No abstract

No abstract

Powder blending was monitored on-line by taking near-infrared measurements at regular time intervals during the mixing process. The average standard deviation between the measurements taken at each time and the dissimilarity between each mixture spectrum and the ideal mixture spectrum were used to monitor the changes in the powder blend over time. The distribution of the pure compounds in the blend can be investigated by looking at the score plot for the first two principal components (PCs), the contribution of each variable to the dissimilarity and, in particular, the contrasts between two characteristic wavelengths for each compound. Statistical process monitoring charts were used to determine the blending time at which the mixture was within (spectroscopic) specifications. Shewhart charts monitor the blend at characteristic wavelengths for each substance separately. The Hotelling's T2 test defines a multivariate confidence interval. For spectral data, feature reduction is needed. This procedure is accomplished by using characteristic wavelengths for the pure compounds or the significant PCs after performing principal components analysis (PCA).

No abstract