典型文献
Improving accuracy of automatic optical inspection with machine learning
文献摘要：
Electronic devices require the printed circuit board(PCB) to support the whole structure,but the assembly of PCBs suffers from welding problem of the electronic components such as surface mounted devices (SMDs) resistors.The auto-mated optical inspection (AOI) machine,widely used in indus-trial production,can take the image of PCBs and examine the welding issue.However,the AOI machine could commit false negative errors and dedicated technicians have to be employed to pick out those misjudged PCBs.This paper proposes a ma-chine learning based method to improve the accuracy of AOI.In particular,we propose an adjacent pixel RGB value based method to pre-process the image from the AOI machine and build a customized deep learning model to classify the image.We present a practical scheme including two machine learn-ing procedures to mitigate AOI errors.We conduct experiments with the real dataset from a production line for three months,the experimental results show that our method can reduce the rate of misjudgment from 0.3％-0.5％ to 0.02％-0.03％,which is meaningful for thousands of PCBs each containing thousands of electronic components in practice.
文献关键词：
中图分类号：
作者姓名：
Xinyu TONG;Ziao YU;Xiaohua TIAN;Houdong GE;Xinbing WANG
作者机构：
Department of Electronic Information and Electrical Engineering,Shanghai Jiao Tong University,Shanghai 200240,China;Ambit Microsystems,Shanghai 201600,China
文献出处：
引用格式：
[1]Xinyu TONG;Ziao YU;Xiaohua TIAN;Houdong GE;Xinbing WANG-.Improving accuracy of automatic optical inspection with machine learning)[J].计算机科学前沿,2022(01):41-52
A类：
misjudged,misjudgment
B类：
Improving,accuracy,automatic,optical,inspection,machine,learning,Electronic,devices,require,printed,circuit,board,support,whole,structure,but,assembly,PCBs,suffers,from,welding,problem,electronic,components,such,surface,mounted,SMDs,resistors,mated,AOI,widely,used,indus,trial,production,can,take,image,examine,issue,However,could,commit,false,negative,errors,dedicated,technicians,have,be,employed,pick,out,those,This,paper,proposes,method,improve,In,particular,adjacent,pixel,RGB,value,process,build,customized,deep,model,classify,We,present,practical,scheme,including,two,procedures,mitigate,conduct,experiments,real,dataset,line,three,months,experimental,results,show,that,our,reduce,rate,which,meaningful,thousands,each,containing,practice
AB值：
0.601662
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
