Premium
An adaptive exponentially weighted moving average chart for the mean with variable sampling intervals
Author(s) -
Tang Anan,
Castagliola Philippe,
Sun Jinsheng,
Hu XueLong
Publication year - 2017
Publication title -
quality and reliability engineering international
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.913
H-Index - 62
eISSN - 1099-1638
pISSN - 0748-8017
DOI - 10.1002/qre.2164
Subject(s) - ewma chart , x bar chart , control chart , chart , markov chain , statistics , shewhart individuals control chart , mathematics , control limits , moving average , sampling (signal processing) , computer science , interval (graph theory) , \bar x and r chart , control theory (sociology) , control (management) , process (computing) , artificial intelligence , filter (signal processing) , combinatorics , computer vision , operating system
The AEWMA control chart is an adaptive EWMA (exponentially weighted moving average) type chart that combines the Shewhart and the classical EWMA schemes in a smooth way. To improve the detection performance of the FSI (fixed sampling interval) AEWMA control chart[7][Capizzi G, 2003] in terms of the A T S (average time to signal), this paper proposes a new VSI (variable sampling interval) AEWMA control chart. A Markov chain approach is used to calculate the A T S values of the new VSI AEWMA control chart, and comparative results show that the proposed control chart performs better than the standard FSI AEWMA control chart and than other VSI control charts over a wide range of shifts.