Comparison of intelligent control methods for the ore jigging process

Abstract

Efficient control of the process of jigging ore of small and fine grain allows avoiding the loss of valuable material in production residual.  Due to the multi-dimensionality and multi-connectivity of this enrichment process, classical control methods do not allow achieving the maximum technological indicators of enrichment. This paper proposes investigating intelligent algorithms for controlling the jigging process, which determine the key variables - the level of the natural «bed» and the ripple frequency of the jigging machine. Algorithms are developed using fuzzy logic, neural and hybrid networks. The adequacy of intelligent algorithms was evaluated using the following criteria: correlation of expert and model values (R); Root Mean Square Error (RMSE); Mean absolute percentage error (MAPE). To assess the adequacy of the obtained algorithms, a test sample of input variables, different from the training one, was compiled. As a consequence, we determined an algorithm that gives a minimal discrepancy between the calculated and experimental data.