Machine learning assisted intelligent design of meta structures: a review

Abstract

In recent years, the rapid development of machine learning (ML) based on data-driven or environment interaction has injected new vitality into the field of meta-structure design. As a supplement to the traditional analysis methods based on physical formulas and rules, the involvement of ML has greatly accelerated the pace of performance exploration and optimization for meta-structures. In this review, we focus on the latest progress of ML in acoustic, elastic, and mechanical meta-structures from the aspects of band structures, wave propagation characteristics, and static characteristics. We finally summarize and envisage some potential research directions of ML in the field of meta-structures.

Keywords

Meta-structure / inverse design / machine learning / continuous fiber reinforced composite meta-structure / additive manufacture

References

[1] Kumar R,Chohan JS.Overview on metamaterial: history, types and applications.Mater Today Proc2022;56:3016-24

[2] Ma G.Acoustic metamaterials: from local resonances to broad horizons.Sci Adv2016;2:e1501595 PMCID:PMC4771441

[3] Yu X,Liang H,Wu L.Mechanical metamaterials associated with stiffness, rigidity and compressibility: a brief review.Prog Mater Sci2018;94:114-73

[4] Cui T.Electromagnetic metamaterials - from effective media to field programmable systems.Sci Sin Inf2020;50:1427

[5] Jin Y,Bonello B.Physics of surface vibrational resonances: pillared phononic crystals, metamaterials, and metasurfaces.Rep Prog Phys2021;84:086502

[6] Wu X,Jin Y,Zhuang X.Broadband rayleigh wave attenuation by gradient metamaterials.Int J Mech Sci2021;205:106592

[7] Cao L,Xu Y.Flexural wave absorption by lossy gradient elastic metasurface.J Mech Phy Solids2020;143:104052

[8] Huang S,Li D.Compact broadband acoustic sink with coherently coupled weak resonances.Sci Bull2020;65:373-9

[9] Jin Y,Khelif A.Elastic metasurfaces for deep and robust subwavelength focusing and imaging.Phys Rev Appl2021;15:024005

[10] Wang W,Jin Y,Khelif A.Experimental realization of a pillared metasurface for flexural wave focusing.APL Mater2021;9:051125

[11] Wen Z,Gao P,Rabczuk T.Topological cavities in phononic plates for robust energy harvesting.Mech Syst Signal Process2022;162:108047

[12] Wen Z,Khelif A,Jin Y.A perspective on elastic metastructures for energy harvesting.Appl Phys Lett2022;120:020501

[13] He H,Ye L.Topological negative refraction of surface acoustic waves in a Weyl phononic crystal.Nature2018;560:61-4

[14] Jin Y,Li Y.Engineered diffraction gratings for acoustic cloaking.Phys Rev Appl2019;11:011004

[15] Zhou H,Wang Y,Laude V.Ultra-broadband passive acoustic metasurface for wide-angle carpet cloaking.Mater Des2021;199:109414

[16] Zhang X,Cheng Y,Christensen J.Topological sound.Commun Phys2018;1:97

[17] Kushwaha MS,Dobrzynski L.Acoustic band structure of periodic elastic composites.Phys Rev Lett1993;71:2022-5

[18] Martínez-sala R,Sánchez JV,Llinares J.Sound attenuation by sculpture.Nature1995;378:241

[19] Liu Z,Mao Y.Locally resonant sonic materials.Science2000;289:1734-6

[20] Liao G,Wang Z,Yao X.Acoustic metamaterials: a review of theories, structures, fabrication approaches, and applications.Adv Mater Technol2021;6:2000787

[21] Yang Z,Yang M,Sheng P.Membrane-type acoustic metamaterial with negative dynamic mass.Phys Rev Lett2008;101:204301

[22] Fang N,Xu J.Ultrasonic metamaterials with negative modulus.Nat Mater2006;5:452-6

[23] Ding C,Zhao X.Two-dimensional acoustic metamaterial with negative modulus.J Appl Phys2010;108:074911

[24] Lee SH,Seo YM,Kim CK.Composite acoustic medium with simultaneously negative density and modulus.Phys Rev Lett2010;104:054301

[25] Li J.Double-negative acoustic metamaterial.Phys Rev E2004;70:055602

[26] Yu N,Kats MA.Light propagation with phase discontinuities: generalized laws of reflection and refraction.Science2011;334:333-7

