An Agentic Approach to Automatic Creation of P&ID Diagrams from Natural Language Descriptions

TL;DR

This paper presents an innovative AI-powered system that automatically generates P&ID diagrams from natural language descriptions, improving efficiency and accuracy in engineering workflows.

Contribution

It introduces a multi-step agentic workflow leveraging LLMs and VLMs for structured diagram creation from natural language, a novel approach in engineering automation.

Findings

Demonstrates the feasibility of automated P&ID generation from natural language.

Shows improved accuracy over zero-shot and few-shot methods.

Validates the soundness and completeness of the generated workflows.

Abstract

The Piping and Instrumentation Diagrams (P&IDs) are foundational to the design, construction, and operation of workflows in the engineering and process industries. However, their manual creation is often labor-intensive, error-prone, and lacks robust mechanisms for error detection and correction. While recent advancements in Generative AI, particularly Large Language Models (LLMs) and Vision-Language Models (VLMs), have demonstrated significant potential across various domains, their application in automating generation of engineering workflows remains underexplored. In this work, we introduce a novel copilot for automating the generation of P&IDs from natural language descriptions. Leveraging a multi-step agentic workflow, our copilot provides a structured and iterative approach to diagram creation directly from Natural Language prompts. We demonstrate the feasibility of the generation process by evaluating the soundness and completeness of the workflow, and show improved results compared to vanilla zero-shot and few-shot generation approaches.