Autoencoder artificial neural network for accelerated forward and inverse design of locally resonant acoustic metamaterials

被引:0
作者
Jiang, Yongfeng [1 ,2 ]
Li, Zheng [1 ,2 ]
Ren, Jianwei [1 ,2 ,3 ]
Feng, Xiangchao [4 ]
Gao, Jinling [2 ]
Shen, Cheng [1 ,2 ]
Meng, Han [1 ,2 ]
Lu, Tianjian [1 ,2 ]
机构
[1] Nanjing Univ Aeronaut & Astronaut, State Key Lab Mech & Control Aerosp Struct, Nanjing 210016, Peoples R China
[2] Nanjing Univ Aeronaut & Astronaut, MIIT Key Lab Multifunct Lightweight Mat & Struct, Nanjing 210016, Peoples R China
[3] PLA Rocket Force Univ Engn, Coll Combat Support, Xian 710025, Peoples R China
[4] China Acad Aerosp Sci & Technol Innovat, Adv Mat & Energy Ctr, Beijing 100088, Peoples R China
基金
中国国家自然科学基金;
关键词
SOUND INSULATION; BROAD-BAND; PREDICTION; PANELS;
D O I
10.1063/5.0242558
中图分类号
O59 [应用物理学];
学科分类号
摘要
The noise issues brought about by the development of the aviation and other industries have put forward an urgent demand for the design of low-frequency noise reduction structures. An autoencoder artificial neural network (ANN) is established in this paper to achieve accelerated low-cost forward and on demand design of locally resonant metamaterials simultaneously. Inspired by the framework of the autoencoder network, the proposed ANN is composed of an in series connected inverse prediction neural network and a forward prediction neural network module to avoid program errors by multisolution problems. A theoretical model is first set up in the paper to calculate the sound transmission loss (STL) of a locally resonant metamaterial plate and then validated by finite element simulation. The autoencoder ANN is subsequently trained using the dataset constructed based on the theoretical model. The accuracy of the well-trained ANN is then evaluated by making a comparison with the theoretical calculation and originally expected STL curves. The advantages of the proposed ANN over the theoretical model and numerical simulation are analyzed, and the results indicate that the proposed autoencoder ANN takes 2 and 6 orders of magnitude less time to complete the forward design than theoretical and numerical methods. The proposed ANN also demonstrates its ability in inverse design, which is hardly achieved using theoretical and numerical methods. The proposed ANN provides a new design method for accelerated forward and inverse design of noise reduction structures.
引用
收藏
页数:15
相关论文
共 41 条
  • [1] Low-Frequency Wideband Sound Absorption Properties of Composite Layer Micro-perforated Panel Absorber
    Agarwalla, D. K.
    Mohanty, A. R.
    [J]. JOURNAL OF VIBRATION ENGINEERING & TECHNOLOGIES, 2024, 12 (04) : 6251 - 6271
  • [2] Converging rainbow trapping silencers for broadband sound dissipation in a low-speed ducted flow
    Bravo, Teresa
    Maury, Cedric
    [J]. JOURNAL OF SOUND AND VIBRATION, 2024, 589
  • [3] Sound insulation performance of membrane-type acoustic metamaterial based on defect state structure
    Cai, Tong
    Huang, Shuang
    Guo, Hui
    Yuan, Tao
    Sun, Pei
    Liu, Ningning
    [J]. PHYSICA SCRIPTA, 2024, 99 (02)
  • [4] Modeling acoustic metamaterials based on reused buttons using data fitting with neural networka)
    Ciaburro, Giuseppe
    Iannace, Gino
    [J]. JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 2021, 150 (01) : 51 - 63
  • [5] Acoustic transmission loss in Hilbert fractal metamaterials
    Comandini G.
    Ouisse M.
    Ting V.P.
    Scarpa F.
    [J]. Scientific Reports, 13 (1)
  • [6] FE-LSTM: A hybrid approach to accelerate multiscale simulations of architectured materials using Recurrent Neural Networks and Finite Element Analysis
    Danoun, Aymen
    Pruliere, Etienne
    Chemisky, Yves
    [J]. COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING, 2024, 429
  • [7] Inverse design and experimental verification of an acoustic sink based on machine learning
    Gao, Nansha
    Wang, Mou
    Cheng, Baozhu
    Hou, Hong
    [J]. APPLIED ACOUSTICS, 2021, 180 (180)
  • [8] Prediction of Sound Insulation of Sandwich Partition Panels by Means of Artificial Neural Networks
    Garg, Naveen
    Dhruw, Siddharth
    Gandhi, Laghu
    [J]. ARCHIVES OF ACOUSTICS, 2017, 42 (04) : 643 - 651
  • [9] Machine-learning-driven on-demand design of phononic beams
    He, Liangshu
    Guo, Hongwei
    Jin, Yabin
    Zhuang, Xiaoying
    Rabczuk, Timon
    Li, Yan
    [J]. SCIENCE CHINA-PHYSICS MECHANICS & ASTRONOMY, 2022, 65 (01)
  • [10] The effect of exposure duration on the subjective discomfort of aircraft cabin noise
    Huang, Yu
    Jiang, Weikang
    [J]. ERGONOMICS, 2017, 60 (01) : 18 - 25