[27] Assouar B,Wu Y,Cheng J.Acoustic metasurfaces.Nat Rev Mater2018;3:460-72

[28] Qi S,Assouar B.Acoustic focusing and energy confinement based on multilateral metasurfaces.Phys Rev Appl2017;7:054006

[29] Faure C,Félix S.Experiments on metasurface carpet cloaking for audible acoustics.Appl Phys Lett2016;108:064103

[30] Sounas DL,Alù A.Unidirectional cloaking based on metasurfaces with balanced loss and gain.Phys Rev Appl2015;4:014005

[31] Huang S,Wang X,Cheng Q.Acoustic perfect absorbers via spiral metasurfaces with embedded apertures.Appl Phys Lett2018;113:233501

[32] Ji J,Li Y.Low-frequency broadband acoustic metasurface absorbing panels.Front Mech Eng2020;6:586249

[33] Li Y,Xie Y.Tunable asymmetric transmission via lossy acoustic metasurfaces.Phys Rev Lett2017;119:035501

[34] Fang X,Li Y.Acoustic splitting and bending with compact coding metasurfaces.Phys Rev Appl2019;11:064033

[35] Wang P,Bertoldi K.Topological phononic crystals with one-way elastic edge waves.Phys Rev Lett2015;115:104302

[36] Torrent D,Sánchez-dehesa J.Elastic analog of graphene: dirac cones and edge states for flexural waves in thin plates.Phys Rev B2013;87:115143

[37] Lera N,San-jose P,Alvarez JV.Valley hall phases in kagome lattices.Phys Rev B2019;99:134102

[38] Chaunsali R,Yang J.Subwavelength and directional control of flexural waves in zone-folding induced topological plates.Phys Rev B2018;97:054307

[39] Lu J,Ye L.Observation of topological valley transport of sound in sonic crystals.Nat Phys2017;13:369-74

[40] Wang H,Jiang J.Band topology in classical waves: wilson-loop approach to topological numbers and fragile topology.New J Phys2019;21:093029

[41] Fukui T,Suzuki H.Chern numbers in discretized brillouin zone: efficient method of computing (spin) hall conductances.J Phys Soc Jpn2005;74:1674-7

[42] Huo SY,Huang HB.Topologically protected edge states for out-of-plane and in-plane bulk elastic waves.J Phys Condens Matter2018;30:145403

[43] He C,Ge H.Acoustic topological insulator and robust one-way sound transport.Nat Phys2016;12:1124-9

[44] Zhai Z,Jiang H.Mechanical metamaterials based on origami and kirigami.Appl Phys Rev2021;8:041319

[45] Wu W,Qian G,Xu X.Mechanical design and multifunctional applications of chiral mechanical metamaterials: a review.Mater Des2019;180:107950

[46] Zheng X,Weisgraber TH.Ultralight, ultrastiff mechanical metamaterials.Science2014;344:1373-7

[47] Ingrole A,Liang R.Design and modeling of auxetic and hybrid honeycomb structures for in-plane property enhancement.Mater Des2017;117:72-83

[48] Molesky S,Piggott AY,Vucković J.Inverse design in nanophotonics.Nat Photon2018;12:659-70

[49] Goldberg DE.Genetic algorithms and machine learning.Mach Learn1988;3:95-9

[50] Zhao Y,Gao J.Broadband diffusion metasurface based on a single anisotropic element and optimized by the simulated annealing algorithm.Sci Rep2016;6:23896 PMCID:PMC4817145

[51] Robinson J.Particle swarm optimization in electromagnetics.IEEE Trans Antennas Propag2004;52:397-407

[52] Greener JG,Moffat L.A guide to machine learning for biologists.Nat Rev Mol Cell Biol2022;23:40-55

[53] Fischer T.Deep learning with long short-term memory networks for financial market predictions.Eur J Oper Res2018;270:654-69

[54] Li W,Xiong B.Deep learning modeling strategy for material science: from natural materials to metamaterials.J Phys Mater2022;5:014003

[55] Goh GB,Vishnu A.deep learning for computational chemistry.J Comput Chem2017;38:1291-307

[56] Oishi A.Computational mechanics enhanced by deep learning.Comput Methods Appl Mech Eng2017;327:327-51

[57] Yao K,Zheng Y.Intelligent nanophotonics: merging photonics and artificial intelligence at the nanoscale.Nanophotonics2019;8:339-66 PMCID:PMC8291385

