Predicting the bake hardenability of steels using neural network modeling

In this work, an artificial neural network (ANN) model for prediction of mechanical properties of baked steels was established. The model introduced here considers the content of carbon, the prestrain amount, the initial yield stress and the baking temperature as inputs. While, the bake hardenability, work hardening values and yield stresses after steel baking are presented as outputs. The network was trained using the data from experimental work and back-propagation algorithm. The results show that the predicted values by the model are much more accurate than the experimental ones. The model suggested a two-stage strengthening for baking of ultra low carbon (ULC) steels, whereas, in the case of low carbon steels only one increment step in strength was reported. Comparing the predicted amounts by ANN model with the experimental ones indicates that well-trained neural network model provides very accurate results.