Individuals control schemes for monitoring the mean and variance of processes subject to drifts

This paper investigates control chart schemes for detecting drifts in the process mean mu and/or process standard deviation cr when individual observations are sampled. Drifts may be due to causes such as gradual deterioration of equipment, catalyst aging, waste accumulation, or human causes, such as operator fatigue or close supervision. The standard Shewhan X chart and moving range (MR) chart are evaluated. as well as several types of exponentially weighted moving average (EWMA) charts and combinations of charts involving these EWMA charts. We show that the combinations of the EWMA charts detect slow-rate and moderate-rate drifts much faster than the combined X and MR charts. We also show that varying the sampling interval adaptively as a function of the process data results in notable reductions in the detection delay of drifts in mu and/or sigma.