Design of one-dimensional acoustic metamaterials using machine learning and cell concatenation

Structural and Multidisciplinary Optimization - Tập 63 - Trang 2399-2423 - 2021
Rih-Teng Wu1, Ting-Wei Liu2, Mohammad R. Jahanshahi1,3, Fabio Semperlotti2
1Lyles School of Civil Engineering, Purdue University, West Lafayette, USA
2Ray W. Herrick Laboratories, School of Mechanical Engineering, Purdue University, West Lafayette, USA
3School of Electrical and Computer Engineering (Courtesy), Purdue University, West Lafayette, USA

Tóm tắt

Metamaterial systems have opened new, unexpected, and exciting paths for the design of acoustic devices that only few years ago were considered completely out of reach. However, the development of an efficient design methodology still remains challenging due to highly intensive search in the design space required by the conventional optimization-based approaches. To address this issue, this study develops two machine learning (ML)-based approaches for the design of one-dimensional periodic and non-periodic metamaterial systems. For periodic metamaterials, a reinforcement learning (RL)-based approach is proposed to design a metamaterial that can achieve user-defined frequency band gaps. This RL-based approach surpasses conventional optimization-based methods in the reduction of computation cost when a near-optimal solution is acceptable. Leveraging the capability of exploration in RL, the proposed approach does not require any training datasets generation and therefore can be deployed for online metamaterial design. For non-periodic metamaterials, a neural network (NN)-based approach capable of learning the behavior of individual material units is presented. By assembling the NN representation of individual material units, a surrogate model of the whole metamaterial is employed to determine the properties of the resulting assembly. Interestingly, the proposed approach is capable of modeling different metamaterial assemblies satisfying user-defined properties while requiring only a one-time network training procedure. Also, the NN-based approach does not need a pre-defined number of material unit cells, and it works when the physical model of the unit cell is not well understood, or the situation where only the sensor measurements of the unit cell are available. The robustness of the proposed two approaches is validated through numerical simulations and design examples.

Tài liệu tham khảo

Adil K, Jiang F, Liu S, Grigorev A, Gupta B, Rho S (2017) Training an agent for fps doom game using visual reinforcement learning and vizdoom. International Journal of Advanced Computer Science and Applications, IJACSA 8(12) Allaire G, Jouve F, Toader AM (2002) A level-set method for shape optimization. Comptes Rend Math 334(12):1125–1130 Allaire G, Jouve F, Toader AM (2004) Structural optimization using sensitivity analysis and a level-set method. J Comput Phys 194(1):363–393 Bacigalupo A, Gnecco G, Lepidi M, Gambarotta L (2019) Machine-learning techniques for the optimal design of acoustic metamaterials. J Optim Theory Appl. https://doi.org/10.1007/s10957-019-01614-8 Basheer IA, Hajmeer M (2000) Artificial neural networks: fundamentals, computing, design and application. J Microbiol Methods 43(1):3–31 Bellman R (1952) On the theory of dynamic programming. Proc Natl Acad Sci 38(8):716–719. https://doi.org/10.1073/pnas.38.8.716 Bendsøe MP (1989) Optimal shape design as a material distribution problem. Struct Optim 1 (4):193–202 Bendsøe MP, Sigmund O (1999) Material interpolation schemes in topology optimization. Arch Appl Mech 69(9–10):635–654 Bilal OR, Hussein MI (2011) Ultrawide phononic band gap for combined in-plane and out-of-plane waves. Phys Rev E 84(6):065701 Byrd