Modelling of rare earth solvent extraction with artificial neural nets
The design and operation of mass transfer units such as rare earth solvent extraction systems require accurate models of the mass transfer phenomena that occur in these systems. The modelling of rare earth solvent extraction systems from first principles is severely constrained by the physico -chemical similarities of the lanthanides and the strong interactions that can occur between the components of these systems. Artificial neural networks are widely recognized as one of the fastest expanding computer technologies for the modelling of complex or ill -defined systems that are difficult to model otherwise. In this paper, it is shown that the general mass transfer of rare earth solvent extraction in various systems can be modelled significantly more accurately by means of artificial neural network models as compared to conventional models. It is shown that the crystal radius of the lanthanide elements can be used to generalize the behaviour of rare earths in solvent extraction systems. In cases where large numeric variations in data occur, the accuracy of the neural network models can be significantly affected by the logarithmic scaling of data. The incorporation of a self -organizing (Kohonen) layer in a neural network can give an improved performance in systems with clustered data.