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

doi:10.16731/j.cnki.1671-3133.2025.09.005

Abstract

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

CLC Number:

GUO Xifeng, LIANG Wenxin, JI Baoning, JIANG Mingjie, CHEN Lun. Intelligent question and answer method for assembly process based on large language models[J]. Modern Manufacturing Engineering, 2025, 540(9): 33-40.

References

[1] 董云龙,李祥飞,刘行,等.航空航天领域机器人化智能装配技术综述[J].人工智能,2022(3):6-20.
[2] 张晓梅.面向航空复杂产品的装配工艺优化设计技术[J].智能制造,2020(6):35-38.
[3] 李兆宇,李小强,金朝海,等.航空航天复杂产品装配仿真实施方案研究[J].航天制造技术,2019(1):60-65.
[4] 刘鹏,程浩然,王莹,等.煤矿工种知识图谱智能问答研究[J].计算机技术与发展,2024,34(3):185-192.
[5] 胡志强,潘鑫瑜,文思捷,等.结合多模态知识图谱与大语言模型的风机装配工艺问答系统[J].机械设计,2023,40(S2):20-26.
[6] 杨小霞,杨建喜,李韧,等.桥梁检测领域知识图谱构建与知识问答方法[J].计算机应用,2022,42(S1):28-36.
[7] 张笑文,汤闻易,单晶,等.飞行态势知识图谱及其问答系统的构建方法[J].指挥信息系统与技术,2023,14(3):70-80.
[8] 巴图,尹川,张彬钰,等.基于地理知识图谱的智能问答系统设计与实现[J].科学技术创新,2023(7):29-32.
[9] 张彩丽,吴赛赛,李玮,等.面向农作物科学施肥管理与土壤肥力查询的农业智能问答系统[J].园艺与种苗,2022,42(10):84-86,92.
[10] 王文广,王昊奋.融合大模型的多模态知识图谱及在金融业的应用[J].人工智能,2023(2):18-28,40.
[11] 何柳,安然,刘姝妍,等.基于知识图谱的航空多模态数据组织与知识发现技术研究[J].图学学报,2024,45(2):300-307.
[12] 丁鑫,邹荣金,潘志庚.基于高效参数微调的生成式大模型领域适配技术[J].人工智能,2023(4):1-9.
[13] 石致远,张佳蕾,孔志伟,等.结合知识图谱与大语言模型的风电装备智能问答系统[J].东方电气评论,2024,38(3):77-84.
[14] ZHANG Y,CHEN F,LIU Z,et al.A materials terminology knowledge graph automatically constructed from text corpus[J].Scientific Data,2024,11(1):600.
[15] CHEN J,JIA X.An approach for assembly process case discovery using multimedia information source[J].Computers in Industry,2020,115:103176.
[16] DENG J,CHEN C,HUANG X,et al.Research on the construction of event logic knowledge graph of supply chain management[J].Advanced Engineering Informatics,2023,56:101921.
[17] CUI Y,CHE W,LIU T,et al.Pre-training with whole word masking for chinese bert[J].IEEE/ACM Transactions on Audio,Speech,and Language Processing,2021(29):3504-3514.