Effects of non-normality on economic and economic statistical designs of -control charts with multiple assignable causes and Weibull in-control times

The common assumption for designing a control chart is that the quality measurements are normally distributed, although this may not be tenable in some industrial systems. This study investigates the effects of non-normal quality data on economic and economic statistical designs of control charts with multiple assignable causes and Weibull process failure mechanism. Numerical examples assess the performance of the multiplicity-cause model in three cases of Normal, Burr, and Johnson distributions along with the single-cause model under the same quantities of time and cost. The results reveal that the choice of quality characteristic distribution significantly affects optimal design parameters.