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

Abstract

We present a hybrid partitioned deep learning framework for the reduced-order modeling of fluid-structure interaction. Using the discretized Navier-Stokes in the arbitrary Lagrangian-Eulerian reference frame, we generate the full-order flow snapshots and point cloud displacements as target data for the learning and inference of fluid-structure dynamics. The hybrid operation of this methodology comes by combining two data-driven models for fluid and solid subdomains via deep learning-based reduced-order models (DL-ROMs). The proposed framework comprises the partitioned data-driven drivers for unsteady flow and the moving point cloud displacements. At the fluid-structure interface, the force information is exchanged between the two partitioned subdomain solvers. The first component of our framework relies on the proper orthogonal decomposition-based recurrent neural network (POD-RNN) as a DL-ROM procedure to infer the point cloud with a moving interface. This model utilizes the POD basis modes to reduce dimensionality and evolve them in time via RNN. The second component employs the convolution-based recurrent autoencoder network (CRAN) as a self-supervised DL-ROM procedure to infer the nonlinear flow dynamics at static Eulerian probes. We introduce these probes as spatially structured query nodes in the moving point cloud to treat the Lagrangian-to-Eulerian conflict together with convenience in training the CRAN driver. To determine these Eulerian probes, we construct a novel snapshot-field transfer and load recovery algorithm. A popular prototypical fluid-structure interaction problem of flow past a freely oscillating cylinder is considered to assess the efficacy of the proposed methodology for a different set of reduced velocities. The proposed framework tracks the interface description with acceptable accuracy and predicts the nonlinear wake dynamics over the chosen test data range.