Zhou Yihong, Ma Lifeng, Kang Xi, Zhu Zhiyuan
School of Mechanical and Automotive Engineering, Shanghai University of Engineering Science, Shanghai, 201620, China.
Sci Rep. 2025 Jan 14;15(1):1946. doi: 10.1038/s41598-025-86077-w.
This research presents a method based on deep learning for the reverse design of sound-absorbing structures. Traditional methods require time-consuming individual numerical simulations followed by cumbersome calculations, whereas the deep learning design method significantly simplifies the design process, achieving efficient and rapid design objectives. By utilizing deep neural networks, a mapping relationship between structural parameters and the sound absorption coefficient curve is established. The forward network predicts the sound absorption coefficient curve, while the reverse network enables the on-demand design of structural parameters for broadband high sound absorption. During the design process, a mean squared error (MSE) below 0.0001 is achieved. The accuracy of the proposed design method is validated through examples. The results demonstrate that the trained deep learning neural network could effectively replace the complex physical mechanisms between structural parameters and sound absorption coefficient curves. This deep learning design method could also be extended to other types of metamaterial reverse designs, significantly enhancing the efficiency of complex metamaterial designs. Lightweight design is crucial for energy saving and emission reduction. With the total mass and average sound absorption coefficient of sound-absorbing materials as targets, the NSGA-II algorithm has been used for multi-objective optimization design. The optimized average sound absorption coefficient increased by 4.84%, and the total material mass was reduced by 18.98%.
本研究提出了一种基于深度学习的吸声结构逆向设计方法。传统方法需要进行耗时的单个数值模拟，随后进行繁琐的计算，而深度学习设计方法显著简化了设计过程，实现了高效快速的设计目标。通过利用深度神经网络，建立了结构参数与吸声系数曲线之间的映射关系。正向网络预测吸声系数曲线，而反向网络能够按需设计用于宽带高吸声的结构参数。在设计过程中，实现了低于0.0001的均方误差（MSE）。通过实例验证了所提出设计方法的准确性。结果表明，训练后的深度学习神经网络能够有效替代结构参数与吸声系数曲线之间复杂的物理机制。这种深度学习设计方法还可扩展到其他类型的超材料逆向设计，显著提高复杂超材料设计的效率。轻量化设计对于节能减排至关重要。以吸声材料的总质量和平均吸声系数为目标，采用NSGA-II算法进行多目标优化设计。优化后的平均吸声系数提高了4.84%，材料总质量降低了18.98%。
