Reduced and all-at-once approaches for model calibration and discovery in computational solid mechanics
In the framework of solid mechanics, the task of deriving material parameters from
experimental data has recently re-emerged with the progress in full-field measurement …
experimental data has recently re-emerged with the progress in full-field measurement …
[HTML][HTML] Versatile data-adaptive hyperelastic energy functions for soft materials
S Wiesheier, MA Moreno-Mateos… - Computer Methods in …, 2024 - Elsevier
Applications of soft materials are customarily linked to complex deformation scenarios and
material nonlinearities. In the bioengineering field, soft materials typically mimic the low …
material nonlinearities. In the bioengineering field, soft materials typically mimic the low …
NN-EVP: A physics informed neural network-based elasto-viscoplastic framework for predictions of grain size-aware flow response
We propose a physics informed, neural network-based elasto-viscoplasticity (NN-EVP)
constitutive modeling framework for predicting the flow response in metals as a function of …
constitutive modeling framework for predicting the flow response in metals as a function of …
[HTML][HTML] HyperCAN: Hypernetwork-driven deep parameterized constitutive models for metamaterials
We introduce HyperCAN, a machine learning framework that utilizes hypernetworks to
construct adaptable constitutive artificial neural networks for a wide range of beam-based …
construct adaptable constitutive artificial neural networks for a wide range of beam-based …
Neural networks meet anisotropic hyperelasticity: A framework based on generalized structure tensors and isotropic tensor functions
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 …
elasticity based on physics-augmented neural networks (PANNs). Our approach allows the …
Differentiable Neural-Integrated Meshfree Method for Forward and Inverse Modeling of Finite Strain Hyperelasticity
The present study aims to extend the novel physics-informed machine learning approach,
specifically the neural-integrated meshfree (NIM) method, to model finite-strain problems …
specifically the neural-integrated meshfree (NIM) method, to model finite-strain problems …
Automated model discovery of finite strain elastoplasticity from uniaxial experiments
Constitutive modeling lies at the core of mechanics, allowing us to map strains onto stresses
for a material in a given mechanical setting. Historically, researchers relied on …
for a material in a given mechanical setting. Historically, researchers relied on …
Direct Data-Driven Algorithms for Multiscale Mechanics
We propose a randomized data-driven solver for multiscale mechanics problems which
improves accuracy by escaping local minima and reducing dependency on metric …
improves accuracy by escaping local minima and reducing dependency on metric …