Application of a neural network for the prediction of crystallization kinetics

A method for more-accurate prediction of crystallization kinetics is greatly needed in the field of industrial crystallization. Traditional empirical correlations cannot give reliable predictions, because of the highly nonlinear behavior of crystallization kinetics, although they have been used for a long time. In this paper, the development of a neural network model is presented. The model was trained with limited data obtained from an anti-solvent crystallization system (ciprofloxacin hydrochloride, H2O, and ethanol). The predictions from the network then were validated against newly measured data. The results confirm that this approach gives much more-accurate predictions of the kinetics, in terms of crystal growth and agglomeration as examples. The mean relative error of the predicted growth rates from this model, versus the measured data, is generally <10% and, in some cases, is as good as 5%. This is a significant improvement on the relative error of 20% or more that is typically achieved by traditional correlations.