Design factors and their effect on PCB assembly yield-statistical and neural network predictive models

Author

Li, Y. ; Mahajan, R.L. ; Tong, J.

Author_Institution

Center for Adv. Manuf. & Packaging of Microwave, Opt. & Digital Electron., Colorado Univ., Boulder, CO, USA

Volume

17

Issue

2

fYear

1994

fDate

6/1/1994 12:00:00 AM

Firstpage

183

Lastpage

191

Abstract

This study relates circuit board design features to assembly yields. Data used were collected over a period of one year from two circuit board assembly shops at AT&T. Design parameters that may affect the assembly yield were identified using knowledge of the assembly process. These parameters were then quantified for a set of board designs and related to the actual assembly yield by the statistical regression models and the artificial neural network (ANN) models. These models are able to predict the assembly yield with a root mean square (RMS) error of less than 5%. They can be used to predict the assembly yield for new board designs on the same line. Alternatively, they can be used to compare the performance of different lines by comparing the expected yield for a given design with the actual yield

Keywords

modelling; neural nets; printed circuit design; printed circuit manufacture; statistical analysis; AT&T; PCB assembly yield; artificial neural network models; assembly process; assembly yield; assembly yields; board designs; circuit board assembly shops; circuit board design features; design factors; design parameters; neural network predictive models; root mean square error; statistical models; statistical regression models; Assembly; Components, packaging, and manufacturing technology; Lead; Neural networks; Optical surface waves; Packaging; Predictive models; Printed circuits; Printing; Production;

fLanguage

English

Journal_Title

Components, Packaging, and Manufacturing Technology, Part A, IEEE Transactions on

Publisher

ieee

ISSN

1070-9886

Type

jour

DOI

10.1109/95.296399

Filename

296399