Transmission line fault detection using deep learning technique

Abstract

Transmission line fault detection and classification is an important area of research in power systems. It should be noted that the recognition of faults and their classification using traditional methods presupposes the application of mathematical models and methods of signal processing. However, these methods have their limitations and are ineffective in identifying and categorizing the defects in the complex power system. Over the past few years, deep learning techniques have been identified as effective in diagnosing faults and their types in power systems. This paper implements deep learning to detect faults and classify transmission lines. It was, therefore, evident that the proposed approach offered high possibilities of detecting and classifying the faults in real time with an outstanding accuracy of 99%. 3%, indicating a model accuracy score of 99. 54%.