Intelligent parametric design for a multiple-quality-characteristic glue-dispensing process

Chien-Yi Huang () and Kuo-Ching Ying ()
Additional contact information
Chien-Yi Huang: National Taipei University of Technology
Kuo-Ching Ying: National Taipei University of Technology

Journal of Intelligent Manufacturing, 2019, vol. 30, issue 5, No 15, 2305 pages

Abstract: Abstract For double-sided circuit boards, a wave soldering carrier is generally used to shield the devices mounted on the surface of the first side of the printed circuit board (PCB), so that the solder joints are not melted again through exposure to tin wave, causing the devices to deviate or fall as a result of flushing. However, carrier adoption increases production costs. This study proposes a glue-dispensing process to replace the wave soldering carrier. In addition, glue curing and reflow soldering were performed simultaneously to enhance production efficiency. An ecofriendly glue-dispensing process using low-cost CEM-1 substrates and a glue materials featuring a low curing temperature helps reduce energy consumption and carbon emissions. The Taguchi method was used to plan and execute this experiment. The quality characteristics of assembly reliability and manufacturing costs were considered in terms of glue thrust strength and per-PCB manufacturing cost, respectively. An intelligent parametric design applying PCA statistical methods and artificial neural networks (ANN) model was proposed. Results of a confirmation test indicated that the optimal parameter combination suggested by the ANN model was superior. The most satisfactory procedure parameter combination obtained comprised GMIR-130HF for the glue material, a curing temperature of $$140\,^{\circ }\hbox {C}$$ 140 ∘ C , a 1.1 m/min conveyor velocity, and a 0.09 Mpa dispensing pressure.

Keywords: Surface-mount technology; Taguchi method; Principal component analysis; Artificial neural network; Genetic algorithm (search for similar items in EconPapers)
Date: 2019
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://link.springer.com/10.1007/s10845-017-1389-0 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:joinma:v:30:y:2019:i:5:d:10.1007_s10845-017-1389-0

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/10845

DOI: 10.1007/s10845-017-1389-0

Access Statistics for this article

Journal of Intelligent Manufacturing is currently edited by Andrew Kusiak

More articles in Journal of Intelligent Manufacturing from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().