This work attempts to apply Artificial Neural Networks in order to estimate the critical flashover
voltage on polluted insulators. First, an ANN was constructed in MATLAB and has been trained with several
MATLAB training functions. Then, an ANN was constructed in FORTRAN using an adaptive algorithm, in
which the parameters of momentum and learning rate changed during the learning procedure, in order to
optimize the training process. In each case the Artificial Neural Network uses as input variables the following
characteristics of the insulator: the diameter, the height, the creepage distance, the form factor and the
equivalent salt deposit density and estimates the critical flashover voltage.
(EN)
9th WSEAS International Conference on Neural Networks
(EN)
