MODELLING OF HYSTERESIS BEHAVIOUR OF NICKEL-TITANIUM SHAPE MEMORY ALLOY USING ARTIFICIAL NEURAL NETWORK

Abstract

Shape memory alloys (SMAs) are a class of materials that have the ability to return to their previous shape when exposed to temperature or mechanical stress. The main functional properties of these alloys, the shape memory effect (SME) and superelasticity (SE), make them indispensable in various industries. The SMA superelasticity is the ability of a material to return to its original shape after loading and unloading due to transformations between austenite and martensite. These phase transitions are accompanied by hysteresis, which can be observed in the stress-strain diagram. In this study, the hysteresis behavior of SMA, particularly nickel-titanium alloy (NiTi or Nitinol), was modeled using artificial neural networks. The use of neural networks in the study made it possible to obtain accurate material strain predictions and reduce the number of actual experiments. The results showed the high accuracy of the prediction model, which indicates the prospects of using artificial neural networks in the study of SMA characteristics.