ORE TYPE BASED EXPERT-SYSTEMS IN MINERAL PROCESSING PLANTS

Artificial intelligence (AI) includes excellent tools for the control and supervision of industrial processes. Several thousand industrial a pplications have been reported worldwide. Recently, the designers of t he Al systems have begun to hybridize the intelligent techniques, expe rt systems, fuzzy logic and neural networks, to enhance the capability of the AI systems. Expert systems have proved to be ideal candidates especially for the control of mineral processes. An expert system base d on on-line classification of the ore type has been developed. Self-o rganizing maps (SOM) are used for pattern recognition of the type of f eed. The system has been tested in two concentrators, the Outokumpu Fi nnmines Oy, Hitura Mine and Outokumpu Chrome Oy, Kemi Mine. The method ology for the development of the ore type based expert system is prese nted and the preliminary results obtained in the above plants are desc ribed.