AI 中文总结
本研究将OpenFOAM库智能体迁移至Rust语言的Outram-Foam库，开发了两相HEM壅塞流求解器，验证显示其吻合度良好，智能体编码可提升开源库开发效率，人类专业知识仍为关键。
AI 中文摘要
已在开源统一瞬态多相先进反应堆模拟工具包（Outram Park）内，开展了将多个开源库迁移至Rust语言的智能体迁移工作，过程中保留了人类参与环节。采用该新方法后，依赖人类专业知识的验证与确认（V&V）而非代码生成，成为开发可靠模拟代码的瓶颈。本研究中，我们介绍将OpenFOAM库迁移至Outram-Foam Rust库的过程、其初步验证与确认（V&V）工作，以及后续将其用于开发Outram Park内Thermo-hydraulic AI Multi-Phase INtegrated Emulator System（TAMPINES）库中的开源两相均相平衡（HEM）壅塞流求解器，如tampines-steam-tables。Outram-Foam的初步V&V工作显示，腔室和Sod激波管案例与文献值吻合良好。此外，tampines-steam-tables的初步开发结果与Moody的HEM图吻合良好。随后，我们介绍了通过智能体开发的一维HEM求解器，并针对Edwards排放案例进行了初步验证。使用Claude Code时观察到生产力提升，但人类专家提供的领域专业知识仍是确保生成代码能有效解决问题的关键。尽管V&V方面仍需进一步工作，但本文提出的智能体编码方法展现出加快Outram Park等开源库生产与开发的巨大潜力。
英文摘要
Agentic porting of multiple open-source libraries into Rust, with human in the loop, has been performed for construction of modules within the Open-source Unified TRAnsient Multi-Phase Advanced Reactor simulation Kit (Outram Park). With this new methodology, verification and validation with human expertise, rather than code generation, has become the bottleneck in developing reliable simulation codes. In this work, we present the porting of OpenFOAM libraries into the Outram-Foam Rust libraries, their preliminary verification and validation (V&V) efforts, and their subsequent use in the development of open-source two-phase homogeneous-equilibrium (HEM) choked-flow solvers for the Thermo-hydraulic AI Multi-Phase INtegrated Emulator System (TAMPINES) libraries within Outram Park, such as tampines-steam-tables. V&V efforts of Outram-Foam show that the cavity and Sod shock tube cases agree with literature values to within acceptable margin. Moreover, the preliminary development of tampines-steam-tables shows good agreement with Moody's HEM charts. Thereafter, the 1D HEM solver, developed agentically, is presented and preliminarily validated against the Edwards blowdown case. Productivity increases were observed with the use of Claude Code, but domain expertise supplied by human experts remains critically required to ensure the generated code can solve the problem effectively. Further work remains to be done in V&V, but the agentic coding methodology described here demonstrates considerable potential to speed up production and development of open-source libraries such as Outram Park.
Comments80 pages, 21 figures
