传感技术学报2025，Vol.38Issue(9)：1575-1586,12.DOI:10.3969/j.issn.1004-1699.2025.09.006
基于MoblieNetV2的焊接件外观缺陷检测研究
Research on Appearance Defect Detection of Welded Assembly Based on MoblieNetV2 Network
摘要
Abstract
An Openmax method is proposed to optimize the network node MoblieNetV2 model for automatic identification and detection of surface defects such as solder leakage,over soldering,and cracks in the production process of electronic connectors.The training process of models with high computing power requirements is completed on high-performance PCs,and the optimized recognition model trained is deployed to resource constrained embedded terminals to complete image recognition inference and detection in factory environ-ments.The sampling,enhancement,and labeling of datasets under small sample welding standards and defect images,and the construc-tion,optimization,and training of PC network models,as well as the engineering organization design and inference implementation of em-bedded terminal inference models are elaborated.Factory tests show that the network model designed has a standard welding recognition rate of 95.5%and a defect classification recognition rate of 96%,which meets the manufacturer's recognition rate requirements.关键词
移动网络节点网络V2/焊接件/缺陷检测/开集分类Key words
MobileNetV2/welding components/defect detection/openmax分类
信息技术与安全科学引用本文复制引用
杨绚渊,王宜怀..基于MoblieNetV2的焊接件外观缺陷检测研究[J].传感技术学报,2025,38(9):1575-1586,12.基金项目
国家自然科学基金项目(62372317) （62372317）
江苏省高职院校教师专业带头人高端研修项目资助项目(2023GRFX065) （2023GRFX065）
