基于知识图谱的精密传动部件工艺路线推荐模型*

doi:10.16731/j.cnki.1671-3133.2025.02.004

现代制造工程 ›› 2025, Vol. 533 ›› Issue (2): 26-36.doi: 10.16731/j.cnki.1671-3133.2025.02.004

• 数字化/ 网络化制造 • 上一篇下一篇

基于知识图谱的精密传动部件工艺路线推荐模型^*

刘利军, 高亚楼, 曹永鹏, 刘凯星

陕西科技大学机电工程学院,西安 710016

收稿日期:2024-07-25 出版日期:2025-02-18 发布日期:2025-02-27
作者简介:刘利军,博士,讲师,主要研究方向为数字化制造研究、面向智能设计的知识管理与大数据分析。E-mail:liulijun@sust.edu.cn;高亚楼,硕士研究生,主要研究方向为数字化制造研究、知识图谱。E-mail:1492393112@qq.com;曹永鹏,硕士研究生,主要研究方向为数字化制造研究、设备运维。刘凯星,硕士研究生,主要研究方向为精益数字化制造研究。E-mail:220512093@sust.edu.cn
基金资助:
^*陕西省重点研发计划项目(2020GY-219)

A knowledge graph-based model for process routes recommending of precision transmission components

LIU Lijun, GAO Yalou, CAO Yongpeng, LIU Kaixing

College of Mechanical and Electrical Engineering,Shaanxi University of Science & Technology,Xi’an 710016,China

Received:2024-07-25 Online:2025-02-18 Published:2025-02-27

摘要/Abstract

摘要： 针对精密传动部件加工过程中普遍存在的工艺路线设计低效、知识重用困难的问题,提出了一种基于知识图谱的精密传动部件工艺路线推荐模型。首先,利用本体方法构建精密传动部件工艺知识模式层;其次,利用Electra+BiLSTM+CRF模型和BiLSTM+Self-Attention模型分别实现实体识别和关系抽取,并基于达梅劳编辑距离进行知识融合,完成数据层构建;然后,基于构建的工艺知识图谱,结合部件工艺单元以及工艺路线结构的相似度实现工艺路线推荐;最后,开发工艺路线推荐系统,并以某型号滚珠丝杠为例展示工艺路线推荐功能。经实验验证表明:推荐准确率达到89.5 %,证明了该模型的可行性,能够提高知识重用性和工艺路线设计效率,为决策提供更加科学合理的参考。

关键词: 精密传动部件, 知识图谱, 工艺设计, 工艺路线推荐

Abstract: To address the inefficiencies in process route design and the difficulty in reusing knowledge in the machining of precision transmission components,a knowledge graph-based process route recommendation model was proposed for precision transmission components. Firstly,an ontology-based method was used to construct the process knowledge schema layer for precision transmission components.Secondly,entity recognition and relation extraction were achieved using the Electra+BiLSTM+CRF model and the BiLSTM+Self-Attention model,respectively,and Damerau-Levenshtein distance was used for knowledge fusion,completing the data layer construction. Then,based on the constructed process knowledge graph,process route recommendations were achieved by combining the similarity of component process units and process route structures. Finally,a process route recommendation system was developed and demonstrated with an example of a specific type of ball screw. Experimental results show that the recommendation accuracy reaches 89.5 %,proving the feasibility of the model,which can enhance knowledge reuse and improve process route design efficiency,providing a more scientific and reasonable reference for decision-making.

Key words: precision transmission components, knowledge graph, process design, process route recommendation

中图分类号:

TP391.1

刘利军, 高亚楼, 曹永鹏, 刘凯星. 基于知识图谱的精密传动部件工艺路线推荐模型^*[J]. 现代制造工程, 2025, 533(2): 26-36.

LIU Lijun, GAO Yalou, CAO Yongpeng, LIU Kaixing. A knowledge graph-based model for process routes recommending of precision transmission components[J]. Modern Manufacturing Engineering, 2025, 533(2): 26-36.

