337 / 2021-11-10 01:27:27

Fault diagnostic approach employing Hilbert-Huang transform and feedforward neural network

Power system and automation > Power system fault simulation and risk assessment

Fault in a distribution grid causes power interruption and hence economic losses. Delay in fault clearance can lead to cascading blackouts. Therefore, A crucial part of protection systems is to diagnose the fault effectively to accelerate the power restoration process. This paper presents a fault diagnostic method that consists of the Hilbert-Huang transform (HHT) along with a feedforward neural network (FFNN) to diagnose faults in the radial distribution grid. Instantaneous amplitude (IA) and frequency (IF) are obtained from HHT. Subsequently, statistical features are extracted from IA and IF plots and fetched to an (FFNN) for detection, classification, and identifying the location of different types of faults. The proposed approach was tested with a simplified distribution grid in MATLAB/SIMULINK. Simulation results demonstrate the efficacy of the presented method for both noise-free and noisy data with the variation of pre-fault loading conditions, fault resistance, location, and inception angle.