An Intelligent Approach of Faults Detection and Location Methods for Power Transmission Line

Abstract

This paper presents an innovative approach for the simultaneous detection and localization of electric faults in transmission lines through machine learning (ML) techniques. By harnessing supervised learning algorithms, the system is trained on a comprehensive dataset comprising normal and fault scenarios. Extracting relevant features from critical parameters such as voltage, current, and phase angle, the ML model is equipped to discern between fault and non- fault states. Additionally, a localization algorithm is incorporated to pinpoint the exact location of the identified faults. Real-time monitoring facilitates rapid response, minimizing downtime and enhancing the overall reliability of the power grid. The proposed ML- based framework not only advances fault detection accuracy but also provides a precise spatial assessment, contributing to the optimization of maintenance efforts and the resilience of the transmission infrastructure. Key Words: Decision tree, Electric Faults, Transmission line, Fault Detection, Feature Extraction, Reliability.