RH, Hribar ME, Nocedal J (1999) An interior point algorithm for large-scale nonlinear programming. SIAM J Optim 9(4):877–900 Chen H, Chan C (2007) Acoustic cloaking in three dimensions using acoustic metamaterials. Appl Phys Lett 183(18):518 Chirită S, Quintanilla R (1996) On saint-venant’s principle in linear elastodynamics. J Elast 42(3):201–215 Cummer SA, Schurig D (2007) One path to acoustic cloaking. New J Phys 9(3):45 Dong HW, Su XX, Wang YS, Zhang C (2014) Topological optimization of two-dimensional phononic crystals based on the finite element method and genetic algorithm. Struct Multidiscip Optim 50(4):593–604 Dong HW, Zhao SD, Wang YS, Zhang C (2017) Topology optimization of anisotropic broadband double-negative elastic metamaterials. J Mech Phys Solids 105:54–80 Du Z, Chen H, Huang G (2020) Optimal quantum valley hall insulators by rationally engineering berry curvature and band structure. J Mech Phys Solids 135(103):784 Feurtado PA, Conlon SC, Semperlotti F (2014) A normalized wave number variation parameter for acoustic black hole design. J Acoust Soc Am 136(2):EL148–EL152 Gazonas GA, Weile DS, Wildman R, Mohan A (2006) Genetic algorithm optimization of phononic bandgap structures. Int J Solids Struct 43(18–19):5851–5866 Gosavi A (2015) Simulation-based optimization: parametric optimization techniques and reinforcement learning. Springer, New York He C, Ni X, Ge H, Sun XC, Chen YB, Lu MH, Liu XP, Chen YF (2016) Acoustic topological insulator and robust one-way sound transport. Nat Phys 12(12):1124 Huang X, Xie Y (2008) Optimal design of periodic structures using evolutionary topology optimization. Struct Multidiscip Optim 36(6):597–606 Huang X, Xie YM (2009) Bi-directional evolutionary topology optimization of continuum structures with one or multiple materials. Comput Mech 43(3):393 Huang H, Sun C, Huang G (2009) On the negative effective mass density in acoustic metamaterials. Int J Eng Sci 47(4):610–617 Hussein MI, Hamza K, Hulbert GM, Saitou K (2007) Optimal synthesis of 2d phononic crystals for broadband frequency isolation. Waves Random Complex Media 17(4):491–510 Jensen JS, Sigmund O (2003) Phononic band gap structures as optimal designs. In: IUTAM symposium on asymptotics, singularities and homogenisation in problems of mechanics. Springer, pp 73–83 Jin R, Chen W, Simpson TW (2001) Comparative studies of metamodelling techniques under multiple modelling criteria. Struct Multidiscip Optim 23(1):1–13 Kittel C, McEuen P, McEuen P (1996) Introduction to solid state physics, vol 8. Wiley, New York Lample G, Chaplot DS (2018) Playing fps games with deep reinforcement learning. arXiv:1609.05521v2 LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324 Lei X, Liu C, Du Z, Zhang W, Guo X (2019) Machine learning-driven real-time topology optimization under moving morphable component-based framework. J Appl Mech 86(1):011004 Li D, Zigoneanu L, Popa BI, Cummer SA (2012) Design of an acoustic metamaterial lens using genetic algorithms. J Acoust Soc Am 132(4):2823–2833 Li X, Ning S, Liu Z, Yan Z, Luo C, Zhuang Z (2020) Designing phononic crystal with anticipated band gap through a deep learning based data-driven method. Comput Methods Appl Mech Eng 361 (112):737. https://doi.org/10.1016/j.cma.2019.112737 Lin SCS, Huang TJ, Sun JH, Wu TT (2009) Gradient-index phononic crystals. Phys Rev B 79(9):094302 Lin CM, Hsu JC, Senesky DG, Pisano AP (2014) Anchor loss reduction in aln lamb wave resonators using phononic crystal strip tethers. In: 2014 IEEE international frequency control symposium (FCS). IEEE, pp 1–5 Liu TW, Semperlotti F (2019) Experimental evidence of robust acoustic valley hall edge states in a nonresonant topological elastic waveguide. Phys Rev Appl 014(1):040 Liu