Design of a New Tukey MA-DEWMA Control Chart to Monitor Process and its Applications

Abstract

Control chart is a useful statistical tool for the production process control to maintain the product value at the standard. The objectives of this research were to propose the Tukey Moving Average - Double Exponentially Weighted Moving Average control chart (MMD-TCC chart) to detect the change of mean in the symmetric and non-symmetric distribution, and to compare the effectiveness of the change detection of MMD-TCC with that of MA, DEWMA, MMD, MDM, TCC, and MDM-TCC at the different parameter levels. $ARL_{1}$ and MRL criteria were used to measure the efficiency by applying Monte Carlo (MC) simulation. Research results indicated that the change of mean in process under the control where $ARL_{0} =370$ with MMD-TCC was more efficient to detect the change than other control charts unless it was the symmetric distribution with the change of parameter at ±1.50, ±2.00, ±3.00, ±4.00, and the non-symmetric distributions with the change of parameter at 3.00, 4.00 with MA control chart. Furthermore, by applying the proposed control chart to real data, it was found to be in accordance with the research results from simulation technique.

Keywords

• Mixed control chart
• Monte Carlo simulation
• Tukey moving average-double exponentially weighted moving average control chart
• nonparametric control charts