Detection and Classification of Defects in Ceramic Insulators using RF Antenna Shaharyar Anjum and Shesha Jayaram Electrical and Computer Engineering University of Waterloo, ON, Canada Ayman El-Hag Department of Electrical Engineering American University of Sharjah, Sharjah, UAE Ali Naderian Jahromi METSCO Energy Solutions Mississauga, ON, Canada ABSTRACT Defects in ceramic insulators like broken, cracked and punctured discs give rise to the initiation of partial discharge (PD) activities within the samples which has a detrimental effect on the insulator life. Hence it is important for the utilities to identify such defective samples as early as possible so that appropriate replacement strategies can be devised. The work presented in this paper involves the investigation of a number of cases of insulator defects, with the goal of developing an online RF-based PD technique for monitoring ceramic disc insulators. The three classes examined are a cracked ceramic insulator disc; a disc with a hole through the cap, and a completely broken insulator disc. The defective discs are considered individually and are also incorporated into strings of 2, 3, and 4 insulators. The captured RF pulses are processed by extracting wavelet packet based features. Feature reduction and selection is carried out and classification results are obtained. To classify the discharges arising from different types of defects, an artificial neural network (ANN) algorithm is applied to the extracted features, and recognition rates of more than 95% were reported for each class. The results of preliminary field tests carried out on a 40 feet high test transmission tower are also reported and their analysis showed good discrimination between the different defect types. Index Terms — Ceramic Insulators, Partial Discharge, Wavelet Packet Transform, Defects, Radio Frequency Antenna, Online Monitoring. 1 INTRODUCTION For the past few decades, owing to deregulation and competition, utilities across North America have been forced to make drastic alterations in the way they conduct business. The days of liberal spending on new assets as a means of achieving higher levels of system performance are long past. The focus is now increasingly shifting toward maximizing the utilization of existing assets and minimizing the huge capital investments needed for the replacement of costly equipment. In addition to these changes, increased demand for reliability and superior performance with respect to power equipment has also become far more significant in recent years. Ageing assets pose significant challenges for utilities. The primary goal for the utility is to utilize the full life of an asset, but ageing increases the probability that the likelihood of equipment failure will become unacceptable from both a financial and a performance perspective [1]. The average age of vital assets, such as circuit breakers, transformers, insulators, cables, and poles, owned by transmission and distribution utilities in Ontario is estimated to be more than 35 years. Nearly 150 million porcelain suspension insulators are calculated to be currently deployed in North America [2]. A significantly high proportion of these insulators are either approaching or have exceeded the life time for which they were designed. Maintenance of these ageing assets is thus of special interest to North American utilities. As the insulators play such a crucial role in the power system reliability, utilities have been giving increasing preference to faulty insulator detection methods that are reliable, cost effective, fast and safe to adopt for the line men. Although significant work has been done in the past to detect failed or punctured insulators, these methods suffer from problems such as safety issues for line personnel. For instance