L, Yan J, Cheng G (2008) Optimum structure with homogeneous optimum truss-like material. Comput Struct 86(13–14):1417–1425 Liu TW, Lin YC, Tsai YC, Ono T, Tanaka S, Wu TT (2014a) Evidence of a love wave bandgap in a quartz substrate coated with a phononic thin layer. Appl Phys Lett 181(18):905 Liu TW, Tsai YC, Lin YC, Ono T, Tanaka S, Wu TT (2014b) Design and fabrication of a phononic-crystal-based love wave resonator in ghz range. AIP Adv 4(12):124201 Liu ZF, Wu B, He CF (2014c) Band-gap optimization of two-dimensional phononic crystals based on genetic algorithm and fpwe. Waves Random Complex Media 24(3):286–305 Ma W, Cheng F, Liu Y (2018) Deep-learning-enabled on-demand design of chiral metamaterials. ACS Nano 12(6):6326–6334. https://doi.org/10.1021/acsnano.8b03569. PMID: 29856595 Ma W, Cheng F, Xu Y, Wen Q, Liu Y (2019) Probabilistic representation and inverse design of metamaterials based on a deep generative model with semi-supervised learning strategy. Adv Mater 31 (35):1901111. https://doi.org/10.1002/adma.201901111 Masri SF, Nakamura M, Chassiakos AG, Caughey TK (1996) Neural network approach to detection of changes in structural parameters. J Eng Mech 122(4):350–360. https://doi.org/10.1061/(ASCE)0733-9399(1996)122:4(350) Masri SF, Smyth AW, Chassiakos AG, Caughey TK, Hunter NF (2000a) Application of neural networks for detection of changes in nonlinear systems. J Eng Mech 126(7):666–676 Masri SF, Smyth AW, Chassiakos AG, Caughey TK, Hunter NF (2000b) Application of neural networks for detection of changes in nonlinear systems. J Eng Mech 126(7):666–676. https://doi.org/10.1061/(ASCE)0733-9399(2000)126:7(666) Meirovitch L (1967) Analytical methods in vibrations. Macmillan series in advanced mathematics and theoretical physics. Macmillan Meng H, Wen J, Zhao H, Wen X (2012) Optimization of locally resonant acoustic metamaterials on underwater sound absorption characteristics. J Sound Vibr 331(20):4406–4416 Mousavi SH, Khanikaev AB, Wang Z (2015) Topologically protected elastic waves in phononic metamaterials. Nature Commun 6:8682 Oh JH, Ahn YK, Kim YY (2015) Maximization of operating frequency ranges of hyperbolic elastic metamaterials by topology optimization. Struct Multidiscip Optim 52(6):1023–1040 Ong YS, Nair PB, Keane AJ (2003) Evolutionary optimization of computationally expensive problems via surrogate modeling. AIAA J 41(4):687–696 Oudich M, Senesi M, Assouar MB, Ruzenne M, Sun JH, Vincent B, Hou Z, Wu TT (2011) Experimental evidence of locally resonant sonic band gap in two-dimensional phononic stubbed plates. Phys Rev B 84(16):165136 Park JH, Ma PS, Kim YY (2015) Design of phononic crystals for self-collimation of elastic waves using topology optimization method. Struct Multidiscip Optim 51(6):1199–1209 Pei JS, Mai EC, Wright JP, Smyth AW (2007) Neural network initialization with prototypes—function approximation in engineering mechanics applications. In: Proceedings of international joint conference on neural networks Pei JS, Wright JP, Masri SF, Mai EC, Smyth AW (2011) Toward constructive methods for sigmoidal neural networks—function approximation in engineering mechanics applications. In: Proceedings of international joint conference on neural networks Popa BI, Zigoneanu L, Cummer SA (2011) Experimental acoustic ground cloak in air. Phys Rev Lett 106(25):253901 Rupp CJ, Evgrafov A, Maute K, Dunn ML (2007) Design of phononic materials/structures for surface wave devices using topology optimization. Struct Multidiscip Optim 34(2):111–121 Sigmund O, Søndergaard Jensen J (2003) Systematic design of phononic band–gap materials and structures by topology optimization. Philos Trans R Soc Lond Ser A: Math Phys Eng Sci 361(1806):1001–1019 Sukhovich A, Merheb B, Muralidharan