Hysteresis Model for Superelasticity of Shape Memory Alloy Based on ANN

摘要

Superelasticity is one of the most important properties of shape memory alloy. In this paper, the superelastic deformation behavior of NiTi shape memory alloy subjected to cyclic loading with stable superelasticity is experimentally investigated. According to test data, a constitutive model for the superelasticity of shape memory alloy is presented based on the artificial neural network (ANN). Numerical results agree well with experimental observations that verified the constitutive model being of high accuracy. This model can avoid the difficulties of other models on the determination of the parameters and is suitable for practical engineering application. Thus, a new method is provided for building the constitutive model of shape memory alloy.