Use of Artificial Neural Networks for Location of Defective Insulators in Power Lines

Received: August 02, 2011 / Accepted: November 18, 2011 / Published: August 31, 2012.Abstract: This is an extended version of the same titled paper presented at the 21st CIRED. It discusses a new technique foridentification and location of defective insulator strings in power lines based on the analysis of high frequency signals generated bycorona effect. Damaged insulator strings may lead to loss of insulation and hence to the corona effect, in other words, to partialdischarges. These partial discharges can be detected by a system composed of a capacitive coupling device (region between the phaseand the metal body of a current transformer), a data acquisition board and a computer. Analyzing the waveform of these partialdischarges through a neural network based software, it is possible to identify and locate the defective insulator string. This paperdiscusses how this software analysis works and why its technique is suitable for this application. Hence the results of key testsperformed along the development are discussed, pointing out the main factors that affect their performance.Key words: Corona effect, current transformer, insulator string, neural network, power line.