Response Surface Methodology for Copper Flotation Optimization in Saline Systems

Response surface methodology (RSM) is one of the most effective tools for optimizing processes, and it has been used in conjunction with Analysis Variance (ANOVA) test to establish effect input factors on output factors. However, when this mineral flotation, its polynomial model usually performs poorly. An alternative use artificial neural networks (ANNs) such situations. Within context, ANOVA not best option these types; moreover, requires statistical assumptions that are difficult satisfy flotation. This work proposes replacing RSM ANNs Sobol methods determine influential instead test. proposal applied two porphyry copper ores a high content pyrite, clay, dilution media. In addition, study shows how other computational intelligence techniques, as swarm intelligence, can be incorporated into type problem improve learning process ANNs. The results gave an adjustment over 0.98 R2 using ANNs, comparison values around 0.5 was utilized. On hand, application Global Sensitivity (GSA) identified aeration rate P80 size variables recovery under conditions studied. Additionally, we significant interactions affect copper, between rate, frother concentration, being important.