[58] Ma W,Kudyshev ZA,Cai W.Deep learning for the design of photonic structures.Nat Photonics2021;15:77-90

[59] Jiang J,Fan JA.Deep neural networks for the evaluation and design of photonic devices.Nat Rev Mater2021;6:679-700

[60] Wang N,Qu Y,Li SZ.Intelligent designs in nanophotonics: from optimization towards inverse creation.PhotoniX2021;2:22

[61] Piccinotti D,A Gregory S,Zheludev NI.Artificial intelligence for photonics and photonic materials.Rep Prog Phys2021;84:012401

[62] Chen J,Zhu S.Metamaterials: from fundamental physics to intelligent design.Interdiscip Mater2023;2:5-29

[63] Zhang Q,Barbiero M,Gu M.Artificial neural networks enabled by nanophotonics.Light Sci Appl2019;8:42 PMCID:PMC6504946

[64] Xu Y,Fu Y.Interfacing photonics with artificial intelligence: an innovative design strategy for photonic structures and devices based on artificial neural networks.Photon Res2021;9:B13552

[65] Wiecha PR,Girard C.Deep learning in nano-photonics: inverse design and beyond.Photon Res2021;9:B182200

[66] So S,Noh J,Rho J.Deep learning enabled inverse design in nanophotonics.Nanophotonics2020;9:1041-57

[67] Khatib O,Malof J.Deep learning the electromagnetic properties of metamaterials - a comprehensive review.Adv Funct Mater2021;31:2101748

[68] Jiao P.Artificial intelligence-enabled smart mechanical metamaterials: advent and future trends.Int Mater Rev2021;66:365-93

[69] Jin Y,Wen Z.Intelligent on-demand design of phononic metamaterials.Nanophotonics2022;11:439-60

[70] Muhammad, Kennedy J, Lim C. Machine learning and deep learning in phononic crystals and metamaterials - a review.Mater Today Commun2022;33:104606

[71] Liu C.Deep learning for the design of phononic crystals and elastic metamaterials.J Computat Des Eng2023;10:602-14

[72] Russell S. Artificial intelligence: a modern approach, 4th US ed. Prentice Hall 2009. Available from: http://aima.cs.berkeley.edu/index.html [Last accessed on 14 Aug 2023]

[73] Jordan MI.Machine learning: trends, perspectives, and prospects.Science2015;349:255-60

[74] Mcculloch WS.A logical calculus of the ideas immanent in nervous activity.Bull Math Biophys1943;5:115-33

[75] Rosenblatt F.The perceptron: a probabilistic model for information storage and organization in the brain.Psychol Rev1958;65:386-408

[76] Rumelhart DE,Williams RJ.Learning representations by back-propagating errors.Nature1986;323:533-6

[77] Elman J.Finding structure in time.Cogn Sci1990;14:179-211

[78] LeCun Y,Bengio Y.Gradient-based learning applied to document recognition.Proc IEEE1998;86:2278-324.

[79] Hinton GE,Teh YW.A fast learning algorithm for deep belief nets.Neural Comput2006;18:1527-54

[80] Goodfellow I,Mirza M. Generative adversarial nets. In: Ghahramani Z, Welling M, Cortes C, Lawrence ND, Weinberger KQ editors. In Proceedings of the 27th International Conference on Neural Information Processing Systems; 2014 Dec 8-13; Montreal, Canada. Cambridge: MIT Press; 2014. pp. 2672-80. Available from: https://dl.acm.org/doi/10.5555/2969033.2969125 [Last accessed on 14 Aug 2023]

[81] Mirza M. Conditional generative adversarial nets. Available from: https://arxiv.org/abs/1411.1784 [Last accessed on 14 Aug 2023]

[82] Liu D,Khoram E.Training deep neural networks for the inverse design of nanophotonic structures.ACS Photonics2018;5:1365-9

[83] Kaelbling LP,Moore AW. Reinforcement learning: a survey. J Artif Intell Res 1996;4:237-85. Available from: https://arxiv.org/abs/cs/9605103 [Last accessed on 14 Aug 2023]

[84] Silver D,Simonyan K.Mastering the game of go without human knowledge.Nature2017;550:354-9

[85] Kiran BR,Talpaert V.Deep reinforcement learning for autonomous driving: a survey.IEEE Trans Intell Transport Syst2022;23:4909-26

