Additively manufactured materials and structures: A state-of-the-art review on their mechanical characteristics and energy absorption

International Journal of Mechanical Sciences, Год журнала: 2023, Номер 246, С. 108102 - 108102

Опубликована: Янв. 6, 2023

Язык: Английский

---

Deep Generative Models in Engineering Design: A Review

Journal of Mechanical Design, Год журнала: 2022, Номер 144(7)

Опубликована: Фев. 16, 2022

Abstract Automated design synthesis has the potential to revolutionize modern engineering process and improve access highly optimized customized products across countless industries. Successfully adapting generative machine learning may enable such automated is a research subject of great importance. We present review analysis deep models in design. Deep (DGMs) typically leverage networks learn from an input dataset synthesize new designs. Recently, DGMs as feedforward neural (NNs), adversarial (GANs), variational autoencoders (VAEs), certain reinforcement (DRL) frameworks have shown promising results applications like structural optimization, materials design, shape synthesis. The prevalence skyrocketed since 2016. Anticipating continued growth, we conduct recent advances benefit researchers interested for structure our exposition algorithms, datasets, representation methods, commonly used current literature. In particular, discuss key works that introduced techniques methods DGMs, successfully applied design-related domain, or directly supported development through datasets auxiliary methods. further identify challenges limitations currently seen fields, creativity, handling constraints objectives, modeling both form functional performance simultaneously. discussion, possible solution pathways areas on which target future work.

Язык: Английский

---

Inverting the structure–property map of truss metamaterials by deep learning

Proceedings of the National Academy of Sciences, Год журнала: 2021, Номер 119(1)

Опубликована: Дек. 30, 2021

Significance More than a decade of research has been devoted to leveraging the rich mechanical playground periodically assembled truss metamaterials. The enormous design space manufacturable unit cells, however, made inverse challenge: How does one efficiently identify complex that given target properties? We answer this question by data-driven method, which instantly (once trained, within milliseconds) generates not but variety whose effective response closely matches (fully anisotropic) stiffness tensor. Moreover, our framework smoothly transition between different cells enables lightweight structures with spatially varying, locally optimized properties, for applications from wave guiding artificial bone.

Язык: Английский

---

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

Advanced Materials, Год журнала: 2023, Номер 35(45)

Опубликована: Июнь 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.

Язык: Английский

---

On the use of artificial neural networks in topology optimisation

Structural and Multidisciplinary Optimization, Год журнала: 2022, Номер 65(10)

Опубликована: Окт. 1, 2022

Язык: Английский

---

Tailoring Structure‐Borne Sound through Bandgap Engineering in Phononic Crystals and Metamaterials: A Comprehensive Review

Advanced Functional Materials, Год журнала: 2022, Номер 33(2)

Опубликована: Ноя. 18, 2022

In solid state physics, a bandgap (BG) refers to range of energies where no electronic states can exist. This concept was extended classical waves, spawning the entire fields photonic and phononic crystals BGs are frequency (or wavelength) intervals wave propagation is prohibited. For elastic found in periodically alternating mechanical properties (i.e., stiffness density). gives birth later metamaterials that have enabled unprecedented functionalities for wide applications. Planar built vibration shielding, while myriad works focus on integrating microsystems filtering, waveguiding, dynamical strain energy confinement optomechanical systems. Furthermore, past decade has witnessed rise topological insulators, which leads creation elastodynamic analogs insulators robust manipulation waves. Meanwhile, additive manufacturing realization 3D architected metamaterials, extends their functionalities. review aims comprehensively delineate rich physical background state-of-the art possess engineered different applications, provide roadmap future directions these manmade materials.

Язык: Английский

---

Machine learning accelerates the materials discovery

Materials Today Communications, Год журнала: 2022, Номер 33, С. 104900 - 104900

Опубликована: Ноя. 9, 2022

Язык: Английский

---

Unifying the design space and optimizing linear and nonlinear truss metamaterials by generative modeling

Nature Communications, Год журнала: 2023, Номер 14(1)

Опубликована: Ноя. 21, 2023

The rise of machine learning has fueled the discovery new materials and, especially, metamaterials-truss lattices being their most prominent class. While tailorable properties have been explored extensively, design truss-based metamaterials remained highly limited and often heuristic, due to vast, discrete space lack a comprehensive parameterization. We here present graph-based deep generative framework, which combines variational autoencoder property predictor, construct reduced, continuous latent representation covering an enormous range trusses. This unified allows for fast generation designs through simple operations (e.g., traversing or interpolating between structures). further demonstrate optimization framework inverse trusses with customized mechanical in both linear nonlinear regimes, including exhibiting exceptionally stiff, auxetic, pentamode-like, tailored behaviors. model can predict manufacturable (and counter-intuitive) extreme target beyond training domain.

Язык: Английский

---

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

Materials Today Communications, Год журнала: 2022, Номер 33, С. 104606 - 104606

Опубликована: Окт. 4, 2022

Язык: Английский

---

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

Advanced Materials, Год журнала: 2023, Номер 36(8)

Опубликована: Дек. 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.

Язык: Английский

---