To read the full version of this content please select one of the options below:

Applying data mining methodology to establish an intelligent decision system for PCBA process

Chien-Yi Huang (Department of Industrial Engineering and Management, National Taipei University of Technology, Taipei, Taiwan)
Marvin Ruano (Department of Management, National Taipei University of Technology, Taipei, Taiwan)
Ching-Hsiang Chen (A Test Lab Techno Corp. Taipei, Taiwan)
Christopher Greene (Binghamton University, Binghamton, New York, USA)

Soldering & Surface Mount Technology

ISSN: 0954-0911

Article publication date: 13 August 2019

Issue publication date: 21 August 2019

Abstract

Purpose

This paper aims to consider the practical production environment of electronics manufacturing industry firms, and the large quantities of information collected on machine processes, testing data and production reports, while simultaneously taking into account the properties of the processing environment, in conducting analysis to obtain valuable information.

Design/methodology/approach

This research constructs a prediction model of the circuit board assembly process yield. A decision tree is used to extract the key attributes. The authors also integrate association rules to determine the relevance of key attributes of undesirable phenomena.

Findings

The results assure the successful application of the methodology by reconfirming the rules for solder skip and short circuit occurrence and their causes.

Originality/value

Measures for improvement are recommended, production parameters determined and debugging suggestions made to improve the process yield when the new process is implemented.

Keywords

Citation

Huang, C.-Y., Ruano, M., Chen, C.-H. and Greene, C. (2019), "Applying data mining methodology to establish an intelligent decision system for PCBA process", Soldering & Surface Mount Technology, Vol. 31 No. 4, pp. 271-278. https://doi.org/10.1108/SSMT-10-2018-0036

Publisher

:

Emerald Publishing Limited

Copyright © 2019, Emerald Publishing Limited