摘要
Ti-15-3 alloy is a new metastableβ-type titanium. The influence of hot deformation parameters on the microstructureof Ti-15-3 alloy after solution treatment has been studied by isothermal compression tests as well as quantitativemetallographic analysis. On the basis of the data obtained from the tests, predicting models for equivalent grainsize and recrystallization volume fraction have been established with an artificial neural network method. An FEnumerical simulation system has been developed to simulate the distribution of microstructure in Ti-15-3 alloy afterhot back extrusion and solution treatment by combining the neural network model with thermal-mechanical coupledrigid-viscoplastic FE model. Corresponding experimental research is performed. The agreement of the simulatedresults with measured ones shows that the simulation system is reliable.
