基于主动学习和U-Net++分割的芯片封装空洞率的研究  

Study on BGA Packaging Void Rate Detection Based on Active Learning and U-Net++Segmentation

作　　者：齐选龙 陈弘扬 赵文兵[1] 赵地 高敬阳[2] QI Xuanlong;CHEN Hongyang;ZHAO Wenbing;ZHAO Di;GAO Jingyang(Beijing University of Technology,Beijing 100124,China;Beijing University of Chemical Technology,Beijing 100029,China;Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100080,China;Chinese Academy of Sciences,Beijing 100049,China)

机构地区：[1]北京工业大学,北京100124 [2]北京化工大学,北京100029 [3]中国科学院计算技术研究所,北京100080 [4]中国科学院大学,北京100049

出　　处：《计算机科学》2023年第S01期332-337,共6页Computer Science

基　　金：中国科学院计算技术研究所-华为联合实验室项目(YBN2020055088)。

摘　　要：内焊球空洞是BGA封装芯片的主要缺陷,可能会导致电气故障。目前,常用的检测方法是人工对照芯片X光影像检查,此类方法检测准确率低且时间、人力资源消耗大。因此,基于深度学习的自动化芯片缺陷检测方法越来越受到关注。芯片空洞检测与语义分割任务对应,但受限于数据缺乏高质量标注,模型准确率通常偏低,主动学习框架是潜在的解决方案。文中基于主动学习和U-Net++构建了芯片空洞率检测模型,通过等距划分将数据集分为多个子集,每个子集采用训练-预测-标注-扩展的框架循环优化U-Net++模型。在BGA封装芯片数据集上进行实验,模型分割平均Dice系数达到了80.99%,总体准确率达到了94.89%,达到了预定目标。首次将主动学习引入芯片检测领域,经实验验证可以有效提升芯片数据的标注水平,使得模型的分割准确率有所提高。Bump void is one of the most common physical defects in BGA packaging,which may lead to electrical failures and shortened lifetime.At present,the commonly used quality inspection is based on manual check on X-ray images,which has low accuracy and high time consumption.Therefore,automated chip detection methods based on deep learning draws increasing attention in industry.This paper proposes an active learning and U-Net++based void rate detection network.Based on active lear-ning,we apply equidistant partition for the whole dataset.For each sub-dataset,we take training-prediction-labeling-extension as pattern to optimize U-Net++network.The average dice coefficient on separated model sets reaches 80.99%on test set,while the overall accuracy rate reaches 94.89%.We innovatively apply active learning in in-line defect detection,and the result shows that,it can effectively enhance the labeling standard of data and model’s division precision.

关 键 词：内焊球空洞 主动学习 图像分割 目标检测 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]