Inverse design of topological metaplates for flexural waves with machine learning

He, Liangshu; Wen, Zhihui; Jin, Yabin; Torrent, Daniel; Zhuang, Xiaoying; Rabczuk, Timon

doi:10.1016/j.matdes.2020.109390

Cited by 53 publications

(13 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This allows them to realize on‐demand wide and tunable BGs. Much more recently machine learning based designs have also found their way for the realization of topological edge states [ 470 ] through a recent effort that illustrated that these could be used to judiciously tailor the bandgap for flexural waves in plates.…”

Section: Bg Engineering Through Inverse Designmentioning

confidence: 99%

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

Oudich

Gerard

Deng

et al. 2022

Adv Funct Materials

View full text Add to dashboard Cite

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

show abstract

Section: Bg Engineering Through Inverse Designmentioning

confidence: 99%

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

Oudich

Gerard

Deng

et al. 2022

Adv Funct Materials

View full text Add to dashboard Cite

show abstract

“…Distinguished from traditionally civil-reinforced structures [ 4 , 5 , 6 , 7 ], EMMs offer a new promising solution for wave protection engineering based on refraction, reflection, and artificial modulation of elastic waves [ 8 ]. More impressively, driven by burgeoning new needs, EMMs are flourishing with their unique physical properties in areas such as programmable robotics [ 9 ], lensing and super-resolution imaging [ 10 , 11 , 12 , 13 ], stealth [ 14 , 15 , 16 , 17 , 18 , 19 ], non-reciprocal wave control [ 20 , 21 ], and topological insulators [ 22 , 23 , 24 , 25 , 26 , 27 , 28 ]. Undoubtedly, new discoveries in the field of metamaterial physics are inspiring people to design even more magical metamaterial barriers (MMBs) to accomplish better seismic resistance or vibration isolation.…”

Section: Introductionmentioning

confidence: 99%

Unlocking Novel Ultralow-Frequency Band Gap: Assembled Cellular Metabarrier for Broadband Wave Isolation

et al. 2022

View full text Add to dashboard Cite

Admittedly, the design requirements of compactness, low frequency, and broadband seem to constitute an impossible trinity, hindering the further development of elastic metamaterials (EMMs) in wave shielding engineering. To break through these constraints, we propose theoretical combinations of effective parameters for wave isolation based on the propagation properties of Lamb waves in the EMM layer. Accordingly, we design compact EMMs with a novel ultralow−frequency bandgap, and the role of auxeticity in the dissociation between the dipole mode and the toroidal dipole mode is clearly revealed. Finally, under the guidance of the improved gradient design, we integrate multiple bandgaps to assemble metamaterial barriers (MMBs) for broadband wave isolation. In particular, the original configuration is further optimized and its ultralow−frequency and broadband performance are proven by transmission tests. It is foreseeable that our work will provide a meaningful reference for the application of the new EMMs in disaster prevention and protection engineering.

show abstract

“…It is worth noting that machine learning techniques have been recently used for the classification of topological insulators (Long et al, 2020), prediction of topological transitions (Wu et al, 2020), summarization of the phase diagram of disordered higher-order topological insulators (Araki et al, 2019), and inverse design of photonic topological insulators (Long et al, 2019). Additionally, topological metaplates for flexural waves and phononic beams with nontrivial topological properties have been obtained by machine learning (He et al, 2021;He et al, 2022b). And a recent review of the intelligent on-demand design of phononic metamaterials is available (Jin et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

Optimal design of topological waveguides by machine learning

Chen

Liu

et al. 2022

Front. Mater.

View full text Add to dashboard Cite

Topological insulators supply robust edge states and can be used to compose novel waveguides to protect energy propagation against various defects. For practical applications, topological waveguides with a large working bandwidth and highly localized interface mode are desired. In the present work, mechanical valley Hall insulators are described by explicit geometry parameters using the moving morphable component method first. From the geometry parameters, artificial neural networks (ANN) are then well-trained to predict the topological property and the bounds of nontrivial bandgaps. Incorporating those ANN models, mathematical formulation for designing optimal mechanical topological waveguides can be solved efficiently, with an acceleration of more than 10,000 times than the traditional topology optimization approach.

show abstract

Inverse design of topological metaplates for flexural waves with machine learning

Cited by 53 publications

References 36 publications

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

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

Unlocking Novel Ultralow-Frequency Band Gap: Assembled Cellular Metabarrier for Broadband Wave Isolation

Optimal design of topological waveguides by machine learning

Contact Info

Product

Resources

About