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

Rachit Gupta, Rajeev Jaiman

Published 2021-02-18Version 1

We present a hybrid physics-based deep learning (DL) framework for handling moving interfaces and predicting fluid-structure interaction (FSI). Using the discretized Navier-Stokes in the Arbitrary Lagrangian-Eulerian (ALE) reference frame, we generate full-order flow snapshots and point-cloud displacements as target physical data for the learning and inference of fluid-structure dynamics. This integrated operation of the physics-based modeling with the DL-based reduced-order model (DL-ROM) makes our framework hybrid. This multi-level framework is composed of two data-driven physics-DL drivers that predict unsteady flow and track the moving point cloud displacements respectively, while synchronously exchange the force information at the interface. The first component relies on the proper orthogonal decomposition-based recurrent neural network (POD-RNN) as a semi-supervised procedure to infer the point cloud ALE description. This model essentially relies on the POD basis modes to reduce dimensionality and evolving them in the time domain of RNN. The second component utilizes the convolution-based recurrent autoencoder network (CRAN) as a self-supervised DL procedure to predict the nonlinear flow dynamics at static Eulerian probes. We introduce these probes as spatially structured query nodes in the moving point cloud to resolve the field Lagrangian to Eulerian conflict and conveniently train the CRAN driver. We design a novel snapshot-field transfer and load recovery (FTLR) algorithm to optimally select the Eulerian probes by recovering bulk force quantities. A prototypical problem of flow past a freely oscillating cylinder is selected to test the efficacy of the proposed methodology. The framework tracks the interface description and predicts highly non-linear wake dynamics for nearly 500 time-steps. These results further the application of digital twinning of FSI engineering systems.