Classification of Types of Faults and Their Location in Power Transmission Lines

The proposed work addresses the essential need for efficient fault detection and classification in electrical power transmission systems to ensure uninterrupted power supply and system safety. It explores various types of faults, their causes, and the severe impacts they can have on power systems. A comprehensive review of existing fault detection methodologies is conducted to highlight advancements in machine learning-based techniques for fault diagnosis. The study investigates different machine learning algorithms, emphasizing their role in improving fault classification and localization accuracy. Feature selection techniques are employed to enhance model performance. Experimental results show the efficiency of these models, with Random Forest emerging as a strong classifier, achieving 97.96% accuracy for fault type prediction and 98.51% for fault location prediction. This work underscores the significance of leveraging machine learning models to improve fault prediction and ensure the reliability and sustainability of transmission networks.