High impedance fault detection in distribution system

High impedance faults (HIFs) present a huge complexity of identification in an electric power distribution network (EPDN) due to their characteristics. Further, the growth of non-linear load adds complexity in HIF detection. One primary challenge of power system engineers is to reliably detect and discriminate HIFs from normal distribution system load and other switching transient disturbances. In this study, a novel HIF detection method is proposed based on the simulation of an accurate model of an actual EPDN study with real data. The proposed method uses current signal alone and does not require voltage signal. Wavelet transform (WT) is used for signal decomposition to extract statistical features and classification of HIF into Non-HIF (NHIF) by Neural Networks (NNs). The simulation study of the proposed method provides good, consistent and powerful protection for HIF.