Prediction of Mechanical Properties of TWIP Steels using Artificial Neural Network Modeling

In recent years, great attention has been paid to the development of high manganese austenitic TWIP steels exhibiting high tensile strength and exceptional total elongation. Due to low stacking fault energy (SFE), cross slip becomes more difficult in these steels and mechanical twinning is then the favored deformation mode besides dislocation gliding. Chemical composition along with processing parameters has profound effects on SFE and mechanical properties of TWIP steels. In this work, artificial neural network (ANN) models were developed to predict tensile properties of these steels. In these models, %Mn, %Al, %Si, %C, cold rolling reduction, strain rate, annealing temperature, and time were chosen as input, while engineering yield strength (Y.S.), tensile strength (T.S.) and total elongation (T.E.) were considered to be output parameters. The network models were trained for each output individually. A reasonable agreement was found between the results of tensile tests and the predictions, showing the robustness of the present ANN models. The developed models can be used as a guide to achieve high strength and ductility by (i) alloy design or (ii) controlling processing parameters through the strain-induced twinning process.