Use Of Artificial Intelligence Techniques To Estimate The Flashover Voltage

Abstract

First this work present an optimization method based on genetic algorithms for the determination of the arc constants, using experimental results from artificially polluted insulators. The well known model of Obenhaus for pollution flashover is used. This model results in a system of equations which cannot be solved with conventional arithmetic methods. The application of genetic algorithms enables the definition of the arc constants, resulting also in the calculation of the critical conditions at the beginning of the pollution flashover mechanism. In this way a mathematical model is established, which simulates accurately the experimental results.
Second this work attempts to apply an artificial neural network in order to estimate the critical flashover voltage on polluted insulators. The artificial neural network uses as input variables the following characteristics of the insulator: diameter, height, creepage distance, form factor and equivalent salt deposit density, and estimates the critical flashover voltage. The data used to train the network and test its performance is derived from experimental measurements and a mathematical model.