Abstract: In the flotation process, the concentrate grade and the tailing grade are crucial technical indices which reflect the product quality and efficiency. There are strong nonlinearity and uncertainties in such technical indices dynamic behavior s, which can hardly be described accurately with mathematical models. The technical indices which cannot be measured online continuously vary with boundary conditions. Therefore conventional control methods are incapable of keeping the actual concentrate grade and tailing grade within their target ranges. An intelligent control method comprised of a pre-setting model based on the case-based reasoning (CBR) method, a feedback compensator and a feed forward compensator based on the rule-based reasoning (RBR) method, and a soft sensors using RBF neural network was presented. The approach proposed has successfully been applied to the flotation process of a hematite ore processing plant, and its effectiveness is proved evidently.