Inverse engineering of micro-perforated plates for targeted acoustic characteristics

Binxia Yuan; Xiangyang Li; Tianqi You; Tianzhong Chen; Rui Zhu

doi:10.59400/sv3908

Inverse engineering of micro-perforated plates for targeted acoustic characteristics

Binxia Yuan
College of Energy and Mechanical Engineering, Shanghai University of Electric Power, Shanghai 200090, China
Xiangyang Li
College of Energy and Mechanical Engineering, Shanghai University of Electric Power, Shanghai 200090, China
Tianqi You
College of Energy and Mechanical Engineering, Shanghai University of Electric Power, Shanghai 200090, China; Wangting Power Generation Branch, Shanghai Huadian Electric Power Development Co., Ltd., Suzhou 215100, China
Tianzhong Chen
Traffic Management Department, Jiangxi Youth Vocational College, Nanchang 330045, China
Rui Zhu
College of Energy and Mechanical Engineering, Shanghai University of Electric Power, Shanghai 200090, China

Article ID: 3908

DOI: https://doi.org/10.59400/sv3908

Keywords: micro-perforated panels; multi-layer perceptron; deep learning; inverse design; acoustic performance

Abstract

The inverse design of micro-perforated panels (MPPs) for target sound absorption remains challenging due to the complex nonlinear relationship between structural parameters and acoustic performance. This study proposes a tandem neural network (TNN) framework to achieve efficient inverse design of single-layer MPPs. A forward multi-layer perceptron (MLP) is first trained to accurately predict the absorption coefficient curve from three key structural parameters: perforation diameter, panel thickness, and cavity depth. The forward model achieves superior accuracy compared to GA-SVR, GridSearch-SVR, and random forest models, with an R² of 0.999 and MAE of 0.007. Subsequently, an inverse design network is connected in series with the frozen forward network, taking a target absorption curve as input and outputting the corresponding structural parameters. The activation function of the output layer constrains the parameters within physically feasible ranges. The framework is validated by designing an MPP with a distinct absorption peak in the 300–600 Hz range. The predicted parameters (diameter 0.93 mm, thickness 0.9 mm, cavity depth 9.9 mm) yield an absorption curve that matches the target with an R² of 0.997. This work demonstrates that deep learning can effectively automate the inverse design of MPPs, offering a flexible and efficient alternative to traditional trial-and-error methods.

Published

2026-04-27

How to Cite

Yuan, B., Li, X., You, T., Chen, T., & Zhu, R. (2026). Inverse engineering of micro-perforated plates for targeted acoustic characteristics. Sound & Vibration, 6(3). https://doi.org/10.59400/sv3908

Download Citation

Issue

Vol. 60 No. 3 (2026): in progress

Section

Article

This work is licensed under a Creative Commons Attribution 4.0 International License.

References

[1]Liu X, Liu J, He J, et al. Analysis of the characteristics of noise from substations in buildings. Building Services Engineering Research and Technology. 2022; 43(1): 41–56. doi: 10.1177/01436244211035672

[2]Chu J, Liang X, Yang Z, et al. A Multi-Layer Micro-Perforated Panel Structure Based on Curled Space for Broadband Sound Absorption at Low Frequencies. Archives of Acoustics. 2023; 529–538. doi: 10.24425/aoa.2023.146813

[3]Tang YC, Cheng HD. Analysis and verification of optimization of micro-perforated panels’ sound absorption using the Taguchi method. The Journal of the Acoustical Society of America. 2025; 157(4): 3099–3111. doi: 10.1121/10.0036504

[4]Wang L, Ma XY, Chen KA, et al. Low frequency sound absorption performance of large sized active micro-perforated panel absorber in free field. Acta Physica Sinica. 2023; 72(6): 064304. doi: 10.7498/aps.72.20222151

[5]Li HM, Wu JW, Ya S, et al. Design and study of broadband sound absorbers with partition based on micro-perforated panel and Helmholtz resonator. Applied Acoustics, 2023, 205,109262

