Multidimensional Optimization of the Copper Flotation in a Jameson Cell by Means of Taxonomic Methods

Three factors were measured in the flotation process of copper ore: the copper grade in a concentrate (β), the copper grade in tailings (ϑ), and the recovery of copper in a concentrate (ε). The experiment was conducted by means of a Jameson cell. The factors influencing the quality of the process were the particle size (d), the flotation time (t), the type of collector (k), and the dosage of the collector (s). The considered vector function is then (β(d, t, k, s), ϑ(d, t, k, s), ε(d, t, k, s)). In this work, the optimization was based on determining the values of the adjustable factors (d, t, k, s). The goal was to obtain the possibly highest values of the functions β and ε (maximum) with the possibly lowest values of the function ϑ (minimum). To this end, taxonomic methods were applied. Thanks to the applied method, the optimum—with the adopted assumptions—was found. The presented methodology can be successfully applied in the search for the optima in a variety of technological processes.

The Use of Neural Networks in Combination with Evolutionary Algorithms to Optimise the Copper Flotation Enrichment Process

The paper presents a way of combining neural networks with evolutionary algorithms in order to find optimal parameters of the copper flotation enrichment process. The neural network was used in order to build a model describing the flotation process. The network learning was carried out with the use of samples from previous empirical measurements of the actual process. The model created in this way made it possible to find optimal parameters not only from among the measurement spaces, but also those that go beyond the measurements. Then, evolutionary algorithms were used in order to find optimal flotation parameters. The learned neural network previously described was used to calculate the criterion in the evolutionary algorithm.