Dominik Klein is doctoral researcher at the cyber-physical systems group at TU darmstadt and will present his doctoral thesis.
Physics-augmented neural network (PANN) constitutive models combine the flexibility of neural networks with a sound mechanical basis. In this presentation, different hyperelastic PANN constitutive models fulfilling the polyconvexity condition are discussed for purely mechanical, parametrized, and electro-mechanical material behavior. The models are applied to different material datasets, including synthetic data of homogenized microstructures and experimental data of 3D printing materials. Thereby, both the benefits and limits of polyconvex constitutive models are discussed.