《计算机应用》唯一官方网站 ›› 2026, Vol. 46 ›› Issue (4): 1086-1095.DOI: 10.11772/j.issn.1001-9081.2025040455

• 人工智能 • 上一篇    下一篇

基于大语言模型的机载产品计量溯源知识图谱构建方法

师凯洲1, 何旋2, 候国义1, 李根3, 李泷杲1, 黄翔1()   

  1. 1.南京航空航天大学 机电学院,南京 210016
    2.航空工业北京长城计量测试技术研究所,北京 100095
    3.南京航空航天大学苏州研究院,江苏 苏州 215000
  • 收稿日期:2025-04-27 修回日期:2025-06-13 接受日期:2025-06-23 发布日期:2025-07-07 出版日期:2026-04-10
  • 通讯作者: 黄翔
  • 作者简介:师凯洲(2000—),男,浙江宁波人,硕士研究生,CCF会员,主要研究方向:大语言模型驱动的工业知识图谱应用、飞机装配与测量的数字化
    何旋(1987—),男,黑龙江齐齐哈尔人,高级工程师,主要研究方向:大型试验设施的计量保障、计量数字化
    候国义(1992—),男,内蒙古丰镇人,副研究员,博士,主要研究方向:航空制造里的计量与测量数字化、大语言模型驱动的工业知识图谱应用
    李根(1989—),男,江苏苏州人,高级工程师,博士,主要研究方向:工业知识图谱应用、航空的装配与测量数字化
    李泷杲(1978—),男,江苏南京人,副教授,博士,主要研究方向:飞机装配、数字测量
  • 基金资助:
    民用飞机专项科研项目(MJZ2-4N21(2));苏州市科技计划项目(SYG202346)

Airborne product metrological traceability knowledge graph construction method based on large language models

Kaizhou SHI1, Xuan HE2, Guoyi HOU1, Gen LI3, Shuanggao LI1, Xiang HUANG1()   

  1. 1.College of Mechanical and Electronic Engineering,Nanjing University of Aeronautics and Astronautics,Nanjing Jiangsu 210016,China
    2.AVIC Changcheng Institute of Metrology and Measurement,Beijing 100095,China
    3.Suzhou Research Institute of Nanjing University of Aeronautics and Astronautics,Suzhou Jiangsu 215000,China
  • Received:2025-04-27 Revised:2025-06-13 Accepted:2025-06-23 Online:2025-07-07 Published:2026-04-10
  • Contact: Xiang HUANG
  • About author:SHI Kaizhou, born in 2000, M. S. candidate. His research interests include industrial knowledge graph applications driven by large language models, digitalization of assembly and measurement of aircraft.
    HE Xuan, born in 1987, senior engineer. His research interests include metrological support for large-scale test facilities, digitalization of metrology.
    HOU Guoyi, born in 1992, Ph. D., associate research fellow. His research interests include digitalization of metrology and measurement in aviation manufacturing, industrial knowledge graph applications driven by large language models.
    LI Gen, born in 1989, Ph. D., senior engineer. His research interests include application of industrial knowledge graph, digitalization of assembly and measurement in aviation.
    LI Shuanggao, born in 1978, Ph. D., associate professor. His research interests include aircraft assembly, digital measurement.
  • Supported by:
    Science and Technology Program of Suzhou(SYG202346);Specialized Scientific Research Project on Civil Aircraft(MJZ2-4N21(2))

摘要:

机载产品类型多样、产业链广泛,存在复杂的检测体系,需要开展完备的计量检定工作。然而,机载产品数据资源主要以非结构化、碎片化和多模态的形式存在,不利于对各类测试要素开展统筹分析,并难以在统一框架下溯源测试规范性与产品质量,给计量工作带来了障碍。面对这一问题,结合生成式大语言模型(LLM)开展机载产品计量溯源(MT-AP)知识图谱构建研究。首先,梳理资源类型和计量溯源环节,构建知识图谱(KG)本体模型;其次,设计LLM工作模块并把它们组合成工作链;最后,提出基于工作链与提示模板的MT-AP知识图谱的构建方法。结合机载产品实例数据和多个工作链进行验证的实验结果表明,所提方法的知识理解与命名能力评分基本在0.91以上,文本拆分与知识解耦能力评分基本在0.83以上,而复杂参数的知识提取与结构化能力评分基本在0.85以上。可见,所提方法在MT-AP知识图谱构建关键任务上体现了较好的工作性能,为机载产品计量工程提供了技术支撑。

关键词: 大语言模型, 多源异构数据, 机载产品, 计量溯源, 知识图谱

Abstract:

Airborne products with diverse range and extensive industrial chain have a complex testing system, requiring comprehensive metrological verification work. However, airborne product data resources primarily exist in unstructured, fragmented, and multimodal forms, making it difficult to conduct overall analysis of various testing elements or trace the standardization of testing and product quality under a unified framework, thereby posing challenges to metrological work. To address this issue, the construction of knowledge graph for Metrological Traceability of Airborne Products (MT-AP) was explored by combining generative Large Language Model (LLM). Firstly, the resource types and metrological traceability links were sorted out, and a Knowledge Graph (KG) ontological model was constructed. Secondly, LLM-based work modules were designed and integrated into workflow chains. Finally, a method for constructing the MT-AP knowledge graph based on the workflow chains and prompt templates was proposed. Experiments were conducted using airborne product instance data and workflow chains. Experimental results show that the proposed method has the knowledge comprehension and naming capability scored above 0.91 basically, the text segmentation and knowledge decoupling capability scored above 0.83 basically, and the complex parameter extraction and structured capability scored above 0.85 basically. It can be seen that the proposed method exhibits satisfactory performance in key tasks of MT-AP knowledge graph construction, providing technical support for metrology engineering of airborne products.

Key words: Large Language Model (LLM), multi-source heterogeneous data, airborne product, metrological traceability, Knowledge Graph (KG)

中图分类号: