Detection of high impedance faults in distribution networks using Stationary Wavelet Transform

In this paper, a new method for detecting high impedance fault in distribution networks is presented. In the proposed method, the Stationary Wavelet Transform (SWT) is used to extract features. Disturbance detection algorithm in the network, using changes in selected features in the data windows after the fault occurrence, compared with the data windows before the fault occurrence, detects the high impedance fault. It also uses the vote-based decision-making system based on the aggregation of the output of the PNN classification and the use of three post-disturbance data windows, has been improved the reliability of the proposed method. The results of the proposed method for detecting high impedance fault on the 34-node IEEE in the EMTP-RV software indicate the accuracy, reliability, and security of the proposed method at a high level.