DeepAI AI Chat
Log In Sign Up

Partitioned Deep Learning of Fluid-Structure Interaction

by   Amin Totounferoush, et al.

We present a partitioned neural network-based framework for learning of fluid-structure interaction (FSI) problems. We decompose the simulation domain into two smaller sub-domains, i.e., fluid and solid domains, and incorporate an independent neural network for each. A library is used to couple the two networks which takes care of boundary data communication, data mapping and equation coupling. Simulation data are used for training of the both neural networks. We use a combination of convolutional and recurrent neural networks (CNN and RNN) to account for both spatial and temporal connectivity. A quasi-Newton method is used to accelerate the FSI coupling convergence. We observe a very good agreement between the results of the presented framework and the classical numerical methods for simulation of 1d fluid flow inside an elastic tube. This work is a preliminary step for using neural networks to speed-up the FSI coupling convergence by providing an accurate initial guess in each time step for classical numerical solvers


page 1

page 2

page 3

page 4


The Performance Impact of Newton Iterations per Solver Call in Partitioned Fluid-Structure Interaction

The cost of a partitioned fluid-structure interaction scheme is typicall...

Adaptive Neural Network-Based Approximation to Accelerate Eulerian Fluid Simulation

The Eulerian fluid simulation is an important HPC application. The neura...

Quasi-Newton Waveform Iteration for Partitioned Fluid-Structure Interaction

We present novel coupling schemes for partitioned multi-physics simulati...

On the number of subproblem iterations per coupling step in partitioned fluid-structure interaction simulations

In literature, the cost of a partitioned fluid-structure interaction sch...

A Multi-Vector Interface Quasi-Newton Method with Linear Complexity for Partitioned Fluid-Structure Interaction

In recent years, interface quasi-Newton methods have gained growing atte...

Computationally Efficient Multiscale Neural Networks Applied To Fluid Flow In Complex 3D Porous Media

The permeability of complex porous materials can be obtained via direct ...

A Robin-Neumann Scheme with Quasi-Newton Acceleration for Partitioned Fluid-Structure Interaction

The Dirichlet-Neumann scheme is the most common partitioned algorithm fo...