点击次数：

论文类型：期刊论文

发表时间：2012-09-01

发表刊物：RARE METAL MATERIALS AND ENGINEERING

收录刊物：SCIE、PKU、ISTIC

卷号：41

页面范围：243-246

ISSN号：1002-185X

关键字：shape memory alloy; superelasticity; radial basis function neural network; cyclic constitutive model

摘要：The mechanical behavior of superelastic shape memory alloy (SMA) under loading and unloading cycles varies gradually and approximates to a steady state ultimately. Based on the cyclic loading tests of superelastic SMA wires, a radial basis function neural network (RBFNN) constitutive model is proposed. In this model, the input includes the number of loading cycles, the index of loading and unloading and the strain; and the output was the stress. Numerical simulations indicate that the model can simulate the cyclic hysteretic behavior of SMA correctly and has a high accuracy of prediction.