Abstract
Abstract The response of true stress to strain rate, temperature and strain is a complex three-dimensional (3D) issue, and the accurate description of such constitutive relationships significantly contributes to the optimum process design. To obtain the true stress–strain data of ultra-high-strength steel, BR1500HS, a series of isothermal hot tensile tests were conducted in a wide temperature range of 973–1,123 K and a strain rate range of 0.01–10 s−1 on a Gleeble 3800 testing machine. Then the constitutive relationships were modeled by an optimally constructed and well-trained backpropagation artificial neural network (BP-ANN). The evaluation of BP-ANN model revealed that it has admirable performance in characterizing and predicting the flow behaviors of BR1500HS. A comparison on improved Arrhenius-type constitutive equation and BP-ANN model shows that the latter has higher accuracy. Consequently, the developed BP-ANN model was used to predict abundant stress–strain data beyond the limited experimental conditions. Then a 3D continuous interaction space for temperature, strain rate, strain and stress was constructed based on these predicted data. The developed 3D continuous interaction space for hot working parameters contributes to fully revealing the intrinsic relationships of BR1500HS steel.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have