Modelling Nimonic 80A rheological behaviour through artificial neural networks

In this paper neural networks are utilized to represent the rheological behaviour of nickel-base superalloys under hot forging conditions. A feedforward back-propagation neural network has been trained and tested on rheological data, obtained from hot compression experiments, performed under single- and multi-step deformation conditions, both at constant and varying strain rates. The good agreement between experimental and calculated flow curves shows that a properly trained neural network can be successfully employed in representing a material response to hot forging cycles.