0
RESEARCH PAPERS

A Multidisciplinary Design and Optimization Methodology for Ball Grid Array Packages Using Artificial Neural Networks

[+] Author and Article Information
Hamid Hadim1

Department of Mechanical Engineering,  Stevens Institute of Technology, Hoboken, NJ 07030ahadim@stevens.edu

Tohru Suwa

Department of Mechanical Engineering,  Stevens Institute of Technology, Hoboken, NJ 07030tsuwa@stevens.edu

1

Corresponding author.

J. Electron. Packag 127(3), 306-313 (Nov 16, 2004) (8 pages) doi:10.1115/1.1997161 History: Received October 20, 2003; Revised November 16, 2004

A systematic multidisciplinary electronics packaging design and optimization methodology, which takes into account the complexity of multiple design trade-offs, operated in conjunction with the artificial neural networks (ANNs) technique is presented. To demonstrate its capability, this method is applied to a plastic ball grid array package design. Multidisciplinary criteria including thermal, structural, electromagnetic leakage, and cost are optimized simultaneously using key design parameters as variables. A simplified routability criterion is also considered as a constraint. ANNs are used for thermal and structural performance predictions which resulted in large reduction in computational time. The present methodology is able to provide the designers a tool for systematic evaluation of the design trade-offs which are represented in the objective function. This methodology can be applied to any electronic product design at any packaging level from the system level to the chip level.

FIGURES IN THIS ARTICLE
<>
Copyright © 2005 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Figure 1

Cross-sectional view of ball grid array

Grahic Jump Location
Figure 2

Multidisciplinary optimization procedure used for ball grid array design

Grahic Jump Location
Figure 3

MLP model used for thermal resistance and thermal strain predictions

Grahic Jump Location
Figure 4

Finite element model used for thermal and thermal strain analyses

Grahic Jump Location
Figure 5

Junction-to-ambient thermal resistance: comparison of neural network prediction with FEM analysis results

Grahic Jump Location
Figure 6

Maximum solder ball strain with 16 thermal vias and 1.5 mm solder ball pitch: comparison of neural network prediction with FEM analysis results

Grahic Jump Location
Figure 7

Electromagnetic analysis results for source frequency of 5 GHz

Grahic Jump Location
Figure 8

Routability analysis result for 0.8 mm solder ball pitch and 175 I/O signals

Grahic Jump Location
Figure 9

Zoom of the objective function near global minimum for 0.8 mm solder ball pitch

Grahic Jump Location
Figure 10

Zoom of the objective function near global minimum for 96 thermal vias and 0.8 mm solder ball pitch

Grahic Jump Location
Figure 11

Zoom of the objective function near global minimum for 0.8 mm solder ball pitch and 22×22mm substrate size

Tables

Errata

Discussions

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In