DEWMA-CUSUM CONTROL CHART FOR MONITORING PROCESS MEAN

Abstract

Monitoring the production activities of a manufacturing process for small and moderate shift in location and variability to meet quality standard have been achieved using control chart. The control chart is one of the useful tools of statistical process control to assure the quality of a product or process in the manufacturing industry. Several design strategy and modifications of control charts for monitoring changes in the process parameters have been developed. One of such control chart modification is the mixed control charts, designed to quickly detect a small and moderate shift in the process. In this study, a new mixed control chart called Double Exponential Weighted Moving Average – Cumulative Sum (DEWMA-CUSUM) control chart is proposed to quickly detect shift in the process location. The features of the DEWMA and CUSUM control charts were combined together to develop the upper and lower statistics of the new DEWMA-CUSUM control chart for a process that is assumed to follow a normal distribution. The performance evaluation of the new DEWMA-CUSUM control chart was carried out using the Monte-Carlo Simulation procedure to compute the run lengths profiles, specifically, the average run length (ARL), standard deviation run length (SDRL) and median run length (MDRL). The proposed control chart was compared with some existing control chart based on ARL, SDRL and MDRL. The result of the study shows that the DEWMA-CUSUM control chart is more sensitive to detecting small shift than the existing control charts.