Intelligent Fault Location in MTDC Networks by Recognizing Patterns in Hybrid Circuit Breaker Currents During Fault Clearance Process

In this article, a novel, learning-based method for accurate location of faults in multiterminal direct current (MTdc) networks is proposed. By assessing the dc circuit breaker currents during fault clearance process, pattern recognition approach adopted from which estimated. The implementation algorithm allocated into three main stages, where similarity coefficients and weighted averaging functions (incorporating exponential kernels) are utilized. For proposed algorithm, only short-time window data (equal to 6 ms) required. performance assessed through detailed transient simulation using verified MATLAB/Simulink models. Training patterns have been retrieved by applying series different within an MTdc network. Simulation experimental results revealed that scheme, first, can reliably determine type fault, second, accurately estimate (including cases highly resistive faults), and, third, practically feasible.