Partial Discharge Source Localization in GIS Based on Image Edge Detection and Support Vector Machine

The gas insulated switchgear (GIS) plays a significant role in the power system. Partial discharge (PD) detection is an effective method for the operation security of GIS. This paper reviews numerous research works about PD source localization and proposes a novel method based on image edge detection and support vector machine (SVM). The energy density distribution of the ultra-high frequency signal is obtained by time-frequency analysis, then the edge features are extracted using Canny algorithm. The Canny algorithm is improved for adaptive threshold selection. The last distinguishable edge point coordinate of electromagnetic wave mode varies with the distance between PD source and detection point by reason of velocity dispersion characteristic. An equation is proposed to identify the longitudinal position of PD source, which is also verified in the experiment. SVM is trained to determine the circumferential positions of PD source. Finally, the procedure of the PD source localization method is summarized.