High-Voltage Outdoor Insulators' Performance Analysis: Bridging Real-world and Simulation Studies for Machine Learning Model Training

2024

Closed access Metadata (CSL-JSON)
DOI 10.1109/icsmartgrid61824.2024.10578168
Data confidence 85 high
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

High-voltage insulators used in transmission lines provide electrical and mechanical support for power line conductors. These insulators are subjected to severe weather conditions and are susceptible to external factors. Consequently, monitoring contaminated insulators is paramount to guarantee the efficient operation of transmission lines. This study investigates and analyzes the influence of contaminated insulator performance on the dielectric dissipation factor. To analyze the effect of pollution on the glass insulator surface, real practical measurements are conducted along with a simulation study and insulators' contamination is examined. Three contamination levels (light, medium, and heavy) and different pollutants including iron (Fe), calcium (Ca), aluminium (Al), and kaolin with distinct relative permittivity and bulk conductivity measurements are discussed. The dielectric dissipation factors are calculated and measured using capacitance C and resistance R values obtained from the simulation and practical work. The results show a tendency for the dielectric dissipation factor to increase as the pollution on the insulator surface thickens and support us in training our models in machine learning for insulators' contamination model training and labelling later.