Author(s) :

Vikas Raskar,Aditya Khandare,Chandrapal Rokade.

Volume/Issue :

Abstract :

The stability and reliability of electrical power systems are essential for the seamless operation of modern societies, with transmission lines serving as the backbone of these systems by transporting electrical energy from power plants to consumers. However, these lines are prone to various faults, such as short circuits, open circuits, and ground faults, which can disrupt power supply and damage infrastructure. Efficient fault detection in transmission lines is thus crucial for maintaining continuous and safe power system operation. Traditional fault detection methods, like impedance-based detection and traveling wave analysis, have been extensively used but have limitations related to system changes and equipment requirements. Recent advancements in sensor technologies and communication systems have enabled more precise and real-time fault detection, while the integration of machine learning techniques has further enhanced fault detection capabilities. Machine learning algorithms can analyze large datasets to identify patterns and anomalies, continuously improving their accuracy and providing real-time fault classification and prediction. This paper reviews the strengths and limitations of traditional and machine learning-based fault detection methods, highlighting the potential of integrated systems. It also discusses the role of modern sensor and communication technologies in improving fault detection effectiveness. The evolution of fault detection techniques signifies a major advancement in ensuring power system stability and reliability, emphasizing the need for ongoing innovation to address the complexities of modern electrical networks.

No. of Downloads :

0