Large Language Model Agent for User-friendly Chemical Process Simulations

2026-01-15

AI Summary

This work proposes a novel integration of large language model (LLM) agents into the industrial-grade process simulation software AVEVA Process Simulation via the Model Context Protocol (MCP), addressing the complexity and expert dependency that hinder non-specialists in early-stage exploration and learning. By enabling users to construct, analyze, and optimize chemical processes through natural language commands, the framework supports both guided interaction and one-click generation. The approach is validated through a methanol–water separation case study, where it successfully automates simulation setup, delivers optimization recommendations, and generates visualized results. This demonstrates its dual potential to enhance engineering efficiency and serve as an educational aid, marking the first such application of LLM agents within a commercial process simulation environment.

Technology Category

Multiagent Systems: Modeling other AgentsCognitive Modeling & Cognitive Systems: Agent ArchitecturesMachine Learning: Large Multimodal Models (LMMs)

Application Category

Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactionsUser Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendationEconomics, Online Markets and Human Computation: Cost models of using LLMs in production systems

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.

Problem

• chemical process simulation
• user accessibility
• expert knowledge barrier
• process design
• simulation usability

Innovation

• Large Language Model (LLM)
• Process Simulation
• Model Context Protocol (MCP)
• Natural Language Interface
• Autonomous Flowsheet Synthesis