A grey-ANN approach for optimizing the QFN component assembly process for smart phone application

Huang, Chien‐Yi; Chen, Ching‐Hsiang; Lin, Yueh-Hsun

doi:10.1108/ssmt-10-2015-0034

Cited by 9 publications

(4 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As the ideal parameter combinations of the three quality characteristics are inconsistent, principal components analysis is used to linearly combine the relational quality characteristics and solve the multi-quality characteristic problem. Gray relational analysis is used to calculate the gray correlation (Vimal et al, 2017;Huang et al, 2016;Lu et al, 2009;Chiang and Chang, 2006). The analysis steps are described, as follows:…”

Section: Principal Components and Gray Relational Analysismentioning

confidence: 99%

Application of multi-quality parameter design in the optimization of underfilling process – a case study of a vehicle electronic module

Huang

Shen

et al. 2020

SSMT

Self Cite

View full text Add to dashboard Cite

Purpose This paper aims to discuss the key factors affecting the quality characteristics, such as the number of solder balls, the spread distance of residual underfill and the completion time of the underfilling. Design/methodology/approach The Taguchi method is applied to configure the orthogonal table and schedule and execute the experiment. In addition, principal components analysis is used to obtain the points. Then, based on gray relational analysis and the technique for order preference by similarity to ideal solution, the closeness between each quality characteristic and the ideal solution is adopted as the basis for evaluating the quality characteristics. Findings The optimal parameter combination is proposed, which includes 4 dispensing (11 mg/dispensing), a “half flow” interval state, 80°C preheating module PCB board and an L-shaped dispensing path and verification testing is performed. Originality/value For vehicles and handheld electronic products, solder joints that connect electronic components to printed circuit boards may be cracked due to collision, vibration or falling. Consequently, solder balls are closely surrounded and protected by the underfill to improve joint strength and resist external force factors, such as collision and vibration. This paper addresses the defects caused during the second reflow process of a vehicle electronic communication module after the underfilling process.

show abstract

Section: Principal Components and Gray Relational Analysismentioning

confidence: 99%

Application of multi-quality parameter design in the optimization of underfilling process – a case study of a vehicle electronic module

Huang

Shen

et al. 2020

SSMT

Self Cite

View full text Add to dashboard Cite

show abstract

“…Existing studies have made efforts to apply data-driven methods to packaging design (Huang et al , 2016; Yi and Jones, 2019). Particle swarm optimization (PSO) algorithm combined with 3-D finite-difference time-domain technique has been proposed to pursue ultra-compact silicon waveguides with low bending loss (Fu et al , 2021).…”

Section: Introductionmentioning

confidence: 99%

Data-driven electronic packaging structure inverse design with an adaptive surrogate model

Liu

Xue

Lian

et al. 2023

SSMT

View full text Add to dashboard Cite

Purpose The conventional design method relies on a priori knowledge, which limits the rapid and efficient development of electronic packaging structures. The purpose of this study is to propose a hybrid method of data-driven inverse design, which couples adaptive surrogate model technology with optimization algorithm to to enable an efficient and accurate inverse design of electronic packaging structures. Design/methodology/approach The multisurrogate accumulative local error-based ensemble forward prediction model is proposed to predict the performance properties of the packaging structure. As the forward prediction model is adaptive, it can identify respond to sensitive regions of design space and sample more design points in those regions, getting the trade-off between accuracy and computation resources. In addition, the forward prediction model uses the average ensemble method to mitigate the accuracy degradation caused by poor individual surrogate performance. The Particle Swarm Optimization algorithm is then coupled with the forward prediction model for the inverse design of the electronic packaging structure. Findings Benchmark testing demonstrated the superior approximate performance of the proposed ensemble model. Two engineering cases have shown that using the proposed method for inverse design has significant computational savings while ensuring design accuracy. In addition, the proposed method is capable of outputting multiple structure parameters according to the expected performance and can design the packaging structure based on its extreme performance. Originality/value Because of its data-driven nature, the inverse design method proposed also has potential applications in other scientific fields related to optimization and inverse design.

show abstract

“…Solder paste printing is commonly used for attaching surface mount device to printed circuit boards (PCBs). It has been reported that a majority of the problems associated with PCB assembly can be traced back to the solder paste printing process (Ladani et al , 2008; Amalu et al , 2011; Wang, 2013; Huang et al , 2016). It is also recognized that the solder paste printing process has a dramatic impact on the productivity and quality of surface mount assembly line (Sriperumbudur et al , 2017).…”

Section: Introductionmentioning

confidence: 99%

A method for optimizing stencil cleaning time in solder paste printing process

Cao

et al. 2019

SSMT

View full text Add to dashboard Cite

Purpose Stencil cleaning is an important operation in solder paste printing process. Frequent cleaning may interrupt printing process and increase idle time, as well as loss for performing cleaning. This paper aims to propose a method to optimize the stencil cleaning time and reduce unnecessary cleaning operations and losses. Design/methodology/approach This paper uses a discrete-time, discrete-state homogeneous Markov chain to model the stencil printing performance degradation process, and the quality loss during the stencil printing process is estimated based on this degradation model. A stencil cleaning decision model based on renewal reward theorem is established, and the optimal cleaning time is obtained through a balance between quality loss and the loss on idle time. Findings A stencil cleaning decision model for solder paste printing is established, and numerical simulation results show that there exists an optimal stencil cleaning time which minimizes the long-term loss. Originality/value Stencil cleaning control is very important for solder paste printing. However, there are very few studies focusing on stencil cleaning control. This research contributes to developing a model to optimize the stencil cleaning time in solder paste printing process.

show abstract

A grey-ANN approach for optimizing the QFN component assembly process for smart phone application

Cited by 9 publications

References 35 publications

Application of multi-quality parameter design in the optimization of underfilling process – a case study of a vehicle electronic module

Application of multi-quality parameter design in the optimization of underfilling process – a case study of a vehicle electronic module

Data-driven electronic packaging structure inverse design with an adaptive surrogate model

A method for optimizing stencil cleaning time in solder paste printing process

Contact Info

Product

Resources

About