Optimal Fault Detection And Classification In Transmission Lines Using Deep Neural Networks And Swarm Intelligence

Abstract

Transmission lines are critical components of modern power systems, and their reliable operation is essential for uninterrupted electricity supply. However, faults such as line-to-ground (LG), line-to-line (LL), double line-to-ground (LLG), and three-phase faults frequently occur due to environmental and operational factors. This paper proposes an optimal fault detection and classification framework using Deep Neural Networks (DNN) integrated with Swarm Intelligence optimization techniques. The proposed model utilizes voltage and current signals extracted from transmission lines, applies feature extraction techniques, and optimizes neural network parameters using Particle Swarm Optimization (PSO). Simulation results demonstrate improved classification accuracy, faster detection time, and enhanced robustness compared to conventional methods.