Artificial Neural Networks for Modelling and Controlling the Variables of a Blast Furnace

Abstract

The blast furnace is a metallurgical reactor that works at high temperature and pressure to obtain cast iron. The process it done by reactions and heat transfer between the solids, presents on the descendent burden (Iron ore, pellets, fluxes and coke) and ascendant reducing gases, generated by the burn of fuels (coke and pulverized coal) in the low part of the reactor. These reactions result in hot metal, slag, blast furnace gas and other by products. The motivation for this role is the successful application of artificial neural networks in blast furnaces. The mathematical modeling accomplished in MATLAB R2020b used 17 input variables and 8 output variables, to develop a neural network to predict the production and quality control of hot metal in a blast furnace using a layer of 25 neurons.