Deep Neural Network Based Fault Classification and Location Detection in Power Transmission Line

Transmission lines constitute a significant portion of any power system as they transmit power from the source to the load end. Faults in the overhead transmission lines are common phenomena which can significantly disrupt the effective operation of the power system. Swift and efficient fault classification along with identification of the exact location of fault occurrence to isolate the affected region is extremely essential for ensuring power system reliability. In this paper, we propose a Deep Neural Network (DNN) based method to address the problem of transmission line fault detection, classification, and fault location identification. Our model is evaluated on a dataset developed by modeling and simulating a four-bus power system with three 100 km transmission lines. The dataset consists of the RMS values of three-phase currents and voltages due to the occurrence of different types of faults on the transmission lines of the system. The model performs satisfactorily in classifying symmetrical faults and unsymmetrical single line to ground faults with 100% accuracy, yielding an overall 98.775% accuracy for all four types of faults studied. It also successfully locates the faulty site within at least 2% precision in more than 80% cases.