Process design for transfer moulding of electronic packages using a case-based reasoning approach with fuzzy regression adaptation

K. W. Tong, Chun Kit Kwong, Ching Yuen Chan

Research output: Journal article publicationJournal articleAcademic researchpeer-review

3 Citations (Scopus)

Abstract

Process design of transfer moulding for electronic packages involves the determination of mould design parameter settings and process parameter settings that are calculated manually on a trial-and-error basis under the current practice. The effectiveness of the parameter settings is largely dependent on the experience of the engineers. In this paper, a process design for the transfer moulding of electronic packages using case-based reasoning (CBR) with fuzzy regression adaptation is described by which a CBR system for the process design of transfer moulding for electronic packages, named as CBR-TM, was developed to determine the initial mould design parameters and process parameter settings. In the design and development of the CBR-TM, fuzzy set theory was introduced in the case retrieval to improve the quality of retrieved cases. Additionally, a novel adaptation technique based on fuzzy regression was proposed to improve the accuracy of adapted solutions. Implementation of the CBR-TM has demonstrated that the time required for determination of proper initial mould design parameters and process parameter settings can be greatly reduced based on utilization of the proposed approach.
Original languageEnglish
Pages (from-to)27-40
Number of pages14
JournalInternational Journal of Computer Integrated Manufacturing
Volume18
Issue number1
DOIs
Publication statusPublished - 1 Jan 2005

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering
  • Computer Science Applications
  • Computational Theory and Mathematics
  • Management Science and Operations Research

Fingerprint

Dive into the research topics of 'Process design for transfer moulding of electronic packages using a case-based reasoning approach with fuzzy regression adaptation'. Together they form a unique fingerprint.

Cite this