AutoFOAM：自优化自主OpenFOAM智能体

中文摘要 AI 辅助

计算流体动力学（CFD）在现代工程中发挥着重要作用，但使用OpenFOAM这类开源求解器需要大量专业知识技能，还需耗时配置设置。为减轻该负担，我们提出AutoFOAM——一种自演进大语言模型（LLM）智能体，仅基于自然语言指令即可创建、评估、运行并迭代自身的OpenFOAM模拟。该模型在Qwen-coder 2.5-14B上预训练，随后针对7种OpenFOAM求解器、13种参数化网格模板以及y+感知数值策略，用252条文本提示进行微调。算法的关键是由7个阶段组成的复杂迭代循环。为防止模型在重复自训练中退化，智能体采用三种互补的抗崩溃机制：检索增强生成（RAG）扩充的重试上下文、字典级精准修补以及提示多样性改写。通过将生成式人工智能与严谨的流体模拟相结合，AutoFOAM加速了快速原型开发并推动高级CFD工作流程的普及。

英文摘要

Computational Fluid Dynamics (CFD) plays an important role in modern engineering, but using open-source solvers such as OpenFOAM requires considerable knowledge and skills, as well as time-consuming configuration file setup. To reduce this burden, we propose AutoFOAM - a self-evolving large language model (LLM) agent that creates, evaluates, runs, and evolves its own OpenFOAM simulations based solely on natural-language instructions. Our model is pre-trained on the Qwen-coder 2.5-14B, which is then fine-tuned on 252 text prompts targeting 7 OpenFOAM solvers, 13 parametrized mesh templates, and a y plus-aware numerical policy. The crucial element of the algorithm is a sophisticated evolution loop composed of 7 stages. To prevent model degeneration under repeated self-training, the agent employs three complementary anti-collapse streams: RAG-augmented retry context, surgical dictionary-level patching, and prompt-diversity paraphrasing. By bridging generative artificial intelligence with rigorous fluid simulations, AutoFOAM accelerates rapid prototyping and democratizes advanced CFD workflows.

发表机构

• SimuNetics
• Onnes Cryogenics
• Quasi AI

机构由 AI 辅助整理，请以论文原文为准。