Release Time:2019-03-09  Hits:

Indexed by: Journal Article

Date of Publication: 2012-09-01

Journal: RARE METAL MATERIALS AND ENGINEERING

Included Journals: ISTIC、PKU、SCIE

Volume: 41

Page Number: 243-246

ISSN: 1002-185X

Key Words: shape memory alloy; superelasticity; radial basis function neural network; cyclic constitutive model

Abstract: 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.