Multivariate design of process experiments (M-DOPE)

An approach to the design of process experiments is presented for the situation where there is a large number of potentially adjustable processvariables, and where these variables are coupled due to process operating constraints. Some variations of the partial least squares (PLS) algorithmcalled ‘selective PLS’ are introduced. These algorithms allow one to combine information in past process data with current knowledge of theprocess, and thereby to separate the variables into a small number of orthogonal groups that form the basis for experimental designs and processoptimization. The concepts are illustrated using data from an industrial mineral flotation circuit used to concentrate valuable minerals from anore.