An EMD Based Fault Type Identification Scheme in Transmission Line

Fault classification in distance protection of transmission lines, with considering the wide variation in the fault operating conditions, has been very challenging task. In this paper, an approach is presented to classify the fault in transmission line based on Empirical Mode Decomposition (EMD) using instantaneous power for each phase of only one terminal. For decision making stage of proposed methodology, three famous algorithms (Artificial neural network, support vector machine and decision tree) are used and it is shown that support vector machine demonstrate a suitable approach for selecting the faulty phase/phases. The results denote that suggested scheme is independent of effects of variation of fault inception angle, fault location, fault resistance, fault type and noise in current and voltage signals and also the proposed method is able to classify all the faults on transmission line within half cycle after the inception of fault.