现代制造工程 ›› 2025, Vol. 540 ›› Issue (9): 33-40.doi: 10.16731/j.cnki.1671-3133.2025.09.005

• 智能制造 • 上一篇    下一篇

基于大语言模型的装配工艺智能问答方法

郭喜锋1, 梁文馨1, 季宝宁1, 蒋明杰2, 陈伦1   

  1. 1 成都飞机工业(集团)有限责任公司,成都 610031;
    2 南京航空航天大学机电学院,南京 210016
  • 收稿日期:2025-01-20 出版日期:2025-09-18 发布日期:2025-09-23
  • 作者简介:郭喜锋,教授级高级工程师。

Intelligent question and answer method for assembly process based on large language models

GUO Xifeng1, LIANG Wenxin1, JI Baoning1, JIANG Mingjie2, CHEN Lun1   

  1. 1 Chengdu Aircraft Industry (Group) Co.,Ltd.,Chengdu 610031,China;
    2 School of Mechanical and Electrical Engineering,Nanjing University of Aeronautics and Astronautics,Nanjing 210016,China
  • Received:2025-01-20 Online:2025-09-18 Published:2025-09-23

摘要: 复杂航空产品的装配工艺信息通常隐含在工艺文档和三维模型等多源信息存储介质中,导致装配工艺设计师复用历史装配工艺的效率不高、学习装配工艺知识所需的时间成本较大。针对以上问题,提出了一种基于大语言模型的装配工艺智能问答方法,以提高装配工艺信息的有效利用。首先,设计了一种装配工艺信息表示方法,结构化地表示装配工艺知识,以实现知识图谱自动构建;其次,提出了一种大语言模型拼接双向长短期记忆网络和条件随机场的关键信息识别方法;最后,依据关键信息生成检索语句,以从装配工艺知识图谱中匹配答案并回答问题。所提出的方法以某型号复杂航空产品的装配工艺信息为验证对象,实验结果表明,装配工艺设计师的工作效率有显著提升。

关键词: 大语言模型, 装配工艺设计, 复杂航空产品, 知识图谱, 智能问答

Abstract: The assembly process information of complex aerospace products is typically hidden in multi-source information storage media such as process documents and 3D models,leading to low efficiency in reusing historical assembly processes and high time costs for learning assembly process knowledge. To address these issues,it proposes an intelligent question and answer method for assembly process information based on large language models to improve the effective utilization of assembly process knowledge. First,a method for representing assembly process information is designed to structurally present assembly process knowledge,enabling automatic knowledge graph construction. Secondly,a key information identification method is proposed,which combines large language models with a Bidirectional Long Short-Term Memory (Bi-LSTM) network and Conditional Random Fields (CRF). Finally,key information is used to generate retrieval queries for matching answers from the assembly process knowledge graph. The proposed method is validated using the assembly process information of a complex aerospace product,and the experimental results show a significant improvement in the efficiency of assembly process designers.

Key words: Large Language Model (LLM), assembly process design, complex aerospace products, knowledge graph, intelligent question and answer

中图分类号: 

版权所有 © 《现代制造工程》编辑部 
地址:北京市东城区东四块玉南街28号 邮编:100061 电话:010-67126028 电子信箱:2645173083@qq.com
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持:support@magtech.com.cn