Modeling of the microstructure variables in the isothermal compression of TC11 alloy using fuzzy neural networks

▶ The approach to model grain size and volume fraction in the isothermal compression of titanium alloy, and to train the model structure is presented in terms of the fuzzy neural networks by using BP learning algorithm. ▶ The experimental grain size and volume fraction of prior α phase in the isothermal compression of TC11 alloy at the deformation temperatures ranging from 1023 to 1323 K, the strain rates ranging from 0.001 to 10.0 s−1, and the height reductions ranging from 50 to 70% are obtained. ▶ The gain size and volume fraction of prior α phase are affected by the deformation temperature, in which gain size and volume fraction appear highly nonlinear and fuzzy characteristic. ▶ The predicted grain size and volume fraction of prior α phase are in a good agreement with the experimental results in the isothermal compression of TC11 alloy.