Multivariate statistical process control for autocorrelated processes

Research output: Contribution to journalArticle

20 Citations (Scopus)

Abstract

Multivariate statistical process control is often used in chemical and process industries where autocorrelation is most prevalent. We present a realistic mode that generates autocorrelation and crosscorrelation and provides a useful approach to characterizing process data. We show how our model relates to the widely-used method of principal component analysis, distinguish between types of assignable causes, and present a useful control statistic based on a principal component decomposition that is not autocorrelated. The control chart for this statistic can be developed by a routine analysis even when the input data is autocorrelated. Furthermore, to characterize our results, we show that any linear combination of the input data that is not autocorrelated is related to our control statistic.

Original languageEnglish (US)
Pages (from-to)1715-1724
Number of pages10
JournalInternational Journal of Production Research
Volume34
Issue number6
StatePublished - 1996
Externally publishedYes

Fingerprint

Statistical process control
Statistics
Autocorrelation
Principal component analysis
Decomposition
Multivariate statistical process control
Industry

ASJC Scopus subject areas

  • Management Science and Operations Research
  • Industrial and Manufacturing Engineering

Cite this

Multivariate statistical process control for autocorrelated processes. / Runger, George.

In: International Journal of Production Research, Vol. 34, No. 6, 1996, p. 1715-1724.

Research output: Contribution to journalArticle

@article{4ddae7fbdc7c4c3a976be74148a45676,
title = "Multivariate statistical process control for autocorrelated processes",
abstract = "Multivariate statistical process control is often used in chemical and process industries where autocorrelation is most prevalent. We present a realistic mode that generates autocorrelation and crosscorrelation and provides a useful approach to characterizing process data. We show how our model relates to the widely-used method of principal component analysis, distinguish between types of assignable causes, and present a useful control statistic based on a principal component decomposition that is not autocorrelated. The control chart for this statistic can be developed by a routine analysis even when the input data is autocorrelated. Furthermore, to characterize our results, we show that any linear combination of the input data that is not autocorrelated is related to our control statistic.",
author = "George Runger",
year = "1996",
language = "English (US)",
volume = "34",
pages = "1715--1724",
journal = "International Journal of Production Research",
issn = "0020-7543",
publisher = "Taylor and Francis Ltd.",
number = "6",

}

TY - JOUR

T1 - Multivariate statistical process control for autocorrelated processes

AU - Runger, George

PY - 1996

Y1 - 1996

N2 - Multivariate statistical process control is often used in chemical and process industries where autocorrelation is most prevalent. We present a realistic mode that generates autocorrelation and crosscorrelation and provides a useful approach to characterizing process data. We show how our model relates to the widely-used method of principal component analysis, distinguish between types of assignable causes, and present a useful control statistic based on a principal component decomposition that is not autocorrelated. The control chart for this statistic can be developed by a routine analysis even when the input data is autocorrelated. Furthermore, to characterize our results, we show that any linear combination of the input data that is not autocorrelated is related to our control statistic.

AB - Multivariate statistical process control is often used in chemical and process industries where autocorrelation is most prevalent. We present a realistic mode that generates autocorrelation and crosscorrelation and provides a useful approach to characterizing process data. We show how our model relates to the widely-used method of principal component analysis, distinguish between types of assignable causes, and present a useful control statistic based on a principal component decomposition that is not autocorrelated. The control chart for this statistic can be developed by a routine analysis even when the input data is autocorrelated. Furthermore, to characterize our results, we show that any linear combination of the input data that is not autocorrelated is related to our control statistic.

UR - http://www.scopus.com/inward/record.url?scp=0030173508&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030173508&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0030173508

VL - 34

SP - 1715

EP - 1724

JO - International Journal of Production Research

JF - International Journal of Production Research

SN - 0020-7543

IS - 6

ER -