Artificial neural networks (ANN) and genetic algorithm modeling and identification of arc parameter in insulators flashover voltage and leakage current

Flashover phenomenon in polluted insulators has not yet been described accurately through a mathematical model. The main difficulty lies in the definition of arc constants, which is formed in the dry bands when the voltage exceeds its critical value. We have present an optimization method based on genetic algorithms and Artificial Neural Networks (ANN) experimental data from artificially polluted insulators for the determination of the arc constants and Dielectric properties in the surface. In this work a pollution flashover generalized model is used. The obtained results show that the mathematical model with optimized arc constants simulates accurately the experimental data and Corroborate the inverse Relationship between flashover voltage and pre-flashover leakage current. 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.