基于基尼不纯度结构优化物理引导神经网络的薄膜型声学超材料传声损失预测

doi:10.1007/s12204-023-2655-2

摘要/Abstract

摘要： 随着机器学习的快速发展，采用神经网络进行声学超材料的性能预测正在取代以实验为基础的传统测试方法。本文提出了基于基尼不纯度的神经网络结构优化器，并研究了五种初始化算法对于模型性能及结构优化的影响。为了进一步提升模型的预测精度，实现了混合共振频率和传声损失公式的两类物理引导模型。结果表明采用灰狼算法作为初始化方法的结构优化器能够显著提升模型的预测精度。同时，混合共振频率的物理引导模型拥有最佳性能且能更好地预测边缘数据点。最后，结合敏感度分析和理论公式解释了输入参数对于传声损失的影响。

关键词: 薄膜型声学超材料, 传声损失, 固有频率, 物理引导神经网络, 结构搜索, 基尼不纯度, 灰狼优化, 初始化方法

Abstract: With the rapid development of machine learning, the prediction of the performance of acoustic metamaterials using neural networks is replacing the traditional experiment-based testing methods. In this paper, a Gini impurity-based artificial neural network structural optimizer (GIASO) is proposed to optimize the neural network structure, and the effects of five different initialization algorithms on the model performance and structure optimization are investigated. Two physically guided models with additional resonant frequencies and sound transmission loss formula are achieved to further improve the prediction accuracy of the model. The results show that GIASO utilizing the gray wolf optimizer as the initialization method can significantly improve the prediction performance of the model. Simultaneously, the physical guidance model with additional resonant frequencies has the best performance and can better predict the edge data points. Eventually, the effect of each input parameter on the sound transmission loss is explained by combining sensitivity analysis and theoretical formulation.

中图分类号:

TB53
TP18

. 基于基尼不纯度结构优化物理引导神经网络的薄膜型声学超材料传声损失预测[J]. J Shanghai Jiaotong Univ Sci, 2025, 30(3): 613-624.

Pan Xinrong, Liu Xuewen, Zhu Bo, Wang Yingyi. Physics-Guided Neural Network with Gini Impurity-Based Structural Optimizer for Prediction of Membrane-Type Acoustic Material Transmission Loss[J]. J Shanghai Jiaotong Univ Sci, 2025, 30(3): 613-624.

参考文献

[1] ABBAD A, ATALLA N, OUISSE M, et al. Numerical and experimental investigations on the acoustic performances of membraned Helmholtz resonators embedded in a porous matrix [J]. Journal of Sound and Vibration, 2019, 459: 114873.

[2] LANGFELDT F, RIECKEN J, GLEINE W, et al. A membrane-type acoustic metamaterial with adjustable acoustic properties [J]. Journal of Sound and Vibration, 2016, 373: 1-18.

[3] WANG H Z, LEI Z X, ZHANG X, et al. A review of deep learning for renewable energy forecasting [J]. Energy Conversion and Management, 2019, 198: 111799.

[4] PIETILA G, LIM T C. Intelligent systems approaches to product sound quality evaluations - A review [J]. Applied Acoustics, 2012, 73(10): 987-1002.

[5] FANG J H, XIE M, HE X Q, et al. Machine learning accelerates the materials discovery [J]. Materials Today Communications, 2022, 33: 104900.

[6] CHEN Y G, YU W J, SUN X, et al. Environment-aware communication channel quality prediction for underwater acoustic transmissions: A machine learning method [J]. Applied Acoustics, 2021, 181: 108128.

[7] MILLER A J, SOMMERFELDT S D, BLOTTER J D. Using machine learning to evaluate the fidelity of heavy equipment acoustic simulations [J]. Applied Acoustics, 2022, 187: 108513.

[8] ROBERTS P L D, JAFFE J S, TRIVEDI M M. Multiview, broadband acoustic classification of marine fish: A machine learning framework and comparative analysis [J]. IEEE Journal of Oceanic Engineering, 2011, 36(1): 90-104.

[9] GAO N S, WANG B Z, LU K, et al. Teaching-learning-based optimization of an ultra-broadband parallel sound absorber [J]. Applied Acoustics, 2021, 178: 107969.

[10] BACIGALUPO A, GNECCO G, LEPIDI M, et al. Machine-learning techniques for the optimal design of acoustic metamaterials [J]. Journal of Optimization Theory and Applications, 2020, 187(3): 630-653.

[11] GHOSH K, STUKE A, TODOROVIĆ M, et al. Deep learning spectroscopy: Neural networks for molecular excitation spectra [J]. Advanced Science, 2019, 6(9): 1801367.

[12] GAO N S, WANG M, CHENG B Z, et al. Inverse design and experimental verification of an acoustic sink based on machine learning [J]. Applied Acoustics, 2021, 180: 108153.

[13] SIMONOVIĆ M, KOVANDŽIĆ M, ĆIRIĆ I, et al. Acoustic recognition of noise-like environmental sounds by using artificial neural network [J]. Expert Systems with Applications, 2021, 184: 115484.

