Process data chemometrics

Abstract

Data are gathered in many chemical processes at a very high rate. Unfortunately, much of that data is not often used unless a major problem has occurred. A technique in which data can first be analyzed to determine what is normal variability in the process and a model or models developed which define in a compact way that variability are presented. The information in the models is then used to measure the state of the process as to whether it represents a likely sample from the model of normal variations. If it is not, information about why the data are not of the form expected is made available to the operators in a readily understandable manner. This technique was researched and implemented on a solution area of a Du Pont plant. The approach taken is to first separate out the major effect of rate variations which are normal and a major contributor to the total variability of the data. On the residuals of the model, a principal component analysis (PCA) model determines if that data fit the pattern of normal variations. If not, then what went wrong is analyzed, and why the data are different and what changes might be made to get the operation into the acceptable region, are determined.<>