Data‐Driven Design for Metamaterials and Multiscale Systems: A Review

Advanced Materials, Journal Year: 2023, Volume and Issue: 36(8)

Published: Dec. 5, 2023

Abstract Metamaterials are artificial materials designed to exhibit effective material parameters that go beyond those found in nature. Composed of unit cells with rich designability assembled into multiscale systems, they hold great promise for realizing next‐generation devices exceptional, often exotic, functionalities. However, the vast design space and intricate structure–property relationships pose significant challenges their design. A compelling paradigm could bring full potential metamaterials fruition is emerging: data‐driven This review provides a holistic overview this rapidly evolving field, emphasizing general methodology instead specific domains deployment contexts. Existing research organized modules, encompassing data acquisition, machine learning‐based cell design, optimization. The approaches further categorized within each module based on shared principles, analyze compare strengths applicability, explore connections between different identify open questions opportunities.

Language: Английский

---

Recent Advances and Applications of Machine Learning in Experimental Solid Mechanics: A Review

Applied Mechanics Reviews, Journal Year: 2023, Volume and Issue: 75(6)

Published: July 17, 2023

Abstract For many decades, experimental solid mechanics has played a crucial role in characterizing and understanding the mechanical properties of natural novel artificial materials. Recent advances machine learning (ML) provide new opportunities for field, including design, data analysis, uncertainty quantification, inverse problems. As number papers published recent years this emerging field is growing exponentially, it timely to conduct comprehensive up-to-date review ML applications mechanics. Here, we first an overview common algorithms terminologies that are pertinent review, with emphasis placed on physics-informed physics-based methods. Then, thorough coverage traditional areas mechanics, fracture biomechanics, nano- micromechanics, architected materials, two-dimensional Finally, highlight some current challenges applying multimodality multifidelity datasets, quantifying predictions, proposing several future research directions. This aims valuable insights into use methods variety examples researchers integrate their experiments.

Language: Английский

---

Inverse design of nonlinear mechanical metamaterials via video denoising diffusion models

Nature Machine Intelligence, Journal Year: 2023, Volume and Issue: 5(12), P. 1466 - 1475

Published: Dec. 11, 2023

Language: Английский

---

Predicting stress, strain and deformation fields in materials and structures with graph neural networks

Scientific Reports, Journal Year: 2022, Volume and Issue: 12(1)

Published: Dec. 17, 2022

Abstract Developing accurate yet fast computational tools to simulate complex physical phenomena is a long-standing problem. Recent advances in machine learning have revolutionized the way simulations are approached, shifting from purely physics- AI-based paradigm. Although impressive achievements been reached, efficiently predicting materials and structures remains challenge. Here, we present an general framework, implemented through graph neural networks, able learn mechanical behavior of few hundreds data. Harnessing natural mesh-to-graph mapping, our deep model predicts deformation, stress, strain fields various material systems, like fiber stratified composites, lattice metamaterials. The can capture nonlinear phenomena, plasticity buckling instability, seemingly relationships between predicted fields. Owing its flexibility, this graph-based framework aims at connecting materials’ microstructure, base properties, boundary conditions response, opening new avenues towards graph-AI-based surrogate modeling.

Language: Английский

---

Topology optimization via machine learning and deep learning: a review

Journal of Computational Design and Engineering, Journal Year: 2023, Volume and Issue: 10(4), P. 1736 - 1766

Published: July 4, 2023

Abstract Topology optimization (TO) is a method of deriving an optimal design that satisfies given load and boundary conditions within domain. This enables effective without initial design, but has been limited in use due to high computational costs. At the same time, machine learning (ML) methodology including deep made great progress 21st century, accordingly, many studies have conducted enable rapid by applying ML TO. Therefore, this study reviews analyzes previous research on ML-based TO (MLTO). Two different perspectives MLTO are used review studies: (i) (ii) perspectives. The perspective addresses “why” for TO, while “how” apply In addition, limitations current future directions examined.

Language: Английский

---

Disordered mechanical metamaterials

Nature Reviews Physics, Journal Year: 2023, Volume and Issue: 5(11), P. 679 - 688

Published: Sept. 29, 2023

Language: Английский

---

Machine intelligence in metamaterials design: a review

Oxford Open Materials Science, Journal Year: 2024, Volume and Issue: 4(1)

Published: Jan. 1, 2024

Abstract Machine intelligence continues to rise in popularity as an aid the design and discovery of novel metamaterials. The properties metamaterials are essentially controllable via their architectures until recently, process has relied on a combination trial-and-error physics-based methods for optimization. These processes can be time-consuming challenging, especially if space metamaterial optimization is explored thoroughly. Artificial (AI) machine learning (ML) used overcome challenges like these pre-processed massive datasets very accurately train appropriate models. models broad, describing properties, structure, function at numerous levels hierarchy, using relevant inputted knowledge. Here, we present comprehensive review literature where state-of-the-art design, development In this review, individual approaches categorized based methodology application. We further trends over wide range problems including: acoustics, photonics, plasmonics, mechanics, more. Finally, identify discuss recent research directions highlight current gaps

Language: Английский

---

AI-Based Metamaterial Design

ACS Applied Materials & Interfaces, Journal Year: 2024, Volume and Issue: 16(23), P. 29547 - 29569

Published: May 29, 2024

The use of metamaterials in various devices has revolutionized applications optics, healthcare, acoustics, and power systems. Advancements these fields demand novel or superior that can demonstrate targeted control electromagnetic, mechanical, thermal properties matter. Traditional design systems methods often require manual manipulations which is time-consuming resource intensive. integration artificial intelligence (AI) optimizing metamaterial be employed to explore variant disciplines address bottlenecks design. AI-based also enable the development by parameters cannot achieved using traditional methods. application AI leveraged accelerate analysis vast data sets as well better utilize limited via generative models. This review covers transformative impact for current challenges, emerging fields, future directions, within each domain are discussed.

Language: Английский

---

A deep generative multiscale topology optimization framework considering manufacturing defects and parametrical uncertainties

Computer Methods in Applied Mechanics and Engineering, Journal Year: 2025, Volume and Issue: 437, P. 117778 - 117778

Published: Jan. 22, 2025

Language: Английский

---

Generative deep learning for designing irregular metamaterials with programmable nonlinear mechanical responses

International Journal of Mechanical Sciences, Journal Year: 2025, Volume and Issue: unknown, P. 110123 - 110123

Published: March 1, 2025

Language: Английский

---