面向知识图谱的智能生产系统工艺知识推理方法

doi:10.16182/j.issn1004731x.joss.21-1305

摘要/Abstract

摘要：

针对智能生产系统中知识和数据之间存在冗余度高、关联性弱，难以进行知识推理的缺点，提出了面向知识图谱的工艺知识推理方法。对输入信息进行语义标注和分类，提取得到用于信息匹配的特征；利用图卷积方法对提取到的局部特征和全局特征进行关联，整合成带有差异值信息的特征无向图，与构建好的知识图谱进行图匹配操作；根据不同的推理类型采用不同的推理规则，推理得出实例之间的关联和拓扑信息，生成关于输入信息的属性和值。与推荐系统算法、融合知识图谱的图卷积算法相比，该算法在MovieLens-1M、Book-Crossing、Last.FM数据集上取得了较高的预测率，通过工艺实例知识推理验证了所提推理模型的可行性。

关键词: 知识图谱, 知识推理, 工艺知识, 图卷积, 图匹配

Abstract:

Aiming at the disadvantages of high redundancy and weakness between knowledge and data in intelligent production system, and the difficulty to perform knowledge reasoning, a process knowledge reasoning method for knowledge maps is proposed. The input information is semantically labeled and classified, the characteristics of the information match are extracted, the extracted local feature and global feature are associated through graph convolution method, and the feature of the difference value information is integrated and mapped with the constructed knowledge graph. Different reasoning rules are used according to different reasoning types, and the association and topology information between instances are deduced, and the properties and values of input information are generated. Compared with the recommended system algorithm and fusion knowledge map, the algorithm has higher predictive rates on Movielens-1M, Book-Crossing, Last.FM data set. The feasibility of the reasoning model is verified by the process instance knowledge.

Key words: knowledge graph, knowledge reasoning, process knowledge, graph convolution, graph matching

中图分类号:

TP391.9

杨伟凯, 王艳, 纪志成. 面向知识图谱的智能生产系统工艺知识推理方法[J]. 系统仿真学报, 2023, 35(4): 773-785.

Weikai Yang, Yan Wang, Zhicheng Ji. Knowledge Graph-based Process Knowledge Reasoning Method for Intelligent Production System[J]. Journal of System Simulation, 2023, 35(4): 773-785.