[86] Zhu R,Wang J.Phase-to-pattern inverse design paradigm for fast realization of functional metasurfaces via transfer learning.Nat Commun2021;12:2974 PMCID:PMC8137937

[87] Kim Y,Yang C,Gu GX.Deep learning framework for material design space exploration using active transfer learning and data augmentation.NPJ Comput Mater2021;140:7

[88] Alzubi J,Kumar A.Machine learning from theory to algorithms: an overview.J Phys Conf Ser2018;1142:012012

[89] Mahesh B. Machine learning algorithms - a review. Int J Sci Res 2020;9:381-6. Available from: https://www.ijsr.net/getabstract.php?paperid=ART20203995 [Last accessed on 9 Oct 2023]

[90] Abadi Mı,Barham P. TensorFlow: large-scale machine learning on heterogeneous distributed systems. Available from: https://arxiv.org/abs/1603.04467 [Last accessed on 14 Aug 2023]

[91] Paszke A,Massa F. PyTorch: an imperative style, high-performance deep learning library. Available from: https://arxiv.org/abs/1912.01703 [Last accessed on 14 Aug 2023]

[92] Liu CX.Predicting the dispersion relations of one-dimensional phononic crystals by neural networks.Sci Rep2019;9:15322 PMCID:PMC6814748

[93] Zhang J,Zhao T,Zuo L.Machine-learning based design of digital materials for elastic wave control.Extreme Mech Lett2021;48:101372

[94] Jiang W,Yin G,Xie L.Dispersion relation prediction and structure inverse design of elastic metamaterials via deep learning.Mater Today Phys2022;22:100616

[95] Han S,Li C.Deep-learning-based inverse design of phononic crystals for anticipated wave attenuation.J Appl Phys2022;132:154901

[96] Liu C,Zhao G.Neural networks for inverse design of phononic crystals.AIP Adv2019;9:085223

[97] Dong J,Xiao Y.Nelder-mead optimization of elastic metamaterials via machine-learning-aided surrogate modeling.Int J Appl Mech2020;12:2050011

[98] Wu L,Wang Y.A machine learning-based method to design modular metamaterials.Extreme Mech Lett2020;36:100657

[99] Li X,Liu Z,Luo C.Designing phononic crystal with anticipated band gap through a deep learning based data-driven method.Comput Methods Appl Mech Eng2020;361:112737

[100] Miao X,Wang Y.Deep learning of dispersion engineering in two-dimensional phononic crystals.Eng Optim2023;55:125-39

[101] Jin Y,Wen Z,Li Y.Deep-subwavelength lightweight metastructures for low-frequency vibration isolation.Mater Des2022;215:110499

[102] On S,Yeon Park S.Design of periodic arched structures integrating the structural nonlinearity and band gap effect for vibration isolation.Mater Des2022;224:111397

[103] Luo C,Liu Z.Interactive inverse design of layered phononic crystals based on reinforcement learning.Extreme Mech Lett2020;36:100651

[104] Wu R,Jahanshahi MR.Design of one-dimensional acoustic metamaterials using machine learning and cell concatenation.Struct Multidisc Optim2021;63:2399-423

[105] He L,Jin Y,Rabczuk T.Machine-learning-driven on-demand design of phononic beams.Sci China Phys Mech Astron2022;65:214612

[106] Donda K,Merkel A.Ultrathin acoustic absorbing metasurface based on deep learning approach.Smart Mater Struct2021;30:085003

[107] Donda K,Merkel A,Assouar B.Deep learning approach for designing acoustic absorbing metasurfaces with high degrees of freedom.Extreme Mech Lett2022;56:101879

[108] Zhang H,Zhao H,Yu D.Accelerated topological design of metaporous materials of broadband sound absorption performance by generative adversarial networks.Mater Des2021;207:109855

[109] Liu L,Huang W,Lu M.Broadband acoustic absorbing metamaterial via deep learning approach.Appl Phys Lett2022;120:251701

[110] Jin Y,Wen Z.Lightweight sound-absorbing metastructures with perforated fish-belly panels.Int J Mech Sci2022;226:107396

[111] Gu T,He L.A lightweight metastructure for simultaneous low-frequency broadband sound absorption and vibration isolation.J Acoust Soc Am2023;153:96104

[112] Mahesh K,Mini RS.Inverse design of a Helmholtz resonator based low-frequency acoustic absorber using deep neural network.J Appl Phys2021;129:174901

