Abstract

Due to the complex geometry, the research for theoretical methods on wave absorption with plunger-type wavemakers is not easy. Therefore, this paper proposes a simple approach for wave absorbing control of plunger wavemakers using machine learning. The main contribution of this approach is to control plunger wavemakers to absorb waves in the time domain, and no theoretical derivation is required. The neural networks are trained to map the time-independent relationship between the wavemaker velocity and recorded wave variables (i.e. wave period, water depth, free-surface elevation along the wavemaker, velocities of the free-surface elevation along the wavemaker and position of the wavemaker). A penalty term is proposed to avoid the overfitting of neural networks. A numerical wave flume is applied to generate training data and simulate wave absorption. Taking a wedge plunger wavemaker as an example, the regular wave absorption with full reflection is tested. The simulated wave profiles and wave orbital velocities are validated with analytical solutions, showing that the proposed approach is effective at eliminating the reflected wave. A cylinder plunger wavemaker is also performed to absorb the solitary and irregular waves. The irregular wave can be absorbed stably in a long-term simulation. The solitary wave with a small height can also be absorbed well, illustrating the potential of the proposed approach in different plunger shapes and wave conditions. • This paper proposes a simple approach for wave absorbing control of plunger wavemakers using machine learning, and no complex theoretical derivation is required. • Penalty term based on wave mechanisms is introduced to prevent neural networks from overfitting. • 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. • The proposed approach is suitable for different plunger shapes and wave conditions.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call