图/表 13

图1

图2

图3

图4

图5

图6

图7

图8

表1

表2

表3

图9

图10

参考文献 24

1	He L L, Jiang P Y. Manufacturing Knowledge Graph: A Connectivism to Answer Production Problems Query With Knowledge Reuse[J]. IEEE Access(S2169-3536), 2019, 7: 101231-101244.
2	Steiner T, Verborgh R, Troncy R, et al. Adding Realtime Coverage to the Google Knowledge Graph[C]// International Semantic Web Conference. 11th ISWC 2012. Boston, USA: Central Europe, 2012: 11-15.
3	王保魁, 吴琳, 胡晓峰, 等. 基于知识图谱的联合作战态势知识表示方法[J]. 系统仿真学报, 2019, 31(11): 2228-2237.
	Wang Baokui, Wu Lin, Hu Xiaofeng, et al. Knowledge Representation Method of Joint Operation Situation Based on Knowledge Graph[J]. Journal of System Simulation, 2019, 31(11): 2228-2237.
4	饶子昀, 张毅, 刘俊涛, 等. 应用知识图谱的推荐方法与系统[J]. 自动化学报, 2021, 47(9): 2061-2077.
	Rao Ziyun, Zhang Yi, Liu Juntao, et al. Recommendation Method and System for Applying Knowledge Graph[J]. Acta Automatica Sinica, 2021, 47(9): 2061-2077.
5	Cheng D W, Yang F Z, Wang X Y, et al. Knowledge Graph-Based Event Embedding Framework for Financial Quantitative Investments[C]// 43th International ACM SIGIR Conference on Research and Development in Information Retrieval(SIGIR). Xian, China, 2020: 2221-2230.
6	Khalid M M, Madan K, Mazen A, et al. Automated Domainn-Specific Healthcare Knowledge Graph Curation Framework: Subarachnoid Hemorrhage as Phenotype[J]. Expert Systems With Applications(S0957-4174), 2020, 145(C) : 113120.
7	Yan H H, Yang J, Wan J F. KnowIME: A System to Construct a Knowledge Graph for Intelligent Manufa-cturing Equipment[J]. IEEE Access(S2169-3536), 2020, 8: 41805-41813.
8	Abu-Salih B, Alsawalqah H, Elshqeirat B, et al. Toward a Knowledge-Based Personalised Recommender System for Mobile App Development[J]. CoRR(S0916-8508), 2019, 9: 12322-12330.
9	Zheng H, Yang S, Lou S H, et al. Knowledge-Based Integrated Product Design Framework Towards Sustainable Low-carbon Manufacturing[J]. Advanced Engineering Informatics(S1474-0346), 2021, 48: 101258-101269.
10	Peng G Z, Wang H W, Zhang H M, et al. A Hypernetwork-Based Approach to Collaborative Retrieval and Reasoning of Engineering Design Knowledge[J]. Advanced Engineering Informatics(S1474-0346), 2019, 42: 100956-100967.
11	Li H T, Ren W, Du Y F, et al. A Parameter-Extended Case-Based Reasoning Method Based on a Functional Basis for Automated Experiential Reasoning in Mechanical Product DesignsP[J]. Advanced Engineering Informatics(S1474-0346), 2021, 50: 101409-101421.
12	Tai J J, Li H T, Du Y F, et al. A Knowledge-Based Automated Design System for Mechanical Products Based on a General Knowledge Framework[J]. Expert Systems with Applications(S0957-4174), 2021: 178: 114960-114971.
13	Zhou B, Bao J S, Li J, et al. A Novel Knowledge Graph-Based Optimization Approach for Resource Allocation in Discrete Manufacturing Workshops[J]. Robotics and Computer-Integrated Manufacturing(S0736-5845), 2021, 71(3): 102160-102179.
14	Hka B, Pw A, Yan L A, et al. Machine Learning and Knowledge Graph Based Design Rule Construction for Additive Manufacturing[J]. Additive Manufacturing (S2214-8604), 2020, 37: 101620-101633.
15	Zheng P, Xia L Q, Li C X, et al. Towards Self-X Cognitive Manufacturing Network: An Industrial Knowledge Graph-Based Multi-agent Reinforcement Learning Approach[J]. Journal of Manufacturing Systems(S0278-6125), 2021, 61: 16-26.
16	Li Q, Wang D L, Feng S, et al. Global Graph Attention Embedding Network for Relation Prediction in Knowledge Graphs[J]. IEEE Transactions on Neural Networks and Learning Systems(S2162-237X), 2021, 31: 34-48.
17	Shi M, Tsai S B. Knowledge Graph Question and Answer System for Mechanical Intelligent Manufacturing Based on Deep Learning[J]. Mathematical Problems in Engineering(S1024-123X), 2021(2): 1-8.
18	Ma T, Lü S, Huang L, et al. HiAM: A Hierarchical Attention Based Model for Knowledge Graph Multi-hop Reasoning[J]. Neural Networks(S0893-6080), 2021, 143: 261-270.
19	Zhu M Y J, Pao B K, Xu C S. Research Progress on Development and Construction of Knowledge Graph[J]. Journal of Nanjing University of Information Science and Techology(S1674-7070), 2017, 9(6): 575-588.
20	Wang Z K, Li L J, Zeng D. SRGCN: Graph-Based Multi-hop Reasoning on Knowledge Graphs[J]. Neurocomputing(S0925-2312), 2021, 454: 280-290.
21	Chen Z W, Xu J M, Peng T, et al. Graph Convolutional Network-Based Method for Fault Diagnosis Using a Hybrid of Measurement and Prior Knowledge[J]. IEEE Transactions on Cybernetics(S2168-2267), 2021, 99: 1-13.
22	Sha X, Sun Z, Zhang J. Hierarchical Attentive Knowledge Graph Embedding for Personalized Recom-mendation[J]. Electronic Commerce Research and Applications(S1567-4223), 2021, 48(3): 101071-101084.
23	Wang H W, Zhang F Z, Wang J L, et al. RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems[C]//27th ACM International Conference on Information and Knowledge Management, Torino, Oct 22-26, 2018. New York: ACM, 2018: 417-426.
24	Wang H W, Zhao M, Xie X, et al. Knowledge Graph Convolutional Networks for Recommender Systems[C]//2019 World Wide Web Conference. SanFrancisco,May 13-17, 2019. New York: ACM, 2019: 3307-3313.

