arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2506.08021cs.LGphysics.flu-dyn
收藏

FlowBERT:用于可变流场预测的提示微调 BERT

FlowBERT: Prompt-tuned BERT for variable flow field prediction

School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China(计算机工程与科学学院,上海大学,上海200444,中国)

Weihao Zou, Weibing Feng, Pin Wu

AI总结:

本文提出 FlowBERT 框架,融合 POD 降维、预训练 LLM 微调与流体专用文本模板,实现可变流场的少样本高精度秒级预测。

摘要:

本研究提出了一种基于大语言模型(LLM)知识迁移的通用流场预测框架,旨在解决传统计算流体力学(CFD)方法计算成本高昂以及现有深度学习模型跨工况迁移能力有限的问题。该框架创新性地将本征正交分解(POD)降维与预训练 LLM 的微调策略相结合:POD 有助于实现流场特征的压缩表示,而微调后的模型则学习在状态空间中编码系统动力学。为增强模型对流场数据的适应性,我们专门设计了面向流体动力学的文本模板,通过丰富的上下语文义信息提升预测性能。实验结果表明,在少样本学习场景下,本框架优于传统 Transformer 模型,并在多种来流条件和翼型几何形状上展现出卓越的泛化能力。消融研究揭示了 FlowBERT 架构中关键组件的贡献。与需要数小时计算的传统 Navier-Stokes 方程求解器相比,本方法将预测时间缩短至秒级,同时保持 90% 以上的准确率。所建立的知识迁移范式为快速流体动力学预测开辟了新方向,其潜在应用可拓展至气动优化、流动控制及其他工程领域。

英文摘要:

This study proposes a universal flow field prediction framework based on knowledge transfer from large language model (LLM), addressing the high computational costs of traditional computational fluid dynamics (CFD) methods and the limited cross-condition transfer capability of existing deep learning models. The framework innovatively integrates Proper Orthogonal Decomposition (POD) dimensionality reduction with fine-tuning strategies for pretrained LLM, where POD facilitates compressed representation of flow field features while the fine-tuned model learns to encode system dynamics in state space. To enhance the model's adaptability to flow field data, we specifically designed fluid dynamics-oriented text templates that improve predictive performance through enriched contextual semantic information. Experimental results demonstrate that our framework outperforms conventional Transformer models in few-shot learning scenarios while exhibiting exceptional generalization across various inflow conditions and airfoil geometries. Ablation studies reveal the contributions of key components in the FlowBERT architecture. Compared to traditional Navier-Stokes equation solvers requiring hours of computation, our approach reduces prediction time to seconds while maintaining over 90% accuracy. The developed knowledge transfer paradigm establishes a new direction for rapid fluid dynamics prediction, with potential applications extending to aerodynamic optimization, flow control, and other engineering domains.

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。

↑