Collaborative Domain Adaptation Network for Partial Discharge Source Localization in Gas-Insulated Switchgear

Abstract

Abnormal discharge in gas-insulated switchgear (GIS) is a key cause of insulation failure, and it is also an external manifestation of insulation defects. Sensitive discharge source localization is an important goal of GIS partial discharge (PD) monitoring. However, most existing GIS PD source localization methods rely on time-delay estimation, which not only requires a high-precision synchronous sampling device but also suffers from serious interference. To this end, a collaborative domain adaptation network (CDAN) is proposed for GIS PD source localization. First, a synchronous squeezing wavelet transform is introduced to filter out the noise, eliminating the influence of noise on GIS PD source localization. Then, one-dimensional attention convolutional neural network is constructed to ensure that discriminative temporal fine-grained information is extracted. Next, a CDAN is proposed to transfer the localization knowledge learned from the simulation to actual GIS and achieve high-precision localization through domain matching and alignment. The results demonstrate that the error of the CDAN proposed is only 19.87 cm, which is considerably better than that from other methods. This work provides a reference solution for GIS PD source localization.