Radio frequency (RF) technique for field inspection of porcelain insulators

Abstract

North American utilities are increasingly concerned with their ageing ceramic insulator assets as they are either fast approaching their expected end of life or have already exceeded them. Defects like broken, cracked and punctured discs are some of the most adverse problems that the utilities encounter. These defects 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. Currently used PD techniques are off-line and are not suitable for detecting defective insulators in the field without interrupting the power supply. In this work, experiments are performed; simulating the actual field environment in an effort to develop a non-contact radio frequency (RF) based condition monitoring system for defective ceramic insulators. RF signatures captured in the field due to PD activities from two different defects are post processed; which involves noise removal and other signal processing techniques to extract appropriate wavelet packet based features. These features are then used to train and test artificial neural network (ANN) classifier. For the tests conducted, high recognition rates above 90% have been achieved.