📝 SummarXiv

Abstract

Computational Fluid Dynamics (CFD) is essential for advancing scientific and engineering fields but is hindered by operational complexity, high expertise requirements, and limited accessibility. This paper introduces ChatCFD, an automated agent system for OpenFOAM simulations that processes multi-modal inputs (e.g., research papers, meshes) via an interactive interface, leveraging DeepSeek-R1 and DeepSeek-V3 large language models, a multi-agent architecture, and OpenFOAM knowledge. Its four-stage pipeline (Knowledge Base Construction, User Input Processing, Case File Generation, and Execution and Error Reflection) enables iterative trial-reflection-refinement for intricate setups, supporting diverse physical models and external meshes. Validation on 205 benchmark tutorial cases, 110 perturbed variants, and 2 literature-derived cases shows ChatCFD's 82.1 percent operational success rate on basic cases, outperforming MetaOpenFOAM (6.2 percent) and Foam-Agent (42.3 percent), and 60-80 percent on literature-derived complex cases. Turbulence model studies show a 40 percent success rate for common models versus 10 percent for rare ones like RNG k-epsilon. Physics coupling analyses reveal higher resource demands for multi-physics-coupled cases, while LLM bias toward simpler setups introduces persistent errors, such as dimensional inconsistency. Ablation studies highlight the efficacy of RAG-based modules and reflection mechanisms. By automating hypothesis testing and parameter exploration, ChatCFD accelerates scientific discovery in fluid mechanics and engineering, addressing LLM limitations through structured design and showing strong potential as a modular component in MCP-based agent networks for collaborative multi-agent systems, paving the way for scalable AI-driven CFD innovation. The code for ChatCFD is available at https://github.com/ConMoo/ChatCFD.