Abstract:
Both the need to produce metallurgical sinter with better and more stable properties regardless of variations in the quality of the inputs used, such as iron ore and coke, as well as the need to ensure competitiveness in steel production in the face of a scenario of constant global economic crises, are motivating factors for the development of forecast models applied to the steel industry. The present work proposes the development of computational tools to estimate the final sinter properties from the physicochemical characteristics of the raw materials and the variables of the sintering process. The sinter properties investigated are Shatter Resistance Index (SI), Reducibility Index (RI), Reduction Degradation Index (RDI), and Mean Particle Size (MPS). Different algorithms were used to obtain the best prediction model for each of the studied responses and the best one was Multilayer Perceptron Neural Network with a Levenberg-Marquardt backpropagation algorithm (MLP – LM). The determination coefficients of the best models found for SI, RI, RDI and MPS, respectively, were 74.10%, 26.60%, 43.88% and 60.30%.