Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                

The Performance Assessment and Optimal Design of EWMA Charts Based on Average Product Length

Article Preview

Abstract:

ARL (Average Run Length) is used as a tool to measure the performance of control chart. But it isn’t very accurate. In this paper, a Markov chain method is proposed to calculate the APL (Average Product Length) of EWMA chart, and APL is used as a criterion of performance assessment to decide optimal design of this chart. By comparing with traditional EWMA design method, we can find that this method can detect little shifts in processes more quickly.

You might also be interested in these eBooks

Info:

Periodical:

Advanced Materials Research (Volumes 383-390)

Pages:

2573-2577

Citation:

Online since:

November 2011

Authors:

Export:

Price:

Сopyright:

© 2012 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

[1] Roberts, S.W. Control Chart Tests Based on Geometric Moving Averages [J]. Technometrics, 1959, 1: 39~250.

DOI: 10.1080/00401706.1959.10489860

Google Scholar

[2] Crowder, S.V. A simple Method for Studying Run Length Distributions of Exponentially.

Google Scholar

[1] Weighted Moving Chart [J]. Technometrics, 1987, 29: 93~407.

Google Scholar

[3] Crowder, S.V. Design of Exponentially Weighted Moving Average Schemes [J]. Journal of.

Google Scholar

[1] Quality Technology, 1989, 21: 55-162.

Google Scholar

[4] Lucas, J.M. and Saccucci, M.S. Exponentially Weighted Moving Average Control Schemes.

Google Scholar

[1] Properties and Enhancements [J]. Technometrics, 1990, 32(1): ~12.

Google Scholar

[5] J. Bert Keats, John D. Miskulin, Runger, G.C. Statistical Process Control Scheme Design [J].

Google Scholar

[1] Journal of Quality Technology, 1995, 27(1): 31~246.

Google Scholar

[6] Calzada, M.E., Scariano, S.M. Reconciling the Integral Equation and Markov Chain.

Google Scholar

[1] Approaches for Computing EWMA Average Run Lengths [J]. Communications in Statistics.

Google Scholar

[1] 2003, 32(2): 91~604.

Google Scholar

[7] S. W. Roberts, Control chart tests based on geometric moving averages, Technometrics, 1959, 1, 239-250.

DOI: 10.1080/00401706.1959.10489860

Google Scholar

[8] S. W. Roberts, A comparison of some control chart procedures, Technometrics, 1966, 8, 411-430.

DOI: 10.1080/00401706.1966.10490374

Google Scholar

[9] P. B. Robison, T. Y. Ho. Average run lengths of geometric moving average charts by numerical methods, Technometrics, 1978, 20, 85-93.

DOI: 10.1080/00401706.1978.10489620

Google Scholar

[10] D. Brook, D. A. Evans, An approach to the probability distribution of CUSUM run length, Biometrics, 1972, 59, 539-549.

DOI: 10.1093/biomet/59.3.539

Google Scholar

[11] J. F. Macgregor, T. J. Harris, Discussion of Exponentially weighted moving average control schemes: properties and enhancements, Technometics, 1990, 32(1), 23-26.

DOI: 10.2307/1269840

Google Scholar

[12] G. Capizzi, G. Masarotto, An adaptive exponentially weighted moving average control chart, Technometics, 2003, 45, 199-207.

DOI: 10.1198/004017003000000023

Google Scholar

[13] Z. G. Stoumbos, M. R. Reynolds, Robustness to non-normality and autocorrelation of individuals control charts, Journal of statistical computing simulation, 2000, 66, 145-187.

DOI: 10.1080/00949650008812019

Google Scholar