice, Italy
Dates: from April 21, 2013 to April 26, 2013