Application of Neural Networks to Generating the Hot Processing Map of V150 Steel

Abstract

Isothermal hot compression of the V150 steel was conducted in the temperature range of 1173-1523K and the strain rate range of 0.01-10s-1, and with a height reduction of 60% on a Gleeble-3500 thermo-mechanical simulator. Friction correction and temperature rise correction were carried out to correct the obtained experimental data. Based on the experimental results, a neural network model was developed for the analysis and prediction of the flow behavior of the V150 steel. The model has been found capable of predicting the flow stress with great success. The correlation is 0.99999 and the relative error is 0.21%.