Material Modeling
Under dynamic loading, the structural behavior is particularly influenced by material damping. Sophisticated models are required to mathematically represent these complex effects, necessitating the identification and calibration of numerous parameters from experimental data to meet the model requirements. The complexity of these models and the large number of parameters demand efficient methods. To address this challenge, we use artificial neural networks to model the superelastic behavior of shape memory alloys and to extract the necessary parameters from experimental data.
Architecture of a Deep Operator Network for determining the martensite content and stress distribution of a shape memory alloy as a function of strain and time.
Lenzen N, Altay O (2024). Physics-informed deep operator network for predicting martensite evolution in superelastic shape memory alloys through cyclic tensile tests. Smart Materials and Structures. 33(6):065039. https://doi.org/10.1088/1361-665x/ad4d39