2016 年 10 巻 4 号 p. JAMDSM0058
A control chart is an important tool of the statistical process control for monitoring deviations from a stable production process. For this purpose different control schemes have been developed for the fast detection of certain changes in the process parameters. We reconsider the recently proposed exponentially weighted moving average (EWMA) chart based on the mean absolute deviation from the median (called EWMA-MD chart) to monitor the process variation. The repetitive group sampling scheme through two pairs of control limits has been incorporated in the proposed control chart to enhance the performance. The performance of the proposed control chart is evaluated in terms of the average run length through simulation when the quality characteristic of interest follows a normal distribution, a gamma distribution or a t-distribution. The results show better detecting ability of the proposed control chart as compared with the existing EWMA-MD chart for small to moderate shifts in the process dispersion.
