STATISTICAL PROCESS-CONTROL OF MULTIVARIATE PROCESSES

With process computers routinely collecting measurements on large numb ers of process variables, multivariate statistical methods for the ana lysis, monitoring and diagnosis of process operating performance have received increasing attention. Extensions of traditional univariate Sh ewhart, CUSUM and EWMA control charts to multivariate quality control situations are based on Hotelling's T-2 statistic. Recent approaches t o multivariate statistical process control which utilize not only prod uct quality data (Y), but also all of the available process variable d ata (X) are based on multivariate statistical projection methods (Prin cipal Component Analysis (PCA) and Partial Least Squares (PLS)). This paper gives an overview of these methods, and their use for the statis tical process control of both continuous and batch multivariate proces ses. Examples are provided of their use for analysing the operations o f a mineral processing plant, for on-line monitoring and fault diagnos is of a continuous polymerization process and for the on-line monitori ng of an industrial batch polymerization reactor.