首页|期刊导航|现代信息科技|DEW-YOLO:PCB板缺陷检测算法

DEW-YOLO:PCB板缺陷检测算法OA

DEW-YOLO:PCB Defect Detection Algorithm

中文摘要英文摘要

针对印刷电路板(Printed Circuit Board,PCB)制造工艺日益复杂,生产过程中易出现开路、短路、缺孔、毛刺、漏铜等多种缺陷.PCB 板小目标缺陷检测精度低、模型复杂、计算量大等问题,本文提出一种基于 YOLOv11 改进的检测算法—DEW-YOLO 算法.利用多尺度特征提供更为丰富且稳定的表示,使用 EMA 注意力模块解决复杂背景干扰和微小目标识别问题.最后将CIoU损失函数替换为了WIoU损失函数.以更充分地捕获这些特征信息,从而有效增强整体检测性能,提升对低质量小目标的检测表现.经测试,DEW-YOLO 模型在 PCB 缺陷检测中 mAP 值达到 93.8%,较 YOLOv11提升了4.9%,取得了同类算法中最优效果.

To address the various defects(such as open circuits,short circuits,missing vias,burrs,and copper leakage)that are prone to occur during the production of PCBs with increasingly complex manufacturing processes,as well as the problems of low detection accuracy for small defects,complex models,and high computational cost,this study proposes an improved detection algorithm based on YOLOv11,named DEW-YOLO.The algorithm utilizes multi-scale features to provide richer and more stable representations and employs an EMA attention module to handle complex background interference and small target recognition.Finally,the CIoU loss function is replaced with the WIoU loss function to capture the feature information more fully,thereby effectively enhancing the overall detection performance and improving the detection of low-quality small targets.Testing shows that the DEW-YOLO model achieves an mAP of 93.8%in PCB defect detection,a 4.9%improvement over YOLOv11,achieving the best performance among similar algorithms.

徐森;肖冰瑶;赵洋

沈阳化工大学,辽宁 沈阳 110142沈阳化工大学,辽宁 沈阳 110142沈阳化工大学,辽宁 沈阳 110142

信息技术与安全科学

PCB板YOLOv11EMA注意力目标检测

PCBYOLOv11EMA attentiontarget detection

《现代信息科技》 2026 (18)

45-52,8

10.19850/j.cnki.2096-4706.2026.18.009

评论