The Optimization of Design of EWMA Control Chart using Box-Behnken Method under Type I Censoring

Abstract

This study is conducted to evaluate the performance of the Exponentially Weighted Moving Average (EWMA) control chart in the presence of Type I censored data. For the purpose of performance evaluation the Average Run Length (ARL) index is used. The Box-Behnken design which is a response surface method in Design Of Experiment (DOE) is being used for obtaining the optimal design for the EWMA structure. The empirical result shows that the censored data following Rayleigh lifetimes has a significant effect on the value of the ARL. Another important finding is that, under the presence of censored data the control limits of the EWMA chart should be narrowed down to L = 2 for the best performance. On the other hand, the value of  does not have a significant effect on performance measure. The EWMA control chart under the censored environment is designed in such a way that the practitioners can achieve the highest possible performance when deploying the EWMA chart.