Comparison of the Warm Deformation Constitutive Model of GH4169 Alloy Based on Neural Network and the Arrhenius Model

In order to realize a better description of plastic flow behavior in the warm deformation process GH4149, GH4169 superalloy was compressed by Gleeble-3800 at temperature 700–900 °C and strain rate 0.01–10 s?1. The constitutive model established using artificial neural network (ANN) Arrhenius equation, accuracy compared. results show that average absolute relative error (AARE) ANN is 4.34%. AARE equation 29.95%. more accurate than model, has consistent whole parameter range. stress–strain curve obtained good agreement with experimental curve. compression test simulated finite element software importing material model. verified reliability can effectively predict stress during process.