THE USE OF ARTIFICIAL NEURAL NETWORKS IN THE CONTROL OF ELECTRIC ARC FURNACES

Today, control systems have become an important branch of science in parallel with the increase production and quality needs. There are purpose-specific automatic algorithms controlling them for industrial facilities.
 In this study, modeling electric arc furnace scrap melting plant, which has essential place iron-steel industry been made using artificial neural networks. The facility where study is carried out active controlled by classical algorithms. Artificial networks were trained data taken over current system pressure sensors attached to electrodes network was out. 
 software developed used furnaces provided 98% success monitoring including operator’s intervention algorithm. All input output copied software. Since does not require various calculations, calibrations parameter changes, it responds faster than algorithm factory.