K, Vasseur J, Pennec Y, Deymier PA, Page J (2009) Experimental and theoretical evidence for subwavelength imaging in phononic crystals. Phys Rev Lett 154(15):301 Tan KT, Huang H, Sun C (2012) Optimizing the band gap of effective mass negativity in acoustic metamaterials. Appl Phys Lett 101(24):241902 Tan RK, Zhang NL, Ye W (2020) A deep learning–based method for the design of microstructural materials. Struct Multidiscip Optim 61:1417–1438 Valenti A, van Nieuwenburg E, Huber S, Greplova E (2019) Hamiltonian learning for quantum error correction. Phys Rev Res 1(3):033092 van Hasselt H, Guez A, Silver D (2015) Deep reinforcement learning with double q-learning. arXiv:1509.06461v3 Vasseur J, Deymier PA, Chenni B, Djafari-Rouhani B, Dobrzynski L, Prevost D (2001) Experimental and theoretical evidence for the existence of absolute acoustic band gaps in two-dimensional solid phononic crystals. Phys Rev Lett 86(14):3012 Wang MY, Wang X, Guo D (2003) A level set method for structural topology optimization. Comput Methods Appl Mech Eng 192(1–2):227–246 Wang Y, Luo Z, Zhang N, Kang Z (2014) Topological shape optimization of microstructural metamaterials using a level set method. Comput Mater Sci 87:178–186 Wang P, Lu L, Bertoldi K (2015) Topological phononic crystals with one-way elastic edge waves. Phys Rev Lett 115(10):104302 Wang Z, Schaul T, Hessel M, van Hasselt H, Lanctot M, de Freitas N (2016) Dueling network architectures for deep reinforcement learning. arXiv:1511.06581v3 White DA, Arrighi WJ, Kudo J, Watts SE (2019) Multiscale topology optimization using neural network surrogate models. Comput Methods Appl Mech Eng 346:1118–1135. https://doi.org/10.1016/j.cma.2018.09.007 Wormser M, Wein F, Stingl M, Körner C (2017) Design and additive manufacturing of 3d phononic band gap structures based on gradient based optimization. Materials 10(10):1125 Wu TT, Wu LC, Huang ZG (2005) Frequency band-gap measurement of two-dimensional air/silicon phononic crystals using layered slanted finger interdigital transducers. J Appl Phys 97(9): 094916 Wu TT, Chen YT, Sun JH, Lin SCS, Huang TJ (2011) Focusing of the lowest antisymmetric lamb wave in a gradient-index phononic crystal plate. Appl Phys Lett 171(17):911 Xie YM, Steven GP (1993) A simple evolutionary procedure for structural optimization. Comput Struct 49(5):885–896 Xie Y, Wang W, Chen H, Konneker A, Popa BI, Cummer SA (2014) Wavefront modulation and subwavelength diffractive acoustics with an acoustic metasurface. Nat Commun 5: 5553 Yi G, Youn BD (2016) A comprehensive survey on topology optimization of phononic crystals. Struct Multidiscip Optim 54(5):1315–1344 Zhang X, Liu Z (2004) Negative refraction of acoustic waves in two-dimensional phononic crystals. Appl Phys Lett 85(2):341–343 Zhang W, Yuan J, Zhang J, Guo X (2016) A new topology optimization approach based on moving morphable components (mmc) and the ersatz material model. Struct Multidiscip Optim 53(6):1243–1260 Zhao L, Semperlotti F (2017) Embedded acoustic black holes for semi-passive broadband vibration attenuation in thin-walled structures. J Sound Vibr 388:42–52. https://doi.org/10.1016/j.jsv.2016.10.029 Zhao L, Conlon SC, Semperlotti F (2014) Broadband energy harvesting using acoustic black hole structural tailoring. Smart Mater Struct 23(6):065021 Zhu H, Semperlotti F (2016) Anomalous refraction of acoustic guided waves in solids with geometrically tapered metasurfaces. Phys Rev Lett 117(3):034302 Zhu H, Semperlotti F (2017) Double-zero-index structural phononic waveguides. Phys Rev Appl 8(6):064031 Zhu Y, Mottaghi R, Kolve E, Lim JJ, Gupta A, Fei-Fei L, Farhadi A (2016) Target-driven visual navigation in indoor scenes using deep reinforcement learning. arXiv:1609.05143v1