New Method Based on Wavelet Transform and ANN for Multiterminal HVDC System Protection

This work presents a new protection scheme based on Artificial Neural Networks (ANNs) and Wavelet Transform (WT) for fault detection and location in Multi-Terminal Direct Current (MTDC) systems. The solution here presented does not require communication links, using only local signals. The proposed solution was developed considering a simplified four terminal MTDC system with three DC lines and then tested against the three-terminal MTDC system based on the CIGRE B4 DC test system. Different fault locations and fault resistances were adopted for developing and testing the proposed method. The MTDC systems were modeled in ATP-Draw and PSCAD, while the proposed algorithm was developed in Matlab. The results reveal that the proposed method is able to properly detect, classify and locate faults within a few milliseconds.