PAT Tools and Their Application

Multivariate Tools for Design, Data Acquisition, and Analysis 

Because the system described above is multifactorial, a simple univariate approach to data analysis would likely not elicit the critical factors. In that regard, 

Briefly, PCA models the data in terms of the significant factors, or principal components, which describe the systematic variability of the data. PCA also describes the data in terms of residuals that represent the noise in the system. PLS may be described as a method for constructing predictive models from data sets with many collinear factors. Both have received considerable attention in the analysis of multivariate data. 

In order to adequately evaluate these complex systems, multivariate data analysis techniques must be used. The examples previously discussed highlight only a few approaches to multivariate data acquisition and analysis. There are many approaches for using these tools to obtain an increased understanding of granulation, and to elicit critical process/material attributes, as well as their relationship with final product quality attributes, for controlling the manufacturing process. 

In terms of innovation, some of the most significant advances have occurred in the area of process analyzers, and there are numerous examples of the application of these tools to obtain a greater understanding of the granulation process. Certainly, once critical process and material attributes have been identified, an appropriate tool for the analysis of these attributes is crucial for timely analysis, as well as ultimately controlling the granulation process. 

---