贴片电阻焊点内部空洞缺陷自适应检测

蔡念; 肖盟; 肖盼; 周帅; 邱宝军; 王晗

doi:10.11999/JEIT211246

贴片电阻焊点内部空洞缺陷自适应检测

doi: 10.11999/JEIT211246

蔡念^{1, 5, ,},
肖盟¹,
肖盼⁴,
周帅^{2, 3},
邱宝军³,
王晗⁴

1.
广东工业大学信息工程学院广州 510006
2.
天津大学天津 300072
3.
工业和信息化部电子第五研究所广州 510006
4.
广东工业大学机电工程学院广州 510006
5.
惠州市广工大物联网协同创新研究院有限公司惠州 516025

基金项目: 国家自然科学基金(62171142)，广东省自然科学基金(2021A1515011908)，惠州市高校科研专项资金项目(2019HZKY003)

详细信息

作者简介:
蔡念：男，1976年生，教授，研究方向为机器学习、机器视觉、数字信号处理等

肖盟：男，1998年生，硕士生，研究方向为机器视觉、缺陷检测、图像分割

肖盼：女，1992年生，博士生，研究方向为机器视觉、缺陷检测

周帅：男，1984年生，高级工程师，研究方向为微电子器件可靠性与检测评价

邱宝军：男，1976年生，高级工程师，研究方向为电子元器件、电子组件可靠性检测、分析和评价以及技术研究

王晗：男，1980年生，教授，研究方向为微电子加工制造装备，光学精密测量仪器设计、生机电制造工艺

通讯作者:
蔡念　cainian@gdut.edu.cn

中图分类号: TP274
计量
- 文章访问数: 912
- HTML全文浏览量: 472
- PDF下载量: 103
- 被引次数: 0
出版历程
- 收稿日期: 2021-11-10
- 修回日期: 2022-01-09
- 录用日期: 2022-01-12
- 网络出版日期: 2022-02-01
- 刊出日期: 2022-05-25

Adaptive Inspection for Void Defects Inside Solder Joints of Chip Resistors

CAI Nian^{1, 5
, ,},
XIAO Meng¹,
XIAO Pan⁴,
ZHOU Shuai^{2, 3},
QIU Baojun³,
WANG Han⁴

1.
School of Information Engineering, Guangdong University of Technology, Guangzhou 510006, China
2.
Tianjin University, Tianjin 300072, China
3.
China Electronic Product Reliability and Environmental Testing Research Institute, Guangzhou 510006, China
4.
School of Electromechanical Engineering, Guangdong University of Technology, Guangzhou 510006, China
5.
Huizhou Guangdong University of Technology IoT Cooperative Innovation Institute Co., Ltd., Huizhou 516025, China

Funds: The National Natural Science Foundation of China (62171142), The Natural Science Foundation of Guangdong Province (2021A1515011908), The Research Fund for Colleges and Universities in Huizhou (2019HZKY003)

