THE ADVANTAGES BY THE USE OF NEURAL NETWORKS IN MODELING THE FLUIDIZED-BED GRANULATION PROCESS

The use of artificial neural networks (ANNs) in modelling a fluidized bed granulation process is reported. The granules were made in a fully instrumented laboratory-scale granulator (Glatt WSG 5, Glatt GmbH, Ge rmany). The independent input variables were inlet air temperature, at omizing air pressure and binder solution amount. The input variables v aried in three levels. The responses used were mean granule size and g ranule friability. Neural computing was carried out using a commercial NeuDesk software (Neural Computer Sciences, U.K.) in a 486 microcompu ter with a specific accelerator card, NeuSprint (Neural Computer Scien ces, U.K.). In total, 36 different ANN models were tested. The results were also compared with a statistical method (multilinear stepwise re gression analysis). The results showed clearly that the best networks were able to predict the experimental responses more accurately than t he multilinear stepwise regression analysis. On the other hand, it als o became evident that several different structures should be trained w ith different training end points to generate a proper model.