空间折叠超材料低频吸声特性优化

Optimization of the low-frequency sound absorption characteristics of spatially folded metamaterials

摘要

针对飞机发动机的低频噪声和传统飞机发动机降噪结构优化方式（人工调参）效率低下问题，首先，本文设计了一种空间折叠超材料结构，并利用有限元仿真方法和阻抗管法证实了该结构优越的低频特性；其次，基于实验与仿真数据，采用机器学习算法作为优化方法对空间折叠超材料的吸声特性进行了优化分析；最后，通过分析机器学习结果，利用并联耦合的方式快速构建了可以满足飞机发动机低频宽带降噪需求的复合宽频空间折叠超材料模型，证实了机器学习优化方法的可行性和高效性本研究可为声学超材料的吸声特性优化和发动机低频降噪设计提供新方法和新思路。

Abstract

To address the low-frequency noise of aircraft engines and the inefficiency of manual parameter tuning in traditional noise-reduction structure optimization, this paper firstly designs a spatially folded metamaterial structure and verifies its superior low -frequency characteristics by finite element simulation and the impedance tube method. Secondly, based on experimental and simulation data, machine learning algorithms are adopted as the optimization method to optimize and analyze the sound absorption characteristics of the spatially folded metamaterial. Finally, by analyzing the machine learning results, a composite broadband spatially folded metamaterial model that meets the low-frequency broadband noise reduction requirements of aircraft engines is rapidly constructed by parallel coupling. This confirms the feasibility and efficiency of the machine learning optimization method. This study can provide new methods and ideas for optimizing the sound absorption characteristics of acoustic metamaterials and for the low-frequency noise reduction design of engines.

关键词

折叠超材料 / 机器学习 / 有限元分析 / 阻抗管法 / 低频宽带 / 飞机发动机降噪

Key words

folded metamaterial / machine learning / finite element analysis / impedance tube method / low-frequency broadband / aircraft engine noise reduction

参考文献

[1] 张忠刚, 朱浩宇, 罗剑, 等. 吸声型薄膜声学超材料低频宽带吸声性能研究[J]. 应用声学, 2019, 38(5): 869-875.

[2] Chen Meng, Jiang Heng, Zhang Han, et al. Design of an acoustic superlens using single-phase metamaterials with a star-shaped lattice structure[J]. Scientific Reports, 2018, 8: 1861.

[3] Do N A G, Vergara E F, Barbosa L R, et al. Sound absorption metasurface with symmetrical coiled spaces and micro slit of variable depth[J]. Applied Acoustics, 2021, 183: 108312.

[4] 张宪旭, 刘怡然, 李丽君. 基于 Helmholtz 共振腔阵列的声学超材料研究[J]. 工程设计学报, 2020, 27(4): 441-447.

[5] 陈应航, 徐驰, 黄唯纯, 等. 基于微缝折叠空间结构的宽带吸声超材料设计[J]. 振动与冲击, 2024, 43(3): 171-178.

[6] Huang Chenyan, Yang Shu, Talukder E, et al. Research progress of noise reduction of composite structures of porous materials and acoustic metamaterials[J]. Physica Scripta, 2024, 99(5): 052004.

[7] 梁春华, 孙广华. 商用飞机发动机先进降噪技术[J]. 航空科学技术, 2011, 22(4): 48-52.

[8] 伍赛特. 民用航空发动机降噪技术研究及展望[J]. 机电产品开发与创新, 2019, 32(4): 55-57.

[9] 赵哲, 杨来侠, 吴玲玲, 等. 一种基于机器学习的零刚度隔振超材料设计及性能验证[J]. 复合材料学报, 2024, 41(5): 2599-2608.

[10] 刘文俭, 熊家军, 范亚, 等. 机器学习在超材料智能设计中的研究现状[J]. 信阳师范学院学报(自然科学版), 2021, 34(3): 501-509.

[11] Qiu Yisong, Ye Hongfei, Zhang Hongwu, et al. Machine learning-driven optimization design of hydrogel-based negative hydration expansion metamaterials[J]. Computer-Aided Design, 2024, 166: 103631.

[12] Ma Wei, Cheng Feng, Liu Yongmin. Deep-learning-enabled on-demand design of chiral metamaterials[J]. ACS Nano, 2018, 12(6): 6326-6334.

[13] Malkiel I, Mrejen M, Nagler A, et al. Plasmonic nanostructure design and characterization via Deep Learning[J]. Light: Science & Applications, 2018, 7: 60.

[14] Jiang Qiang, Jin Guofan, Cao Liangcai. When metasurface meets hologram: Principle and advances[J]. Advances in Optics and Photonics, 2019, 11(3): 518-576.

[15] Orazbayev B, Fleury R. Far-field subwavelength acoustic imaging by deep learning[J]. Physical Review X, 2020, 10(3): 031029.

[16] Robeck C, Cipolla J, Kelly A. Convolutional neural network driven design optimization of acoustic metamaterial microstructures[J]. The Journal of the Acoustical Society of America, 2019, 146 (4_Supplement): 2830.

[17] Amirkulova F, Tran T, Khatami E. Generative deep learning model for broadband acoustic metamaterial design[J]. The Journal of the Acoustical Society of America, 2021, 150(4): A209.

[18] 黄桂灶, 马同鑫, 杨泽锋, 等. 基于 GBDT 算法的弓网动态匹配特性预测模型[J]. 振动与冲击, 2024, 43(16): 26-32.

[19] 廖勇, 韩小金, 刘金林, 等. 可解释性人工智能研究进展[J/OL]. 计算机工程, 2024-10-30. https://doi.org/10.19678/j.issn.1000-3428.0069925.

[20] 曹放, 孙徐, 张钰. 基于“XGBoost-SHAP”的可解释性崩塌落石风险预测在公路工程中的应用[J]. 工程技术研究, 2024, 9(14): 1-4.

[21] 崔婷婷, 安雪莲, 孙德亮, 等. 基于 SHAP 的可解释机器学习的滑坡易发性评价模型[J]. 成都理工大学学报(自然科学版), 2025, 52(1): 153-172.

[22] 姚广春, 代阳, 马训鸣, 等. 基于传递函数法的吸声系数测试系统设计与实现[J]. 仪表技术与传感器, 2022(11): 55-59.

[23] Zhang Wengang, Zhang Runhong, Wu Chongzhi, et al. State-of-the-art review of soft computing applications in underground excavations[J]. Geoscience Frontiers, 2020, 11(4): 1095-1106.

基金资助

中央高校基本科研业务费专项(3122023PY08)