Deep Learning in Mechanical Metamaterials: From Prediction and Generation to Inverse Design

Advanced Materials, Journal Year: 2023, Volume and Issue: 35(45)

Published: June 19, 2023

Abstract Mechanical metamaterials are meticulously designed structures with exceptional mechanical properties determined by their microstructures and constituent materials. Tailoring material geometric distribution unlocks the potential to achieve unprecedented bulk functions. However, current metamaterial design considerably relies on experienced designers' inspiration through trial error, while investigating responses entails time‐consuming testing or computationally expensive simulations. Nevertheless, recent advancements in deep learning have revolutionized process of metamaterials, enabling property prediction geometry generation without prior knowledge. Furthermore, generative models can transform conventional forward into inverse design. Many studies implementation highly specialized, pros cons may not be immediately evident. This critical review provides a comprehensive overview capabilities prediction, generation, metamaterials. Additionally, this highlights leveraging create universally applicable datasets, intelligently intelligence. article is expected valuable only researchers working but also those field materials informatics.

Language: Английский

---

Machine learning and deep learning in phononic crystals and metamaterials – A review

Materials Today Communications, Journal Year: 2022, Volume and Issue: 33, P. 104606 - 104606

Published: Oct. 4, 2022

Language: Английский

---

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

---

Growth rules for irregular architected materials with programmable properties

Science, Journal Year: 2022, Volume and Issue: 377(6609), P. 975 - 981

Published: Aug. 25, 2022

Biomaterials display microstructures that are geometrically irregular and functionally efficient. Understanding the role of irregularity in determining material properties offers a new path to engineer materials with superior functionalities, such as imperfection insensitivity, enhanced impact absorption, stress redirection. We uncover fundamental, probabilistic structure-property relationships using growth-inspired program evokes formation stochastic architectures natural systems. This virtual growth imposes set local rules on limited number basic elements. It generates exhibit large variation functional starting from very initial resources, which echoes diversity biological identify control mechanical by independently varying microstructure's topology geometry general, graph-based representation materials.

Language: Английский

---

Ultrastiff metamaterials generated through a multilayer strategy and topology optimization

Nature Communications, Journal Year: 2024, Volume and Issue: 15(1)

Published: April 6, 2024

Abstract Metamaterials composed of different geometrical primitives have properties. Corresponding to the fundamental forms line, plane, and surface, beam-, plate-, shell-based lattice metamaterials enjoy many advantages in aspects, respectively. To fully exploit each structural archetype, we propose a multilayer strategy topology optimization technique design metamaterial this study. Under frame strategy, space is enlarged diversified, freedom increased. Topology applied explore better designs larger diverse space. Beam-plate-shell-combined automatically emerge from achieve ultrahigh stiffness. Benefiting high stiffness, energy absorption performances optimized results also demonstrate substantial improvements under large deformation. The can bring series tunable dimensions for design, which helps desired mechanical properties, such as isotropic elasticity functionally grading material property, superior acoustic tuning, electrostatic shielding, fluid field tuning. We envision that broad array synthetic composite with unprecedented performance be designed optimization.

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

---

Deep‐Learning‐Enabled Intelligent Design of Thermal Metamaterials

Advanced Materials, Journal Year: 2023, Volume and Issue: 35(33)

Published: July 2, 2023

Thermal metamaterials are mixture-based materials that engineered to manipulate, control, and process the flow of heat, enabling numerous advanced thermal metadevices. Conventional predominantly designed with tractable regular geometries owing delicate analytical solution easy-to-implement effective structures. Nevertheless, it is challenging achieve design arbitrary geometry, letting alone intelligent (automatic, real-time, customizable) metamaterials. Here, an framework presented via a pre-trained deep learning model, which gracefully achieves desired functional structures exceptional speed efficiency, regardless geometry. It possesses incomparable versatility great flexibility corresponding different background materials, anisotropic geometries, functionalities. The transformation thermotics-induced, freeform, background-independent, omnidirectional cloaks, whose structural configurations automatically in real-time according shape background, numerically experimentally demonstrated. This study sets up novel paradigm for automatic new scenario. More generally, may open door realization also other physical domains.

Language: Английский

---

Topology optimisation for design and additive manufacturing of functionally graded lattice structures using derivative-aware machine learning algorithms

Additive manufacturing, Journal Year: 2023, Volume and Issue: 78, P. 103833 - 103833

Published: Sept. 1, 2023

Although additive manufacturing has offered substantially new opportunities and flexibility for fabricating 3D complex lattice structures, effective design of such sophisticated structures with desired multifunctional characteristics remains a demanding task. To tackle this challenge, we develop an inventive multiscale topology optimisation approach additively manufactured lattices by leveraging derivative-aware machine learning algorithm. Our objective is to optimise non-uniform unit cells achieving as uniform strain pattern possible. The proposed exhibits great potential biomedical applications, implantable devices mitigating stress shielding. validate the effectiveness our framework, present two illustrative examples through dedicated digital image correlation (DIC) tests on optimised samples fabricated using powder bed fusion (PBF) technique. Furthermore, demonstrate practical application developing bone tissue scaffolds composed iso-truss typical musculoskeletal reconstruction cases. These lattice-based more field in anatomical physiological condition, thereby creating favourable biomechanical environment maximising formation effectively. anticipated make significant step forward desirable mechanical broad range applications.

Language: Английский

---

Inverse-designed growth-based cellular metamaterials

Mechanics of Materials, Journal Year: 2023, Volume and Issue: 182, P. 104668 - 104668

Published: May 2, 2023

Advancements in machine learning have sparked significant interest designing mechanical metamaterials, i.e., materials that derive their properties from inherent microstructure rather than just constituent material. We propose a data-driven exploration of the design space growth-based cellular metamaterials based on star-shaped distances. These two-dimensional are periodically-repeating unit cells consisting material and void patterns with non-trivial geometries. Machine models exploiting large datasets then employed to inverse for tailored anisotropic stiffness. Firstly, forward model is created bypass growth homogenization process accurately predict given finite set parameters. Secondly, an used invert structure–property maps enable accurate prediction designs stiffness query. successfully demonstrate frameworks' generalization capabilities by chosen outside domain space.

Language: Английский

---

Perspective: Machine Learning in Design for 3D/4D Printing

Journal of Applied Mechanics, Journal Year: 2023, Volume and Issue: 91(3)

Published: Oct. 5, 2023

Abstract 3D/4D printing offers significant flexibility in manufacturing complex structures with a diverse range of mechanical responses, while also posing critical needs tackling challenging inverse design problems. The rapidly developing machine learning (ML) approach new opportunities and has attracted interest the field. In this perspective paper, we highlight recent advancements utilizing ML for designing printed desired responses. First, provide an overview common forward problems, relevant types structures, space responses printing. Second, review works that have employed variety approaches different ranging from structural properties to active shape changes. Finally, briefly discuss main challenges, summarize existing potential approaches, extend discussion broader problems field This paper is expected foundational guides insights into application design.

Language: Английский

---