| 李海宇,燕芳,李小娜,冯金秋,杨阳.基于YOLOv8n的锆合金板表面缺陷检测模型[J].电子测量与仪器学报,2026,40(5):191-203 |
| 基于YOLOv8n的锆合金板表面缺陷检测模型 |
| Surface defect detection model for zirconium alloy plates based on YOLOv8n |
| |
| DOI： |
| 中文关键词: 锆合金板 缺陷检测 YOLOv8n 多尺度门控信息聚合 |
| 英文关键词:zirconium alloy plate defect detection YOLOv8n multi-scale gated information aggregation |
| 基金项目:国家自然科学基金（62161042）、内蒙古自然基金（2025MS06002）、内蒙古重点研发和成果转化计划项目（2025SYFHH0875）资助 |
|
|
| Author | Institution |
| Li Haiyu | School of Automation and Electrical Engineering,Inner Mongolia University of Science and Technology, Key Laboratory of
Synthetical Automation for Process Industries at Universities of Inner Mongolia Autonomous Region, Baotou 014010, China |
| Yan Fang | School of Automation and Electrical Engineering,Inner Mongolia University of Science and Technology, Key Laboratory of
Synthetical Automation for Process Industries at Universities of Inner Mongolia Autonomous Region, Baotou 014010, China |
| Li Xiaona | YZS Precision Technology Co., Ltd., Xi′an 712000, China |
| Feng Jinqiu | School of Automation and Electrical Engineering,Inner Mongolia University of Science and Technology, Key Laboratory of
Synthetical Automation for Process Industries at Universities of Inner Mongolia Autonomous Region, Baotou 014010, China |
| Yang Yang | School of Automation and Electrical Engineering,Inner Mongolia University of Science and Technology, Key Laboratory of
Synthetical Automation for Process Industries at Universities of Inner Mongolia Autonomous Region, Baotou 014010, China |
|
| 摘要点击次数: 335 |
| 全文下载次数: 71 |
| 中文摘要: |
| 传统的锆合金板生产质量检测主要依靠人工，费时费力且精度不高。为提高锆合金板表面缺陷的检测精度、检测效率，针对YOLOv8n目标检测模型的网络结构进行改进，提出一种轻量级多尺度融合缺陷检测模型（lite edge fusion-YOLOv8，LEF-YOLOv8）。首先，为了解决锆合金板表面小目标缺陷特征容易丢失的问题，设计一种提取缺陷边缘特征并结合空间信息的C2f-EDEM（C2f-edge detail enhancement module，C2f-EDEM）模块，有效提高模型的特征提取能力；然后，针对原模型缺乏显式的特征选择和注意力机制的问题，提出一种全局-局部注意力融合模块（global-local interactive attention，GLIA），以提高模型融合局部、全局语义上下文的能力；最后，针对原模型检测头信息融合能力较弱且计算量较大等问题，提出一种轻量级多尺度融合检测头(lightweight multi-scale fusion detection head，LMSFD)，以提升模型的特征表达能力并减少模型的复杂度。在自制锆合金板数据集和NEU-DET公共数据集上分别进行模型验证实验。实验结果显示，LEF-YOLOv8模型在不引入过多计算量的同时mAP@0.5分别达到86.7%和75.9%，相较基线模型YOLOv8n分别提高3.2和2.4个百分点。实验结果证实，改进后的模型提高了检测精度，适用于计算能力受限的检测终端，为锆合金板材表面缺陷自动检测提供了解决方案。 |
| 英文摘要: |
| Traditional quality inspection of zirconium alloy plates mainly relies on manual methods, which are time-consuming, labor-intensive, and prone to low accuracy. To improve the detection accuracy and efficiency of surface defects on zirconium alloy plates, the network structure of the YOLOv8n object detection model was enhanced, and a lightweight multi-scale fusion defect detection model (LEF-YOLOv8) was proposed. To address the issue of small defect features being easily lost, a C2f-edge detail enhancement module (C2f-EDEM) was designed to extract defect edge features while incorporating spatial information, thereby enhancing feature extraction capability. To overcome the lack of explicit feature selection and attention mechanisms in the original model, a global-local interactive attention (GLIA) module was introduced, improving the integration of local and global semantic context. Furthermore, to mitigate the weak information fusion and high computational cost of the original detection head, a lightweight multi-scale fusion detection head (LMSFD) was proposed, which enhances feature representation while reducing model complexity. Experiments on a self-collected zirconium alloy plate dataset and the NEU-DET public dataset demonstrate that LEF-YOLOv8 achieves mAP@0.5 of 86.7% and 75.9%, respectively, improving by 3.2% and 2.4% over the baseline YOLOv8n, without introducing significant computational overhead. These results indicate that the proposed model improves detection accuracy and is suitable for resource-constrained inspection systems, providing an effective solution for automated surface defect detection of zirconium alloy plates. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
