Model-driven distance protection cannot correctly identify the fault phases when it is applied to the DCTL (double circuit transmission lines on the same tower). This paper proposes a fault phase identification method based on CNN (convolutional neural network). The performance of the proposed method is verified by a larger number of fault data, and the results show that the proposed method can effectively identify the fault phases of the DCTL.

convolutional neural network; double circuit transmission lines on the same tower; distance protection; fault phase identification; fault data.