Bolt-YOLO: Research on an Algorithm Framework for Detecting Bolt Defects in Transmission Lines

In transmission lines, bolt fittings are critical components that connect towers and insulators. These fittings are prone to defects, such as loosening or missing bolts, due to natural environmental factors, posing significant risks to the system's operation. Drone inspection images are increasingly used for the intelligent detection of bolt fittings, yet the small size of bolt components and the uneven distribution of sample quantities limit detection accuracy. To address these challenges, this paper proposes a multi-type bolt fitting defect detection algorithm aimed at improving detection accuracy and robustness. To tackle the issue of small target detection, we design a novel down-sampling method that incorporates both global and local feature perception, reducing the loss of small target information. This method is integrated into the Res-PANet, a multi-scale feature fusion structure based on residual skip connections, which compensates for the loss of small target details in high-level semantic features. Additionally, to address the sample imbalance problem, we introduce adaptive class weighting and a Minimum Peripheral Point Distance (MPPD) bounding box similarity constraint to better locate imbalanced sample regions from the loss function perspective. Experimental results, using a detection dataset containing four types of targets—normal bolts, missing pins, loose pins, and missing nuts—demonstrate the effectiveness of the proposed algorithm. Compared to the original YOLOv8 model, the improved model shows a 1.9% accuracy improvement for detecting missing pins, a 3.2% improvement for loose pins, and a 4.2% improvement for missing nuts. The overall mean accuracy increased from 69.5% to 72.1%. These results provide a solid technical foundation for detecting bolt fitting defects in transmission lines, offering significant practical value for future inspection tasks.