ONLINE DETERMINATION OF ORE TYPE USING CLUSTER-ANALYSIS AND NEURAL NETWORKS

Expert systems have proved to be excellent tools for the control of mi neral processes. An expert system based on on-line classification of t he ore type has been designed and is described in. this paper The neur al approach to computation has emerged in recent years for dealing wit h the sort of problems for which more conventional solutions have prov en ineffective. In the study a comparison between the on-line cluster algorithm and the Kohonen feature map for ore type classification is p resented. The study was carried out with measurement data from the Out okumpu Hitura mine.