[14] CHENG B Z, WANG M, GAO N S, et al. Machine learning inversion design and application verification of a broadband acoustic filtering structure [J]. Applied Acoustics, 2022, 187: 108522.

[15] LÄHIVAARA T, KÄRKKÄINEN L, HUTTUNEN J M J, et al. Deep convolutional neural networks for estimating porous material parameters with ultrasound tomography [J]. The Journal of the Acoustical Society of America, 2018, 143(2): 1148-1158.

[16] NGUYEN N D, NGUYEN V T. Development of ANN structural optimization framework for data-driven prediction of local two-phase flow parameters [J]. Progress in Nuclear Energy, 2022, 146: 104176.

[17] BENARDOS P G, VOSNIAKOS G C. Optimizing feedforward artificial neural network architecture [J]. Engineering Applications of Artificial Intelligence, 2007, 20(3): 365-382.

[18] RAJAKUMAR R, SEKARAN K, HSU C H, et al. Accelerated grey wolf optimization for global optimization problems [J]. Technological Forecasting and Social Change, 2021, 169: 120824.

[19] MENG X Q, JIANG J H, WANG H. AGWO: Advanced GWO in multi-layer perception optimization [J]. Expert Systems with Applications, 2021, 173: 114676.

[20] LUO Q, RAO Y Q, PENG D. GA and GWO algorithm for the special Bin packing problem encountered in field of aircraft arrangement [J]. Applied Soft Computing, 2022, 114: 108060.

[21] XIONG J, ZHANG T Y. Data-driven glass-forming ability criterion for bulk amorphous metals with data augmentation [J]. Journal of Materials Science & Technology, 2022, 121: 99-104.

[22] PATTANAYAK S, DEY S, CHATTERJEE S, et al. Computational intelligence based designing of microalloyed pipeline steel [J]. Computational Materials Science, 2015, 104: 60-68.

[23] SHEN C G, WANG C C, WEI X L, et al. Physical metallurgy-guided machine learning and artificial intelligent design of ultrahigh-strength stainless steel [J]. Acta Materialia, 2019, 179: 201-214.

[24] LY H B, NGUYEN M H, PHAM B T. Metaheuristic optimization of Levenberg-Marquardt-based artificial neural network using particle swarm optimization for prediction of foamed concrete compressive strength [J]. Neural Computing and Applications, 2021, 33(24): 17331-17351.

[25] NYATHI T, PILLAY N. Comparison of a genetic algorithm to grammatical evolution for automated design of genetic programming classification algorithms [J]. Expert Systems with Applications, 2018, 104: 213-234.

[26] CHEN Y G, LI L X, XIAO J H, et al. Particle swarm optimizer with crossover operation [J]. Engineering Applications of Artificial Intelligence, 2018, 70: 159-169.

[27] DEMETRIOU D, MICHAILIDES C, PAPANASTASIOU G, et al. Coastal zone significant wave height prediction by supervised machine learning classification algorithms [J]. Ocean Engineering, 2021, 221: 108592.

[28] WANG D Y, SHAO F M. Research of neural network structural optimization based on information entropy [J]. Chinese Journal of Electronics, 2020, 29(4): 632-638.

[29] BREKHOVSKIKH L M, GODIN O A. Acoustics of layered media I: Plane and quasi-plane waves [M] 2nd ed. Berlin: Springer, 1998

[30] NAIFY C J, CHANG C M, MCKNIGHT G, et al. Transmission loss and dynamic response of membrane-type locally resonant acoustic metamaterials [J]. Journal of Applied Physics, 2010, 108(11): 114905.

[31] NAIFY C J, CHANG C M, MCKNIGHT G, et al. Transmission loss of membrane-type acoustic metamaterials with coaxial ring masses [J]. Journal of Applied Physics, 2011, 110(12): 124903.

[32] KINSLER L E. Fundamentals of acoustics [M]. New York: John Wiley & Sons, Inc., 2000

[33] MENG G, FANG L, YIN Y, et al. Intelligent control of the electrochemical nitrate removal basing on artificial neural network (ANN) [J]. Journal of Water Process Engineering, 2022, 49: 103122.

[34] GOLAFSHANI E M, BEHNOOD A, ARASHPOUR M. Predicting the compressive strength of normal and High-Performance Concretes using ANN and ANFIS hybridized with Grey Wolf Optimizer [J]. Construction and Building Materials, 2020, 232: 117266.

[35] GLOROT X, BENGIO Y. Understanding the difficulty of training deep feedforward neural networks [C]// 13th International Conference on Artificial Intelligence and Statistics. Chia Laguna Resort: PMLR, 2010: 249-256.

[36] HE K M, ZHANG X Y, REN S Q, et al. Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification [C]//2015 IEEE International Conference on Computer Vision. Santiago: IEEE, 2015: 1026-1034.

编辑推荐 0

Metrics

阅读次数

全文

HTML			PDF

最新录用	在线预览	正式出版	最新录用	在线预览	正式出版
0	0	0	0	0	1

	来源	本网站

	次数	1
	比例	100%

摘要

最新录用	在线预览	正式出版

0	0	43

来源	本网站	其他网站

次数	2	41
比例	5%	95%