A comparative study of some network approaches to predict the effect of the reinforcement content on the hot strength of Al-base composites

Due to the nonlinear complex effect of the reinforcement content and the deformation conditions such as temperature and strain rate on the flow stress, the existing models especially those dependent on the activation energy are not suitable to predict the hot deformation behavior. To achieve this purpose, it was decided to use the property of some of the existing models such as radial-base function network (RBF), multi-layer perceptron (MLP) network, and neuro-fuzzy network to predict the nonlinear behavior in the stress-strain behavior of the material. The results showed that the neuro-fuzzy network is the best tool to predict the hot deformation behavior of Al-base composites with different reinforcement content (5, 10, 15, and 20%) of Al2O3 particles that have an average particle size of 25 μm at different deformation conditions since the reinforcement content and the deformation conditions have a nonlinear complex effect on the flow stress.