Simulation Code Generation for Fluid Systems using Large Language Models: Benchmarking Models and Prompting Strategies

AI 中文解读

大语言模型在写代码这件事上又迈出了一步：现在它们能帮工程师把流体系统的设计图直接“翻译”成可运行的仿真程序。这篇研究一口气测试了10款主流AI模型和6种提问策略，看看谁能最靠谱地把管道、水泵这些流体系统的图纸变成计算机能跑的模拟代码。结果发现，AI生成的代码在语法上已经相当过关，但在实际仿真运行时的准确度还差着不少火候。打个比方，就像AI能写出一篇结构通顺、用词准确的文章，但里面的数据和事实不一定经得起推敲。这意味着，对于搞水利、能源、化工设计的工程师来说，AI可以成为得力的“初稿助手”，帮他们快速搭建仿真模型、省下大量编码时间，但关键数据和最后的验证环节还得靠人来把关。长远来看，这类工具成熟后，小到城市供水管网的管理，大到工业设备的优化设计，研发效率都可能显著提升——当然，在AI真正“靠谱”之前，工程师的饭碗还是稳稳的。

Large language models (LLMs) have demonstrated a strong ability to generate syntactically correct code from natural-language specifications. In this study, we explore how LLMs can be harnessed to automatically translate a neutral graph representation of fluid system models into executable code for two widely adopted simulation environments: the Python library WNTR and the Modelica Standard Library. We conduct a systematic comparison of ten state-of-the-art LLMs and six prompting strategies that differ in the contextual information supplied (e.g., code or documentation). For each configuration we assess the generated code using a suite of software-quality metrics and we validate the functional fidelity of the resulting simulation models by reproducing benchmark fluid system scenarios. Our findings offer concrete guidance for researchers and engineers seeking to integrate LLM-driven code synthesis into model-based design pipelines. While the best-performing configurations achieve acceptable syntactic quality, we observe substantial gaps remain in simulation fidelity.