当前位置: X-MOL 学术Proc. Inst. Mech. Eng. Part G J. Aerosp. Eng. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Machine learning–based reduced-order modeling of hydrodynamic forces using pressure mode decomposition
Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering ( IF 1.1 ) Pub Date : 2021-03-29 , DOI: 10.1177/0954410021999864
Hassan F Ahmed 1 , Hamayun Farooq 2 , Imran Akhtar 1 , Zafar Bangash 1
Affiliation  

In this article, we introduce a machine learning–based reduced-order modeling (ML-ROM) framework through the integration of proper orthogonal decomposition (POD) and deep neural networks (DNNs), in addition to long short-term memory (LSTM) networks. The DNN is utilized to upscale POD temporal coefficients and their respective spatial modes to account for the dynamics represented by the truncated modes. In the second part of the algorithm, temporal evolution of the POD coefficients is obtained by recursively predicting their future states using an LSTM network. The proposed model (ML-ROM) is tested for flow past a circular cylinder characterized by the Navier–Stokes equations. We perform pressure mode decomposition analysis on the flow data using both POD and ML-ROM to predict hydrodynamic forces and demonstrate the accuracy of the proposed strategy for modeling lift and drag coefficients.



中文翻译:

基于机器学习的压力模式分解对水动力的降阶建模

在本文中,我们通过集成适当的正交分解(POD)和深度神经网络(DNN),以及长短期记忆(LSTM),介绍了一种基于机器学习的降阶建模(ML-ROM)框架网络。DNN用于提升POD时间系数及其各自的空间模式,以解决由截断模式表示的动态问题。在算法的第二部分中,通过使用LSTM网络递归预测POD系数的未来状态来获得POD系数的时间演化。对于通过Navier–Stokes方程表征的圆柱体的流动,测试了所提出的模型(ML-ROM)。

更新日期:2021-03-30
down
wechat
bug