对比多个大模型在开源流体仿真自动化中的表现，发现小模型难处理复杂任务。
A Status Quo Investigation of Large Language Models towards Cost-Effective CFD Automation with OpenFOAMGPT: ChatGPT vs. Qwen vs. Deepseek
- 用多款大模型测试开源流体仿真自动化效果
- 小模型生成复杂求解器文件成功率低，大模型也常因提示词失败
- 需专家监督才能稳定运行，自动化仍不成熟
我们评估了集成多种大语言模型的OpenFOAMGPT在计算流体动力学（CFD）任务中的表现。部分模型能有效处理边界条件调整、湍流模型选择和求解器配置等任务，但其分词成本与稳定性差异显著。本地部署的小型模型如QwQ-32B在生成复杂流程的求解器文件时表现不佳。零样本提示在设置复杂的仿真中普遍失效，即使对大型模型也是如此。边界条件与求解器关键词处理困难凸显了专家监督的必要性，表明当前技术尚不足以实现专业化CFD仿真的完全自动化。
原文摘要 · Abstract (English)
We evaluated the performance of OpenFOAMGPT incorporating multiple large-language models. Some of the present models efficiently manage different CFD tasks such as adjusting boundary conditions, turbulence models, and solver configurations, although their token cost and stability vary. Locally deployed smaller models like QwQ-32B struggled with generating valid solver files for complex processes. Zero-shot prompting commonly failed in simulations with intricate settings, even for large models. Challenges with boundary conditions and solver keywords stress the requirement for expert supervision, indicating that further development is needed to fully automate specialized CFD simulations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。