Prediction of Mechanical Properties of Steel Using Artificial Neural Network

For product development manufacturers and designers need information about the existing materials and new material and its properties as early as possible. This paper presents a method of predicting the properties of unknown material using artificial neural network. The developed neural network model is employed for simulations of the relationship between mechanical property and the chemical composition of steel. Simulating and analyzing result shows that network model can effectively predict the mechanical properties of material. Application of the presented method enables a scientist to make free analyses of the effect of the alloying elements occurring in processing condition also using only computer simulation, without having to carry out additional and expensive experimental investigations.