Current transients based phase selection and fault location in active distribution networks with spurs using artificial intelligence

In electrical distribution networks, short-circuit faults are undesirable since they cause interruption of supply, affect system reliability and influence revenue for distribution companies. This paper investigates the use of current signals to determine the faulted phases during a fault and also proposes a novel approach to distinguish whether the fault lies on the feeder or one of the spurs. The distance of the fault from the substation is also evaluated using artificial neural network techniques and sensitivity tests further demonstrate the robustness of the proposed method.