A fuzzy-neural approach with BPN post-classification for job completion time prediction in a semiconductor fabrication plant

Tin-Chih Chen*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

1 Scopus citations

Abstract

Predicting the completion time of a job is a critical task to a semiconductor fabrication plant. Many recent studies have shown that pre-classifying a job before predicting the completion time was beneficial to prediction accuracy. However, most classification approaches applied in this field could not absolutely classify jobs. Besides, whether the pre-classification approach combined with the subsequent prediction approach was suitable for the data was questionable. For tackling these problems, a fuzzy-neural approach with back-propagation-network (BPN) post-classification is proposed in this study, in which a job is post-classified with some BPNs instead after predicting its completion time with a fuzzy BPN (FBPN). In this novel way, only jobs which estimated completion times are the same accurate will be clustered into the same category. To evaluate the effectiveness of the proposed methodology, production simulation is applied to generate test data. According to experimental results, post-classifying jobs might be very effective in enhancing the accuracy of job completion time prediction in a semiconductor fabrication plant.

Original languageEnglish
Title of host publicationAnalysis and Design of Intelligent Systems using Soft Computing Techniques
EditorsPatricia Melin, Eduardo Gomez Ramirez, Janusz Kacprzyk, Witold Pedrycz
Pages580-589
Number of pages10
DOIs
StatePublished - 1 Dec 2007

Publication series

NameAdvances in Soft Computing
Volume41
ISSN (Print)1615-3871
ISSN (Electronic)1860-0794

Fingerprint Dive into the research topics of 'A fuzzy-neural approach with BPN post-classification for job completion time prediction in a semiconductor fabrication plant'. Together they form a unique fingerprint.

Cite this