Enhancing Insulator String Performance: Pollution and Icing Flashover Analysis Through Artificial Neural Network-Based Layout Optimization for Inverted T-Type String

Abstract

This study explores the impact of various high-voltage insulator string configurations on pollution and icing flashover characteristics under different environmental conditions. The inverted T-string design is suggested, offering improvements over the traditional I-string configuration. An experimental investigation is conducted using high-voltage glass-type disks (LD-160), along with the development of two artificial neural network (ANN) models to simulate and predict flashover voltages. The results demonstrate that the inverted T-string arrangement enhances the flashover voltage for polluted insulator strings by approximately 7% and increases the icing flashover voltage by 3.43%–5.01% compared to standard I-strings. The ANN models successfully determine optimal insulator configurations, demonstrating their potential to enhance high-voltage insulation performance with minimal experimentation. This study emphasizes the innovative use of ANN in optimizing insulator string arrangements, providing a practical solution for tackling pollution and icing issues in power systems.