An optimal design of the synthetic coefficient of variation chart based on the median run length
Document Type
Article
Publication Date
6-1-2021
Abstract
The synthetic coefficient of variation (CV) chart is currently evaluated based only on the average run length (ARL), but this paper evaluates the chart based on different percentiles of the run length, which shows that false alarms frequently happen earlier than that shown by the in-control ARL (ARL0), and for small sample sizes and shift sizes, the out-of-control condition is frequently detected before what is shown by the out-of-control ARL (ARL1). Furthermore, the run lengths show large variations. Hence, the chart's performance could not be interpreted only in terms of the ARL. This paper proposes the median run length (MRL)-based design for the synthetic CV chart, which is not available in the literature. The MRL-based design shows larger MRL0 and ARL(0), smaller MRL1 and ARL(1), and less variation in the out-of-control run lengths compared to existing ARL-based designs. However, the in-control run lengths show more variation. Comparisons show that the synthetic chart outperforms the VSS and Shewhart charts, while comparison with the Exponentially Weighted Moving Average (EWMA) chart shows that although it outperforms the synthetic chart based on the ARL for small shift sizes, the synthetic chart shows better performance in terms of the MRL. The MRL-based synthetic chart is then implemented on an industrial example.
Keywords
Average run length, Coefficient of variation, Median run length, Percentiles of the run length, Standard deviation of the run length, Synthetic chart
Divisions
Science
Funders
Fundamental Research Grant Scheme[FP052-2018A],Fundamental Research Grant Scheme[GPF030B-2018]
Publication Title
International Journal of Reliability Quality and Safety Engineering
Volume
28
Issue
3
Publisher
World Scientific Publ