参考文献

[1] 李晓华.我国新能源汽车的发展现状与前景趋势[J].人民论坛,2024(9):76-79.
[2] AMIT Singhal.Introducing the Knowledge Graph:Things,Not strings[EB/OL].(2012-05-16)[2024-07-19].https://blog.google/products/search/introducing-knowledge-graph-things-not/.
[3] 陶家琦,李心雨,郑湃,等.制造领域知识图谱的应用研究现状与前沿[J/OL].计算机集成制造系统,2022,28(12):3720-3736 [2024-07-15].https://doi.org/10.13196/j.cims.2022.12.002.
[4] 张思超,孔绍然,孔宪光,等.基于知识图谱的典型零件加工工艺知识构建方法[J].自动化应用,2023,64(1):53-57.
[5] 李秀玲,张树生,黄瑞,等.面向工艺重用的工艺知识图谱构建方法[J].西北工业大学学报,2019,37(6):1174-1183.
[6] WANG W,LI Y,HUANG L.Rule and branch-and-bound algorithm based sequencing of machining features for process planning of complex parts[J/OL].Journal of Intelligent Manufacturing,2018,29(6):1329-1336[2024-07-15].https://doi.org/10.1007/s10845-015-1181-y.
[7] 李柏林,王洪申,黄忠金,等.面向工艺规划重用的复杂曲面精加工知识图谱构建及可视化研究[J].现代制造工程,2022(3):6-12.
[8] 吕宽宽,薛进学,苗舒康,等.基于知识图谱的工艺决策方法研究[J].制造技术与机床,2023(5):129-134.
[9] 田玲,张谨川,张晋豪,等.知识图谱综述——表示、构建、推理与知识超图理论[J].计算机应用,2021,41(8):2161-2186.
[10] 杨玉基,许斌,胡家威,等.一种准确而高效的领域知识图谱构建方法[J].软件学报,2018,29(10):2931-2947.
[11] 陈伯谦,王坚.融合概念和属性信息的领域知识图谱补全方法[J].控制与决策,2024,39(7):2325-2333.
[12] CLARK K,LUONG M T,LE Q V.ELECTRA:PRE-TRAINING TEXT ENCODERS AS DISCRIMINATORS RATHER THAN GENERATORS[EB/OL].(2020-3-24)[2024-07-15]:arXiv:2003.10555.https://arxiv.org/abs/2003.10555.
[13] HUANG Z,XU W,YU K.Bidirectional LSTM-CRF Models for Sequence Tagging[M/OL].arXiv,2015[2024-07-19].http://arxiv.org/abs/1508.01991.
[14] 陈星月,倪丽萍,倪志伟.基于ELECTRA模型与词性特征的金融事件抽取方法研究[J].数据分析与知识发现,2021,5(7):36-47.
[15] SUÁREZ-PANIAGUA V,RIVERA ZAVALA R M,SEGURA-BEDMAR I,et al.A two-stage deep learning approach for extracting entities and relationships from medical texts[J/OL].Journal of Biomedical Informatics,2019,99:103285[2024-07-15].https://doi.org/10.1016/j.jbi.2019.103285.
[16] LI Z,LI Q,ZOU X,et al.Causality Extraction based on Self-Attentive BiLSTM-CRF with Transferred Embeddings[J/OL].Neurocomputing,2021,423:207-219[2024-07-15].https://doi.org/10.1016/j.neucom.2020.08.078.
[17] SYAROFINA S,BUSTAMAM A,YANUAR A,et al.The distance function approach on the MiniBatchKMeans algorithm for the DPP-4 inhibitors on the discovery of type 2 diabetes drugs[J/OL].Procedia Computer Science,2021,179:127-134[2024-07-15].https://doi.org/10.1016/j.procs.2020.12.017.
[18] 张鸿飞,王小龙,薛亚东,等.基于知识图谱的盾构隧道服役状态评估[J].现代隧道技术,2022,59(4):58-68.
[19] 郭祥雨,王琳,张永健.规则约束下基于免疫遗传算法的机加工艺规划[J].中国机械工程,2020,31(4):482-488.
[20] PRIYA D,RAMESH G.The Hungarian Method for the Assignment Problem,With Generalized Interval Arithmetic and Its Applications[J/OL].Journal of Physics:Conference Series,2019,1377(1):012046[2024-07-15].https://doi.org/10.1088/1742-6596/1377/1/012046.
[21] SHIH H M.Product structure (BOM)-based product similarity measures using orthogonal procrustes approach[J/OL].Computers & Industrial Engineering,2011,61(3):608-628[2024-07-15].https://doi.org/10.1016/j.cie.2011.04.016.
[22] 刘洋,石睿,王镇川,等.核技术知识图谱的构建研究[J].计算机与数字工程,2024,52(3):722-728.
[23] LIU M,ZHOU B,LI J,et al.A Knowledge Graph-Based Approach for Assembly Sequence Recommendations for Wind Turbines[J/OL].Machines,2023,11(10):930[2024-07-15].https://doi.org/10.3390/machines11100930.
[24] 蒲岍岍,雷航,李贞昊,等.增强列表信息和用户兴趣的个性化新闻推荐算法[J].计算机科学,2022,49(6):142-148.

基于知识图谱的精密传动部件工艺路线推荐模型^*

A knowledge graph-based model for process routes recommending of precision transmission components

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 10

编辑推荐

Metrics

[1]	徐山. 盾构机主驱动装配生产线关键技术研究与应用[J]. 现代制造工程, 2024, 523(4): 26-32.
[2]	郭亮;沈文平;杨滔;李心灵;万长成. 面向MBD模型的相似匹配方法研究[J]. 现代制造工程, 2023, 515(8): 99-107.
[3]	李壮，杨伯军，刘南兵，张若愚. 公理设计解耦在工艺设计的应用研究[J]. 现代制造工程, 2023, 519(12): 38-47.
[4]	赵大伟，张太华，卢尧，吴荻，姚立国. 基于数字孪生体的液压系统知识模型构建及应用[J]. 现代制造工程, 2022, 501(6): 17-24.
[5]	李柏林，王洪申，黄忠金，连亚东. 面向工艺规划重用的复杂曲面精加工知识图谱构建及可视化研究[J]. 现代制造工程, 2022, 498(3): 6-12.
[6]	吴雁，王晓军，何勇，王冰，郭立新. 基于Teamcenter的集成三维工艺设计方法分析[J]. 现代制造工程, 2021, 490(7): 66-72.
[7]	崔亚超，李义林. 高立柱群结构类零件精加工工艺优化设计[J]. 现代制造工程, 2021, 490(7): 83-87.
[8]	郭亮,晏釜,李湉,郑娟,熊吉键. 基于知识图谱的工艺推理系统[J]. 现代制造工程, 2021, 493(10): 1-10.
[9]	邱凯飞,周其洪,李青青,王培. Teamcenter环境下的结构化工艺系统设计及研究[J]. 现代制造工程, 2018, 448(1): 92-97.
[10]	徐同明, 彭义兵, 李少阳, 李建勋. 一种工序模型自动生成方法总装[J]. 现代制造工程, 2017, 437(2): 81-86.