Reviving traditional blast furnace models with new mathematical approach

Abstract

This paper describes how traditional analytical blast furnace (BF) models can be revived by the inclusion of new mathematical tools. Combining some fundamental models with new mathematical algorithms can create efficient and simple to use hybrid models. A hybrid model based on artificial neural network (ANN) and its industrial application to the new BF No. 3 at Companhia Siderúrgica Nacional (CSN, Volta Redonda, Brazil) was developed, tested and put in use. In BF operation, which is a multivariable complex process subject to oscillations in raw material characteristics, a precise model is essential to adjust charging and blow conditions to match productivity, chemical quality and target costs. A neural model was developed in order to estimate chemical and thermal parameters to feed a first principles model capable of evaluating alternative operation standards. As a consequence, operation efficiency is being enhanced, leading to higher productivity and lower costs.