Forecast model for dephosphorization process of ferromanganese steels using artificial neural networks

Abstract

One of the main problems affecting the quality of steel products is the existence of contaminants in alloy steel, being phosphorus (P) a major contamination element interfering with the steelmaking process. The increased P concentration levels can severely affect physical integrity of steel bonds, thus threatening the quality of the final product. The dephosphorization process of Ferromanganese consists by carbothermic reaction that involves the control of the manganese volatilization and reduction of manganese oxide in injection of oxygen. Therefore, we propose to forecast model for dephosphorization process of Ferromanganese steels in a steelmaker industry, that allows estimating the phosphorus concentration levels at the final refining process. We chose the artificial neural network models because it is computational models inspired in the human nervous system and an architecture of neural network with the Levenberg-Marquadt algorithm and Kolmogorov theorem for improving the estimation technique. The developed model presented excellent performance with a percentage error of 0.09%. Based on this created estimation model it is possible to estimate the impact of certain P concentration levels in FeMnMC beforehand, with a considerable amount of reliability.

Consideração da deformação permanente de solos ocorridos na região nordeste na análise mecanística-empírica de pavimentos

“…Basicamente RNA trata-se de técnicas de Inteligência Artificial (IA) que possuem a propriedade essencial de serem capazes de aprender uma função a partir de processos que simulam sistemas nervosos biológicos. Atualmente um dos principais usos são aplicações que trabalham com simulação de dados [6,7] relatam que as principais vantagens das RNA são a capacidade de aproximar o comportamento de fenômenos físicos não lineares, não exigindo compreensão estatística profunda e tratamento estatístico complexo dos dados modelados, bem como a capacidade de aprender quaisquer variáveis de entrada/saída de forma contínua.…”