摘要

摘要: 贴片电阻在回流焊过程中，受工艺影响，焊点内部或多或少会存在空洞缺陷，空洞占比率过高会严重降低器件的可靠性。该文融合局部预拟合(LPF)活动轮廓模型和自适应圆形卷积核，提出一种贴片电阻焊点内部空洞缺陷自适应检测方法。首先，根据贴片电阻图像具有明暗两个明显区域的特点，通过求解区域平均灰度差异最大的优化问题将其自适应地分为较暗和较亮两个区域。然后，针对较暗区域中空洞与背景之间对比度低、空洞分布较稀疏、面积偏大等特点，采用局部预拟合活动轮廓模型进行空洞检测；针对较亮区域中空洞与背景之间差异明显、空洞分布密集、面积偏小等特点，提出一种自适应圆形卷积核检测空洞。最后，采用形状因子和平均灰度策略剔除误检测，实现贴片电阻焊点内部空洞精细检测。实验结果表明，该文算法相较于其他检测算法性能有明显的提升，平均Dice系数高达0.8846。
- 空洞检测 /
- 贴片电阻 /
- 局部预拟合活动轮廓模型 /
- 自适应圆形卷积核 /
- 平均灰度策略
Abstract: In the process of reflow soldering, void defects inevitably emerge inside solder joints of chip resistors, which will influence reliability of the device. In this paper, an adaptive inspection method for void defects inside solder joints of chip resistors is proposed by combining a Local Pre-Fitted (LPF) active contour model and circular convolutions with adaptive kernels. First, since the image of chip resistor has two distinct regions, dark and bright regions are adaptively separated from the image after solving the optimization problem with the largest difference between the average gray level values of the two regions. Then, considering low contrast between voids and the image background, sparse distribution and large areas of voids in the dark region, LPF active contour model is used to inspect voids. As for the obvious difference between voids and the image background, dense distribution and small areas of voids in the bright region, circular convolutions with adaptive kernels are proposed to inspect voids. Finally, false detection can be eliminated by the shape factor and an average gray strategy to realize accurate void inspection. Experimental results show that the proposed method is superior to other inspection methods with an average Dice coefficient of 0.8846.
- Void detection /
- Chip resistor /
- Local Pre-Fitted (LPF) model /
- Circular convolution with adaptive kernel /
- Average-gray strategy

HTML全文

图 1 贴片电阻焊点内部空洞缺陷自适应检测算法框架

下载: 全尺寸图片幻灯片

图 2 基于自适应圆形卷积核的空洞缺陷粗检测方法

下载: 全尺寸图片幻灯片

图 3 不同算法的空洞缺陷检测视觉效果

下载: 全尺寸图片幻灯片

表 1 不同尺寸圆形卷积核的检测性能对比

9×9 29×29 49×49 99×99 199×199 本文

Dice系数 0.4413 0.7287 0.7321 0.7736 0.7479 0.8453
处理时间(s) 0.204 0.218 0.224 0.229 0.253 0.327

下载: 导出CSV

表 2 LPF不同对核的分割Dice系数和消耗时间

3×3 5×5 7×7 9×9 11×11 13×13

Dice系数 0.8562 0.8872 0.8880 0.8910 0.8907 0.8881
处理时间(s) 2.648 4.360 7.075 10.626 15.020 20.305

下载: 导出CSV

表 3 亮、暗区域的消融实验(Dice)

较亮区域较暗区域

自适应圆形卷积核 0.8453 0.3976
LPF 0.7951 0.8637

下载: 导出CSV

表 4 不同算法的空洞缺陷检测统计结果

指标 Acc(%) F1 Dice

DRLSE 79.10 0.8833 0.5630
RSF+LoG 79.10 0.8833 0.5965
LoG 92.54 0.9545 0.8576
U-Net 88.06 0.9298 0.7650
LPF 85.82 0.9177 0.8637
本文 95.52 0.9725 0.8846

下载: 导出CSV

参考文献(20)

