This study presents a new deep learning (DL) model to design topological configurations of periodic wave barriers to meet different target frequencies and site conditions. The new DL model is composed of an auto-encoder (AE) and a conditional variational AE, and 230,000 sets of data are generated for training, validating, and testing it. The designed results are in good agreement with the targets, and it only takes a few seconds to complete a design. Two barriers are designed by the proposed method for two practical examples, and the vibrations in peak frequency ranges are attenuated. The DL model makes the design of periodic wave barriers smarter and more efficient.

中文翻译：

---

二维周期波势垒拓扑设计的深度学习模型

本研究提出了一种新的深度学习 (DL) 模型来设计周期性波屏障的拓扑配置，以满足不同的目标频率和场地条件。新的 DL 模型由自动编码器 (AE) 和条件变分 AE 组成，生成 230,000 组数据用于训练、验证和测试。设计结果与目标吻合良好，仅需几秒钟即可完成设计。通过所提出的方法针对两个实例设计了两个屏障，并衰减了峰值频率范围内的振动。DL 模型使周期性波屏障的设计更加智能和高效。