Physically based and neuro-fuzzy hybrid modelling of thermomechanical processing of aluminium alloys

Abstract

Modelling of the microstructural evolution of aluminium alloys during thermomechanical processing is a desirable method for predicting the alloy's properties and designing the process variables to achieve the desired goals. A dynamic model has been developed in terms of the internal states variables of the process comprising the dislocation density, the subgrain size, and the misorientation between the subgrains. The developed model is based on a hybrid modelling technique known as grey-box modelling where intelligent models and physical equations are merged to predict the material properties with respect to the deformation conditions. The model predicts the evolution of the internal states variables under transient deformation conditions, as well as the static subsequent recrystallisation behaviour, nucleation of recrystallisation based on experimental results and quantitative metallurgical observations. In the model, the flow stress and recrystallisation behaviour are predicted with respect to temperature, strain rate and strain for different aluminium alloys providing a reasonable agreement with experimental data.