YOLOv8改进策略在焊接外部缺陷检测模型中的应用研究OA
Research on the Application of YOLOv8 Improvement Strategy in Welding External Defect Detection Model
针对焊接外部缺陷图像检测中存在的小目标缺陷检测漏检、误检以及缺陷角度任意分布的挑战,提出了一种基于YOLOv8 的优化改进模型——YOLO-weld.首先,设计SPPF-weld和C2f_DBB_CBAM模块,用于增强YOLO-weld模型的上下文信息聚合能力、多尺度特征融合效果.接着,引入OBB检测头,用以准确捕捉有方向性的缺陷,以此提高检测精度.最后,实验结果表明,对比YOLOv8 模型,YOLO-weld模型在精度、召回率、调和平均值(F1)和mAP@0.5分别提升了3.2%、2.6%、4.0%和3.9%,充分证明了YOLO-weld模型改进的有效性.
Aiming at the challenges of missed detection,false detection and arbitrary distribution of defect angles in small target defect detection in welding external defect image detection,an optimized and improved model based on YOLOv8,YOLO-weld,is proposed.Firstly,SPPF-weld and C2f_DBB_CBAM modules are designed to enhance the context information aggregation ability and multi-scale feature fusion effect of YOLO-weld model.Secondly,the OBB detection head is introduced to accurately capture directional defects,so as to improve the detection accuracy.Finally,the experimental results show that compared with the YOLOv8 model,the YOLO-weld model improves the accuracy,recall,harmonic mean(F1)and mAP@0.5 by 3.2%,2.6%,4.0%and 3.9%,respectively,which fully proves the effectiveness of the YOLO-weld model improvement.
朱永红;杨开富
景德镇陶瓷大学,江西 景德镇 333403景德镇陶瓷大学,江西 景德镇 333403
计算机与自动化
焊接外部缺陷识别无损检测YOLOv8C2f_DBB
welding external defect identificationnon-destructive testingYOLOv8C2f_DBB
《现代信息科技》 2025 (12)
68-73,6
评论