Research on data-driven topology optimization method for microstructures of acoustic-structure interaction system

XU Jiongyang1, YU Qiuzi1, ZHANG Jialong1, CAO Xiaolong2, CHEN Haibo1

Journal of Vibration and Shock ›› 2025, Vol. 44 ›› Issue (8) : 133-142.

PDF(1754 KB)
PDF(1754 KB)
Journal of Vibration and Shock ›› 2025, Vol. 44 ›› Issue (8) : 133-142.
VIBRATION THEORY AND INTERDISCIPLINARY RESEARCH

Research on data-driven topology optimization method for microstructures of acoustic-structure interaction system

  • XU Jiongyang1,YU Qiuzi1,ZHANG Jialong1,CAO Xiaolong2,CHEN Haibo*1
Author information +
History +

Abstract

Traditional microstructural topology optimization for acoustic-structure interaction system relies on numerical methods such as the finite element method and boundary element method, which has the problems of high computational cost and long time consumption. In this paper, a data-driven topology optimization method for the microstructures of acoustic-structure interaction system iwas proposed to overcome the problems. In this method, the density distribution of microstructures is was used as the feature, and the system response and sensitivity values are were used as labels to construct a dataset to train the artificial neural network,  respectively, and the nonlinear mapping relationships between the distribution of microstructures and the response and /sensitivity values are were established. The response and sensitivity calculation part are were replaced by neural network prediction in the optimization process, so as to reduce the computational cost. Numerical tests indicate that the proposed method can significantly improve the computational efficiency while ensuring computational accuracy. At the same time, the proposed method has good generalization ability and can quickly converge to optimization configurations for different initial structures. This work is significant in searching for the global topology optimization design of the microstructures in acoustic-structure interaction system. 

Key words

acoustic-structure interaction system / topology optimization / microstructure / data-driven / neural network

Cite this article

Download Citations
XU Jiongyang1, YU Qiuzi1, ZHANG Jialong1, CAO Xiaolong2, CHEN Haibo1. Research on data-driven topology optimization method for microstructures of acoustic-structure interaction system[J]. Journal of Vibration and Shock, 2025, 44(8): 133-142

