Scale-Up of Agitation Fluidized Bed Granulation by Neural Network.

Scale-up of wet granulation by agitation fluidized bed was conducted using a hierarchy neural network with a back-propagation learning. Scale-up characteristics of agaitation fluidized bed granulation were self-learned using a developed neural network system, and properties of size, size distribution, apparent density and shape factor of granules prepared by the commercial scale under various operating conditions (moisture content, agitator rotational speed and fluidization air velocity) were predicted. To confirm the method's validity, the predicted properties were compared with the actual granulation data. Good correlation was obtained beteen the predicted and the experimental data of agitation fluidized bed granulation. It was found that the neural network could be a reliable tool to analyze the scale-up characteristics of granulation, and to predict granule properties being produced by the unknown larger scale granulator.