稀疏重构SAM芯片焊点检测方法研究

doi:10.3901/JME.2023.06.095

机械工程学报 ›› 2023, Vol. 59 ›› Issue (6): 95-102.doi: 10.3901/JME.2023.06.095

扫码分享

稀疏重构SAM芯片焊点检测方法研究

陆向宁^1,2, 刘凡¹, 何贞志¹, 廖广兰², 史铁林²

1. 江苏师范大学机电工程学院徐州 221116;
2. 华中科技大学数字制造装备与技术国家重点实验室武汉 430074

收稿日期:2022-09-08 修回日期:2023-01-30 出版日期:2023-03-20 发布日期:2023-06-03
通讯作者: 何贞志(通信作者),男,1982年出生,博士,副教授,硕士研究生导师。主要研究方向为无损检测、智能传感技术。E-mail:hezz82@163.com
作者简介:陆向宁,男,1981年出生,博士,教授,硕士研究生导师。主要研究方向为无损检测、微电子封装及可靠性分析。E-mail:lxnam89@163.com
基金资助:
国家自然科学基金(52075231)、江苏省高校“青蓝工程”和徐州市科技计划(KC21327)资助项目。

Solder Joint Inspection Using SAM Image through Sparse Reconstruction

LU Xiangning^1,2, LIU Fan¹, HE Zhenzhi¹, LIAO Guanglan², SHI Tielin²

1. School of Mechatronic Engineering, Jiangsu Normal University, Xuzhou 221116;
2. State Key Laboratory of Digital Manufacturing Equipment and Technology, Huazhong University of Science and Technology, Wuhan 430074

Received:2022-09-08 Revised:2023-01-30 Online:2023-03-20 Published:2023-06-03

摘要/Abstract

摘要： 提出了基于稀疏表示的声扫描显微镜(Scanning acoustic microscope, SAM)图像超分辨率重构方法，以解决其空间检测分辨率受超声波频率和穿透深度的限制，原始SAM图像分辨率较低，不利于封装缺陷辨识等问题。通过字典设计训练和稀疏系数α求解获得了重构的高分辨率SAM图像，利用Levenberg-Marquardt算法改进BP神经网络(LM-BP)，并用于倒装芯片焊点缺陷识别。与原始图像及双三次插值图像相比，稀疏重构图像的峰值信噪比明显增大，提高了SAM图像质量，减小了芯片焊点的错误识别数目，错误率降至2.76%。试验结果表明稀疏表示的SAM重构算法和LM-BP神经网络训练速度快、识别精度高，可用于高密度半导体封装缺陷的检测及可靠性评估。

关键词: 倒装芯片, 缺陷检测, 扫描声学显微镜, 稀疏表示算法, 神经网络

Abstract: An algorithm based on sparse representation was proposed to reconstruct high-resolution (HR) SAM images. Scanning acoustic microscope (SAM) is always used for defect detection of electronic packages, but the spatial resolution is limited by the frequency and penetration depth of ultrasound. The original SAM image with low resolution is adverse to defect recognition. The HR SAM image is obtained through dictionary training and sparse coefficient α solving. The Levenberg-Marquardt modified BP neural network (LM-BP) was used to classify the solder joints. Compared with the original image and the bicubic interpolation image, the peak signal-to-noise ratio of the sparsely reconstructed image is significantly increased, the quality of the SAM image is improved, the number of misidentified solder joints is reduced, and the error rate is reduced to 2.76%. The experimental results demonstrated that the sparse representation algorithm and the LM-BP neural network are effective and accurate for defect inspection of high-density packages.

Key words: flip chip, defects inspection, SAM, sparse representation, neural network method

中图分类号:

TG156

陆向宁, 刘凡, 何贞志, 廖广兰, 史铁林. 稀疏重构SAM芯片焊点检测方法研究[J]. 机械工程学报, 2023, 59(6): 95-102.

LU Xiangning, LIU Fan, HE Zhenzhi, LIAO Guanglan, SHI Tielin. Solder Joint Inspection Using SAM Image through Sparse Reconstruction[J]. Journal of Mechanical Engineering, 2023, 59(6): 95-102.