[6]Maa DY. Theory and design of microperforated panel sound-absorbing constructions. Scientia Sinica. 1975; 18(1): 55–71. Available online: https://www.sciengine.com/Math%20A0/doi/10.1360/ya1975-18-1-55

[7]Wan XH, Zhang J, Huang Y, et al. Deep learning for Dirac dispersion engineering in sonic crystals. Journal of Applied Physics. 2024; 135(24): 244303. doi: 10.1063/5.0206258

[8]Liu Y, He H, Cao Y, et al. Inverse design of TPMS piezoelectric metamaterial based on deep learning. Mechanics of Materials. 2024; 198: 105109. doi: 10.1016/j.mechmat.2024.105109

[9]Javadi S, Maghami A, Hosseini SM. A deep learning approach based on a data-driven tool for classification and prediction of thermoelastic wave’s band structures for phononic crystals. Mechanics of Advanced Materials and Structures. 2022; 29(27): 6612–6625. doi: 10.1080/15376494.2021.1983088

[10]Zhou W, Wang S, Wu Q, et al. An inverse design paradigm of multi-functional elastic metasurface via data-driven machine learning. Materials & Design. 2023; 226: 111560. doi: 10.1016/j.matdes.2022.111560

[11]Liu TW, Chan CT, Wu RT. Deep-Learning-Based Acoustic Metamaterial Design for Attenuating Structure-Borne Noise in Auditory Frequency Bands. Materials. 2023; 16(5): 1879. doi: 10.3390/ma16051879

[12]He L, Wen Z, Jin Y, et al. Inverse design of topological metaplates for flexural waves with machine learning. Materials & Design. 2021; 199: 109390. doi: 10.1016/j.matdes.2020.109390

[13]Zhang H, Liu J, Ma W, et al. Learning to inversely design acoustic metamaterials for enhanced performance. Acta Mechanica Sinica. 2023; 39(7): 722426. doi: 10.1007/s10409-023-22426-x

[14]He L, Guo H, Jin Y, et al. Machine-learning-driven on-demand design of phononic beams. Science China Physics, Mechanics & Astronomy. 2022; 65(1): 214612. doi: 10.1007/s11433-021-1787-x

[15]Zhang Z, Ye R, Zhu G, et al. Research on sound absorption performance prediction of microporous structures based on integrated learning. Materials Today Communications. 2025; 46: 112866. doi: 10.1016/j.mtcomm.2025.112866

[16]Gao N, Wang M, Cheng B, et al. Inverse design and experimental verification of an acoustic sink based on machine learning. Applied Acoustics. 2021; 180: 108153. doi: 10.1016/j.apacoust.2021.108153

[17]Mahesh K, Kumar Ranjith S, Mini RS. Inverse design of a Helmholtz resonator based low-frequency acoustic absorber using deep neural network. Journal of Applied Physics. 2021; 129(17): 174901. doi: 10.1063/5.0046582

[18]Rodriguez-Guillen D, Díez A, Andrés MV, et al. Inverse design of photonic crystal fibers for dispersion engineering using neural networks. Optics Communications. 2025; 587: 131891. doi: 10.1016/j.optcom.2025.131891

[19]Acharige D, Johlin E. Generative tandem neural network for optimization of nanophotonic color splitters. Physica Scripta. 2025; 100(4): 046006. doi: 10.1088/1402-4896/adba19

[20]Gupta A, Karahan EA, Bhat C, et al. Tandem Neural Network Based Design of Multiband Antennas. IEEE Transactions on Antennas and Propagation. 2023; 71(8): 6308–6317. doi: 10.1109/TAP.2023.3276524

[21]Yan J, Li Y, Yin G, et al. Inverse design on customised absorption of acoustic metamaterials with high degrees of freedom by deep learning. Mechanical Systems and Signal Processing. 2025; 237: 112989. doi: 10.1016/j.ymssp.2025.112989

