Robustness of χ CUSUM and CP CUSUM Using Fast Initial Response in Detecting of Process Dispersion

Main Article Content

Suganya Phantu
Saowanit Sukparungsee

Abstract

Statistical quality control relates with monitoring of process disturbances which they may be caused by changing either mean or dispersion process. The aim of this research is to study the robustness of chi-cumulative sum (χ CUSUM) and CP CUSUM charts by giving an initial value of CUSUM statistics in order to quick detect a change in process dispersion. The Fast Initial Response (FIR) or Head Start (HS) are given to 25%, 50% and 75% of control limit of control chart. The performance of control chart is usually measured by an out of control Average Run Length (ARL1) where the best performance of control chart will give the minimum ARL1. The performance of χ CUSUM and CP CUSUM control charts are compared when the processes are distributed Laplace(0,2), Logistic(2,2) and Gamma(9,1). The numerical results are carried out by Monte Carlo simulation with replication 10,000 times. We found that the performance of χ CUSUM is superior to CP CUSUM for small shifts in dispersion parameter, otherwise the CP CUSUM performs better than χ CUSUM for moderate to large shifts with using 75% HS. In addition, those control charts are robust to symmetric and asymmetric distributions of process for all level of ARL0.

Article Details

Section
Applied Science Research Articles

References

[1] D. C. Montgomery, Introduction to Statistical Quality Control, 4th ed. John Wiley & Sons, 2009.

[2] W. A. Shewhart, Economic Control of Quality of manufactured Product. D. Van Nostrand Company, Inc., 1931.

[3] E. S. Page, “Continuous inspection schemes,” Biometrika, vol. 41, no. 1–2, pp. 100–115, 1954.

[4] S. W. Roberts, “Control chart tests based on geometric moving average,” Techmometrics, vol. 42, no. 1, pp. 239–250, 1959.

[5] C. A. Acosta-Mejia, J. J. Pignatiello, and B. R. Venkateshwara, “A comparison of control charting procedures for monitoring process dispersion,” IIE Transactions, vol. 31, no. 6, pp. 569–579, 1999.

[6] K. Tuprah and M. Ncube, “A comparison of dispersion quality control charts,” Sequential Analysis, vol. 6, no. 2, pp. 155–163, 1987.

[7] C. H. Ng, “Development and evaluation of control charts using exponentially weighted moving averages,” M.S. thesis, Faculty of the Graduate College, Oklahoma State University, 1988.

[8] S. V. Crowder and M. D. Hamilton, “An EWMA for monitoring a process standard deviation,” Journal of Quality Technology, vol. 24, no. 1, pp. 12–21, 1992.

[9] T. C. Chang and F. F. Gan, “A cumulative sum control chart for monitoring process variance,” Journal of Quality Technology, vol. 27, no. 2, pp. 109–119, 1995.

[10] J. M. Lucas and R. B. Crosier, “Fast initial response for CUSUM quality-control schemes: Give your CUSUM a head start,” Technometrics, vol. 24, no. 3, pp. 199–205, 1982.

[11] S. H. Steiner, “EWMA control charts with Time-Varying control limits and fast initial response,” Journal of Quality Technology, vol. 31, no. 1, pp. 75–86, 1999.

[12] D. M. Hawkins and D. H. Olwell, “Cumulative sum charts and charting for quality improvement,” Springer Science & Business Media, 1998.

[13] A. Haq, “A new hybrid exponentially weighted moving average control chart for monitoring process mean,” Quality and Reliability Engineering International, vol. 29, no. 7, pp. 1015–1025, 2013.

[14] R. A. Sanusi, M. Riaz, N. Abbas, and M. R. Abujiya “Using FIR to improve CUSUM charts for monitoring process dispersion,” Quality and Reliability Engineering International, vol. 33, no. 5, pp. 1045–1056, 2017.

[15] R. Thitisoowaranon, S. Sukparungsee, and Y. Areepong, “A mixed cumulative sum – Tukey’s control chart for detecting process dispersion,” The Journal of KMUTNB, vol. 29, no. 3, pp. 507–517, 2019 (in Thai).

[16] E. B. Wilson and M. M. Hilferty, “The distribution of chi-square,” in Proceedings of the National Academy of Sciences, 1931, pp. 684–688.