发表机构
Politecnico di Milano; Inria（米兰理工大学; 法国国家数字与信息技术研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对血液动力学松耦合FSI模拟的稳定性问题，提出数据驱动策略，用前馈神经网络自动估计LC-DN-α方案的最优稳定参数α，提升了方案的鲁棒性与泛化能力。
AI 中文摘要
由于流固耦合（FSI）问题在工程和生物医学领域有广泛应用，开发准确且高效的计算方法仍是活跃的研究领域。分区松耦合（LC）方案因模块化和低计算成本，在大规模模拟中颇具吸引力，但其适用性受限于高附加质量 regime 下的稳定性问题——此时流体与结构密度相当，如血液动力学场景。在我们近期的工作中，提出了一种基于Dirichlet-Neumann界面耦合的LC算法，即LC-DN-α方案，该方案通过稳定参数α提升耦合稳定性。尽管在α满足适当约束时已证明其理论稳定性，但α的最优值取决于FSI问题的物理与数值特性，实际中难以确定。本研究提出一种数据驱动策略以自动估计α的最优值，开发了前馈神经网络，可从FSI问题的描述符预测α。模型在高附加质量 regime 下的基线FSI问题数据集上训练，并在更真实的构型上评估以验证鲁棒性与泛化能力。数值结果表明，所提模型在考虑的FSI场景中具备泛化能力，且在问题设置适度变化（包括几何形状与载荷条件改变，且未完全改变训练集所代表的相互作用机制）时，能提供α的鲁棒估计。该方法特意在简化FSI问题上开发与验证，为数据驱动策略提升分区FSI模拟效率提供了概念验证，并支持其向更复杂、更真实场景扩展。
英文摘要
The development of accurate and efficient computational methods for fluid-structure interaction (FSI) problems remains an active research area due to its broad engineering and biomedical applications. Partitioned loosely coupled (LC) schemes are attractive for large-scale simulations because of their modularity and low computational cost. However, their applicability is limited by stability issues in high added-mass regimes, where fluid and structure densities are comparable, as in hemodynamics. In our recent work, we proposed an LC algorithm based on Dirichlet-Neumann interface coupling, the LC-DN-α scheme, which improves the stability of the coupling through a stabilization parameter α. Although theoretical stability has been demonstrated under suitable constraints on α, its optimal value depends on the physical and numerical characteristics of the FSI problem and is difficult to determine in practice. In this work, we propose a data-driven strategy to automatically estimate the optimal value of α. We develop a feed-forward neural network to predict α from the descriptors of the FSI problem. The model is trained on a dataset of baseline FSI problems in large added-mass regimes and evaluated on more realistic configurations to assess robustness and generalization. Numerical results show that the proposed model generalizes across the considered FSI scenarios and provides robust estimates of α under moderate variations in the problem setup, including changes in geometry and loading conditions, that do not completely alter the interaction mechanics represented in the training set. The methodology is intentionally developed and validated on simplified FSI problems, providing a proof of concept for data-driven strategies to improve the efficiency of partitioned FSI simulations and supporting their extension to more complex and realistic scenarios.
