NEURAL-NET ANALYSIS OF THE LIBERATION OF GOLD USING DIAGNOSTIC LEACHING DATA

The interrelationship between mineral liberation and leaching behaviou r of a gold ore is ill defined, mainly due to the complexity of both l eaching and mineral liberation. A better understanding of this relatio nship could result in lower operating costs on gold extraction plants, since an increase in the efficiency of gold dissolution and a decreas e in costs related to the crushing and grinding operations could be ex pected. In this investigation artificial neural nets were used to anal yse diagnostic leaching data of gold ores obtained from South African gold mines. A self-organising neural net with a Kohonen layer was used to generate order-preserving topological maps of the characteristics of both the unmilled and milled ores. The arrangement and shapes of th ese clusters could then be used to develop simple neural net models wh ich were capable of predicting the degree of liberation more accuratel y than previously proposed models. Moreover, the neural net models wer e also capable of providing direct estimates of the reliability of the ir predictions by comparing new inputs with the data in their training bases.