Real Time Detection of Corroded Bolts of High-Voltage Tower Based on UAV Technology and Deep Learning Method

Le résumé fourni par la source

Corrosion detection of high-voltage transmission tower bolts is an important part of power system safety operation and maintenance. Aiming at the problem of low recognition accuracy of traditional detection methods in complex environment, this paper proposes a real-time detection method for corroded bolts of UAV high-voltage tower based on deep learning. Firstly, a single image denoising model based on cue learning and potential diffusion is used to denoise the collected image; Then the image enhancement model based on gating expert is used for image enhancement; Furthermore, the image quality is further optimized by the hint guided potential diffusion model; Finally, the YOLOV5s detection model is used to accurately identify the corroded bolts. The experimental results show that the detection accuracy of this method in the background condition is 96.3%, which is 15.7% higher than the traditional method, which proves the effectiveness and practicability of our method.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.