Artificial neural networks in estimation of hydrocyclone parameter d50c with unusual input variables

The accuracy in the estimation of hydrocyclone parameter, d50_c, can substantially be improved by application of artificial neural networks (ANN). With ANN, many nonconventional operational variables such as water and solid split ratios, overflow and underflow densities, apex and spigot flowrates can easily be incorporated as the input parameters in the prediction of d50_c. The ANN yields high correlation of data, hence it can be used in automatic control and multiphase operations of hydrocyclones