Remodeling Multivariate Control Chart by Using Spatial Signed Rank for Detecting Mean Shift in Normal and Non-Normal Processes

This research aimed to modify the traditional multivariate control charts by using the multivariate spatial signed rank under the normal distribution, the t distribution, and the gamma distribution. The performance of the modern multivariate control charts is measured based on the average run length (ARL). The ARL is computed using a Monte Carlo simulation. The Monte Carlo approach is applied to simulate the circumstances via MATLAB software. The spatial signed-rank multivariate exponentially weighted moving average (SSRM) control chart is found to be the most appropriate approach to detect the small mean shifts (delta <= 0.5) and the large smoothing parameters (lambda <= 0.35) of all three distributions. Besides, SSRM is a robust tool for detecting waste and is suitable for most industrial processes.