A Detection Algorithm for Distribution Network Insulators Based on YOLOv8n-EdgePro

The detection of insulators in power distribution networks plays a vital role in ensuring the overall safety and stability of the power system. Insulators serve as essential components in maintaining the integrity of power transmission by preventing electrical faults. As distribution networks expand and become more complex, efficient and accurate detection methods are required to prevent potential failures and ensure system reliability. Traditional manual inspection methods are labor-intensive and prone to errors, making automated detection an essential solution. This paper introduces YOLOv8n-EdgePro, a lightweight yet effective object detection algorithm tailored for insulator detection. By incorporating advanced techniques such as depthwise separable convolutions and attention mechanisms, the algorithm significantly enhances feature extraction, especially for small and hard-to-detect insulators in challenging environments. Additionally, the lightweight design reduces computational complexity, enabling deployment on edge devices such as drones or portable inspection units. The algorithm strikes an optimal balance between detection accuracy and efficiency, addressing the dual needs for high performance and fast inference speeds, essential for real-time applications in large-scale distribution networks. Through this approach, the paper aims to provide a reliable, scalable solution for automating insulator detection and monitoring, contributing to the development of smarter and more resilient power grids.