The presence of defective dampers in power transmission lines poses a significant risk to the secure and stable operation of the electrical grid. Advancing the intelligent development of damper inspections in transmission lines, a fast and accurate defect detection method holds paramount importance. Addressing the issue of insufficient damper defect recognition due to scarce defect samples, complex backgrounds, and varying regional dimensions, a novel damper defect detection network (RCA-YOLOv8) based on a multi-scale convolution attention mechanism was proposed. Firstly, the diverse sizes of dampers in images are analyzed and a multi-scale convolution attention mechanism composed of three sets of bar-shaped convolutions is constructed to precisely capture features of different-sized dampers. Subsequently, a structural reparameterization method is utilized to convert the multi-branch structure in the network into a single-branch structure, enabling to maintain consistent inference speed with the single-branch structure while benefiting from the detection performance improvement brought by the multi-branch structure. In addition, based on the YOLOv8 feature extraction structure, a Conv Block structure containing Conv-A structure and structural reparameterization method was constructed to propose multi-scale features of dampers. Moreover, more shallow network features are integrated by using the AFPNs structure, resolving feature conflicts between large, medium, and small targets in the images, thereby enabling accurate detection of small damper targets and further enhancing detection performance. In this model, Conv-A is more able to focus on the dampers area in the image, reducing background interference, and structural reparameterization greatly reduces computational costs. AFPNs solve the problem of feature conflicts between large and small dampers in the image, thus achieving a low computational cost and high detection accuracy model. For model experimentation, a dataset of damper defects in power transmission lines within substation scenes using image processing techniques is generated. To enhance dataset diversity and save annotation time, employ automatic data augmentation operations, including scale transformations, such as y-axis flipping, adding Gaussian noise, adding salt and pepper noise, adjusting brightness and non-scale transformations, such as size enlargement and reduction, along with automatically generated annotation files. Based on the dataset, the RCA-YOLOv8 network achieves an average precision mAP0.5 of 91.9% and mAP0.5:0.95 of 77.5%. Compared with other advanced one-stage and two-stage object detection networks, RCA-YOLOv8 has better damper defect detection performance. The mAP values of RCA-YOLOv8 network increased by 5.4% and 4.2% respectively compared to the basic network YOLOv8, with an inference speed of 60.88 frames per second under TITAN XP platform. It can be concluded that the proposed RCA-YOLOv8 network can rapidly and effectively detect dampers and their defects in power transmission lines. The following conclusions can be drawn from the simulation analysis: (1) The network based on the multiscale convolution attention mechanism can focus on crucial regions in the images, suppressing background regions' feature representations to obtain more relevant information. (2) Structural reparameterization successfully converts the multi-branch structure into a single-branch structure without any loss, striking a balance between detection accuracy and speed. (3) AFPNs with progressive feature fusion from different levels enable the network to achieve more precise detection of small damper targets. © 2024 China Machine Press. All rights reserved.
