Enhancing process mean monitoring efficiency using extended-EWMA control chart with auxiliary information

For monitoring the outputs of production processes, statistical process control (SPC) is widely used. The control chart (CC) stands as the most important SPC tool for differentiating between unnatural and natural sources of variation. Unnatural sources typically result in changes in the value of process parameters, which are categorized into three levels: minor, moderate, and high. While memory-less CCs excel in identifying large shifts, memory-based CCs such as exponentially weighted moving average (EWMA) and extended exponentially weighted moving average (EEWMA) CCs are optimal for detecting minor-to-moderate shifts in process parameter values. Detection ability of CCs is enhanced by using auxiliary variable. This study is conducted to propose an EEWMA CC using auxiliary information named as MyEEWMA CC. The proposed MyEEWMA chart is evaluated through average run length criterion. In the practical industrial applications with the density and stiffness of particle board data, the MyEEWMA CC detected process deviations earlier than existing EEWMA, and MyEWMA CCs. Specifically, the MyEEWMA chart signaled an issue by the 25th sample, whereas the EEWMA, and MyEWMA CCs did not detect any deviations even after the 25th sample. This tangible evidence underscores the superior efficiency of the proposed MyEEWMA CC in industrial settings.