An Extensive Review of Techniques for Transmission Line Fault Classification

• Published in: 2025 International Conference in Advances in Power, Signal, and Information Technology (APSIT) pp. 1 - 7
• Main Authors: Panigrahi, Basanta K., Kumar, Ashok, Shukla, Jyoti, Mishra, Somanath, Panda, Archana
• Format: Conference Proceeding
• Language: English
• Published: IEEE 23.05.2025
• Subjects: Chebyshev neural network (ChNN); Circuit faults; Data mining; Discrete Wavelet Transform (DWT); Discrete wavelet transforms; Feed forward neural network (FNN); Neural networks; Power system reliability; Power transmission lines; Reviews; Transforms; Transmission line measurements; Urban areas
• DOI: 10.1109/APSIT63993.2025.11086137

Transmission lines are an essential part of the electrical power system network, with the primary goal of delivering generated power to consumers with the least amount of disruption. Transmission lines are always subject to faults owing to a kind of factors, including human error, short circuits, equipment obsolescence, lightning storms, and component failure of the power system. Those kinds of phenomena have an effect on system dependability and cause expensive maintenance, lost productivity, and consumer power outages. As the demand for electric power grows each and every day as a result of growing urbanization of life styles and industrialization, quick and precise fault diagnosis is allimportant for superior performance and fewer power supply interruptions. Hence, several techniques for classification of transmission line faults have been developed in the past. Classifying faults is a difficult task that should be completed in order to optimize the system's overall performance and reliability. This article reviews the majority of the previously established techniques for classifying the transmission line faults. This article aimed to present information from earlier research in a comprehensive manner. This paper highlights research initiatives in classification of faults, as well as the operating principle, merits, and demerits of previous works relevant to each fault classification technique. This, relevant and compact assessment possible for the researchers in understanding various methodologies and techniques.