Non-Pilot Empirical Wavelet-ANN Protection Scheme for Robust Fault Detection, Classification, and Location in Hybrid Line of VSC-HVDC System

Traditional protection systems are not suitable for cable and overhead (hybrid) transmission lines in voltage source converter (VSC)-based high voltage direct current (HVDC) systems. Therefore, this paper presents a robust fault detection, classification, and location based on the energy of the empirical wavelet transform (EWT) and artificial neural network (ANN) for a hybrid transmission line in the VSC-HVDC system. The operation scheme of the developed method comprises two loops: (i) EWT-based feature extraction loop and (ii) ANN-based fault detection, classification, and location loop. In the proposed method, the voltage and current signals are decomposed into several sub-passbands with low and high frequencies using the EWT method. The energy content extracted by the EWT is fed into the ANN algorithm for fault detection, classification, and location. Various fault cases, including high impedance fault (HIF) and noise, are performed to train the ANN with two hidden layers. The test system and signal decomposition are carried out by PSCAD/EMTDC and MATLAB software, respectively. The performance of the proposed method is compared with the traditional non-pilot traveling wave (TW) technique. The results confirm the proposed method’s high accuracy for VSC-HVDC hybrid lines, achieving a mean percentage error of approximately 0.1%.