Data-driven structural design of lightweight metal-fiberglass laminates for enhanced sound insulation

Abstract

Acoustic materials and composite structural design play an important role in mitigating low-frequency noise in transportation systems. This study proposes a data-driven modeling and structural design approach for lightweight metal-fiberglass laminated structures with improved sound insulation performance. Two laminated configurations were investigated: aluminum sheet-fiberglass-aluminum sheet (AFA) and galvanized sheet-fiberglass-aluminum honeycomb panel-fiberglass-galvanized sheet (GFAFG). A piecewise regression framework was developed to predict the sound transmission loss (STL) across different frequency ranges. The model parameters were estimated using the Levenberg-Marquardt (LM) nonlinear optimization algorithm based on experimental impedance tube measurements. The resulting prediction model achieved a mean absolute error of 1.15 dB. Structural optimization of the AFA configuration resulted in a surface density of 12.36 kg/m² and a fiberglass thickness of 4.079 cm, achieving an average STL of 19.74 dB. Orthogonal experimental analysis for the GFAFG structure revealed that fiberglass layers had the most significant influence on STL performance, followed by the second fiberglass layer and the aluminum honeycomb panel. The optimal configuration (GFAFG432) achieved an average STL of approximately 40 dB. The proposed data-driven prediction framework and the GFAFG laminated structure provide an effective solution for lightweight noise reduction structures in transportation systems.

Keywords

fiberglass data-driven modeling laminated structures sound insulation prediction models

Get full access to this article

View all access options for this article.

References

Akyildiz

Sezgin

Özen

, et al. (2025) Upcycling microfiber waste from wastewater into acoustic panels: a sustainable solution for sound absorption. Environmental Research Letters 20(5): 054010. https://doi.org/10.1088/1748-9326/adc28b

Al-Areeq

Saleh

Ghaleb

, et al. (2024) Implication of novel hybrid machine learning model for flood subsidence susceptibility mapping: a representative case study in Saudi Arabia. Journal of Hydrology 630: 130692. https://doi.org/10.1016/j.jhydrol.2024.130692

Allard

Atalla

(2009) Propagation of Sound in Porous Media: Modelling Sound Absorbing Materials. 2nd edition. Hoboken, NJ: Wiley.

Bravo-Moncayo

Puyana-Romero

Argotti-Gómez

, et al. (2024) Enhanced environmental sustainability for the Acoustic absorption properties of cabuya fiber in building construction using machine learning predictive model. Sustainability 16(14): 6204. https://doi.org/10.3390/su16146204

Chen

Zhou

Mohrmann

, et al. (2022) Acoustics performance research and analysis of light timber construction wall elements based on Helmholtz metasurface. Journal of Renewable Materials 10: 2791–2803. https://doi.org/10.32604/jrm.2022.021531

Chen

Shen

, et al. (2025) Tough and soundproof PBAT/PLA composite foams with a multilayer oriented porous architecture. Composites Communications 56: 102402. https://doi.org/10.1016/j.coco.2025.102402

Doan

Kalita

(2015) Selecting machine learning algorithms using regression models 2015 IEEE International Conference on Data Mining Workshop (ICDMW). Atlantic City, NJ, USA, pp. 1498–1505.

Fahy

Gardonio

(2007) Sound and Structural Vibration: Radiation, Transmission and Response. 2nd edition. London: Academic Press.

Fink

(2017) What is a safe noise exposure level for the public? Journal of the Acoustical Society of America In: Abstract presented at Acoustics 17 Boston, Boston, MA, USA: Coustical Society of America, 141(52): 3731. https://doi.org/10.1121/1.4988188

10.

Gai

Guan

, et al. (2025) Study on acoustic properties of Helmholtz-type honeycomb sandwich acoustic metamaterials. Materials 18(7): 1600. https://doi.org/10.3390/ma18071600

11.

Xue

Liu

, et al. (2024) Preparation and sound insulation of honeycomb composite structures filled with glass fiber. Polymer Composites 45: 1649–1663. https://doi.org/10.1002/pc.27879

12.

Goldstein

Navar

Carter

(2017) Moving beyond regression techniques in cardiovascular risk prediction: applying machine learning to address analytic challenges. European Heart Journal 38: 1805–1814. https://doi.org/10.1093/eurheartj/ehw302

13.

Hahad

Kuntic

Al-Kindi

, et al. (2025) Noise and mental health: evidence, mechanisms, and consequences. Journal of Exposure Science and Environmental Epidemiology 35: 16–23. https://doi.org/10.1038/s41370-024-00642-5

14.

Khan

Sulaiman

(2025) Predictive insights into nonlinear nanofluid flow in rotating systems: a machine learning approach. Engineering with Computers 41: 179–196. https://doi.org/10.1007/s00366-024-01993-1

15.

Kim

Lee

(2025) Comprehensive review of textile waste recycling: from origins to innovations. Fibers and Polymers 26: 1449–1464. https://doi.org/10.1007/s12221-025-00892-6

16.

