Artificial Neural Network Modeling the Tensile Strength of Hot Strip Mill Products

Abstract

In this study, the effects of chemical composition and process parameters on the tensile strength of hot strip mill products were modeled by Artificial Neural Network (ANN). A good performance of network was achieved when compared with the experimental data taken from Mobarakeh Steel Company (MSC). Moreover, the relative importance of each input variable was evaluated by sensitivity analysis. The results are evaluated based on metallurgical phenomena of steels. Therefore, it is proposed that, this model can be employed as a guide to predict the final mechanical properties of commercial low carbon steel products.