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 …

Hierarchical deep learning neural network (HiDeNN): an artificial intelligence (AI) framework for computational science and engineering

S Saha, Z Gan, L Cheng, J Gao, OL Kafka, X **e… - Computer Methods in …, 2021 - Elsevier
In this work, a unified AI-framework named Hierarchical Deep Learning Neural Network
(HiDeNN) is proposed to solve challenging computational science and engineering …

Discovering plasticity models without stress data

M Flaschel, S Kumar, L De Lorenzis - npj Computational Materials, 2022 - nature.com
We propose an approach for data-driven automated discovery of material laws, which we
call EUCLID (Efficient Unsupervised Constitutive Law Identification and Discovery), and we …

Modular machine learning-based elastoplasticity: Generalization in the context of limited data

JN Fuhg, CM Hamel, K Johnson, R Jones… - Computer Methods in …, 2023 - Elsevier
The development of highly accurate constitutive models for materials that undergo path-
dependent processes continues to be a complex challenge in computational solid …

A Bayesian multiscale CNN framework to predict local stress fields in structures with microscale features

V Krokos, V Bui Xuan, SPA Bordas, P Young… - Computational …, 2022 - Springer
Multiscale computational modelling is challenging due to the high computational cost of
direct numerical simulation by finite elements. To address this issue, concurrent multiscale …

A mechanistic-based data-driven approach for general friction modeling in complex mechanical system

H Peng, N Song, F Li, S Tang - Journal of Applied …, 2022 - asmedigitalcollection.asme.org
The effect of friction is widespread around us, and most important projects must consider the
friction effect. To better depict the dynamic characteristics of multibody systems with friction …

A machine learning-based multi-scale computational framework for granular materials

S Guan, T Qu, YT Feng, G Ma, W Zhou - Acta Geotechnica, 2023 - Springer
With the development of experimental measurement technology and high-fidelity numerical
simulations of granular materials, empirical-based classical constitutive models may not be …

Mechanistically informed data-driven modeling of cyclic plasticity via artificial neural networks

D Liu, H Yang, KI Elkhodary, S Tang, WK Liu… - Computer Methods in …, 2022 - Elsevier
A mechanistically informed data-driven approach is proposed to simulate the complex
plastic behavior of microstructured/homogenized solids subjected to cyclic loading …

A database construction method for data-driven computational mechanics of composites

L Li, Q Shao, Y Yang, Z Kuang, W Yan, J Yang… - International Journal of …, 2023 - Elsevier
A new method combining computational homogenization and the Artificial Neural Network
(ANN) is proposed to construct elastoplastic composites database efficiently for data-driven …

A mechanics-informed machine learning approach for modeling the elastoplastic behavior of fiber-reinforced composites

Z Li, X Li, Y Chen, C Zhang - Composite Structures, 2023 - Elsevier
When machine learning (ML) techniques are used to predict the elastoplastic behavior of a
fiber-reinforced composite, a large training database is typically required due to the …