Recognition of Surface Discharges in High-voltage Lines Insulators using Artificial Intelligence

Environmental contamination and pollution under specific meteorological conditions can cause surface discharges on the insulators in high-voltage lines and stations, with consequent possible service interruptions. In this paper, it is presented the first attempt of a novel approach in the detection of surface discharges, based on AI and computer vision state of the art techniques. The research is carried out in the frame of an active collaboration with TERNA (the Italian TSO). The videos collected by the camera of the LANPRIS testing station for the purpose of ageing monitoring, have been used to explore the potentials of an object detection approach using an artificial neural network to recognize insulators in a video and to distinguish between normal behaviour insulators from those subject to surface discharge phenomena. The input data are described in the context of the LANPRIS experimentation, the model, chosen for the object detection, and the pipeline, built to process the video files, are introduced; the tools, used for this work, are widely illustrated and the results discussed. This study is the initial part of a larger work aimed at experimenting artificial intelligence and computer vision techniques in systems that monitor very important electrical system components, such as high-voltage line insulators.

I. Introduction

High levels of surface contamination due to saline or pollutant deposits of an industrial and agricultural nature can cause discharges on the insulators surface in high-voltage lines and stations, with consequent possible service interruptions. The mitigation of the effects of pollution on insulators can be achieved both by using insulators with better withstand characteristics, such as those provided by insulators in composite material, through the use of surface treatments of traditional insulators, and by intervening with cleaning operations. The possibility of knowing and predicting the actual dielectric withstand conditions of the insulation allows an increase in the reliability of the national electricity grid with regard to these phenomena for the different peculiarities of the Italian territory. The measurement and monitoring of the level of environmental severity and the assessment of the state of the insulators in the grid can be carried out by using remote surface current measurement systems such as the one installed in the LANPRIS (Laboratorio Naturale Prova Isolatori) ), a natural testing insulator laboratory co-owned by RSE and Terna [1], [2], [3], [4]. The system consists of an insulator testing and ageing station. The laboratory is located in the city of Portoscuso (CI) in Sardinia, in a highly aggressive environment in terms of saline and industrial pollution. The experimentation is carried out on four types of insulators (composite, RTV partially coated glass, RTV fully coated glass, uncoated glass), with three different creepage length reduced compared to the normal sizing to accelerate the ageing phenomena. Figure 1 shows a photo of the LANPRIS experimental station and setup.