arXiv subjects

Yanfang Lyu

Publications and source records attributed to Yanfang Lyu.

2 recordsLinked to original sources

arXiv2025

A novel hybrid neural network of fluid-structure interaction prediction for two cylinders in tandem arrangement

Deep learning has shown promise in improving computing efficiency while ensuring modeling accuracy in fluid-structure interaction (FSI) analysis. However, its current capabilities are limited when it comes to constructing multi-object coupling systems with dynamic boundaries. To address such limitation, a novel FSI neural solver integrated by a fluid deep learning model with multi-time steps and a structural dynamic solver is proposed to accurately and reliably predict the vortex-induced vibration (VIV) evolution for two cylinders in tandem. This well-designed model in the form of end-to-end can precisely predict the instantaneous flow field state at the subsequent time by coupling the temporal flow fields of historical multi-time sequences and the current structural responses, moreover, derives the structural state at the next time. Furthermore, the novel fluid deep learning model consists of a wall shear model utilizing a multilayer perception network and flow field model with U-shaped architecture jointing the Fourier neural operator and modified convolution long-short term memory model. Both models effectively capture coupling transfer forces and predict instantaneous flow fields, with the latter demonstrating superior accuracy compared to Convolutional Neural Network- or Unet- based models with similar parameters. The prediction speed of the proposed models realizes an improvement of over 1000 times compared with the numerical simulation. Significantly, the proposed FSI neural model demonstrates exceptional capability in constructing the nonlinear complex multi- vibration systems and has substantial potential for advancing FSI modeling of flexible structures featuring pronounced nonlinear deformation boundaries.

physics.flu-dyn↗

arXiv2023

Multi-fidelity prediction of fluid flow and temperature field based on transfer learning using Fourier Neural Operator

Data-driven prediction of fluid flow and temperature distribution in marine and aerospace engineering has received extensive research and demonstrated its potential in real-time prediction recently. However, usually large amounts of high-fidelity data are required to describe and accurately predict the complex physical information, while in reality, only limited high-fidelity data is available due to the high experiment/computational cost. Therefore, this work proposes a novel multi-fidelity learning method based on the Fourier Neural Operator by jointing abundant low-fidelity data and limited high-fidelity data under transfer learning paradigm. First, as a resolution-invariant operator, the Fourier Neural Operator is first and gainfully applied to integrate multi-fidelity data directly, which can utilize the scarce high-fidelity data and abundant low-fidelity data simultaneously. Then, the transfer learning framework is developed for the current task by extracting the rich low-fidelity data knowledge to assist high-fidelity modeling training, to further improve data-driven prediction accuracy. Finally, three typical fluid and temperature prediction problems are chosen to validate the accuracy of the proposed multi-fidelity model. The results demonstrate that our proposed method has high effectiveness when compared with other high-fidelity models, and has the high modeling accuracy of 99% for all the selected physical field problems. Significantly, the proposed multi-fidelity learning method has the potential of a simple structure with high precision, which can provide a reference for the construction of the subsequent model.

physics.flu-dyn↗