This work proposes a methodology to automate the recognition of Partial Discharges (PD) sources in Electrical Distribution Networks using Deep Neural Network (DNN) model called Convolutional Autoencoder (CAE), which is able automatically extract features from data classify different sources. The database used train constructed with real defects commonly found MV switchgear service, and it also ...

In recent years, gas-insulated switchgear (GIS) substations have become widely used in power systems. Due to their compact structure, extremely high oscillation frequencies are prone transient overvoltages or very fast (VFTOs) when the isolating switch circuit breaker is operated. The characteristics of these special processes GIS and effect hybrid reactive compensation (HRPC) on were studied. ...

Abstract The health status of 35kv switchgear directly affects the safe operation subway. In view current problems single feature quantity, inadequate detection elements and inaccurate overall state evaluation switch gear, a method for metro gear based on multi-feature quantity was proposed. characteristic parameters such as transient ground voltage, ultrasonic value, cable joint temperature bu...

This article provides an overview of research on SF 6 replacement gases for electric power equipment, existing -free technologies, and worldwide developments in legislation to support these new technologies.