Estimation of the flashover voltage on insulators using artificial neural networks

  • Authors:

  • A. A. Gialketsi;V. T. Kontargyri;I. F. Gonos;I. A. Stathopulos

  • Affiliations:

  • High Voltage Laboratory, School of Electrical and Computer Engineering, National Technical University of Athens, Athens, Greece;High Voltage Laboratory, School of Electrical and Computer Engineering, National Technical University of Athens, Athens, Greece;High Voltage Laboratory, School of Electrical and Computer Engineering, National Technical University of Athens, Athens, Greece;High Voltage Laboratory, School of Electrical and Computer Engineering, National Technical University of Athens, Athens, Greece

  • Venue:
  • ICC'05 Proceedings of the 9th International Conference on Circuits
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

This work attempts to elucidate the potentials of Artificial Neural Networks (ANNs) in high voltage applications and especially to estimate the flashover voltage on polluted insulators, using an ANN which is trained with the error backpropagation algorithm. For this purpose, an ANN was constructed in MATLAB and has been trained with several MATLAB training functions, while tests regarding the number of neurons, the number of epochs and the value of learning rate have taken place, in order to find which net architecture and which value of the other parameters give the best result. Some of the data had resulted from former experiments, while some other had resulted by applying a mathematical type based on a simplified model for the calculation of the flashover voltage.