Preserving kinematic synchronization in fluid–structure interactions via high-order spatiotemporal neural surrogate models
Year: 2026
Type: article
Abstract: Fully coupled fluid-structure interactions (FSI), notably vortex-induced vibrations (VIV), present severe computational bottlenecks for real-time forecasting and active flow control. Existing data-driven surrogates often exhibit error accumulation and phase drift in long-horizon FSI prediction, especially under strong nonlinear coupling. To address these modeling gaps, we introduce a physics-informed multi-scale spatiotemporal Transformer (PI-MST) that combines multi-resolution representation learning with discrete physics regularization. Rather than relying on standard auto-differentiation, the model uses fourth-order central differences for spatial gradients and a second-order Backward Differentiation Formula (BDF2) scheme for temporal residual construction during training. Furthermore, a macroscopic turbulent kinetic energy (k) channel is included as an auxiliary physics state to improve closure-related consistency in high-Reynolds-number cases. To safely navigate the stiff PDE constraints inherent to coupled boundaries, a bounded curriculum strategy is used to balance data and physics losses and reduce optimization instability in early training. Under aligned 10-in/6-out and block-wise autoregressive rollout evaluation across broad Reynolds variants (Re∈[50, 1×106]), PI-MST reduces field and kinematic errors versus unconstrained baselines. Under autonomous rollout, it delays error growth and preserves phase-consistent force-displacement behavior over a finite horizon. These results indicate that explicit discrete physics regularization can improve the practical robustness of FSI surrogates within the tested regimes and prediction horizons.
Source: Physics of Fluids
DOI: 10.1063/5.0342302
Authors: Xin Zhang, Yunlong Wang
Language: English
Subfield: Statistical and Nonlinear Physics
Field: Physics and Astronomy
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7166885964