The breakdown voltage estimation of SF6+N-2 mixture using neural network approach

Onal E., Seker S., Kalenderli O., Mardikyan K.

8th International Conference on Dielectric Materials, Measurements and Applications, Edinburgh, Saint Helena, 17 - 21 September 2000, pp.166-169 identifier

  • Publication Type: Conference Paper / Full Text
  • City: Edinburgh
  • Country: Saint Helena
  • Page Numbers: pp.166-169
  • Istanbul Technical University Affiliated: Yes


In this paper. AC breakdown strengths of SF6+N-2 mixtures containing 0.125, 0.5, 1% of SF6 in non uniform field are studied The relative gas pressure are varied within the range of 100-500 kPa and the electrode gap spacing is 5 mm. The results are first measured experimentally and then estimated bq means of Neural Network Approach. The comparison of measured and computed values shows that there is a good agreement between two values. The breakdown voltages of the mixtures can be found correctly by. the Neural Network (NN) Approach. Therefore, the Neural Network Approach can be considered as an alternative tool to estimate the new values at the out of the measurement range.