基于OpenFOAM的CFD编码智能体案例捆绑操作模型

中文摘要 AI 辅助

通用编码智能体能够设置计算流体动力学（CFD）案例、执行求解器并管理远程作业。可审查和可重用工作还依赖于持久的工程上下文和证据。我们提出了一种具有两种模式的案例捆绑操作模型。构建模式支持在工程审查下进行智能体辅助的案例开发。重放模式将已审查的案例应用于新的变体。我们在一个OpenFOAM-7 interFoam研究中使用了该模型，用于筛选喷射器设计。Codex中的GPT-5.5帮助开发了一个案例捆绑包，其中包含仿真配置、几何处理和网格划分程序、远程执行脚本、后处理代码和审查记录。该捆绑包被重放以在远程高性能计算系统上执行并后处理140个立体光刻（STL）几何变体。另一次重放练习使用Pi编码智能体作为运行时，搭配四个不同的LLM后端。所有四次运行均成功并产生了经过验证的结果。工具使用和令牌消耗在各次运行中有所不同。结果表明，经过审查的案例捆绑包可以支持有界、可重用的自动化，并为常规执行和工程判断分配不同的角色。

英文摘要

General-purpose coding agents can set up computational fluid dynamics (CFD) cases, execute solvers, and manage remote jobs. Reviewable and reusable work additionally depends on persistent engineering context and evidence. We present a case-bundle operating model with two modes. Build supports agent-assisted case development under engineering review. Replay applies a reviewed case to new variants. We used this model in an OpenFOAM-7 interFoam study for screening injector designs. GPT-5.5 in Codex helped develop a case bundle containing the simulation configuration, geometry-processing and meshing procedures, remote-execution scripts, post-processing code, and review records. The bundle was replayed to execute and post-process 140 Stereolithography (STL) geometry variants on a remote high-performance computing system. A separate replay exercise used the Pi coding agent as the runtime with four different LLM backends. All four runs succeeded and produced verified results. Tool use and token consumption varied across runs. The results show how reviewed case bundles can support bounded, reusable automation with distinct roles for routine execution and engineering judgment.

发表机构

• State Key Laboratory of Turbulence and Complex Systems, College of Engineering, Peking University（北京大学工学院湍流研究国家重点实验室）
• AI for Science Institute (AISI)（人工智能科学研究所）

机构由 AI 辅助整理，请以论文原文为准。