References

[1] MARBURG S. Developments in structural-acoustic optimization for passive noise control [J]. Archives of Computational Methods in Engineering, 2002, 9(4): 291-370.
[2] DU J, OLHOFF N. Minimization of sound radiation from vibrating bi-material structures using topology optimization [J]. Structural and Multidisciplinary Optimization, 2007, 33(4-5): 305-321.
[3] XIA Q, SHI T, WANG M Y. A level set based shape and topology optimization method for maximizing the simple or repeated first eigenvalue of structure vibration [J]. Structural and Multidisciplinary Optimization, 2010, 43(4): 473-485.
[4] YANG R, DU J. Microstructural topology optimization with respect to sound power radiation [J]. Structural and Multidisciplinary Optimization, 2012, 47(2): 191-206.
[5] CHEN N, YU D, XIA B, et al. Microstructural topology optimization of structural-acoustic coupled systems for minimizing sound pressure level [J]. Structural and Multidisciplinary Optimization, 2017, 56(6): 1259-1270.
[6] BENDSøE M P, KIKUCHI N. Generating optimal topologies in structural design using a homogenization method [J]. Computer Methods in Applied Mechanics and Engineering, 1988, 71(2): 197-224.
[7] ZUO W, SAITOU K. Multi-material topology optimization using ordered SIMP interpolation[J]. Structural and Multidisciplinary Optimization, 2017, 55: 477-491.
[8] PEREIRA R L, LOPES H N, PAVANELLO R. Topology optimization of acoustic systems with a multiconstrained BESO approach[J]. Finite Elements in Analysis and Design, 2022, 201: 103701.
[9] ZHANG W, LI D, YUAN J, et al. A new three-dimensional topology optimization method based on moving morphable components (MMCs)[J]. Computational Mechanics, 2017, 59: 647-665.
[10] YAMADA T, IZUI K, NISHIWAKI S, et al. A topology optimization method based on the level set method incorporating a fictitious interface energy[J]. Computer Methods in Applied Mechanics and Engineering, 2010, 199(45-48): 2876-2891.
[11] LIU H, WANG Y, ZONG H, et al. Efficient structure topology optimization by using the multiscale finite element method [J]. Structural and Multidisciplinary Optimization, 2018, 58(4): 1411-1430.
[12] GROEN J P, LANGELAAR M, SIGMUND O, et al. Higher-order multi-resolution topology optimization using the finite cell method [J]. International Journal for Numerical Methods in Engineering, 2016, 110(10): 903-920.
[13] XIA Z, WANG Y, WANG Q, et al. GPU parallel strategy for parameterized LSM-based topology optimization using isogeometric analysis [J]. Structural and Multidisciplinary Optimization, 2017, 56(2): 413-434.
[14] AAGE N, ANDREASSEN E, LAZAROV B S. Topology optimization using PETSc: An easy-to-use, fully parallel, open source topology optimization framework [J]. Structural and Multidisciplinary Optimization, 2014, 51(3): 565-572
[15] LEE S, KIM Y, KAHNG H, et al. Intelligent traffic control for autonomous vehicle systems based on machine learning[J]. Expert Systems with Applications, 2020, 144: 113074.
[16] NAZARETH N, RAMANA REDDY Y V. Financial applications of machine learning: A literature review [J]. Expert Systems with Applications, 2023, 219: 119640.
[17] WU X, LI J. Deep learning-based siltation image recognition of water conveyance tunnels using underwater robot [J]. Journal of Civil Structural Health Monitoring, 2024, 14(3): 801-816.
[18] 陈小前, 张泽雨, 李昱, 等. 深度学习赋能结构拓扑优化设计方法研究 [J]. 力学进展, 2024, 54(2): 213-258.
CHEN Xiao-qian, ZHANG Ze-yu, LI Yu, et al. Research on structure topology optimization design empowered by deep learning method. Advances in Mechanics, 2024, 54(2): 213-258.
[19] TAN R K, ZHANG N L, YE W. A deep learning–based method for the design of microstructural materials [J]. Structural and Multidisciplinary Optimization, 2019, 61(4): 1417-1438.
[20] WANG L, CHAN Y C, AHMED F, et al. Deep generative modeling for mechanistic-based learning and design of metamaterial systems[J]. Computer Methods in Applied Mechanics and Engineering, 2020, 372: 113377.
[21] 朱赫鹏, 丁喆, 张严, 等. 基于生成对抗网络的跨分辨率拓扑优化方法的比较研究 [J]. 振动与冲击, 2024, 43(6): 132-140.
ZHU He-peng, DING Zhe, ZHANG Yan, et al. Comparative study on cross-resolution topology optimization methods based on generative adversarial networks[J]. Journal of Vibration and Shock, 2024, 43(6): 132-140.
[22] QIAN C, YE W. Accelerating gradient-based topology optimization design with dual-model artificial neural networks [J]. Structural and Multidisciplinary Optimization, 2020, 63(4): 1687-1707.
[23] RANJBAR M, MARBURG S. Fast Vibroacoustic Optimization of Mechanical Structures Using Artificial Neural Networks [J]. International Journal of Mechanical Engineering and Applications, 2013, 1(3): 64-68.
[24] 许磊, 张维声, 朱宝, 等. 数据驱动下的声学器件音质优化 [J]. 应用数学和力学, 2024, 45(3): 253-260.
XU Lei, ZHANG Wei-sheng, ZHU Bao, et al. Data-Driven Sound Quality Optimization of Acoustic Devices[J]. Applied Mathematics and Mechanics, 2024, 45(3): 253-260.
[25] 赵文畅.基于快速多极边界元的声学及声振拓扑优化设计[D].中国科学技术大学,2019.
[26] BURTON A J, MILLER G F. The application of integral equation methods to the numerical solution of some exterior boundary-value problems[J]. Proceedings of the Royal Society of London. A. Mathematical and Physical Sciences, 1971, 323(1553): 201-210.
[27] 杜建镔. 结构优化及其在振动和声学设计中的应用 [M]. 北京: 清华大学出版社, 2015.
[28] ZHAO W, CHEN L, CHEN H, et al. Topology optimization of exterior acoustic-structure interaction systems using the coupled FEM-BEM method [J]. International Journal for Numerical Methods in Engineering, 2019, 119(5): 404-431.
[29] 周志华. 机器学习 [M]. 北京: 清华大学出版社, 2016.
[30] LIANG X, DU J. Concurrent multi-scale and multi-material topological optimization of vibro-acoustic structures [J]. Computer Methods in Applied Mechanics and Engineering, 2019, 349: 117-48. 
PDF(1754 KB)

Accesses

Citation

Detail

Sections
Recommended

/