Performance of Max-HEWMAMS control chart for simultaneous monitoring of process mean and variability in the presence of measurement errors Online publication date: Fri, 10-Mar-2023
by Maziar Saemian; Mohammad Reza Maleki; Ali Salmasnia
International Journal of Applied Decision Sciences (IJADS), Vol. 16, No. 2, 2023
Abstract: In recent years, the simultaneous monitoring of the process mean and variability has received increasing attention in statistical process monitoring (SPM). Most of control charts in this context have been carried out under the assumption of no measurement errors. This paper develops the Max-HEWMAMS chart for simultaneous detection of mean and variance shifts when the measurements are imprecise due to the gauge inaccuracy. Multiple measurements approach is employed to reduce the impact of measurement errors on detecting ability of Max-HEWMAMS chart. Extensive simulations are conducted to explore the impact of measurement errors on run length properties of Max-HEWMAMS chart. The results indicate under different out-of-control scenarios including mean, variance, and joint shifts, the measurement error has an undesired impact on detecting efficiency of the Max-HEWMAMS chart. It is also confirmed that taking multiple measurements per item improves the performance of Max-HEWMAMS chart when the observations are contaminated with measurement errors. Finally, the adverse impact of gauge imprecision on sensitivity of the Max-HEWMAMS chart is probed by a real-life data example.
Online publication date: Fri, 10-Mar-2023
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Applied Decision Sciences (IJADS):
Login with your Inderscience username and password:
Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.
If you still need assistance, please email email@example.com