In-line moisture measurement during granulation with a four-wavelength near-infrared sensor: an evaluation of process-related variables and a development of non-linear calibration model

The near-infrared set-up based on simultaneous detection of four wavelength s was applied for in-line moisture measurement during fluid bed granulation . In addition to the spectral response, several other process measurements describing the stare of the granulation were evaluated. The near-infrared m oisture measurement is disturbed by the variation in physical properties of the sample (eg, temperature, particle size, bulk density). The factors exp laining the non-linearity of spectral response during different phases of g ranulation could he extracted. Combining all this process information impro ved the prediction capability of the multivariate calibration models tested (partial least squares and artificial neural network (ANN)). The back-prop agation neural network approach was found to have most predictive power wit h the independent test data. (C) 2001 Elsevier Science B.V. All rights rese rved.