Summary
In controlling the mean of a multivariate normally distributed quality characteristic the main disadvantage of the globalT 2-control charts is that they don't indicate the component of the quality characteristic which gives rise to an alarm. To avoid this disadvantage the joint use of¯x-charts is proposed in this paper, where — for the sake of simplicity — the investigations are restricted to the case of independent components and to one-sided¯x-charts. On the basis of an economic objective function an approximation to the optimal design of the¯x-charts procedure is derived and discussed. It turns out that at least in the bivariate case the nearly optimal economic design is very close to the exact solution.
Zusammenfassung
Kontrolliert man den Mittelwert eines multivariat-normalverteilten Merkmals mit Hilfe einer globalenT 2-Karte, so besteht deren wesentlicher Nachteil darin, daß man bei einem Alarm nicht weiß, welche Komponente des Merkmals mutmaßlich außer Kontrolle geraten ist. Dies wird im vorliegenden Aufsatz dadurch vermieden, daß die parallele Verwendung mehrerer Mittelwertkarten empfohlen wird. Dabei beschränken wir uns der Einfachheit halber auf den Fall unabhängiger Komponenten und auf den Fall einseitiger Mittelwertkarten. Aufgrund einer ökonomischen Zielfunktion wird eine Näherung für ein optimales Verfahren dieses Types hergeleitet und diskutiert. Es stellt sich heraus, daß zumindest im bivariaten Fall die Näherungslösung mit der exakten Lösung nahezu identisch ist.
Similar content being viewed by others
References
Arnold BF (1987a) Minimax-Prüfpläne für die Prozeßkontrolle. Band 28 der Reihe “Arbeiten zur Angewandten Statistik”. Physica-Verlag, Heidelberg
Arnold BF (1987b) The economic design of¯X-charts used in parallel to control the means of independent quality characteristics. Economic Quality Control, Technical Report No. 8 of the Würzburg Research Group on Quality Control
Arnold BF, Collani E v (1987) Economic process control. Statistica Neerlandica 41:89–97
Arnold BF, Collani E v (1988) On the robustness of¯X-charts. To appear in: Statistics
Collani E v (1981) Kostenoptimale Prüfpläne für die laufende Kontrolle eines normalverteilten Merkmals. Metrika 28:211–236
Collani E v (1988) A unified approach to optimal process control. Metrika 35:145–159
Collani E v (1989) The economic design of control charts. To appear. Teubner-Verlag, Stuttgart
Duncan AJ (1956) The economic design of¯X-charts used to maintain current control of a process. Journal of the American Statistical Association 51:228–242
Gibra IN (1975) Recent developments in control chart techniques. Journal of Quality Technology 7:183–192
Lorenzen TJ, Vance LC (1986) The economic design of control charts: a unified approach. Technometrics 28:3–10
Montgomery DC (1980) The economic design of control charts: a review and literature survey. Journal of Quality Technology 12:75–87
Montgomery DC (1985) Introduction to statistical quality control. Wiley, New York
Mongomery DC, Klatt PJ (1972a) Economic design ofT 2 control charts to maintain current control of a process. Management Science 19
Montgomery DC, Klatt PJ (1972b) Minimum cost multivariate quality control test. AIIE (American Institute of Industrial Engineers) Transactions 4
Taguchi G (1985) Quality engineering in Japan. Communications in Statistics — Theory and Methods 14:2785–2801
Uhlmann W (1982) Statistische Qualitätskontrolle. Teubner-Verlag, Stuttgart
Vance LC (1983) A bibliography of statistical quality control chart techniques, 1970–1980. Journal of Quality Technology 15:59–62
Author information
Authors and Affiliations
Additional information
Supported by the Deutsche Forschungsgemeinschaft (DFG).
Rights and permissions
About this article
Cite this article
Arnold, B.F. An economic¯X-chart approach to the joint control of the means of independent quality characteristics. ZOR - Methods and Models of Operations Research 34, 59–74 (1990). https://doi.org/10.1007/BF01415951
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF01415951