Detection of high impedance faults in distribution networks using Discrete Fourier Transform

This paper proposes a new method for extracting dynamic properties for high impedance fault (HIF) detection using discrete Fourier transform (DFT). Unlike conventional methods that use features extracted from data windows after fault to detect high impedance fault, in the proposed method, using the disturbance detection algorithm in the network, the normalized changes of the selected features are used to compare the data windows after the fault occurrence and before the fault occurrence. It also uses the post-disturbance data windows, develops a decision system based on the output of the support vector machines (SVM) classifier, and compares the amount of certainty of other network events with high impedance fault. The reliability and security of the proposed method have been improved. The proposed method is implemented on an IEEE 34 bus network in EMTP-RV software. The simulation results show 97.2% accuracy, 98.5% reliability, and 98.8% security..