Pipeline Surface Defect Detection Using YOLOv11 with Attention Mechanisms: A Comparative Study of SA, LKA, and CBAM Approaches

Pipeline systems play a crucial role in transporting fluids and gases across industrial infrastructures; however, detecting and classifying defects in these pipelines is essential to ensure safety, reliability, and uninterrupted operations. In this study, we employ the latest YOLOv11 deep learning model for automated detection of six common types of pipeline defects: Deformation, Obstacle, Rupture, Disconnect, Misalignment, and Deposition. A custom dataset of 1,500 images was prepared, where 900 images (60%) were used for training comprising 150 images per class and 600 images (40%) were reserved for validation, with 100 images per class. The YOLOv11 model demonstrated strong detection capability, achieving an overall accuracy of 91.77%. To further enhance performance, we integrated and compared three attention mechanisms: Self-Attention (SA), Local Kernel Attention (LKA), and Convolutional Block Attention Module (CBAM). The results showed that YOLOv11 + SA achieved the highest accuracy of 98.95%, followed by YOLOv11 + LKA with 98.54%, while YOLOv11 + CBAM reached 89.60%. These findings highlight that integrating attention mechanisms can significantly improve the defect detection accuracy of YOLOv11. Future work will focus on extending the dataset.