Inverse design of nonlinear phononic crystal configurations based on multi-label classification learning neural networks

doi:10.1088/1674-1056/ad6b85

Abstract Phononic crystals, as artificial composite materials, have sparked significant interest due to their novel characteristics that emerge upon the introduction of nonlinearity. Among these properties, second-harmonic features exhibit potential applications in acoustic frequency conversion, non-reciprocal wave propagation, and non-destructive testing. Precisely manipulating the harmonic band structure presents a major challenge in the design of nonlinear phononic crystals. Traditional design approaches based on parameter adjustments to meet specific application requirements are inefficient and often yield suboptimal performance. Therefore, this paper develops a design methodology using Softmax logistic regression and multi-label classification learning to inversely design the material distribution of nonlinear phononic crystals by exploiting information from harmonic transmission spectra. The results demonstrate that the neural network-based inverse design method can effectively tailor nonlinear phononic crystals with desired functionalities. This work establishes a mapping relationship between the band structure and the material distribution within phononic crystals, providing valuable insights into the inverse design of metamaterials.

Keywords: multi-label classification learning nonlinear phononic crystals inverse design

Received: 22 June 2024
Revised: 31 July 2024
Accepted manuscript online: 06 August 2024

PACS:

43.25.+y

(Nonlinear acoustics)

Fund: Project supported by the National Key Research and Development Program of China (Grant No. 2020YFA0211400), the State Key Program of the National Natural Science of China (Grant No. 11834008), the National Natural Science Foundation of China (Grant Nos. 12174192, 12174188, and 11974176), the State Key Laboratory of Acoustics, Chinese Academy of Sciences (Grant No. SKLA202410), and the Fund from the Key Laboratory of Underwater Acoustic Environment, Chinese Academy of Sciences (Grant No. SSHJ-KFKT-1701).

Corresponding Authors: Yun Lai, Xiaozhou Liu
E-mail: laiyun@nju.edu.cn;xzliu@nju.edu.cn

Cite this article:

Kunqi Huang(黄坤琦), Yiran Lin(林懿然), Yun Lai(赖耘), and Xiaozhou Liu(刘晓宙) Inverse design of nonlinear phononic crystal configurations based on multi-label classification learning neural networks 2024 Chin. Phys. B 33 104301

[1] Ma T, Su X, Dong H, Wang Y and Zhang C 2017 Chin. J. Theor. Appl. Mech. 49 743
[2] Cabaret J, Tournat V and Béquin P 2012 Phys. Rev. E 86 041305
[3] Delph T, Herrmann G and Kaul R 1979 J. Appl. Mech. 46 113
[4] Biwa S, Nakajima S and Ohno N 2004 J. Appl. Mech. 71 508
[5] Li Z N, Wang Y Z and Wang Y S 2021 Proc. Royal Soc. A 477 20200357
[6] Ishii Y and Biwa S 2012 AIP Conf. Proc. 1474 223
[7] Ishii Y and Adachi T 2019 Dynamics and Control of Advanced Structures and Machines pp. 65-73
[8] Wang Y F, Wang Y Z, Wu B, Chen W and Wang Y S 2020 Appl. Mech. Rev. 72 040801
[9] Liu J, Guo H and Wang T 2020 Crystals 10 305
[10] Liu C X and Yu G L 2023 Journal of Computational Design and Engineering 10 602
[11] Jin Y, He L, Wen Z, Mortazavi B, Guo H, Torrent D, Djafari-Rouhani B, Rabczuk T, Zhuang X and Li Y 2022 Nanophotonics 11 439
[12] Li Y, Chen D, Li X and Wang W 2024 Journal of Vibration and Control 30 807
[13] He L, Li Y, Torrent D, Zhuang X, Rabczuk T and Jin Y 2023 Microstructures 3 2023037
[14] Cui J, Li Y, Zhao C and Zheng W 2023 Chin. Phys. B 32 096101
[15] Peurifoy J, Shen Y, Jing L, Yang Y, Cano-Renteria F, DeLacy B G, Joannopoulos J D, Tegmark M and Soljačić M 2018 Sci. Adv. 4 eaar4206
[16] Finol D, Lu Y, Mahadevan V and Srivastava A 2019 International Journal for Numerical Methods in Engineering 118 258
[17] Kollmann H T, Abueidda D W, Koric S, Guleryuz E and Sobh N A 2020 Mater. Design 196 109098
[18] Li X, Ning S, Liu Z, Yan Z, Luo C and Zhuang Z 2020 Computer Methods in Applied Mechanics and Engineering 361 112737
[19] Gurbuz C, Kronowetter F, Dietz C, Eser M, Schmid J and Marburg S 2021 J. Acoust. Soc. USA 149 1162
[20] Wei Y and He D 2023 Chin. Phys. Lett. 40 090502
[21] Ahmed W W, Farhat M, Zhang X and Wu Y 2021 Phys. Rev. Res. 3 013142
[22] Du Z and Mei J 2022 Phys. Rev. Res. 4 033165
[23] Huang K, Li Y, Lai Y and Liu X 2023 IEEE Open Journal of Ultrasonics, Ferroelectrics, and Frequency Control 3 166
[24] Zhao C, Zhang K, Zhao P and Deng Z 2022 Nonlinear Dyn. 108 743
[25] Grinberg I and Matlack K 2020 Wave Motion 93 102466
[26] Liang S, Liu J, Lai Y and Liu X 2023 Chin. Phys. B 32 044301
[27] Chen Z, Zhou W and Lim C 2020 International Journal of Nonlinear Mechanics 125 103535
[28] Wang Y Z and Wang Y S 2018 Wave Motion 78 1
[29] Manimala J M and Sun C 2016 J. Acoust. Soc. USA 139 3365
[30] Che Z G, Chiang T A and Che Z H 2011 International Journal of Innovative Computing, Information and Control 7 5839
[31] Srivastava N, Hinton G, Krizhevsky A, Sutskever I and Salakhutdinov R 2014 The Journal of Machine Learning Research 15 1929
[32] Boob D, Dey S S and Lan G 2022 Discrete Optimization 44 100620
[33] Kingma D P and Ba J 2014 arXiv preprint arXiv: 1412.6980

[1]	A graph neural network approach to the inverse design for thermal transparency with periodic interparticle system Bin Liu(刘斌) and Yixi Wang(王译浠). Chin. Phys. B, 2024, 33(8): 084401.
[2]	Inverse design-based metamaterial transparent device and its multilayer realization Li Ting-Hua (李廷华), Huang Ming (黄铭), Yang Jing-Jing (杨晶晶), Yuan Gang (袁刚), Cai Guang-Hui (蔡光卉). Chin. Phys. B, 2014, 23(5): 054102.

No Suggested Reading articles found!

Viewed

Full text

Abstract

Cited

Metrics
Related Articles

Inverse design of nonlinear phononic crystal configurations based on multi-label classification learning neural networks

Cite this article:

Online attention