Prediction of mechanical properties of DP steels using neural network model

In this investigation, a neural network model was used to predict mechanical properties of dual phase (DP) steels and sensivity analysis was performed to investigate the importance of the effects of pre-strain, deformation temperature, volume fraction and morphology of martensite on room temperature mechanical behavior of these steels. In order to train the neural network, dual-phase (DP) steels with different morphology and volume fractions of martensite were deformed between 2 and 8%, at high temperature range of 150-450 °C. The results of this investigation show that there is a good agreement between experimental and predicted values and the well-trained neural network has a great potential in mechanical behavior modeling of DP steels.