On Designing Mixed EWMA Dual-CUSUM Chart With Applications in Petro-Chemical Industry

Abstract

In recent times, the trending modification of control chart is a result of its effective application in various aspects of life. In this paper, we propose a new charting scheme called mixed exponentially weighted moving average (EWMA) dual-cumulative sum (CUSUM) to monitor the location parameter. The driving goal, which inspired this scheme, was the enhancement in the sensitivity of the control scheme used by analyzers in the petro-chemical industry which identify different quantities of components present in different catalysts. The proposed scheme is the combination of a dual-CUSUM chart and a time-varying EWMA chart. We explore the scheme with robust estimators by evaluating their thresholds in the presence of disturbances and contaminations. We do this by introducing both location and variance contaminants into the process environment. The average and standard deviation of the run lengths were used as the benchmark for performance evaluation through the various estimators. We applied this scheme on real life datasets from refinery laboratory statistics which is the case study.