arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.02483physics.flu-dyncs.AI
收藏

一种基于多模态视觉Transformer的建模框架,用于能量系统中流体流动的预测

A Multimodal Vision Transformer-based Modeling Framework for Prediction of Fluid Flows in Energy Systems

Transportation and Power Systems Division, Argonne National Laboratory(阿贡国家实验室交通与电力系统部)

Kiran Yalamanchi, Shivam Barwey, Ibrahim Jarrah, Pinaki Pal

AI总结:

本文提出基于Transformer的建模框架,用于预测复杂流体流动,通过多模态数据集训练模型,实现跨分辨率和模态的泛化能力。

摘要:

计算流体动力学(CFD)模拟复杂流体流动在能量系统中由于强非线性和多尺度多物理相互作用而成本高昂。本文提出基于Transformer的建模框架,用于预测流体流动,并展示其在活塞发动机相关高压气体注入现象中的应用。该方法采用分层视觉Transformer(SwinV2-UNet)架构,处理来自多保真度模拟的多模态流体数据集。模型架构通过辅助标记显式编码数据模态和时间增量。模型性能在两个不同任务上进行评估:(1)时空滚动预测,模型自回归预测未来时间的流体状态;(2)特征转换,模型从观测场/视图推断未观测的场/视图。我们分别在多模态数据集上训练模型,这些数据集由内部CFD模拟生成,包括多个网格分辨率、湍流模型和状态方程。所得到的数据驱动模型能够跨分辨率和模态泛化,准确预测流体演化并从有限视图中重建缺失的流场信息。本文展示了如何将大规模视觉Transformer模型适应于复杂流体流动系统的预测建模。

英文摘要:

Computational fluid dynamics (CFD) simulations of complex fluid flows in energy systems are prohibitively expensive due to strong nonlinearities and multiscale-multiphysics interactions. In this work, we present a transformer-based modeling framework for prediction of fluid flows, and demonstrate it for high-pressure gas injection phenomena relevant to reciprocating engines. The approach employs a hierarchical Vision Transformer (SwinV2-UNet) architecture that processes multimodal flow datasets from multi-fidelity simulations. The model architecture is conditioned on auxiliary tokens explicitly encoding the data modality and time increment. Model performance is assessed on two different tasks: (1) spatiotemporal rollouts, where the model autoregressively predicts the flow state at future times; and (2) feature transformation, where the model infers unobserved fields/views from observed fields/views. We train separate models on multimodal datasets generated from in-house CFD simulations of argon jet injection into a nitrogen environment, encompassing multiple grid resolutions, turbulence models, and equations of state. The resulting data-driven models learn to generalize across resolutions and modalities, accurately forecasting the flow evolution and reconstructing missing flow-field information from limited views. This work demonstrates how large vision transformer-based models can be adapted to advance predictive modeling of complex fluid flow systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