参考文献

[1] HUANG J F,HE Z Z,LI C X,et al. Heat dissipation optimization and prediction for three-dimensional fan-out package[J]. International Journal of Thermal Sciences,2021(8):166.
[2] 关晓丹,梁万雷. 微电子封装技术及发展趋势综述[J]. 北华航天工业学院学报,2013(1):34-37. GUAN Xiaodan,LIANG Wanlei. Overview of microelectronic packaging technology and development trends[J]. Journal of Beihua Institute of Aeronautics and Astronautics,2013(1):34-37.
[3] 陈志文,梅云辉,刘胜,等. 电子封装可靠性:过去,现在及未来[J]. 机械工程学报,2021,57(16):248-268. CHEN Zhiwen,MEI Yunhui,LIU Sheng,et al. Reliability in electronic packaging:Past,now and future[J]. Journal of Mechanical Engineering,2021,57(16):248-268.
[4] 刘培生,杨龙龙,卢颖,等. 倒装芯片封装技术的发展[J]. 电子元件与材料,2014,33(2):1-5. LIU Peisheng,YANG Longlong,LU Ying,et al. The development of flip chip packaging technology[J]. Electronic Components and Materials,2014,33(2):1-5.
[5] SU L,Wang L Y,LI K,et al. Automated X-ray recognition of solder bump defects based on ensemble-ELM[J]. Science China Technological Sciences,2019,62(9):1512-1519.
[6] 李跃,田艳红,丛森,等. PCB组装板多器件焊点疲劳寿命跨尺度有限元计算[J]. 机械工程学报,2019,55(6):54-60. LI Yue,TIAN Yanhong,CONG Sen,et al. Multi-scale finite element analysis into fatigue lives of various component solder joints on printed circuit board[J]. Journal of Mechanical Engineering,2019,55(6):54-60.
[7] NOURANI A,AKBARI S,SPELT J K. Fracture load prediction of BGA solder joints:Cohesive zone modeling and experimental verification[J]. International Journal of Solids and Structures,2016,90(4):30-44.
[8] Sha Y,HE Z,DU J,et al. Intelligent detection technology of flip chip based on H-SVM algorithm[J]. Engineering Failure Analysis,2022,134:106032.
[9] 徐寒. 面向集成电路封装检测的X射线图像滤波与增强方法研究[D]. 广州:华南理工大学,2013. XU Han. Research on X-ray image filtering and enhancement methods for integrated circuit package inspection[D]. Guangzhou:South China University of Technology,2013.
[10] Liao G,Chen P,DU L,et al. Using SOM neural network for X-ray inspection of missing-bump defects in three-dimensional integration[J]. Microelectronics Reliability,2015,55(12):2826-2832.
[11] 高明阳. 电路板元件贴装缺陷视觉检测系统[D]. 武汉:华中科技大学,2007. GAO Mingyang. Circuit board component placement defect visual inspection system[D]. Wuhan:Huazhong University of Science and Technology,2007.
[12] 杨英豪,柳青,崔洁. 机器视觉在焊点检测中的应用[J]. 电子工业专用设备,2014(11):29-32. YANG Yinghao,LIU Qing,CUI Jie. Application of machine vision in solder joint inspection[J]. Special Equipment for Electronics Industry,2014(11):29-32.
[13] 班兆伟. 基于红外热成像技术的电子封装缺陷检测方法研究[D]. 北京:北京工业大学,2012. BAN Zhaowei. Research on defect detection method of electronic packaging based on infrared thermal imaging technology[D]. Beijing:Beijing University of Technology,2012.
[14] 陆向宁,何贞志,胡宁宁,等. 主动红外热成像焊球缺陷检测方法研究[J]. 机械工程学报,2016,52(10):17-24. LU Xiangning,HE Zhenzhi,HU Ningning,et al. Research on defects inspection of solder bumps using active infrared thermography technology[J]. Journal of Mechanical Engineering,2016,52(10):17-24.
[15] LU X,HE Z,SU L,et al. Detection of micro solder balls using active thermography technology and K-means algorithm[J]. IEEE Transactions on Industrial Informatics,2018,14(12):5620-5628.
[16] ZHAO L,HE Z,WANG Z,et al. Simulation and experimental investigation on active thermography test of the solder balls[J]. IEEE Transactions on Industrial Informatics,2020,16(3):1617-1624.
[17] VOGG G,HEIDMANN T,BRAND S. Scanning acoustic GHz-microscopy versus conventional SAM for advanced assessment of ball bond and metal interfaces in microelectronic devices[J]. Microelectronics Reliability,2015,55(9-10):1554-1558.
[18] 蒋洁. 基于分类字典稀疏表示的超分辨率重建算法的研究[D]. 广州:华南理工大学,2017. JIANG Jie. Research on super-resolution reconstruction algorithm based on sparse representation of classification dictionary[D]. Guangzhou:South China University of Technology,2017.