[113] Mahesh K,Mini RS.A deep autoencoder based approach for the inverse design of an acoustic-absorber.Eng Comput2023;

[114] Luo YT,Li DT.Probability-density-based deep learning paradigm for the fuzzy design of functional metastructures.Research2020;2020:8757403. PMCID:PMC7528036

[115] Gurbuz C,Dietz C,Schmid J.Generative adversarial networks for the design of acoustic metamaterials.J Acoust Soc Am2021;149:1162

[116] Ding H,Jia B,Cheng Q.Deep learning enables accurate sound redistribution via nonlocal metasurfaces.Phys Rev Appl2021;16:064035

[117] Du Z.Metagrating-based acoustic wavelength division multiplexing enabled by deterministic and probabilistic deep learning models.Phys Rev Res2022;4:033165

[118] Ahmed WW,Zhang X.Deterministic and probabilistic deep learning models for inverse design of broadband acoustic cloak.Phys Rev Res2021;3:013142

[119] Zhao T,Zuo L.Machine-learning optimized method for regional control of sound fields.Extreme Mech Lett2021;45:101297

[120] Chen J,Xu X,Huang G.A physics-guided machine learning for multifunctional wave control in active metabeams.Extreme Mech Lett2022;55:101827

[121] Long Y,Chen H.Unsupervised manifold clustering of topological phononics.Phys Rev Lett2020;124:185501

[122] He L,Jin Y,Zhuang X.Inverse design of topological metaplates for flexural waves with machine learning.Mater Des2021;199:109390

[123] Muhammad, Ogun O, Kennedy J. Inverse design of a topological phononic beam with interface modes.J Phys D Appl Phys2022;56:015106.

[124] Du Z,Chen H.Optimal design of topological waveguides by machine learning.Front Mater2022;9:1075073

[125] Yu LW.Unsupervised learning of non-Hermitian topological phases.Phys Rev Lett2021;126:240402

[126] Cheng Z.Supervised machine learning topological states of one-dimensional non-Hermitian systems.Chin Phys Lett2021;38:070302.

[127] Narayan B.Machine learning non-Hermitian topological phases.Phys Rev B2021;103:035413

[128] Zhang L,Huang Z,Huang W.Machine learning topological invariants of non-Hermitian systems.Phys Rev A2021;103:012419

[129] Miri MA.Exceptional points in optics and photonics.Science2019;363:eaar7709

[130] Reja MA. Characterizing exceptional points using neural networks. Available from: https://arxiv.org/abs/2305.00776 [Last accessed on 14 Aug 2023]

[131] Gu GX,Richmond DJ.Bioinspired hierarchical composite design using machine learning: simulation, additive manufacturing, and experiment.Mater Horiz2018;5:939-45

[132] Hanakata PZ,Campbell DK.Accelerated search and design of stretchable graphene kirigami using machine learning.Phys Rev Lett2018;121:255304

[133] Hanakata PZ,Campbell DK.Forward and inverse design of kirigami via supervised autoencoder.Phys Rev Res2020;2:042006

[134] Kollmann HT,Koric S,Sobh NA.Deep learning for topology optimization of 2D metamaterials.Mater Des2020;196:109098

[135] Tan RK,Ye W.A deep learning - based method for the design of microstructural materials.Struct Multidisc Optim2020;61:1417-38

[136] Garland AP,Jensen SC.Pragmatic generative optimization of novel structural lattice metamaterials with machine learning.Mater Des2021;203:109632

[137] Tian J,Chen X.Machine learning-based prediction and inverse design of 2D metamaterial structures with tunable deformation-dependent Poisson's ratio.Nanoscale2022;14:12677-91

[138] Liu F,Wang X.Machine learning-based design and optimization of curved beams for multistable structures and metamaterials.Extreme Mech Lett2020;41:101002

[139] Challapalli A,Li G.Inverse machine learning framework for optimizing lightweight metamaterials.Mater Des2021;208:109937

[140] Wang Y,Wang J,Fang D.Inverse design of shell-based mechanical metamaterial with customized loading curves based on machine learning and genetic algorithm.Comput Methods Appl Mech Eng2022;401:115571

[141] Chang Y,Dong Q.Machine learning-based inverse design of auxetic metamaterial with zero Poisson's ratio.Mater Today Commun2022;30:103186