Artificial Neural Network-Based Three-dimensional Continuous Response Relationship Construction of 3Cr20Ni10W2 Heat-Resisting Alloy and Its Application in Finite Element Simulation

Abstract

The application of accurate constitutive relationship in finite element simulation would significantly contribute to accurate simulation results, which plays a critical role in process design and optimization. In this investigation, the true stress–strain data of 3Cr20Ni10W2 heat-resisting alloy were obtained from a series of isothermal compression tests conducted in a wide temperature range of 1203–1403 K and strain rate range of 0.01–10 s−1 on a Gleeble 1500 testing machine. Then the constitutive relationship was modeled by an optimally constructed and well-trained back-propagation artificial neural network (BP-ANN). The evaluation of the BP-ANN model revealed that it has admirable performance in characterizing and predicting the flow behaviors of 3Cr20Ni10W2 heat-resisting alloy. Meanwhile, a comparison between 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 and construct the three-dimensional continuous response relationship for temperature, strain rate, strain, and stress. Finally, the three-dimensional continuous response relationship was applied to the numerical simulation of isothermal compression tests. The results show that such constitutive relationship can significantly promote the accuracy improvement of numerical simulation for hot forming processes.

Keywords

• constitutive relationship
• heat-resisting alloy
• back-propagation artificial neural network
• accuracy improvement
• numerical simulation