Autonomous UAV-Based Power Transmission Line-Guided Inspection Using Yolo Deep Learning

The continuous monitoring and inspection of power transmission lines are vital to ensure the stability and reliability of the power grid. Traditional inspection methods are time-consuming, costly,
and pose significant safety risks to workers. This research presents an autonomous Unmanned Aerial Vehicle (UAV)-based system for power transmission line inspection, utilizing advanced deep
learning techniques, specifically the YOLOv11 model, to enhance fault detection and navigation accuracy. The proposed system integrates a YOLOv11 object detection model to identify power lines from UAV-captured footage and employs a proportional control navigation algorithm to autonomously guide the UAV along the transmission lines. The model was trained on a diverse
dataset of powerline imagery to ensure robustness across varying environmental conditions. Evaluation metrics such as precision, recall, and mean Average Precision (mAP) demonstrated the
model’s ability to accurately detect power lines with high confidence. The developed system effectively tracks power lines in video, offering a significant improvement over traditional inspection methods. This approach not only reduces operational costs and risks but also increases the efficiency and accuracy of power line inspections. The results highlight the potential of integrating UAVs and deep learning for autonomous infrastructure maintenance in critical power transmission systems.