Generalized and Robust LSTM Model for Fault Detection and Classification in Power Transmission Line

Accurate and timely fault detection is critical for the safe and reliable operation of power systems. This study introduces a robust Long Short-Term Memory (LSTM) model designed for fault detection and classification in power transmission lines. The proposed approach leverages operational data to capture temporal variations under both normal and fault conditions, eliminating the need for complex feature extraction processes commonly used in traditional methods. By learning directly from labeled datasets, the LSTM model streamlines the fault identification process. The model's generalization capability has been rigorously tested across various fault resistance scenarios. Furthermore, its accuracy and computational efficiency have been thoroughly evaluated and benchmarked against existing methods to validate its performance.