Hybrid Modelling of the Sucrose Crystal Growth Rate

Abstract This paper deals with the development of the crystal growth rate model according to a novel modelling strategy. The method combines an artificial neural network (ANN) as an approximator of the growth rate with prior knowledge represented by the mass balance on sucrose crystals. This approach reduces the modelling effort since the ANN does not impose a priori parameterization of the growth rate expression. Moreover, the resultant greater flexibility of the model augurs large predictive capability under a wide range of operating conditions. The model was developed with industrial data collected from a 60 m3 batch evaporative crystallizer.