The combined EWMA-CUSUM control chart with autocorrelation / Abbas Umar Farouk and Ismail Mohamad

It is well known that statistical control charts such as Shewhart, CUSUM and EWMA charts have found widespread application in improving the quality for manufacturing and service processes. Control charts process monitoring have traditionally been designed and evaluated under assumption that observations on the process output at different times are independent. However, autocorrelation may be present in many processes, and may have a strong impact on the properties of control charts. Due to high sophisticated computer programs and soft ware's that are used in nowadays production processes the output of the production processes used to be very high and large in quantities which give rises to serial correlation among the output, hence the need to check for the effect of the autocorrelation in the production processes. The combined EWMA and CUSUM control chart is an improved technique proposed to check the excess of the autocorrelation in the production processes so that the effect can be minimized. A source code has been developed. A result of 10000 simulations was recorded for the ARL values. The performance of the proposed chart was evaluated in terms of average run length (ARL), the standard deviation of the run length as well as the percentile of the run length. Comparison of these charts with some existing control charts designed for monitoring small and large shifts revealed that the proposed chart is more sensitive and offer better shift detection than the others considered in this study.