FlowBERT: Prompt-tuned BERT for variable flow field prediction

TL;DR

FlowBERT introduces a prompt-tuned BERT-based framework that leverages knowledge transfer and POD for rapid, accurate flow field prediction across various conditions, significantly reducing computation time.

Contribution

This work presents a novel integration of LLM fine-tuning with POD for efficient, generalizable flow prediction, surpassing traditional models in few-shot learning and transferability.

Findings

Outperforms conventional Transformer models in few-shot scenarios.

Reduces prediction time from hours to seconds with over 90% accuracy.

Demonstrates strong generalization across different flow conditions and geometries.

Abstract

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.