局放Enhancement of acoustic based partial discharge detection using pattern recognition techniques.pdfVIP

Enhancement of Acoustic Based Partial Discharge Detection Using Pattern Recognition Techniques A. Swedan , A. H. El-Hag and K. Assaleh American University of Sharjah, Sharjah, UAE Abstract - Partial Discharge (PD) phenomenon is one of the major In this paper, the effects of different factors such as PD source factors that may lead to insulation deterioration in power location, insulation status and size of transformer tanks on the transformers. Several techniques were developed to detect partial detection performance of acoustic emission technique are discharge activity. Acoustic detection has been utilized for PD investigated. Different types of features are extracted and signal detection in power transformers. Acoustic detection has artificial neural networks are used to assess the detection several advantages compared to other techniques such as: it is immune to electromagnetic interference and it can be used to performance. locate the PD activity. However, the acoustic signals suffer from II. EXPERIMENTAL SETUP high attenuation which makes the detection of PD activity a difficult task. This paper presents a pattern recognition based Partial discharge generation and measurements were carried technique for enhancing the acoustic detection of partial out using the experimental setup shown in Figure 1. A 15 discharge signals