Title :
Calculation of breakdown voltages in Ar+SF6 using an artificial neural network
Author :
Tezcan, S.S. ; Dincer, M.S. ; Hiziroglu, H.R.
Author_Institution :
Dept. of Electr. & Electron. Eng., Gazi Univ., Ankara, Turkey
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.
Keywords :
SF6 insulation; argon; discharges (electric); insulation testing; learning (artificial intelligence); neural nets; power engineering computing; Ar+SF6 gas mixture; artificial neural network; average relative error; breakdown voltage; hidden layer; streamer criterion; testing; training; Argon; Artificial neural networks; Biological neural networks; Breakdown voltage; Central nervous system; Intelligent networks; Multi-layer neural network; Neurons; Sulfur hexafluoride; Testing;
Conference_Titel :
Electrical Insulation and Dielectric Phenomena, 2005. CEIDP '05. 2005 Annual Report Conference on
Print_ISBN :
0-7803-9257-4
DOI :
10.1109/CEIDP.2005.1560620
