用AI自动将自然语言描述转为工程管道图，提升效率与准确性。
An Agentic Approach to Automatic Creation of P&ID Diagrams from Natural Language Descriptions
- 采用多步骤智能体工作流，分步生成图纸。
- 相比直接提示方法，流程完整性和正确性显著提升。
- 适合工程设计自动化、智能辅助制图场景。
管道仪表图（P&IDs）是工程与流程工业中设计、建设和运行流程的基础。然而，其手动绘制过程通常耗时费力，易出错，且缺乏有效的错误检测与修正机制。尽管生成式AI，特别是大语言模型（LLMs）和视觉-语言模型（VLMs），在多个领域展现出巨大潜力，但在自动化工程流程生成方面的应用仍不充分。本文提出一种新型协作者系统，可从自然语言描述自动生成P&IDs。该系统采用多步骤智能体工作流，提供从自然语言提示直接构建图纸的结构化、迭代式方法。通过评估流程的合理性和完整性，验证了生成过程的可行性，并证明其效果优于传统的零样本和少样本生成方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。