A review on data-driven constitutive laws for solids

JN Fuhg, G Anantha Padmanabha, N Bouklas… - … Methods in Engineering, 2024 - Springer
This review article highlights state-of-the-art data-driven techniques to discover, encode,
surrogate, or emulate constitutive laws that describe the path-independent and path …

[HTML][HTML] Hard magnetics and soft materials—a synergy

P Narayanan, R Pramanik… - Smart Materials and …, 2024 - iopscience.iop.org
Hard-magnetic soft materials (hMSMs) are smart composites that consist of a mechanically
soft polymer matrix impregnated with mechanically hard magnetic filler particles. This dual …

Extreme sparsification of physics-augmented neural networks for interpretable model discovery in mechanics

JN Fuhg, RE Jones, N Bouklas - Computer Methods in Applied Mechanics …, 2024 - Elsevier
Data-driven constitutive modeling with neural networks has received increased interest in
recent years due to its ability to easily incorporate physical and mechanistic constraints and …

[HTML][HTML] Physics-augmented neural networks for constitutive modeling of hyperelastic geometrically exact beams

JO Schommartz, DK Klein, JCA Cobo… - Computer Methods in …, 2025 - Elsevier
We present neural network-based constitutive models for hyperelastic geometrically exact
beams. The proposed models are physics-augmented, ie, formulated to fulfill important …

[HTML][HTML] Nonlinear electro-elastic finite element analysis with neural network constitutive models

DK Klein, R Ortigosa, J Martínez-Frutos… - Computer Methods in …, 2024 - Elsevier
In the present work, the applicability of physics-augmented neural network (PANN)
constitutive models for complex electro-elastic finite element analysis is demonstrated. For …

Improving the performance of Stein variational inference through extreme sparsification of physically-constrained neural network models

GA Padmanabha, JN Fuhg, C Safta, RE Jones… - Computer Methods in …, 2024 - Elsevier
Most scientific machine learning (SciML) applications of neural networks involve hundreds
to thousands of parameters, and hence, uncertainty quantification for such models is …

Viscoelasticty with physics-augmented neural networks: Model formulation and training methods without prescribed internal variables

M Rosenkranz, KA Kalina, J Brummund, WC Sun… - Computational …, 2024 - Springer
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 …

Recovering Mullins damage hyperelastic behaviour with physics augmented neural networks

M Zlatić, M Čanađija - Journal of the Mechanics and Physics of Solids, 2024 - Elsevier
The aim of this work is to develop a neural network for modelling incompressible
hyperelastic behaviour with isotropic damage, the so-called Mullins effect. This is obtained …

Data-driven methods for computational mechanics: A fair comparison between neural networks based and model-free approaches

M Zlatić, F Rocha, L Stainier, M Čanađija - Computer methods in applied …, 2024 - Elsevier
We present a comparison between two approaches to modelling hyperelastic material
behaviour using data. The first approach is a novel approach based on Data-driven …

Accounting for plasticity: An extension of inelastic Constitutive Artificial Neural Networks

B Boes, JW Simon, H Holthusen - arXiv preprint arXiv:2407.19326, 2024 - arxiv.org
The class of Constitutive Artificial Neural Networks (CANNs) represents a new approach of
neural networks in the field of constitutive modeling. So far, CANNs have proven to be a …