Development of a Fire-Induced Flashover Probability Index (FIFPI) for Eskom Transmission Lines

摘要

The need for a fire-induced flashover probability index (FIFPI) for Eskom's transmission lines (South Africa) became evident soon after the installation the Advanced Fire Information System (AFIS) in 2004. Thousands of wildfires were detected by satellites close to transmission lines, but only a small percentage (4%) of these fires caused a flashover. Historical flashover data was compared to satellite fire information as well as air temperature, relative humidity, wind speed and wind direction within a logistic regression analysis to develop a flashover prediction model. The FIFPI model was able to predict problem fires with a misclassification cost of only 3.87%. The aim of this study was to develop a prediction model with the ability to accurately predict fire-induced flashover occurrences on Eskom transmission lines in order to reduce the large amount of false alarms (SMS and email messages) produced annually by AFIS.