Research on the Application of AI-Based Intelligent Inspection Systems in Power Grid Safety Operations

With the increasing complexity of power grid systems, traditional inspection methods are no longer sufficient. This paper presents an AI-powered intelligent inspection system designed to improve the efficiency and accuracy of power grid maintenance. The system integrates a deep learning-based YOLOv8 model with unmanned aerial vehicles (UAVs) and edge computing, enabling real-time defect detection, component classification, and alert generation. The model incorporates attention mechanisms and transformer modules to enhance the detection of small and occluded targets typically found in power grid environments. Experimental results demonstrate that the system outperforms traditional models in terms of both detection accuracy and processing speed, making it well-suited for real-time, edge deployment in complex field conditions. This research provides a scalable, cost-effective solution for modernizing power grid inspections.