Decision tree based fault detection and classification in distance relaying

This paper presents a new approach for fault detection and classification in transmission line using Decision Tree (DT). The DT based fault detection algorithm uses 1/4th cycle data of fault currents from fault inception, to generate the optimal decision tree for fault detection. Similarly, the DT based classification algorithm takes half cycle data from fault inception of three phase currents along with zero sequence current, and constructs the optimal decision tree for classifying all 10 types of shunt faults in the transmission line fault process. The algorithm is tested on simulated fault data with wide variations in operating parameters of the power system network. The results indicate that the proposed method can reliably detect and classify faults in transmission line within the sub-cycle time-frame while keeping the computational burden sufficiently low to make a real-time implementation feasible.