[22]Jiang L, Cao B, Huang A, et al. Accelerated Inverse Design of Multi-Parallel Microperforated Panel Absorbers via Physics-Informed Neural Networks. Applied Sciences. 2025; 15(22): 11955. doi: 10.3390/app152211955

[23]Afzal S, Ziapour BM, Shokri A, et al. Building energy consumption prediction using multilayer perceptron neural network-assisted models; comparison of different optimization algorithms. Energy. 2023; 282: 128446. doi: 10.1016/j.energy.2023.128446

[24]He J, Chen T, Li G, et al. Embedding physics information into neural networks to enhance the accuracy of star-shaped elastic metamaterial design. Physics Letters A. 2025; 533: 130213. doi: 10.1016/j.physleta.2024.130213

[25]Yuan B, You T, Jiang H, et al. Prediction of the sound absorption performance for micro-perforated panel based on machine learning. Journal of Engineering and Applied Science. 2025; 72(1): 27. doi: 10.1186/s44147-025-00598-9

This paper introduces a universal framework for understanding the vibration responses of systems subjected to harmonic excitation. By examining a simplified cylinder-spring-damper model, the study refurbishes traditional scaling methods for the excitation frequency ratio and critical damping ratio. The findings indicate that in damped systems, the maximum amplitude of vibration does not align with the natural frequency. This observation leads to the introduction of a new scaling method for reduced frequency. This new approach aligns resonance peaks at the new reduced velocity of 1.0 across different damping ratios, providing a consistent characterization of vibration behavior. A new critical damping ratio of 0.707 is identified for an excited system as opposed to the traditional damping ratio of 1.0 for an unexcited system. Key properties such as maximum amplitude, phase lag, bandwidth, and quality factor are analyzed, demonstrating that the proposed reduced frequency and critical damping ratio effectively capture the dynamics of both damped and undamped excited systems. The findings offer significant insights for practical applications in engineering and various scientific fields.

This study makes significant contributions to the field of ultrasonic testing (UT) by offering a novel approach to the identification of artificially introduced defects within Japanese cedar wood (Cryptomeria japonica). The findings are of particular relevance for the heritage conservation and construction sectors, where non-invasive defect detection is paramount. The study establishes a robust framework for assessing the structural integrity of timber by correlating ultrasonic wave velocity reductions with defect size and distribution. Big-sized defects led to more substantial decreases in wave velocity. The study establishes a robust framework for assessing the structural integrity of historical timber by correlating ultrasonic wave velocity reductions with defect size and distribution. This framework has the potential to be applicable to diverse wood species and defect types.

The control of vehicle interior noise has become a critical metric for assessing noise, vibration, and harshness (NVH) in vehicles. During the initial phases of vehicle development, accurately predicting the impact of road noise on interior noise is essential for reducing noise levels and expediting the product development cycle. In recent years, data-driven methods based on machine learning have gained significant attention due to their robust capability in navigating complex data mapping relationships. Notably, surrogate models have demonstrated exceptional performance in this domain. Numerous researchers have integrated diverse intelligent algorithms into the study of vehicle noise, leveraging advantages such as the elimination of precise modeling requirements, extensive solution space exploration, continuous learning from data, and robust algorithmic versatility. However, in NVH engineering applications, data-driven models face inherent limitations, particularly in interpretability and stability. To address these issues, this paper introduces an improved Long Short-Term Memory (LSTM) network that combines knowledge and data. Inspired by the physical information neural network concept, this approach incorporates values calculated through empirical formulas into the neural network as constraints. Comparative assessments with traditional LSTM networks highlight the advantages of this deep learning model. By integrating empirical formulas constraints, the model not only enhances interpretability but also achieves robust generalization with fewer data samples. The proposed method is validated on a specific vehicle model, showing significant improvements in prediction accuracy and efficiency.