基于深度学习的废旧电路板表面缺陷分类  

Deep learning⁃based surface defect classification of scrap circuit boards

作　　者：余光海 盛光鸣 张元昊 徐观明 Yu Guanghai;Sheng Guangming;Zhang Yuanhao;Xu Guanming(School of Mechanical Engineering,Hefei University of Technology,Hefei 230009,China;Hunan Green Recycling Resources Co.,Ltd.,Changsha 410699,China)

机构地区：[1]合肥工业大学机械工程学院,合肥230009 [2]湖南绿色再生资源有限公司,长沙410699

出　　处：《现代计算机》2024年第10期17-22,共6页Modern Computer

基　　金：国家重点研发计划重点专项项目(2019YFC1908002)。

摘　　要：针对废旧电路板表面缺陷识别,提出了一种利用深度学习进行分类的方法。在ResNet34模型的基础上,增加了CBAM注意力机制。通过将ResNet34架构与注意力机制相结合,旨在增强模型关注输入图像中重要特征并对其进行优先排序的能力,从而提高分类的准确性。结果表明提出的方法在提高废旧电路板表面缺陷分类方面的有效性。A classification method using deep learning is proposed for the recognition of surface defects on scrap circuit boards.Based on the ResNet34 model,the CBAM attention mechanism is added.By combining the ResNet34 architecture with the attention mechanism,it aims to enhance the model’s ability to focus on important features in the input image and prioritize them,thus improving the classification accuracy.The results demonstrate the effectiveness of the proposed method in improving the clas-sification of surface defects on scrap circuit boards.

关 键 词：废旧电路板 注意力机制 表面缺陷分类 

分 类 号：TN41[电子电信—微电子学与固体电子学] TP18[自动化与计算机技术—控制理论与控制工程] TP391.41[自动化与计算机技术—控制科学与工程]