Acta Materialia, Год журнала: 2025, Номер unknown, С. 120784 - 120784
Опубликована: Фев. 1, 2025
Язык: Английский
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
Процитировано
79
Nature Machine Intelligence, Год журнала: 2023, Номер 5(12), С. 1466 - 1475
Опубликована: Дек. 11, 2023
Язык: Английский
Процитировано
79
CIRP Annals, Год журнала: 2024, Номер 73(2), С. 723 - 749
Опубликована: Янв. 1, 2024
Inspired by the natural intelligence of humans and bio-evolution, Artificial Intelligence (AI) has seen accelerated growth since beginning 21st century. Successful AI applications have been broadly reported, with Industry 4.0 providing a thematic platform for AI-related research development in manufacturing. This paper highlights manufacturing, ranging from production system design planning to process modeling, optimization, quality assurance, maintenance, automated assembly disassembly. In addition, presents an overview representative manufacturing problems matching solutions, perspective future leverage towards realization smart
Язык: Английский
Процитировано
45
Archives of Computational Methods in Engineering, Год журнала: 2024, Номер unknown
Опубликована: Ноя. 3, 2024
Язык: Английский
Процитировано
36
Computational Mechanics, Год журнала: 2024, Номер 74(2), С. 281 - 331
Опубликована: Янв. 13, 2024
Abstract The rapid growth of deep learning research, including within the field computational mechanics, has resulted in an extensive and diverse body literature. To help researchers identify key concepts promising methodologies this field, we provide overview deterministic mechanics. Five main categories are identified explored: simulation substitution, enhancement, discretizations as neural networks, generative approaches, reinforcement learning. This review focuses on methods rather than applications for thereby enabling to explore more effectively. As such, is not necessarily aimed at with knowledge learning—instead, primary audience verge entering or those attempting gain discussed are, therefore, explained simple possible.
Язык: Английский
Процитировано
30
Scientific Reports, Год журнала: 2024, Номер 14(1)
Опубликована: Фев. 29, 2024
Abstract Microstructure reconstruction serves as a crucial foundation for establishing process–structure–property (PSP) relationship in material design. Confronting the limitations of variational autoencoder and generative adversarial network within models, this study adopted denoising diffusion probabilistic model (DDPM) to learn probability distribution high-dimensional raw data successfully reconstructed microstructures various composite materials, such inclusion spinodal decomposition chessboard fractal noise so on. The quality generated microstructure was evaluated using quantitative measures like spatial correlation functions Fourier descriptor. On basis, also achieved regulation randomness generation gradient materials through continuous interpolation latent space implicit (DDIM). Furthermore, two-dimensional extended three-dimensional framework integrated permeability feature encoding embedding. This enables conditional random porous defined range. permeabilities these were further validated application lattice Boltzmann method. above methods provide new ideas references reverse
Язык: Английский
Процитировано
17
European Journal of Mechanics - A/Solids, Год журнала: 2024, Номер 105, С. 105242 - 105242
Опубликована: Янв. 18, 2024
During the last few decades, industries such as aerospace and wind energy (among others) have been remarkably influenced by introduction of high-performance composites. One challenge, however, for modeling designing composites is lack computational efficiency accurate high-fidelity models. For design purposes, using conventional optimization approaches typically results in cumbersome procedures due to huge dimensions space high expense full-field simulations. In recent years, deep learning techniques found be promising methods increase robustness a variety algorithms multi-scale this perspective paper, short overview developments micromechanics-based machine given. More importantly, existing challenges further model enhancements future perspectives field development are elaborated.
Язык: Английский
Процитировано
15
Computer Methods in Applied Mechanics and Engineering, Год журнала: 2023, Номер 416, С. 116343 - 116343
Опубликована: Авг. 22, 2023
Finite element analysis (FEA), a common approach for simulating stress distribution given geometry, is generally associated with high computational cost, especially when mesh resolution required. Furthermore, the non-adaptive nature of FEA requires entire model to be solved even minor geometric variations creating bottleneck during iterative design optimization. This necessitates framework that can efficiently predict in geometries based on boundary and loading conditions. In this paper, we present StressD, predicting von Mises fields denoising diffusion model. The StressD involves two models, U-net-based an auxiliary network generate structures. generates normalized map conditions condition, while used determine scaling information needed un-normalize generated map. We evaluate cantilever structures show it able accurately significantly reducing cost compared traditional FEA.
Язык: Английский
Процитировано
18
Acta Materialia, Год журнала: 2024, Номер 271, С. 119877 - 119877
Опубликована: Апрель 1, 2024
Язык: Английский
Процитировано
9
npj Computational Materials, Год журнала: 2024, Номер 10(1)
Опубликована: Май 8, 2024
Abstract Acquiring reliable microstructure datasets is a pivotal step toward the systematic design of materials with aid integrated computational engineering (ICME) approaches. However, obtaining three-dimensional (3D) often challenging due to high experimental costs or technical limitations, while acquiring two-dimensional (2D) micrographs comparatively easier. To deal this issue, study proposes novel framework called ‘Micro3Diff’ for 2D-to-3D reconstruction microstructures using diffusion-based generative models (DGMs). Specifically, approach solely requires pre-trained DGMs generation 2D samples, and dimensionality expansion (2D-to-3D) takes place only during process (i.e., reverse diffusion process). The proposed incorporates concept referred as ‘multi-plane denoising diffusion’, which transforms noisy samples latent variables) from different planes into data structure maintaining spatial connectivity in 3D space. Furthermore, harmonized sampling developed address possible deviations Markov chain expansion. Combined, we demonstrate feasibility Micro3Diff reconstructing connected slices that maintain morphologically equivalence original images. validate performance Micro3Diff, various types (synthetic experimentally observed) are reconstructed, quality generated assessed both qualitatively quantitatively. successful outcomes inspire potential utilization upcoming ICME applications achieving breakthrough comprehending manipulating space DGMs.
Язык: Английский
Процитировано
9