Skip to main navigation Skip to search Skip to main content

Modified exponentially weighted moving average control chart for monitoring process dispersion

  • Xi'an Jiaotong University
  • Women University of Azad Jammu & kashmir Bagh
  • Govt Akhtar Nawaz Khan (Shaheed) Degree College KTS
  • University of Azad Jammu and Kashmir

Research output: Contribution to journalArticlepeer-review

6 Scopus citations

Abstract

The exponentially weighted moving average ((Formula presented.)) charts are widely used memory-type charts for monitoring small to moderate shifts in process parameters. However, the performance of the (Formula presented.) chart has been improved over time due to various modifications and enhancements. This paper proposes two modified (Formula presented.) ((Formula presented.)) charts to monitor process dispersion. The upper-sided modified (Formula presented.) chart is denoted by (Formula presented.) while a lower-sided modified (Formula presented.) chart is symbolized as the (Formula presented.) chart. Monte Carlo simulations determine the proposed schemes’ run length (RL) properties in zero- and steady-state scenarios. The proposed upper- and lower-sided (Formula presented.) charts are compared to the upper- and lower-sided (Formula presented.) and SJ-EWMA charts. The comparisons reveal that the proposed M-EWMA charts have better detection ability than the upper- and lower-sided CH-EWMA, and SJ-EWMA charts, respectively. Finally, a real-life application is provided to illustrate the implementation of the upper-sided M-EWMA and CH-EWMA charts practically in both zero-state and steady-state cases.

Original languageEnglish
Pages (from-to)3545-3572
Number of pages28
JournalCommunications in Statistics: Simulation and Computation
Volume54
Issue number9
DOIs
StatePublished - 2025

Keywords

  • Average run length
  • EWMA chart
  • Extra quadratic loss
  • Monte Carlo simulations
  • Process dispersion

Fingerprint

Dive into the research topics of 'Modified exponentially weighted moving average control chart for monitoring process dispersion'. Together they form a unique fingerprint.

Cite this