arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.22528cs.IRcs.AI
收藏

GraphRAG用于工程图纸:ChatP&ID实现LLM与P&IDs的交互

GraphRAG for Engineering Diagrams: ChatP&ID Enables LLM Interaction with P&IDs

Process Intelligence Research Group(过程智能研究组);Department of Chemical Engineering(化学工程系);Delft University of Technology(代尔夫特理工大学)

Achmad Anggawirya Alimin, Artur M. Schweidtmann

AI总结:

本文提出ChatP&ID框架,通过GraphRAG实现高效、低成本的P&IDs自然语言交互,提升准确率并降低计算成本。

摘要:

大型语言模型(LLMs)结合检索增强生成(RAG)和知识图谱为与工程图纸如管道和仪器图(P&IDs)交互提供了新机会。然而,直接用LLMs处理原始图像或智能P&IDs文件往往成本高、效率低且易产生幻觉。本文引入ChatP&ID,一种代理框架,通过图检索增强生成(GraphRAG)实现基于P&IDs的 grounded 且低成本的自然语言交互。智能P&IDs编码在DEXPI标准中转换为结构化知识图谱,作为LLM代理进行图检索和推理的基础。此方法在可靠查询工程图纸的同时显著降低了计算成本。在商业LLM API(如OpenAI、Anthropic)上的基准测试显示,基于图的表示比原始图像输入准确率提高18%,且相比直接摄入智能P&IDs文件,token成本降低85%。尽管小型开源模型仍难以解读知识图谱格式和结构化工程数据,但将其与VectorRAG和PathRAG结合可提升响应准确率高达40%。值得注意的是,GPT-5-mini结合ContextRAG在仅$0.004每任务的成本下达到91%的准确率。最终的ChatP&ID界面使用户能够直观地与复杂工程图纸进行自然语言交互,并为AI辅助的过程工程任务如危害和可操作性研究(HAZOP)和多代理分析奠定了基础。

英文摘要:

Large Language Models (LLMs) combined with Retrieval-Augmented Generation (RAG) and knowledge graphs offer new opportunities for interacting with engineering diagrams such as Piping and Instrumentation Diagrams (P&IDs). However, directly processing raw images or smart P&ID files with LLMs is often costly, inefficient, and prone to hallucinations. This work introduces ChatP&ID, an agentic framework that enables grounded and cost-effective natural-language interaction with P&IDs using Graph Retrieval-Augmented Generation (GraphRAG), a paradigm we refer to as GraphRAG for engineering diagrams. Smart P&IDs encoded in the DEXPI standard are transformed into structured knowledge graphs, which serve as the basis for graph-based retrieval and reasoning by LLM agents. This approach enables reliable querying of engineering diagrams while significantly reducing computational cost. Benchmarking across commercial LLM APIs (OpenAI, Anthropic) demonstrates that graph-based representations improve accuracy by 18% over raw image inputs and reduce token costs by 85% compared to directly ingesting smart P&ID files. While small open-source models still struggle to interpret knowledge graph formats and structured engineering data, integrating them with VectorRAG and PathRAG improves response accuracy by up to 40%. Notably, GPT-5-mini combined with ContextRAG achieves 91% accuracy at a cost of only $0.004 per task. The resulting ChatP&ID interface enables intuitive natural-language interaction with complex engineering diagrams and lays the groundwork for AI-assisted process engineering tasks such as Hazard and Operability Studies (HAZOP) and multi-agent analysis.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