Digital Commons @ Kettering University

Title

Calculation of breakdown voltages in Ar+SF/sub 6/ using an artificial neural network

Authors

S. S. Tezcan
M. S. Dincer
Huseyin R. Hiziroglu, Kettering UniversityFollow

Document Type

Conference Proceeding

Publication Date

12-19-2005

Publication Title

IEEE Xplore

Conference Name

2005 Annual Report Conference on Electrical Insulation and Dielectric Phenomena

Abstract

An artificial neural network is proposed to predict the breakdown voltages in Ar+SF₆ gas mixtures. The proposed neural network is designed with one hidden layer that includes twenty-five neurons. The output layer of the ANN consists of one neuron, which is essentially the predicted breakdown voltage. In order to train the ANN, the experimental data available for Ar+SF₆ have been used. The results of this ANN are compared with the experimental data as well as calculated data using the streamer criterion. With the proposed ANN, the average relative errors on breakdown voltages are found to be 3.85% for training and 4.32% for testing. Since the average errors are less than 5%, it is recommended to use ANN to predict the breakdown voltages.

Comments

Nashville, TN, USA

Rights Statement

This is a RoMEO green publisher - Must link to publisher version

© Copyright 2005 IEEE

Recommended Citation

Tezcan, S. S.; Dincer, M. S.; and Hiziroglu, Huseyin R., "Calculation of breakdown voltages in Ar+SF/sub 6/ using an artificial neural network" (2005). Electrical & Computer Engineering Presentations And Conference Materials. 45.
https://digitalcommons.kettering.edu/electricalcomp_eng_conference/45