Adaptive fault diagnosis in power transmission lines using deep learning and LSTM autoencoders for enhancing grid reliability

Abstract

Abstract: The increasing complexity and dynamic nature of modern electrical grids necessitate advanced, adaptive fault diagnosis systems to maintain high reliability and ensure minimal downtime. This study presents a novel, adaptive fault detection and localization method for three-phase transmission lines utilizing a Long Short-Term Memory (LSTM) Autoencoder. An unsupervised LSTM autoencoder is proposed for adaptive fault detection in three-phase power lines. It achieves 98% accuracy with less than 2% false positives, surpassing existing methods. Noise-aware training ensures over 92% F1-score at 20 dB SNR for real-time monitoring. Validated on 50,000 simulated and 1,000 real fault cases, proving scalability and efficiency.