Fault type identification of arc grounding based on time-frequency domain characteristics of zero sequence current

Different types of faults pose different degrees of threat to the distribution network. Accurate identification of fault types is essential for distribution network maintenance and hazard prevention. The simulation of a typical single-phase arc grounding fault in a distribution network is carried out based on a 10 kV test platform, and the zero-sequence current of cable fault, tree touch, line break, and insulator flashover is obtained. The BP neural network is established and trained to recognize the feature data, which is extracted by Fourier transform and wavelet transform. The identification results prove the effectiveness of the proposed method for single-phase arc grounding fault type identification in distribution networks.