期刊
OCEAN ENGINEERING
卷 240, 期 -, 页码 -出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.oceaneng.2021.109932
关键词
Vortex-induced vibration; Physics informed neural network; Wake-induced vibration; Fully connected neural network; Long-short term memory
资金
- Fundamental Research Fund for the Central Universities of China [B200203073]
- Practice Innovation Program of Jiangsu Province [KYCX20_0483]
This paper utilizes physics informed neural network (PINN) to solve VIV and WIV problems of cylinders, combining RANS equations and structure dynamic equations, using CFD technique for data acquisition, and validating the effectiveness of PINN method in solving VIV and WIV problems of cylinders.
Vortex-induced vibration (VIV) exists widely in natural and industrial fields. The main approaches for solving VIV problems are numerical simulations and experimental methods. However, experiment methods are difficult to obtain the whole flow field information and also high-cost while numerical simulation is extraordinary timeconsuming and limited in low Reynolds number and simple geometric configuration. In addition, numerical simulations are difficult to handle the moving mesh technique. In this paper, physics informed neural network (PINN) is utilized to solve the VIV and wake-induced vibration (WIV) of cylinder with different reduced velocities. Compared to tradition data-driven neural network, the Reynolds Average Navier-Stokes (RANS) equation, by implanting an additional turbulent eddy viscosity, coupled with structure's dynamic motion equation are also embedded into the loss function. Training and validation data is obtained by computational fluid dynamic (CFD) technique. Three scenarios are proposed to validate the performance of PINN in solving VIV and WIV of cylinders. In the first place, the stiffness parameter and damping parameter are calculated via limited force data and displacement data; secondly, the turbulence flow field and lifting force/drag force are inferred by scattered velocity information; eventually, the displacement can be directly predicted only through lifting forces and drag forces based on LSTM. Results demonstrate that, compared with traditional neural network, PINN method is more effective in inferring and re-constructing the unknown parameters and flow field with different Reynolds numbers under VIV and WIV circumstances.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据