Superplasticity in PbSn60: Experimental and neural network implementation

This paper proposes a new technique based on artificial neural network useful for the characterization of superplastic behaviour, in particular for PbSn60 alloy. A three-layer neural network with back propagation (BP) algorithm is employed to train the network. The network input parameters are: alloy grain size, strain and strain rate. Just one is the output: the flow stress. Experiments are performed to evaluate the behaviour of PbSn60 alloy, subject to uniaxial tensile test, when the cross speed is kept constant. The strain rate sensitivity value (m) has been estimated analyzing the slope of the log σ – log ε ˙ curve. It is shown that BP artificial neural network can predict the flow stress and, consequently, the m index during superplastic deformation with considerable efficiency and accuracy.