Monitoring variance by EWMA charts with time varying smoothing parameter

Memory charts like EWMA-S² or CUSUM-S² can be designed to be optimal to detect a specific shift in the process variance. However, this feature could be a serious inconvenience since, for instance, if the charts are designed to detect small shift, then, they can be inefficient to detect moderate or large shifts. In the literature, several alternatives have been proposed to overcome this limitation, like the use of control charts with variable parameters or adaptive control charts. This paper proposes new adaptive EWMA control charts for the dispersion (AEWMA-S²) based on a timevarying smoothing parameter that takes into account the potential misadjustment in the process variance. The obtained control charts can be interpreted as a combination of EWMA control charts designed to be efficient for different shift values. Markov chain procedures are established to analyse and design the proposed charts. Comparisons with other adaptive and traditional control charts show the advantages of the proposals.