Machine Learning Strategies for Control of Flotation Plants

Abstract Although flotation process are notoriously difficult to model from first principles, knowledge-based systems can be used to great advantage to monitor and control plants, provided that process knowledge can be captured effectively on the plant. By making use of machine learning techniques the features of the surface froths of flotation cells can be used to construct representations of the behaviour of a plant. In this investigation a probabilistic decision tree method and a back propagation neural net were used to classify different froth structures. Both were equally capable of classifying the different froths at least as well as a human expert and did not require extensive data to characterize the behaviour of industrial plants.