Machine-vision-based control of zinc flotation—A case study

Abstract It is widely accepted that mineral flotation is a very challenging control problem due to chaotic nature of process. This paper introduces a novel approach of combining multi-camera system and expert controllers to improve flotation performance. The system has been installed into the zinc circuit of Pyhasalmi Mine (Finland). Long-term data analysis in fact shows that the new approach has improved considerably the recovery of the zinc circuit, resulting in a substantial increase in the mill's annual profit.