模型	MovieLens-1M	Book-Crossing	Last.FM
RippleNet	0.843 6	0.646 9	0.722 3
KGCN	0.832 7	0.635 5	0.723 8
EIM	0.849 7	0.697 3	0.746 5

属性	描述
ID	5bb578b6831b973a137e3ee6
零件名称	导轴
特征	外圆、边槽、孔
表面粗糙度/mm	2.5、10、1.5
制造精度	IT9、IT10、IT7
加工工序	粗车-半精车-精车、精磨、钻孔-铣孔
加工车床	AD-35型全功能数控车床
是否淬火	否
有色金属	不存在

ID	零件名称	特征	表面粗糙度/mm	精度	加工工序
133	导轴	外圆	2.5	IT9	粗车-半精车-精车
133	导轴	边槽	10	IT10	精磨
133	导轴	孔	1.5	IT7	钻孔-铣孔
134	主轴	外螺纹	2	IT10	粗车-半精车-车螺纹
134	主轴	轴段	8	IT9	粗车-半精车-精车-精磨
134	主轴	键槽	1.5	IT9	粗车-半精车
134	主轴	螺纹孔	0.5	IT8	粗车-车螺纹

[1]	宋縯蛟, 周佳悦, 王龙浩, 吴婧, 李睿, 芮小平. 采用R树和轨迹分段的HMM高效地图匹配方法[J]. 系统仿真学报, 2023, 35(2): 339-349.
[2]	林士琪, 王纪凯, 裴浩渊, 赵皓, 陈宗海. 基于物体关系描述的单目语义SLAM方法[J]. 系统仿真学报, 2022, 34(2): 278-284.
[3]	蒋庆, 王儒敬. 稻麦联合收获机清选智能调控模型仿真与试验[J]. 系统仿真学报, 2022, 34(11): 2485-2496.
[4]	吴曦, 孟祥林, 杨镜宇. 下一代战略博弈推演系统研究[J]. 系统仿真学报, 2021, 33(9): 2017-2024.
[5]	刘小军, 贺长雁, 刘畅, 贾金原. 基于结构匹配的建筑信息模型构件快速对齐方法[J]. 系统仿真学报, 2021, 33(7): 1626-1637.
[6]	王步维, 王敏, 范谦, 王雅男, 章涵文, 乐云亮. 基于深度学习的晶体性质预测研究[J]. 系统仿真学报, 2021, 33(12): 2854-2863.
[7]	王保魁, 吴琳, 胡晓峰, 贺筱媛. 基于知识图谱的联合作战态势知识表示方法[J]. 系统仿真学报, 2019, 31(11): 2228-2237.
[8]	谷志丹, 李擎, 赵辉. 行人自主导航定位的多级滤波方法[J]. 系统仿真学报, 2018, 30(12): 4727-4732.
[9]	周亦, 周明全, 王学松, 黄友良. 大数据环境下历史人物知识图谱构建与实现[J]. 系统仿真学报, 2016, 28(10): 2560-2566.