| Autor: |
Hongjian Liang, Enjin Zhao, Hao Qin, Lin Mu, Haowen Su |
| Jazyk: |
angličtina |
| Rok vydání: |
2022 |
| Předmět: |
|
| Zdroj: |
IEEE Access, Vol 10, Pp 98290-98308 (2022) |
| Druh dokumentu: |
article |
| ISSN: |
2169-3536 |
| DOI: |
10.1109/ACCESS.2022.3204968 |
| Popis: |
In order to protect structures along the offshore and off the coast, breakwaters are commonly applied to reduce the influence of waves. Flat plate breakwater is studied frequently due to its great performance near the water surface, however, traditional passive methods such as fixed and floating flat plate breakwaters usually fail to give full play of effective wave dissipation when encountering variable unknown incoming waves. Therefore, this paper develops an interdisciplinary model coupling computational fluid dynamics (CFD) and deep reinforcement learning (DRL) to study the wave dissipation of a submerged movable flat plate breakwater against regular waves. An in-house numerical wave tank (NWT) is built to simulate the fluid-structure interaction between the plate and regular waves. The fluid domain in NWT is regarded as environment while the flat plate breakwater is agent. In addition, the wave dissipation strategy is learned by the artificial neural network (ANN) through the continuous wave-plate interaction. It is excited to find that the coupling model is able to learn the control strategies automatically and exhibits good adaptability to the changes of environment. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
