Title: Performance of hybrid exponentially weighted moving average control chart in the presence of measurement errors

Authors: Seyed Ali Modarresi; Mohammad Reza Maleki

Addresses: Department of Industrial Engineering, University of Eyvanekey, Semnan, Iran ' Industrial Engineering Group, Golpayegan College of Engineering, Golpayegan 87717-67498, Isfahan University of Technology, Iran

Abstract: The inability of a measurement system to accurately measure the characteristics that affect the performance of control charts in detecting process disturbances, is being highlighted. This paper studies the impact of gauge inaccuracy on sensitivity of the hybrid exponentially weighted moving average (HEWMA) chart for Phase II monitoring of the process mean. Multiple measurements approach is also utilised to reduce the undesired impact of measurement errors on detection capability of the HEWMA chart. Simulation studies are conducted to evaluate the detecting performance of HEWMA chart in terms of average run length (ARL), standard deviation of run length (SDRL) and median run length (MRL) metrics. The results confirm the negative impact of imprecise measurements on sensitivity of HEWMA chart. The results also show that taking multiple measurements on each item enhances the detecting performance of HEWMA chart. Finally, real industrial data is utilised to illustrate how gauge imprecision affects the HEWMA chart in identifying process shifts.

Keywords: statistical process monitoring; HEWMA chart; measurement errors; multiple measurements; run length.

DOI: 10.1504/IJMDM.2022.124411

International Journal of Management and Decision Making, 2022 Vol.21 No.3, pp.285 - 304

Received: 26 Jul 2021
Accepted: 16 Aug 2021
Published online: 26 Jul 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article