[1]	ILLÉS B, KRAMMER O, and GÉCZY A. Reflow Soldering: Apparatus and Heat Transfer Processes[M]. Amsterdam: Elsevier, 2020: 5–8.
[2]	SAID A F, BENNETT B L, KARAM L J, et al. Automated void detection in solder balls in the presence of vias and other artifacts[J]. IEEE Transactions on Components, Packaging and Manufacturing Technology, 2012, 2(11): 1890–1901. doi: 10.1109/TCPMT.2011.2182613
[3]	WILD P, LORENZ D, GRÖZINGER T, et al. Effect of voids on thermo-mechanical reliability of chip resistor solder joints: Experiment, modelling and simulation[J]. Microelectronics Reliability, 2018, 85: 163–175. doi: 10.1016/j.microrel.2018.04.014
[4]	BUŠEK D, DUŠEK K, RŮŽIČKA D, et al. Flux effect on void quantity and size in soldered joints[J]. Microelectronics Reliability, 2016, 60: 135–140. doi: 10.1016/j.microrel.2016.03.009
[5]	WANG Yu, WANG Mingquan, and ZHANG Zhijie. Microfocus X-ray printed circuit board inspection system[J]. Optik, 2014, 125(17): 4929–4931. doi: 10.1016/j.ijleo.2014.04.027
[6]	PENG Shaohu and DO NAM H. Void defect detection in ball grid array X-ray images using a new blob filter[J]. Journal of Zhejiang University SCIENCE C, 2012, 13(11): 840–849. doi: 10.1631/jzus.C1200065
[7]	MOURI M, KATO Y, YASUKAWA H, et al. A study of using nonnegative matrix factorization to detect solder-voids from radiographic images of solder[C]. The 2014 IEEE 23rd International Symposium on Industrial Electronics, Istanbul, Turkey, 2014: 1074–1079.
[8]	NUANPRASERT S, BABA S, and SUZUKI T. A simple automated void defect detection for poor contrast x-ray images of BGA[C]. The 3rd International Conference on Industrial Application Engineering, Kitakyushu, Japan, 2015.
[9]	MOORE T D, VANDERSTRAETEN D, and FORSSELL P M. Three-dimensional X-ray laminography as a tool for detection and characterization of BGA package defects[J]. IEEE Transactions on Components and Packaging Technologies, 2002, 25(2): 224–229. doi: 10.1109/TCAPT.2002.1010010
[10]	NEELURU V K and AHUJA V. Void region segmentation in ball grid array using u-net approach and synthetic data[J]. arXiv: 1907.04222, 2019.
[11]	AKDENİZ C T, DOKUR Z, and ÖLMEZ T. Detection of BGA solder defects from X-ray images using deep neural network[J]. Turkish Journal of Electrical Engineering & Computer Sciences, 2020, 28(4): 2020–2029. doi: 10.3906/elk-1910-135
[12]	DING Keyan, XIAO Linfang, and WENG Guirong. Active contours driven by local pre-fitting energy for fast image segmentation[J]. Pattern Recognition Letters, 2018, 104: 29–36. doi: 10.1016/j.patrec.2018.01.019
[13]	HE Kaiming and SUN Jian. Fast guided filter[J]. arXiv: 1505.00996, 2015.
[14]	LI Chunming, XU Chenyang, GUI Changfeng, et al. Distance regularized level set evolution and its application to image segmentation[J]. IEEE Transactions on Image Processing, 2010, 19(12): 3243–3254. doi: 10.1109/TIP.2010.2069690
[15]	DING Keyan, XIAO Linfang, and WENG Guirong. Active contours driven by region-scalable fitting and optimized Laplacian of Gaussian energy for image segmentation[J]. Signal Processing, 2017, 134: 224–233. doi: 10.1016/j.sigpro.2016.12.021
[16]	GAO Shangbing, YANG Jian, and YAN Yunyang. A novel multiphase active contour model for inhomogeneous image segmentation[J]. Multimedia Tools and Applications, 2014, 72(3): 2321–2337. doi: 10.1007/s11042-013-1553-2
[17]	WANG Lei, CHANG Yan, WANG Hui, et al. An active contour model based on local fitted images for image segmentation[J]. Information Sciences, 2017, 418/419: 61–73. doi: 10.1016/j.ins.2017.06.042
[18]	ZHAO Wencheng, XU Xianze, ZHU Yanyan, et al. Active contour model based on local and global Gaussian fitting energy for medical image segmentation[J]. Optik, 2018, 158: 1160–1169. doi: 10.1016/j.ijleo.2018.01.004
[19]	罗钧, 杨永松, 侍宝玉. 基于改进的自适应差分演化算法的二维Otsu多阈值图像分割[J]. 电子与信息学报, 2019, 41(8): 2017–2024. doi: 10.11999/JEIT180949 LUO Jun, YANG Yongsong, and SHI Baoyu. Multi-threshold image segmentation of 2D Otsu based on improved adaptive differential evolution algorithm[J]. Journal of Electronics &Information Technology, 2019, 41(8): 2017–2024. doi: 10.11999/JEIT180949
[20]	SHANG Caijie, ZHANG Dong, and YANG Yan. A gradient-based method for multilevel thresholding[J]. Expert Systems with Applications, 2021, 175: 114845. doi: 10.1016/j.eswa.2021.114845