学术文献库

High-order wave-making theories are becoming available but are limited to certain ranges of waves and wavemaker types in their applicability. Alternatively, machine learning can be considered to find nonlinear functional relationships. Therefore, this paper proposes a simple and universal framework for generating and absorbing waves based on machine learning. This framework trains neural networks to establish the transfer function between the free-surface elevation on the wavemaker and the wavemaker velocity. Significantly, penalty term and data augmentation techniques based on wave-making mechanisms are introduced to increase the generalization ability of neural networks, rather than pure data-driven. Therefore, once the target wave profiles in front of the wavemaker are given, it can realize generating waves and absorbing reflected waves at the same time. Taking piston and plunger wavemakers as examples, an in-house numerical solver is applied to simulate both wave generation and absorption. The simulated wave profiles and wave orbital velocities are validated with analytical solutions, showing that the proposed framework is effective at eliminating the re-reflection wave. Then, the validation for generating the solitary wave and the New-year wave is performed, indicating that the generated waves agree quite well with the desired wave elevation. The proposed framework can facilitate the wavemaker design in the future, and no complex theoretical derivation is required.