A design and analysis strategy for situations with uncontrolled raw material variation

Abstract

To be able to control an industrial process, it is necessary to know the relationship between raw materials, process settings and end-product results. In many situations the raw materials are highly complex and difficult to vary in a systematic way. This makes the use of standard experimental design techniques with a systematic variation in the variables difficult. To solve this, one might measure the raw materials at hand, but then the problem is to know what to measure. In this paper we present a general approach for such situations based on an experimental design in factors that are possible to control, a set up of raw material in blocks in combination with multivariate measurements (using FT-IR) of the raw material. To analyse the results, we include these measurements as principal components of the spectra. The usefulness of the approach is demonstrated with an example from cheese production. It is shown that it is possible to obtain a model for the amount of 'cheese fines' (a yield loss parameter) based on this approach. The final model contains readily measurable information about the raw materials but is obtained without any prior hypothesis about their contribution.

A comparison of methods for analysing regression models with both spectral and designed variables

“…It is mainly design variables 3 and 4 that explain the variation in y. A regular hypothesis test of the data supports this [3].…”

“…Typical examples of such techniques are spectroscopic methods such as FT-IR or NIR. The problem with these types of measurements, however, is that they usually contain a large number of highly collinear variables, and it is not obvious how this information can be combined within the framework of model (3).…”

“…This data set is described in more detail in Reference [3]. It consists of 32 samples and comes from the production of cheese.…”

“…In other situations, however, it may be more natural to use the spectral data as they are [3,4]. The reason may be either lack of adequate reference values to calibrate against or simply lack of knowledge about which properties of the samples are of interest.…”

“…In a previous paper [3] we discussed a simple way of analysing this kind of data. We first performed principal component analysis (PCA) on the spectral measurements and included the PCA scores as covariates in the analysis of variance for the designed variables.…”