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 …

Neural networks for constitutive modeling: From universal function approximators to advanced models and the integration of physics

J Dornheim, L Morand, HJ Nallani, D Helm - Archives of Computational …, 2024 - Springer
Analyzing and modeling the constitutive behavior of materials is a core area in materials
sciences and a prerequisite for conducting numerical simulations in which the material …

Microstructure-guided deep material network for rapid nonlinear material modeling and uncertainty quantification

T Huang, Z Liu, CT Wu, W Chen - Computer Methods in Applied Mechanics …, 2022 - Elsevier
Modeling nonlinear materials with arbitrary microstructures and loading paths is crucial in
structural analyses with heterogeneous materials with uncertainty. However, it is …

[HTML][HTML] A multi-fidelity data-driven model for highly accurate and computationally efficient modeling of short fiber composites

HL Cheung, M Mirkhalaf - Composites Science and Technology, 2024 - Elsevier
To develop physics-based models and establish a structure–property relationship for short
fiber composites, there are a wide range of micro-structural properties to be considered. To …

Deep homogenization networks for elastic heterogeneous materials with two-and three-dimensional periodicity

J Wu, J Jiang, Q Chen, G Chatzigeorgiou… - International Journal of …, 2023 - Elsevier
We present a deep learning framework that leverages computational homogenization
expertise to predict the local stress field and homogenized moduli of heterogeneous …

Rapid inverse calibration of a multiscale model for the viscoplastic and creep behavior of short fiber-reinforced thermoplastics based on Deep Material Networks

AP Dey, F Welschinger, M Schneider, S Gajek… - International Journal of …, 2023 - Elsevier
In this work, we propose to use deep material networks (DMNs) as a surrogate model for full-
field computational homogenization to inversely identify material parameters of constitutive …

LS-DYNA machine learning–based multiscale method for nonlinear modeling of short fiber–reinforced composites

H Wei, CT Wu, W Hu, TH Su, H Oura… - Journal of …, 2023 - ascelibrary.org
Short fiber–reinforced composites (SFRCs) are high-performance engineering materials for
lightweight structural applications in the automotive and electronics industries. Typically …

[HTML][HTML] A probabilistic virtual process chain to quantify process-induced uncertainties in Sheet Molding Compounds

N Meyer, S Gajek, J Görthofer, A Hrymak… - Composites Part B …, 2023 - Elsevier
The manufacturing process of Sheet Molding Compound (SMC) influences the properties of
a component in a non-deterministic fashion. To predict this influence on the mechanical …

[HTML][HTML] Deep neural network homogenization of multiphysics behavior for periodic piezoelectric composites

Q Chen, C **ao, Z Yang, J Tabet, X Chen - Composites Part A: Applied …, 2024 - Elsevier
We present a physically informed deep neural network homogenization theory for identifying
homogenized moduli and local electromechanical fields of periodic piezoelectric …

Deep material network via a quilting strategy: visualization for explainability and recursive training for improved accuracy

D Shin, R Alberdi, RA Lebensohn… - npj Computational …, 2023 - nature.com
Recent developments integrating micromechanics and neural networks offer promising
paths for rapid predictions of the response of heterogeneous materials with similar accuracy …