A neuro-fuzzy approach for estimation of time-to-flashover characteristic of polluted insulators

Function estimation is one of the major fields of fuzzy logic applications. Because of the useful properties of fuzzy systems such as adaptivity and nonlinearity, they are well suited to function estimation tasks where the equation describing the function is unknown as the only prerequisite is a representative sample of the function behavior. In this paper, a neuro-fuzzy approach for estimation of time-to-flashover of a polluted insulator under power frequency voltage is discussed. The prerequisite training data are available from experimental studies performed on models of polluted insulators. The results show the effectiveness of the proposed approach.