Premium
An improved Hotelling's T 2 chart for monitoring a finite horizon process based on run rules schemes: A Markov‐chain approach
Author(s) -
Chew XinYing,
Khoo Michael Boon Chong,
Khaw Khai Wah,
Lee Ming Ha
Publication year - 2020
Publication title -
applied stochastic models in business and industry
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.413
H-Index - 40
eISSN - 1526-4025
pISSN - 1524-1904
DOI - 10.1002/asmb.2596
Subject(s) - markov chain , horizon , process (computing) , computer science , chart , markov process , work in process , control chart , time horizon , mathematical optimization , algorithm , mathematics , engineering , statistics , operations management , machine learning , geometry , operating system
Quality improvement has been receiving great attention in industries. In recent years, the finite horizon process is commonly encountered in industries due to flexible manufacturing production. Past research works on finite horizon process monitoring are still limited. Because of this, three run rules Hotelling's T 2 charts are proposed to monitor a finite horizon process. The performance measures of the proposed charts are derived using the Markov‐chain approach. The proposed schemes can serve as a framework for quality engineers who wish to perform process monitoring easily and efficiently. Numerical comparisons between the proposed and existing Shewhart (SH) T 2 charts have been made. The statistical performance measures were investigated in this article. The findings reveal that the proposed charts outperform the SH T 2 chart for detecting small and moderate process shifts in a finite horizon process. The illustration of the run rules (RR) T 2 chart is shown on a real manufacturing dataset in a finite horizon process.