An ALE-Consistent Graph Neural Operator-Transformer Framework for Fluid-Structure Interaction

TL;DR

This paper introduces an ALE-consistent graph neural operator-transformer framework for accurate, stable long-term fluid-structure interaction predictions on deforming meshes, combining novel coupling and training strategies.

Contribution

It develops a new ALE-consistent coupling method with a GNO-ViT surrogate and a two-stage training process for improved long-term FSI prediction accuracy and stability.

Findings

Achieves accurate phase-consistent long-term predictions.

Demonstrates robustness under inlet-profile variations.

Systematic ablation confirms the importance of each component.

Abstract

We propose an arbitrary Lagrangian-Eulerian (ALE)-consistent machine learning framework for long-term fluid-structure interaction (FSI) prediction on deforming unstructured meshes. Specifically, the fluid dynamics are modeled by a surrogate that combines a graph neural operator (GNO) with a vision Transformer (ViT) for spatiotemporal prediction, while a lightweight long short-term memory (LSTM) network predicts structural kinematics at the interface. The two surrogates are coupled through a standard partitioned procedure. Most importantly, kinematic compatibility at the moving interface is enforced via an ALE-consistent boundary-correction step that updates the fluid-side interface velocity with the predicted structural velocity at each coupling update, thereby improving near-interface accuracy and long-term rollout stability. To mitigate autoregressive error accumulation, a two-stage training strategy is adopted, consisting of single-step supervised pretraining followed by long-term autoregressive fine-tuning. The proposed framework is validated on the benchmark problem of a flexible beam vibration in the wake of a cylinder. Results demonstrate accurate phase-consistent predictions over long rollouts and robust generalization under inlet-profile variations in both interpolation and extrapolation settings. Systematic ablation studies further assess the respective contributions of the ViT module, ALE-consistent boundary correction, and long-term training to predictive accuracy and rollout robustness.