Modeling of breakdown voltage of white Minilex paper in the presence of voids under AC and DC conditions Using neural networks

Abstract

Insulating materials contain various voids due to which upon passing of an electrical signal above a threshold level they start deteriorating and thus breakdown occurs. Hence finding out the breakdown voltage of an insulator is of utmost importance. In this project the Neural Network method has been employed to model the desired breakdown voltages under both AC and DC conditions. With the help of neural networks a relationship between the input parameters and breakdown voltage has been established. The insulating material under consideration is White Minilex Paper. The voids are created artificially with varied dimensions. The values of the mean square error and mean absolute mean error are calculated and these results show the effectiveness of the model.