172 citations · 620 across the 24 of their papers we have counts for
13 papers · 1 filter
Calibration of neural viscoelastic models via full-field data
Brain M. Riemer, Markus Kästner, Karl A. Kalina
We propose an unsupervised learning framework for calibrating a physics-augmented neural network (PANN) for small-strain viscoelasticity via full-field data. It only requires quant…
On limitations of polyconvexity
Dominik K. Klein, Rogelio Ortigosa, Heinrich T. Roth +4
Polyconvex constitutive modeling is attractive as it guarantees stability of numerical simulations and can improve the generalization behavior of material models. However, in certa…
Advances in polyconvex anisotropic hyperelasticity
Dominik K. Klein, Karl A. Kalina, Rogelio Ortigosa +3
A key challenge in material theory is the formulation of models that satisfy all common mechanical constitutive conditions while retaining sufficient flexibility. In this context,…
A physics-augmented neural network framework for finite strain incompressible viscoelasticity
Karl A. Kalina, Jörg Brummund, Markus Kästner
We propose a physics-augmented neural network (PANN) framework for finite strain incompressible viscoelasticity within the generalized standard materials theory. The formulation is…
A data-driven multiscale scheme for anisotropic finite strain magneto-elasticity
Heinrich T. Roth, Philipp Gebhart, Karl A. Kalina +2
In this work, we develop a neural network-based, data-driven, decoupled multiscale scheme for the modeling of structured magnetically soft magnetorheological elastomers (MREs). On…
Data-efficient inverse design of spinodoid metamaterials
Max Rosenkranz, Markus Kästner, Ivo F. Sbalzarini
We create an data-efficient and accurate surrogate model for structure-property linkages of spinodoid metamaterials with only 75 data points -- far fewer than the several thousands…
A dual-stage constitutive modeling framework based on finite strain data-driven identification and physics-augmented neural networks
Lennart Linden, Karl A. Kalina, Jörg Brummund +2
In this contribution, we present a novel consistent dual-stage approach for the automated generation of hyperelastic constitutive models which only requires experimentally measurab…
Neural networks meet anisotropic hyperelasticity: A framework based on generalized structure tensors and isotropic tensor functions
Karl A. Kalina, Jörg Brummund, WaiChing Sun +1
We present a data-driven framework for the multiscale modeling of anisotropic finite strain elasticity based on physics-augmented neural networks (PANNs). Our approach allows the e…
Viscoelasticty with physics-augmented neural networks: Model formulation and training methods without prescribed internal variables
Max Rosenkranz, Karl A. Kalina, Jörg Brummund +2
We present an approach for the data-driven modeling of nonlinear viscoelastic materials at small strains which is based on physics-augmented neural networks (NNs) and requires only…
Neural network-based multiscale modeling of finite strain magneto-elasticity with relaxed convexity criteria
Karl A. Kalina, Philipp Gebhart, Jörg Brummund +3
We present a framework for the multiscale modeling of finite strain magneto-elasticity based on physics-augmented neural networks (NNs). By using a set of problem specific invarian…
A comparative study on different neural network architectures to model inelasticity
Max Rosenkranz, Karl A. Kalina, Jörg Brummund +1
The mathematical formulation of constitutive models to describe the path-dependent, i.e., inelastic, behavior of materials is a challenging task and has been a focus in mechanics r…
Neural networks meet hyperelasticity: A guide to enforcing physics
Lennart Linden, Dominik K. Klein, Karl A. Kalina +3
In the present work, a hyperelastic constitutive model based on neural networks is proposed which fulfills all common constitutive conditions by construction, and in particular, is…
FE An efficient data-driven multiscale approach based on physics-constrained neural networks and automated data mining
Karl A. Kalina, Lennart Linden, Jörg Brummund +1
Herein, we present a new data-driven multiscale framework called FE which is based on two main keystones: the usage of physics-constrained artificial neural networks…