Estimation of platinum flotation grades from froth image data

Abstract

Features extracted online from froth images on flotation plants are potentially useful to the developmentof advanced control for flotation systems, provided that these features can be related to the key indicatorvariables of the plant, such as valuable metal loadings and recovery. Although such relationships havebeen established in a number of base metal plants in industry, this is not the case in the platinum industry.In this paper, estimation of flotation grades and recoveries from froth image data is therefore consideredbased on laboratory and industrial plant data. It is shown that grades and recoveries can be reliablyestimated from a number of different features by use of linear and nonlinear models. This includes simple colour information that on the industrial plant showed a strong correlation with grade measurement.