Sketch2Simulation: Automating Flowsheet Generation via Multi Agent Large Language Models

2026-03-24

AI Summary

This work proposes the first end-to-end multi-agent large language model system capable of automatically converting hand-drawn process sketches into executable simulation models in Aspen HYSYS, overcoming longstanding reliance on manual intervention and specialized software. The system integrates three coordinated components: visual parsing of raw process diagrams, generation of an intermediate graph-based structural representation, and synthesis of HYSYS COM interface code. Evaluated on four chemical engineering cases, the framework successfully produced fully runnable HYSYS models, achieving perfect structural fidelity for simple flowsheets and demonstrating connection and stream consistency scores exceeding 0.93 and 0.96, respectively, for complex cases. This study establishes the first fully automated pipeline from conceptual process sketches to executable simulation models.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

Converting process sketches into executable simulation models remains a major bottleneck in process systems engineering, requiring substantial manual effort and simulator-specific expertise. Recent advances in generative AI have improved both engineering-diagram interpretation and LLM-assisted flowsheet generation, but these remain largely disconnected: diagram-understanding methods often stop at extracted graphs, while text-to-simulation workflows assume structured inputs rather than raw visual artifacts. To bridge this gap, we present an end-to-end multi-agent large language model system that converts process diagrams directly into executable Aspen HYSYS flowsheets. The framework decomposes the task into three coordinated layers: diagram parsing and interpretation, simulation model synthesis, and multi-level validation. Specialized agents handle visual interpretation, graph-based intermediate representation construction, code generation for the HYSYS COM interface, execution, and structural verification. We evaluate the framework on four chemical engineering case studies of increasing complexity, from a simple desalting process to an industrial aromatic production flowsheet with multiple recycle loops. The system produces executable HYSYS models in all cases, achieving complete structural fidelity on the two simpler cases and strong performance on the more complex ones, with connection consistency above 0.93 and stream consistency above 0.96. These results demonstrate a viable end-to-end sketch-to-simulation workflow while highlighting remaining challenges in dense recycle structures, implicit diagram semantics, and simulator-interface constraints.

Problem

• process sketch
• executable simulation
• flowsheet generation
• process systems engineering
• diagram-to-simulation

Innovation

• multi-agent LLM
• flowsheet generation
• process diagram interpretation
• Aspen HYSYS automation
• sketch-to-simulation