稀疏重构SAM芯片焊点检测方法研究

Solder Joint Inspection Using SAM Image through Sparse Reconstruction

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	郑杰, 权伟, 刘洋, 卢学民, 刘晓红, 岳雅楠, 周腾, 蔡振兵. Cr/Zr涂层环向压缩表面裂纹识别研究[J]. 机械工程学报, 2024, 60(8): 1-10.
[2]	刘占广, 张云, 刘晴雨. 基于差分融合长短期记忆神经网络数控机床热误差建模[J]. 机械工程学报, 2024, 60(7): 249-257.
[3]	狄子钧, 袁东风, 李东阳, 梁道君, 周晓天, 信苗苗, 曹凤, 雷腾飞. 基于多尺度-高效通道注意力网络的刀具故障诊断方法[J]. 机械工程学报, 2024, 60(6): 82-90.
[4]	王俊玖, 刘金玉, 侯秀娟, 齐振国, 李志敏, 刘涛. 列车车体柔性装配精度预测的力学-数据混合建模方法[J]. 机械工程学报, 2024, 60(6): 177-186.
[5]	李春凯, 王嘉昕, 石玗, 代悦. GTAW熔池激光条纹动态行为与熔透预测方法研究[J]. 机械工程学报, 2024, 60(6): 236-244.
[6]	周宁, 姚建勇, 邓文翔. 基于神经网络的比例伺服阀阀芯液动力补偿鲁棒智能控制[J]. 机械工程学报, 2024, 60(4): 126-133.
[7]	王丹丹, 黄伟迪, 张军辉, 赵守军, 于斌, 刘施镐, 吕飞, 苏琦, 徐兵. 基于边缘计算的轴向柱塞泵磨损状态辨识方法研究[J]. 机械工程学报, 2024, 60(4): 189-199.
[8]	傅杨, 张跃, 毛颖, 唐小华, 陈祖高, 徐和武, 杨雨沛, 高斌, 田贵云. 基于Feature Boosting的管道电磁内检测多传感信号缺陷解析算法[J]. 机械工程学报, 2024, 60(20): 51-67.
[9]	张昊, 魏超, 胡纪滨, 陈泳丹. 基于转向模式切换的三轴独立转向车辆路径跟踪控制研究[J]. 机械工程学报, 2024, 60(2): 243-251.
[10]	段书用, 杨建华, 韩旭, 刘桂荣. 高维数据自适应降维方法[J]. 机械工程学报, 2024, 60(17): 283-296.
[11]	刘建琴, 胡桂菘, 乔金丽, 郭晓. 基于双路神经网络的TBM实时性能预测研究[J]. 机械工程学报, 2024, 60(16): 43-53.
[12]	胡伟飞, 廖家乐, 郭云飞, 鄢继铨, 李光, 岳海峰, 谭建荣. 基于物理信息神经网络的时变可靠性分析方法[J]. 机械工程学报, 2024, 60(13): 141-153.
[13]	张德权, 李星奥, 张宁, 宁国松, 韩旭. 工业机器人全域误差场精细化建模方法及其误差补偿策略[J]. 机械工程学报, 2024, 60(13): 316-329.
[14]	王俊, 杨轶青, 刘金朝, 沈长青, 黄伟国, 朱忠奎. 小波核编码的脉冲卷积神经网络在可解释性智能诊断中的应用研究[J]. 机械工程学报, 2024, 60(12): 41-50.
[15]	袁静, 任港星, 蒋会明, 赵倩, 魏臣隽, 朱骏. 基于多元提升核神经网络的机械故障诊断方法及其特征提取可解释性研究[J]. 机械工程学报, 2024, 60(12): 51-64.