Hybrid Physicochemical/Neural-Network Model For Phosphate Column Flotation

Froth flotation is a process commonly employed for the selective separation of phosphate from unwanted mineral. Column flotation has become widely accepted in the mineral processing industry, including phosphate industries, due to its ability to improve selectivity, lower operating cost, lower capital cost, and superior control. In this work, a hybrid model is developed that combines a physicochemical model with artificial neural networks. The physicochemical model is based on axial dispersion with first order collection rates. A new approach, in which both frankolite (the desired mineral containing phosphate) and gangue (undesired product) are modeled, enables prediction of grade of the recovered product. Thus, two basic parameters are required in this model: flotation rate constants for frankolite and gangue. Artificial neural networks are used to predict flotation rate constants. The model also takes into account the particle size distribution and predicts grade and recovery for each particle size range. The model then combines grade and recovery for each particle size range to determine the overall grade and recovery of the column. The model is validated against laboratory column data.