Neural Identification of Technological Process of Iron Ore Beneficiation

Abstract

This document presents results to identification of technological process (TP) of beneficiation of iron ore on bases of models NNARX (Neural Network based AutoRegressive eXogenous signal), NNARXMAX (Neural Network based AutoRegressive, Moving Average, eXogenous signal), NNOE (Neural Network Output Error). Computer modeling has been carried out with application of Neuro Solution software package. As internal modeling structure bases on the basis of multilayered perceptron (MLP) and networks of the radial basis functions (RBF) network have been analyzed. The sample of parameters of the Southern mining complex (Krivoy Rog city, Ukraine) has been used for training and verification. It is proved efficiency of application of neural networks for identification of parameters of concentrating technology.

Synthesis of robust controllers for the control systems of technological units at iron ore processing plants

“…Applying the intelligent systems in order to control technological processes of the ore enrichment was proposed in papers [16,17]. Underlying a given approach is the use of neural networks to model and control technological processes.…”