Modeling of Breakdown Voltage of White
Minilex Paper in Presence of Voids Under AC and DC conditions using Artificial Neural Network as Computational Method

Abstract

Insulating materials contain various voids due to which when an electrical signal is passed through the insulator above a threshold level they start deteriorating and breakdown occurs. Hence it is of great importance to find out the breakdown voltage of an insulator. In this project the Artificial Neural Network method has been employed to model the desired breakdown voltages under AC and DC conditions. By using neural networks a relationship between the input parameters and breakdown voltage has been established. The insulating material used is White Minilex Paper. Voids of varying dimensions are created artificially. The calculated values of mean absolute error and mean square error show the effectiveness of the model.