Non-linear model predictive control to improve the mineralogical efficiency of flotation circuits

Abstract

Flotation optimisation strategies often trade off grade for recovery, without attempting to improve the mineralogical efficiency of the flotation process as part of the automatic control and optimisation strategy. Non-linear flotation characteristics such as air recovery complicate the implementation of such an optimisation strategy due to rapidly changing dynamics, and consequently there is a need for a non-linear controller implementation with real-time parameter estimation, to perform the optimisation. This simulation study demonstrates how the parameters of an air recovery model can be estimated dynamically from measurements commonly available on an industrial flotation circuit, and how dynamic optimisation of the flotation process - in the form of non-linear model predictive control - shifts the grade-recovery curve upwards - implying improved metallurgical efficiency through air recovery maximisation.