[1]曹鹏娟,王明泉,范 涛,等.基于改进 U-Net 的球栅阵列气泡缺陷检测方法[J].机械与电子,2023,41(01):20-24.
　CAO Pengjuan,WANG Mingquan,FAN Tao,et al.Defect Detection Method of Bubble in Ball Grid Array Based on Improved U-Net[J].Machinery & Electronics,2023,41(01):20-24.
点击复制

基于改进 U-Net 的球栅阵列气泡缺陷检测方法()
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
41
期数:
2023年01期
页码:
20-24
栏目:
自动控制与检测
出版日期:
2023-01-25

文章信息/Info

Title:
Defect Detection Method of Bubble in Ball Grid Array Based on Improved U-Net
文章编号:
1001-2257 ( 2023 ) 01-0020-05
作者:
曹鹏娟; 王明泉; 范 涛; 朱榕榕; 刘嘉宇
中北大学仪器科学与动态测试教育部重点实验室,山西 太原 030051
Author(s):
CAO Pengjuan ;  WANG Mingquan ;  FAN Tao ;  ZHU Rongrong ;  LIU Jiayu
( Key Laboratory of Instrumentation Science and Dynamic Measurement ( Ministry of Education ), North University of China , Taiyuan 030051 , China
关键词:
U-Net ; 深度可分离卷积; 密集块; 图像分割
Keywords:
U-Net ;  depth separable convolution ;  dense block ;  image segmentation
分类号:
TP391.4 ; TN405
文献标志码:
A
摘要:
针对现有基于深度学习的图像分割算法在球栅阵列( BGA )焊点气泡检测中检测效率较低,无法满足工业生产中实时性的检测需求,提出了一种基于改进 U-Net 的球栅阵列缺陷识别方法。该方法在现有的 U-Net 经典网络的基础上提出用深度可分离卷积与密集连接结合的轻量密集连接单元替换常规的卷积单元,同时添加多尺度跳跃连接减少编解码特征之间的差异,实现针对 BGA 焊点气泡的精确分割和提取。采用自建数据集对该方法的有效性进行实验,结果表明,改进的 U-Net 模型网络在减少 U-Net 网络计算复杂度的同时提升了网络性能,能够增加 BGA 焊点气泡的检测效率。
Abstract:
Aiming at the low detection efficiency of existing image segmentation algorithms based on deep learning in ball grid array ( BGA ) solder spot bubble detection , which can not meet the real-time detection requirements in industrial production , a defect recognition method based on improved U-Net for ball grid array is proposed.Based on the existing U-Net classical network , this method proposes to replace the conventional convolution unit with a lightweight dense connection unit combining deep separable convolution and dense connection , and add multi-scale jump connection to reduce the differences among codec features , so as to achieve accurate segmentation and extraction of BGA solder joint bubbles.The results show that the improved U-Net model network improves network performance while reducing the computational complexity of the U-Net network and can increase the efficiency of BGA solder joint bubble detection.

参考文献/References:

[ 1 ] 张瑞秋 . 面向 SMT 的锥束 CT 图像重构关键理论与 BGA 焊点检测算法[ D ] . 广州:华南理工大学, 2014.

[ 2 ] 李乐,陈忠,张宪民 . 复杂背景下 X 射线 BGA 焊点气泡检测[ J ] . 焊接学报, 2015 , 36 ( 3 ): 80-84 , 5.
[ 3 ] 张俊生,王明泉,郭晋秦,等 .BGA 焊点气泡缺陷 X 射线图像的动态阈值分割方法 [ J ] . 火力与指挥控制,2018 , 43 ( 10 ): 113-116.
[ 4 ] CAI N , CEN G D , WU J X , et al.SMT solder joint inspection via a novel cascaded convolutional neural network [ J ] .IEEE Transactions on components , packaging and manufacturing technology , 2018 , 8 ( 4 ): 670-677.
[ 5 ] KIM S C , JEON H J , HONG S J.Ball grid array solder void inspection using mask R-CNN [ J ] .Journal of the semiconductor and display technology , 2021 , 20 ( 2 ): 126-130.
[ 6 ] ZHANG Q R , ZHANG M , GAMANAYAKE C , et al. Deep learning based solder joint defect detection on industrial printed circuit board X-ray images [ J ] .Complex and intelligent systems , 2022 , 8 ( 2 ): 1525-1537.
[ 7 ] 赵瑞祥,侯宏花,张鹏程,等 . 结合全卷积网络和 K 均值聚类的球栅阵列焊球边缘气泡分割[ J ] . 计算机应用,2019 , 39 ( 9 ): 2580-2585.
[ 8 ] RONNEBERGER O , FISCHER P , BROX T.U-Net : convolutional networks for biomedical image segmentation [ C ] ∥The 18th International Conference on Medical Image Computing and Computer-Assisted Intervention , Munich , Germany , 2015 : 234-241.
[ 9 ] 安冉 . 基于卷积神经网络的遥感图像变化检测[ D ] . 石家庄:河北地质大学,2020.
[ 10 ] 张萍 . 肺部病理图像细胞分割方法研究[ D ] . 沈阳:沈阳工业大学,2021.
[ 11 ] SANDLER M , HOWARD A , ZHU M L , et al.MobileNetV2 : inverted residuals and linear bottlenecks [ C ] ∥ 2018 IEEE / CVF Conference on Computer Vision and Pattern Recognition ( CVPR ),2018 : 4510-4520.
[ 12 ] CHOLLET F.Xception : deep learning with depthwise separable convolutions [ C ] ∥ 2017 IEEE Conference on Computer Vision and Pattern Recognition( CVPR ),2017 : 1800-1807.
[ 13 ] DONG J Y , ZHENG H C , LIAN L N.Dynamic facial expression recognition based on convolutional neural networks with dense connections [ C ] ∥2018 24th International Conference on Pattern Recognition( ICPR ), 2018 : 3433-3438.
[ 14 ] IBTEHAZ N , RAHMAN M S.MultiResUNet : rethinking the U-Net architecture for multimodal biomedical image segmentation [ J ] .Neural networks , 2020 , 121 : 74-87.

备注/Memo

备注/Memo:
收稿日期: 2022-07-06
基金项目:山西省重点研发计划( 201803D121069 );山西省高等学校科技创新项目( 2020L0624 );山西省信息探测与处理重点实验室基金( ISPT2020 5 )
作者简介:曹鹏娟 ( 1998- ),女,山西忻州人,硕士研究生,研究方向为图像处理等;王明泉 ( 1970- ),男,博士,教授,博士研究生导师,研究方向为图像处理与重建,通信作者。
更新日期/Last Update: 2023-02-28