Solder joint defect classification based on ensemble learning

Wu, Hao

doi:10.1108/ssmt-08-2016-0016

Cited by 29 publications

(16 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reduced cost and high-quality products are the foremost requirements of the electronics industry; hence, manufacturers are persistently working on cost diminution and quality improvements in PCBs (Alpha assembly solution, 2016). On the other hand, the electronics industry is confronting numerous challenges in the SMA printing process, for instance, insufficient solder, bridging, pseudo solder and tombstoning (Wu, 2017). Insufficient solder paste causes electrical opens in which there is isolation between two electrically connected points whilst with bridging, two or more pads become linked up through excess solder paste (Huang et al, 2011).…”

Section: Problem Statement and Implementationmentioning

confidence: 99%

Defect minimization and process improvement in SMT lead-free solder paste printing: a comparative study

Asghar

Rehman

Aman

et al. 2019

SSMT

View full text Add to dashboard Cite

Purpose The purpose of this paper is to investigate and minimize the printing-related defects in the surface mount assembly (SMA) process. Design/methodology/approach This paper uses an experimental approach to explore process parameter and printing defects during the SMA process. Increasing printing performance, various practices of solder paste (Ag3.0/Cu0.5/Sn) storage and handling are suggested. Lopsided paste problem is studied by varying squeegee pressure and the results are presented. Unfilled pads problems are observed for ball grid array (BGA) and quad flat package (QFP) which is mitigated by proper force tuning. In this paper, a comparative study is conducted which evaluates the manifestation of printing offset due to low-grade stencil. The input/output (I/O) boards were oxidized when the relative humidity was maintained beyond 70 per cent for more than 8 h. This pad oxidation problem is overcome by proper printed circuit board (PCB) handling procedures. When the unoptimized line is used, the paste wedged in the stencil and influences the performance of the screen printer, for this reason, an optimized line is proposed that minimize the printing defects. Findings The key findings are as follows: in the SMA process, printing quality is directly associated with solder paste quality. Experimentally, it is observed that a considerable variance in solder deposition occurred when the front and rear squeegee have different configurations. High-grade and unsoiled stencil results in superior paste deposition and less distinction. Insufficient solder paste and bridge problems also occur in printing when PCB pads are oxidized. Optimized line resolves solder paste clog issues, associated with stencil’s aperture. The cooling arrangement on the conveyor, after reflow, explicates hot jig problem. Control environmental conditions minimized static charges and printing defects. Originality/value The preceding studies emphasis mostly on the squeegee pressure, while other important parameters are not completely investigated. Moreover, it is very imperative to concurrently measure all parameters while varying the environmental conditions. This study highlights and provides an experimental approach to various PCB printing defects, and a comparative study has been conducted that concurrently measure all process parameters.

show abstract

Section: Problem Statement and Implementationmentioning

confidence: 99%

Defect minimization and process improvement in SMT lead-free solder paste printing: a comparative study

Asghar

Rehman

Aman

et al. 2019

SSMT

View full text Add to dashboard Cite

show abstract

“…Feature inspection methods have been widely used to inspect non-IC solder joints, especially chip components, which use some methods to extract the features from solder joint images for subsequent discrimination. Then, one or several classifiers (Acciani et al, 2006;Yun et al, 2000;Wu et al, 2013;Xie et al, 2009;Ko and Cho., 2000;Yan and Zhou., 2011;Wu, 2017;Acciani et al, 2007) are usually used to comprehensively and globally reveal the inherent relationships of the samples to implement the discrimination. However, salient and reliable features are hardly extracted from IC solder joint images with small sizes that have almost no distinct appearance differences between qualified and unqualified ones.…”

Section: Introductionmentioning

confidence: 99%

Automatic optical inspection system for IC solder joint based on local-to-global ensemble learning

Chen

Cai

Wang

et al. 2020

SSMT

View full text Add to dashboard Cite

Purpose Automatic optical inspection (AOI) systems have been widely used in many fields to evaluate the qualities of products at the end of the production line. The purpose of this paper is to propose a local-to-global ensemble learning method for the AOI system based on to inspect integrated circuit (IC) solder joints defects. Design/methodology/approach In the proposed method, the locally statistically modeling stage and the globally ensemble learning stage are involved to tackle the inspection problem. At the former stage, the improved visual background extraction–based algorithm is used for locally statistically modeling to grasp tiny appearance differences between the IC solder joints to achieve potential defect images for the subsequent stage. At the latter stage, mean unqualified probability is introduced based on a novel ensemble learning, in which an adaptive weighted strategy is proposed for revealing different contributions of the base classifier to the inspection performance. Findings Experimental results demonstrate that the proposed method achieves better inspection performance with an acceptable inspection time compared with some state-of-the-art methods. Originality/value The approach is a promising method for IC solder joint inspection, which can simultaneously grasp the local characteristics of IC solder joints and reveal inherently global relationships between IC solder joints.

show abstract

“…At present, the electronic components are mounted on the printed circuit board (PCB) by surface mount technology (SMT), therefore, the inspection of the solder joint component is critical (Wu, 2017; Cai et al , 2017; Benedek et al , 2013). Traditionally, the quality of solder joint has been detected by the way of manual inspection.…”

Section: Introductionmentioning

confidence: 99%

Solder joint inspection using eigensolder features

2018

SSMT

Self Cite

View full text Add to dashboard Cite

Purpose The authors propose a solder joint recognition method based on eigenspace technology. Design/methodology/approach The original solder joint image is transformed into a small set of feature subspace called “eigensolder”, which is the eigenvector of the training set and can represent a solder joint well. Then, the eigensolder feature is extracted by projecting the new solder joint image into the subspace, and the Euclidean distance measure is used to classify the solder joint. Findings The experimental results show that the proposed method is superior to the traditional classification method in solder joint recognition, and it can achieve 96.43 per cent recognition rate using only 15 eigenvalue images. It is suitable for the classification with small samples. Originality/value Traditional classification method like neural network and statistical method cost long time. Here, Eigensolder method is used to extract feature. Eigensolder method is more efficient, as it uses the principal component analysis method to reduce the feature dimension of input image and only measure the distance to classify.

show abstract

Solder joint defect classification based on ensemble learning

Cited by 29 publications

References 20 publications

Defect minimization and process improvement in SMT lead-free solder paste printing: a comparative study

Defect minimization and process improvement in SMT lead-free solder paste printing: a comparative study

Automatic optical inspection system for IC solder joint based on local-to-global ensemble learning

Solder joint inspection using eigensolder features

Contact Info

Product

Resources

About