Large Language Model Agent for User-friendly Chemical Process Simulations

TL;DR

The paper presents a novel framework that integrates a Large Language Model (LLM) agent with AVEVA Process Simulation (APS) via the Model Context Protocol (MCP) to enable natural-language interactions with rigorous process simulations. It demonstrates the approach through two water–methanol separation case studies, examining analysis and flowsheet synthesis under different interaction modes. The results show that LLM-based agents can autonomously analyze flowsheets, extract data, propose improvements, and construct flowsheets, while preserving engineering rigor through deterministic APS execution and human oversight. This work highlights the potential of LLM agents as collaborative copilots for process engineers, enabling educational use and productivity gains for practitioners, with future work focusing on multi-agent architectures, advanced optimization, and broader scalability.

Abstract

Modern process simulators enable detailed process design, simulation, and optimization; however, constructing and interpreting simulations is time-consuming and requires expert knowledge. This limits early exploration by inexperienced users. To address this, a large language model (LLM) agent is integrated with AVEVA Process Simulation (APS) via Model Context Protocol (MCP), allowing natural language interaction with rigorous process simulations. An MCP server toolset enables the LLM to communicate programmatically with APS using Python, allowing it to execute complex simulation tasks from plain-language instructions. Two water-methanol separation case studies assess the framework across different task complexities and interaction modes. The first shows the agent autonomously analyzing flowsheets, finding improvement opportunities, and iteratively optimizing, extracting data, and presenting results clearly. The framework benefits both educational purposes, by translating technical concepts and demonstrating workflows, and experienced practitioners by automating data extraction, speeding routine tasks, and supporting brainstorming. The second case study assesses autonomous flowsheet synthesis through both a step-by-step dialogue and a single prompt, demonstrating its potential for novices and experts alike. The step-by-step mode gives reliable, guided construction suitable for educational contexts; the single-prompt mode constructs fast baseline flowsheets for later refinement. While current limitations such as oversimplification, calculation errors, and technical hiccups mean expert oversight is still needed, the framework's capabilities in analysis, optimization, and guided construction suggest LLM-based agents can become valuable collaborators.

Figures (4)

• Figure 1: Schematic overview of the proposed framework including MCP.
• Figure 2: Simulation flowsheet of APS example "C1 - Water Methanol Separation".
• Figure 3: Constructed simulation flowsheet via step-by-step dialogue with LLM agent.
• Figure 4: Schematic overview of an extended framework including MAS and RAG.