An accurate fault location algorithm based on application of artificial neural networks (ANN) for protection of double circuit transmission lines is presented in this research paper. The proposed method uses the magnitude and phase angle of current available at only the local end of line. This method is adaptive to the variation of fault resistance, fault inception angle and fault location. The Simulation results show that all types of phase-to-phase and phase-to-ground faults can be correctly located under varying system conditions. Large numbers of fault simulations using MATLAB/Simulink software has proved the accuracy and effectiveness of the proposed algorithm. Keywords: Fault location (FL); Double circuit transmission line; artificial neural networks (ANN).
I.INTRODUCTION Double circuit transmission lines increase the power transmission capability and reliability of the power system hence it is most widely used. However, the fault location of double circuit lines becomes more difficult and complex than a single circuit line due to the effect of mutual coupling among the circuits. When the fault location algorithm used for single lines is directly used for double circuit lines, which is often the case in practice, the fault location estimation accuracy can't be guaranteed because of the mutual coupling effect. Therefore a dedicated fault location algorithm has to be developed for the double circuit transmission lines. Various fault location algorithms on double circuit transmission lines have been proposed [1][2][3][4][5][6][7][8]. A distributed parameter modelbased fault location algorithm was proposed in [1] and it uses two-terminal voltages and currents and does not require the source impedance and fault resistance. Another researcher proposed a novel time-domain fault location algorithm that uses a differential component net by using two terminal currents [2]. Although two-terminal algorithms may present a better performance but singleterminal algorithms have advantages from the commercial viewpoint. This is mainly due to the additional complexity associated with two ends algorithms including communication and synchronization between both ends as well as the cost increases. Therefore, more researches focused on the application of the single end method so far. A practical fault location approach depending on modal transformation is using single end data of the double circuit transmission lines was proposed in [3]. A least error squares method for locating fault on coupled double-circuit HV transmission line are using one terminal data [4]. An accurate fault location algorithm on two-parallel transmission lines for both single phase-to-ground fault [5] and non-earth fault using one terminal data [6] were proposed by researchers. A new approach based on artificial neural networks using the fundamental components of the fault and pre-fault voltage and current magnitudes of the reference end also has been presented in [7]. More accurate fault location algorithm for double-circuit transmission syste...