Automating Modelica Module Generation Using Large Language Models (Prompt2Control)
PI: Yan Chen
Prompt2Control is a pilot project exploring the use of large language models (LLMs) to automatically generate, optimize, and validate Control Description Language (CDL) modules for building equipment and HVAC systems. It converts high-level control task descriptions into valid Modelica modules using a LangChain-driven prompt-engineering pipeline, OpenModelica backend, and LLM integration. https://github.com/pnnl/prompt2control