A hybrid approach for identification of concurrent control chart patterns

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

31 Scopus Citations
View graph of relations


  • Chih-Hsuan Wang
  • Tse-Ping Dong
  • Way Kuo


Original languageEnglish
Pages (from-to)409-419
Journal / PublicationJournal of Intelligent Manufacturing
Issue number4
Publication statusPublished - Aug 2009
Externally publishedYes


Control chart patterns (CCPs) are widely used to identify the potential process problems in modern manufacturing industries. The earliest statistical techniques, including $${\bar{\rm X}}$$ chart and R chart, are respectively used for monitoring process mean and process variance. Recently, pattern recognition techniques based on artificial neural network (ANN) are very popular to be applied to recognize unnatural CCPs. However, most of them are limited to recognize simple CCPs arising from single type of unnatural variation. In other words, they are incapable to handle the problem of concurrent CCPs where two types of unnatural variation exist together within the manufacturing process. To facilitate the research gap, this paper presents a hybrid approach based on independent component analysis (ICA) and decision tree (DT) to identify concurrent CCPs. Without loss of generality, six types of concurrent CCPs are used to validate the proposed method. Experimental results show that the proposed approach is very successful to handle most of the concurrent CCPs. The proposed method has two limitations in real application: it needs at least two concurrent CCPs to reconstruct their source patterns and it may be incapable to handle the concurrent pattern incurred by two correlated process ("upward trend" and "upward shift"). © 2008 Springer Science+Business Media, LLC.

Research Area(s)

  • Concurrent control chart, Decision tree, Independent component analysis, Pattern recognition