A Hybrid Data-Driven Deep Learning Technique for Fluid-Structure Interaction

  title={A Hybrid Data-Driven Deep Learning Technique for Fluid-Structure Interaction},
  author={Tharindu P. Miyanawala and R. Jaiman},
  journal={Volume 2: CFD and FSI},
This paper is concerned with the development of a hybrid data-driven technique for unsteady fluid-structure interaction systems. The proposed data-driven technique combines the deep learning framework with a projection-based low-order modeling. While the deep learning provides low-dimensional approximations from datasets arising from black-box solvers, the projection-based model constructs the low-dimensional approximations by projecting the original high-dimensional model onto a low… 

Figures from this paper

A hybrid partitioned deep learning methodology for moving interface and fluid–structure interaction

Accurate prediction of the particle image velocimetry flow field and rotor thrust using deep learning

Abstract With particle image velocimetry (PIV), cross-correlation and optical flow methods have been mainly adopted to obtain the velocity field from particle images. In this study, a novel

Three-dimensional deep learning-based reduced order model for unsteady flow dynamics with variable Reynolds number

The proposed DL-ROM framework aligns with the development of a digital twin for 3D unsteady flow field and instantaneous force predictions with variable Re-based effects and an assessment of the computing requirements in terms of the memory usage, training, and testing cost of the 3D CRAN framework.

Prediction of Ultrasonic Guided Wave Propagation in Solid-fluid and their Interface under Uncertainty using Machine Learning

A procedure that uses Gaussian process regression and convolutional neural network for predicting the UGW propagation in a solid-fluid and their interface under uncertainty and results indicate that the proposed approach provides an accurate prediction for the WpFSI problem in the presence of uncertainty.

Hybrid physics-based deep learning methodology for moving interface and fluid-structure interaction

This work uses the discretized Navier-Stokes in the Arbitrary Lagrangian-Eulerian (ALE) reference frame to generate full-order flow snapshots and point-cloud displacements as target physical data for the learning and inference of coupled fluid-structure dynamics.

Hybrid deep neural network based prediction method for unsteady flows with moving boundary

A new kind of reduced order model (ROM) based on hybrid deep neural network is proposed to model flow field evolution process of unsteady flow around moving boundary which can be used in many fluid dynamics research fields, which needs fast and accurate simulation.

A Point-Cloud Deep Learning Framework for Prediction of Fluid Flow Fields on Irregular Geometries

This work presents a novel deep learning framework for flow field predictions in irregular domains when the solution is a function of the geometry of either the domain or objects inside the domain, and generalizes the predictions to multiple objects as well as an airfoil.



Model Reduction for Flow Analysis and Control

Advances in experimental techniques and the ever-increasing fidelity of numerical simulations have led to an abundance of data describing fluid flows. This review discusses a range of techniques for

An Efficient Deep Learning Technique for the Navier-Stokes Equations: Application to Unsteady Wake Flow Dynamics

The proposed CNN-based approximation procedure has a profound impact on the parametric design of bluff bodies and the feedback control of separated flows.

Deep learning in fluid dynamics

  • J. Kutz
  • Computer Science
    Journal of Fluid Mechanics
  • 2017
Although neural networks have been applied previously to complex fluid flows, the article featured here is the first to apply a true DNN architecture, specifically to Reynolds averaged Navier Stokes turbulence models, suggesting that DNNs may play a critically enabling role in the future of modelling complex flows.

Decomposition of wake dynamics in fluid–structure interaction via low-dimensional models

We present a dynamic decomposition analysis of the wake flow in fluid–structure interaction (FSI) systems under both laminar and turbulent flow conditions. Of particular interest is to provide the

Learning representations by back-propagating errors

Back-propagation repeatedly adjusts the weights of the connections in the network so as to minimize a measure of the difference between the actual output vector of the net and the desired output vector, which helps to represent important features of the task domain.