Journal
MATERIALS SCIENCE AND ENGINEERING A-STRUCTURAL MATERIALS PROPERTIES MICROSTRUCTURE AND PROCESSING
Volume 527, Issue 23, Pages 6193-6199Publisher
ELSEVIER SCIENCE SA
DOI: 10.1016/j.msea.2010.06.059
Keywords
Ti-17 titanium alloy; Dynamic globularization; Artificial neural network; Finite element method
Categories
Funding
- State Key Foundational Research Plan [2007CB613807]
- Program for New Century Excellent Talents in University [NCET-07-0696]
Ask authors/readers for more resources
Isothermal compression experiments were conducted on Ti-17 titanium alloy with initial lamellar microstructure. The fractions of dynamic globularization of the microstructure under various conditions of strain, strain rate and temperature were obtained by quantitative metallographic analysis. On the basis of these data, the prediction model for describing the non-linear relationship between the dynamic globularization fraction and the deformation strain, strain rate and temperature of Ti-17 alloy was developed with a back-propagation artificial neural network (ANN) method. This model was incorporated into rigid-viscoplastic thermo-coupled finite element method (FEM). The large-size cylinder compression of Ti-17 alloy was simulated and corresponding experimental research was performed, to verify the reliability and accuracy of the integration of FEM and ANN model. The well coincidence of the predicted results with measured ones showed that the model was able to reasonably predict the fractions of dynamic globularization of Ti-17 alloy with initial lamellar microstructure during hot deformation procedure. (C) 2010 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available