Application of Artificial Neural Network to the Prediction of Tensile Properties in High-Strength Low-Carbon Bainitic Steels

An artificial neural network (ANN) model was designed to predict the tensile properties in high-strength, low-carbon bainitic steels with a focus on fraction of constituents such as PF (polygonal ferrite), AF (acicular GB (granular bainite), and BF (bainitic ferrite). The input parameters were constituents, while output composed yield strength, yield-to-tensile ratio, uniform elongation. ANN exhibited higher accuracy than multi linear regression (MLR) model. According average index relative importance for parameters, elongation could be effectively improved by increasing AF, microstructures (AF, GB, BF), PF, respectively, terms work hardening dislocation slip behavior depending their microstructural characteristics grain size density. is expected provide clearer understanding complex relationships between constituent steels.