Chen

Dong

, et al. (2021) A review of silicon-based aerogel thermal insulation materials: performance optimization through composition and microstructure. Journal of Non-crystalline Solids 553: 120517. https://doi.org/10.1016/j.jnoncrysol.2020.120517

17.

Zhang

Wang

, et al. (2024) Artificial neural network-based sound insulation optimization design of composite floor of high-speed train. Proceedings of the Institution of Mechanical Engineers - Part C: Journal of Mechanical Engineering Science 238: 10964–10977. https://doi.org/10.1177/09544062241278790

18.

Liu

Dun

Wei

, et al. (2023) Creation of hollow silica-fiberglass soft ceramics for thermal insulation. Chemical Engineering Journal 454: 140134. https://doi.org/10.1016/j.cej.2022.140134

19.

Mallesh

Hwang

Choi

, et al. (2024) Advanced acoustic design: 3D-Printed thermoplastic folded core sandwich structures with porous materials and microperforations for enhanced sound absorption. Composite Structures 345: 118371. https://doi.org/10.1016/j.compstruct.2024.118371

20.

Nazari

Ivanova

Mishra

, et al. (2024) Effect of natural fiber and biomass on acoustic performance of 3D hybrid fabric-reinforced composite panels. Materials 17(23): 5695. https://doi.org/10.3390/ma17235695

21.

Niazi

Ashjari

Janqamsari

(2022) Ultrasound-promoted synthesis of high-porosity silica aerogels using embedded recycled PET fibers. Microporous and Mesoporous Materials 332: 111682. https://doi.org/10.1016/j.micromeso.2022.111682

22.

Paul

Ahirwar

Behera

(2024) Acoustic behavior of three-dimensional woven fabrics and their composites: role of fiber type and weave architecture. Journal of The Textile Institute 115: 2258–2271. https://doi.org/10.1080/00405000.2023.2284512

23.

Wang

, et al. (2025) Vibro-acoustic behavior of partially submerged composite sandwich plates with negative Poisson's ratio grids. Journal of Sandwich Structures and Materials 27(2): 599–624. https://doi.org/10.1177/10996362241307176

24.

Qin

Kang

Mei

, et al. (2024) Foam-filled aramid honeycomb sandwich composites with high acoustic insulation properties prepared using a unique thermal expansion molding process. Composites Communications 47: 101866. https://doi.org/10.1016/j.coco.2024.101866

25.

Săftoiu

Constantin

Nicoară

, et al. (2024) Glass fibre-reinforced composite materials used in the aeronautical transport sector: a critical circular economy point of view. Sustainability 16(11): 4632. https://doi.org/10.3390/su16114632

26.

Song

Wang

, et al. (2024) Inverse design of laminated plate-type Acoustic metamaterials for sound insulation based on deep learning. Applied Acoustics 218: 109906. https://doi.org/10.1016/j.apacoust.2024.109906

27.

Sun

Zhang

Sun

, et al. (2025) Construction of an asymmetric structure to enhance the sound absorption and mechanical properties of PUF/Polypropylene honeycomb composites. ACS Applied Polymer Materials 7: 6439–6449. https://doi.org/10.1021/acsapm.5c00859

28.

Tang

Liu

Bai

, et al. (2024) Effect of stacking order on the properties of hybrid palm sheath/polyester fiber felt-reinforced polymer composite laminates. Polymer Composites 45: 6525–6535. https://doi.org/10.1002/pc.28215

29.

Wang

Min

Tian

, et al. (2025) Empirical prediction of random incidence sound transmission loss of small-sized plates from normal incidence measurements. Journal of Building Engineering 108: 112820. https://doi.org/10.1016/j.jobe.2025.112820

30.

Wilamowski

(2010) Improved computation for levenberg-marquardt training. IEEE Transactions on Neural Networks 21: 930–937. https://doi.org/10.1109/TNN.2010.2045657

31.

Wilkinson

Potter

Gaustad

(2024) Glass waste solutions: current trends, emerging markets, and new technologies. American Ceramic Society Bulletin 103(7): 30–35.

32.

Yan

Shi

Bai

, et al. (2025) Three-layered multifunctional woven lattice truss sandwich panels with multifunction of load carrying and sound absorbing. Composite Structures 357: 118934. https://doi.org/10.1016/j.compstruct.2025.118934

33.

Zhang

, et al. (2012) Correlation between the acoustic and porous cell morphology of polyurethane foam: effect of interconnected porosity. Materials & Design 41: 319–325. https://doi.org/10.1016/j.matdes.2012.04.031

34.

Zhang

, et al. (2024) Research progress on thin-walled sound insulation metamaterial structures. Acoustics 6(2): 298–330. https://doi.org/10.3390/acoustics6020016

35.

Zhang

Yang

Cao

, et al. (2024) Design and optimization of acoustic packages using RSM coupled with range analysis. Proceedings of the Institution of Mechanical Engineers - Part D: Journal of Automobile Engineering 239: 4345–4361.

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

0.62 MB

0.00 MB