EFFICIENT SHIFT DETECTION USING MULTIVARIATE EXPONENTIALLY-WEIGHTED MOVING AVERAGE CONTROL CHARTS AND PRINCIPAL COMPONENTS

This paper demonstrates the use of principal components in conjunction with the multivariate exponentially-weighted moving average (MEWMA) c ontrol procedure for process monitoring. It is demonstrated that the n umber of variables to be monitored is reduced through this approach, a nd that the average run length to detect process shifts or upsets is s ubstantially reduced as well. The performance of the MEWMA applied to all the variables may be related to the MEWMA control chart that uses principal components through the non-centrality parameter. An average run length table demonstrates the advantages of the principal componen ts MEWMA over the procedure that uses all of the variables. An illustr ative example is provided.