Artificial neural network applications in electrical gaseous discharges of Argon-SF6 gas mixtures

Sulphur-hexafluoride (SF6) is an electronegative gas used frequently for circuit breakers in power systems because of its high dielectric strength and good thermal conductivity. Argon (Ar) is also used for pulsed power switching applications because of its low arc inductance and its ability to conduct high currents. The major disadvantage of argon is its low dielectric strength. This disadvantage can be overcome by mixing argon with SF6. To make a proper mixture, electron swarm parameters and electron energy distribution function (EEDF) must be found. This study proposes an artificial neural network (ANN) to obtain the electron energy distribution functions (EEDFs) in SF6, Argon and SF6 ? Ar mixture from the mean energies, the drift velocities and the other related swarm data. In order to obtain the required swarm data, the electron swarm behavior in SF6, Argon and SF6 ? Ar mixture is analyzed over the wide range of the density reduced electric field strength E/N from a Boltzmann equation analysis based on the finite difference method under a steady-state Townsend condition. A comparison between EEDFs calculated by the Boltzmann equation and by ANN for various values of E/N suggests that the proposed ANN yields good agreement of EEDFs with those of the Boltzmann equation solution results.