A State-of-the-Art Review on Machine Learning-Based Multiscale Modeling, Simulation, Homogenization and Design of Materials

Bishara, Dana; Xie, Yachen; Liu, Wing Kam; Li, Shaofan

doi:10.1007/s11831-022-09795-8

Cited by 76 publications

(23 citation statements)

References 222 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…( 515)-(516) have been used to model, e.g., the visually responsive neurons in the premotor cortex [19], p. 242. 318 In original notation, Eq. (510) was written as [32], whose outputs x i in the previous expression are now rewritten as y i in Eq.…”

Section: Cmes 2023mentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning Applied to Computational Mechanics: A Comprehensive Review, State of the Art, and the Classics

Vu‐Quoc¹,

Humer²

2023

Computer Modeling in Engineering &Amp; Sciences

View full text Add to dashboard Cite

show abstract

Section: Cmes 2023mentioning

confidence: 99%

“…Remark 12.9. In concluding this section, we mention the 2023 review paper [318], brought to our attention by a reviewer, on "A state-of-the-art review on machine learning-based multiscale modeling, simulation, homogenization and design of materials." This review paper would nicely complement our present review paper.…”

mentioning

confidence: 99%

Deep Learning Applied to Computational Mechanics: A Comprehensive Review, State of the Art, and the Classics

Vu‐Quoc¹,

Humer²

2023

Computer Modeling in Engineering &Amp; Sciences

View full text Add to dashboard Cite

show abstract

“…Recent progress in machine learning and data science have brought great opportunities to develop advanced data-driven material modeling and multiscale simulation methods (LeCun et al 2015; Goodfellow et al 2016;Liu et al 2021;Bishara et al 2022; Vu-Quoc and Humer 2022). To circumvent the limitations of conventional constitutive modeling, the model-free data-driven approach has been developed, which formulates an optimization problem to search for a stress solution directly from the material database characterizing constitutive behaviors subjected to essential physical constraints, such as equilibrium and compatibility conditions (Kirchdoerfer and Ortiz 2016; Ibanez et al 2018;Eggersmann et al 2019; He and Chen 2020; ; He et al 2021a; He et al 2021b;Xu et al 2020).…”

Section: Introductionmentioning

confidence: 99%

LS-DYNA Machine Learning–Based Multiscale Method for Nonlinear Modeling of Short Fiber–Reinforced Composites

Wei

et al. 2023

J. Eng. Mech.

View full text Add to dashboard Cite

Short-fiber-reinforced composites (SFRC) are high-performance engineering materials for lightweight structural applications in the automotive and electronics industries. Typically, SFRC structures are manufactured by injection molding, which induces heterogeneous microstructures, and the resulting nonlinear anisotropic behaviors are challenging to predict by conventional micromechanical analyses. In this work, we present a machine learning-based multiscale method by integrating injection molding-induced microstructures, material homogenization, and Deep Material Network (DMN) in the finite element simulation software LS-DYNA for structural analysis of SFRC. DMN is a physics-embedded machine learning model that learns the microscale material morphologies hidden in representative volume elements of composites through offline training. By coupling DMN with finite elements, we have developed a highly accurate and efficient data-driven approach, which predicts nonlinear behaviors of composite materials and structures at a computational speed orders-of-magnitude faster than the high-fidelity direct numerical simulation. To model industrial-scale SFRC products, transfer learning is utilized to generate a unified DMN database, which effectively captures the effects of injection molding-induced fiber orientations and volume fractions on the overall composite properties. Numerical examples are presented to demonstrate the promising performance of this LS-DYNA machine learning-based multiscale method for SFRC modeling.

show abstract

“…In addition to this subject, there has been a growing trend to use deep learning (DL) models for material design in recent years [36][37][38]. The primary application of DL is to unveil the intricate relationships between high-dimensional data (e.g., such as microstructure geometry) and the specific variables of interest (e.g., microstructural descriptors or material response).…”

Section: Introductionmentioning

confidence: 99%

A Data-Driven Framework for Designing Microstructure of Multifunctional Composites with Deep-Learned Diffusion-Based Generative Models

Lee

Lim

Yun

2023

Preprint

View full text Add to dashboard Cite

This paper puts forward a novel integrated microstructure design methodology that replaces the common existing design approaches for multifunctional composites: 1) reconstruction of microstructures, 2) analyzing and quantifying material properties, and 3) inverse design of materials using the diffusion-based generative model (DGM). The problem of microstructure reconstruction is addressed using DGM, which is a new state-of-the-art generative model formulated with a forward Markovian diffusion process and the reverse process. Then, the conditional formulation of DGM is introduced for guidance to the embedded desired material properties with a transformer-based attention mechanism, which enables the inverse design of multifunctional composites. A convolutional neural network (CNN)-based surrogate model is utilized to facilitate the prediction of nonlinear material properties for building microstructure-property linkages. Combined, the proposed artificial intelligence-based design framework enables large data processing and database construction that is often not affordable with resource-intensive finite element method (FEM)-based direct numerical simulation (DNS) and iterative reconstruction methods. What is important is that the proposed DGM-based methodology is not susceptible to unstable training or mode collapse, which are common issues in neural network models that are often difficult to address even with extensive hyperparameter tuning. An example case is presented to demonstrate the effectiveness of the proposed approach, which is designing mechanoluminescence (ML) particulate composites made of europium and dysprosium ions. The results show that the inversely-designed multiple ML microstructure candidates with the proposed generative and surrogate models meet the multiple design requirements (e.g., volume fraction, elastic constant, and light sensitivity). The evaluation of the generated samples' quality and the surrogate models' performance using appropriate metrics are also included. This assessment demonstrates that the proposed integrated methodology offers an end-to-end solution for practical material design applications.

show abstract

A State-of-the-Art Review on Machine Learning-Based Multiscale Modeling, Simulation, Homogenization and Design of Materials

Cited by 76 publications

References 222 publications

Deep Learning Applied to Computational Mechanics: A Comprehensive Review, State of the Art, and the Classics

Deep Learning Applied to Computational Mechanics: A Comprehensive Review, State of the Art, and the Classics

LS-DYNA Machine Learning–Based Multiscale Method for Nonlinear Modeling of Short Fiber–Reinforced Composites

A Data-Driven Framework for Designing Microstructure of Multifunctional Composites with Deep-Learned Diffusion-Based Generative Models

Contact Info

Product

Resources

About