Research on Transmission Line Defect Detection System Based on Cloud-Edge-End Collaboration

With the continuous expansion of transmission lines and the development of power systems, defect detection is crucial for the safe operation of transmission lines. However, cloud-based detection faces issues such as high bandwidth consumption, delayed response, and insufficient functionality of visualization platforms, which affect the efficiency and accuracy of detection. To address these problems, this paper proposes a collaborative defect detection system for transmission lines at the edge and cloud, aiming to improve detection efficiency and accuracy. The system utilizes the YOLO-Faster defect detection algorithm and event-triggering mechanism, and employs PyQt5 to build a user-friendly visualization platform with convenient operation and strong interactivity. Furthermore, by leveraging the advantages of cloud servers, edge devices, and terminal devices, real-time monitoring and defect warning for unmanned aerial vehicle (UAV) inspections are achieved, effectively enhancing inspection efficiency. Experimental results demonstrate that the YOLO-Faster algorithm achieves a mean average precision (mAP) 1.4% higher than YOLOv5n, striking a good balance between defect detection accuracy and speed. In conclusion, the system offers high precision and efficiency, providing vital support for the safe operation of transmission lines.