Title: The effect of autocorrelation on control charts performance and process capability indices calculation
Authors: Martin Kovářík; Petr Briš
Addresses: Department of Statistics and Quantitative Methods, Tomas Bata University in Zlín, Mostní 5139, 760 01 Zlín, Czech Republic ' Department of Industrial Engineering and Information Systems, Tomas Bata University in Zlín, Mostní 5139, 760 01 Zlín, Czech Republic
Abstract: Chemical processes as well as many non-industrial processes exhibit autocorrelation, for which the above-mentioned control procedures are not suitable. This paper considers the problem of monitoring a process in which the observations can be represented as a first-order autoregressive model following a heavy tailed distribution. It also presents practical usage of time series control charts on the chemical process of monitoring concentrations. The second part discusses the effect of autocorrelation on the process capability analysis when the observations are made by an autoregressive model of the first order. The process capability indices provide a measure of how a process fits within the specification limits. When calculating indices, it is usual to assume that the process data are independent. The simulation study in this part discusses the effect of a higher autocorrelation order on process capability indices.
Keywords: statistical process control; SPC; autocorrelation; control charts; process capability indices; process variability; time series modelling; CUSUM control chart; EWMA control chart; ARIMA control chart; Shewhart's control charts.
International Journal of Quality Engineering and Technology, 2021 Vol.8 No.3, pp.283 - 305
Accepted: 12 Dec 2020
Published online: 27 Jul 2021 *