CHARACTERIZATION OF FLOTATION PROCESSES WITH SELF-ORGANIZING NEURAL NETS

Flotation processes are difficult to describe fundamentally, owing to the stochastic nature of the froth structures and the ill-defined chem orheology of the froth. Considerable information on the process is ref lected by the structure of the froth. In previous work it has been sho wn that structural features extracted from flotation froths can be rel ated to the behavior of flotation processes in a qualitative way throu gh the identification of certain behavioral regimes or classes by usin g a supervised neural net as classifier. Although useful as an aid to control decisions, this method is less suitable for quantitative or dy namic analysis of the behavior of flotation plants. In this paper a ne w method for the analysis of flotation plants is consequently proposed , based on the use of order preserving maps of features extracted from digitized images of the froth phase. The construction of these maps b y means of a self-organizing neural net is demonstrated by way of exam ples concerning the analysis of industrial copper and platinum flotati on plants.