Under the paradigm of intelligent manufacturing, web-based intelligent CAPP will become the trend of machining process planning. Machining process knowledge base is the foundation for implementing web-based intelligent CAPP. Massive historical machining process planning data accumulated in different sources become the main carrier of machining process knowledge. Hence, web-based intelligent CAPP puts forward the demand for data-driven construction of machining process knowledge base. Heterogeneous knowledge and unstructured data pose challenges for data-driven construction of machining process knowledge base. This article proposes a data-driven method combining knowledge graph with deep learning for constructing machining process knowledge base to provide more effective support for web-based intelligent CAPP. Firstly, a unified ontology model of machining process knowledge which integrates multi-domain machining process knowledge at the fine-grained semantic level is proposed, providing a unified semantic structure for the acquisition and organization of machining process knowledge based on distributed and unstructured process data. Secondly, a deep learning model consisting of Bert, Bi-LSTM, and CRF models deployed within the federated learning framework is proposed to automatically extract structured machining process knowledge from unstructured process texts with improved performance. Eventually, the prototype system for machining process knowledge graph construction can verify the effectiveness of the proposed method.
TaoFQiQ.New IT driven service-oriented smart manufacturing: framework and characteristics. IEEE Trans Syst Man Cybern Syst2019; 49(1): 81–91.
2.
WangL.Machine availability monitoring and machining process planning towards cloud manufacturing. CIRP J Manuf Sci Technol2013; 6(4): 263–273.
3.
YeYHuTZhangC, et al. Design and development of a CNC machining process knowledge base using cloud technology. Int J Adv Manuf Technol2018; 94(9–12): 3413–3425.
4.
YusofYLatifK.Survey on computer-aided process planning. Int J Adv Manuf Technol2014; 75(1–4): 77.
5.
TaoFChengYZhangL, et al. Advanced manufacturing systems: socialization characteristics and trends. J Intell Manuf2017; 28(5): 1079–1094.
6.
GivehchiMHaghighiAWangL.Cloud-DPP for distributed process planning of mill-turn machining operations. Rob Comput Integr Manuf2017; 47: 76–84.
7.
MilosevicMLukicDAnticA, et al. E-CAPP: a distributed collaborative system for internet-based process planning. J Manuf Syst2017; 42: 210–223.
8.
O’DonovanPLeahyKBrutonK, et al. An industrial big data pipeline for data-driven analytics maintenance applications in large-scale smart manufacturing facilities. J Big Data2015; 2(1): 1–26.
9.
GaoJNeeAYC. An overview of manufacturing knowledge sharing in the product development process. Proc IMechE, Part B: J Engineering Manufacture2018; 232(13): 2253–2263.
10.
Leo KumarSP. State of the art-intense review on artificial intelligence systems application in process planning and manufacturing. Eng Appl Artif Intell2017; 65: 294–329.
11.
MiltnerFVogelTHemmjeM. Towards knowledge based process planning support for CAPP-4-SMEs: problem description, relevant state of the art and proposed approach. In: 9th international manufacturing science and engineering conference, Detrit, MI, 9–13 June 2014, vol. 1. New York: ASME.
VosniakosGCSegredouIGiannakakisT.Logic programming for process planning in the domain of sheet metal forming with progressive dies. J Intell Manuf2005; 16(4–5): 479–497.
14.
WangZDuPYuY.An intelligent modeling and analysis method of manufacturing process using the first-order predicate logic. Comput Ind Eng2009; 56(4): 1559–1565.
15.
GivehchiMHaghighiAWangL.Generic machining process sequencing through a revised enriched machining feature concept. J Manuf Syst2015; 37(Part 2): 564–575.
16.
ZhouJTLiXQWangMW, et al. Thinking process rules extraction for manufacturing process design. Adv Manuf2017; 5: 321–334.
17.
WangWLiYHuangL.Rule and branch-and-bound algorithm based sequencing of machining features for process planning of complex parts. J Intell Manuf2018; 29: 1329–1336.
18.
KumarSSinghRSekhonGS.CCKBS: a component check knowledge-based system for assessing manufacturability of sheet metal parts. J Mater Process Technol2006; 172(1): 64–69.
19.
Guerra-ZubiagaDAYoungRIM. Design of a manufacturing knowledge model. Int J Comput Integr Manuf2008; 21(5): 526–539.
20.
LeiQWangHSongY.Hybrid knowledge model of process planning and its green extension. J Intell Manuf2016; 27(5): 975–990.
21.
ChenGChenJZhaoZ, et al. An object-oriented hierarchical case representation of automotive panels in a computer-aided process planning system. Int J Adv Manuf Technol2005; 26(11–12): 1323–1330.
22.
JiangYChenJRuanX.Fuzzy similarity-based rough set method for case-based reasoning and its application in tool selection. Int J Mach Tool Manuf2006; 46(2): 107–113.
23.
Leo KumarSP. Knowledge-based expert system in manufacturing planning: state-of-the-art review. Int J Prod Res2019; 57(15–16): 4766–4790.
24.
LiXZhangSHuangR, et al. A survey of knowledge representation methods and applications in machining process planning. Int J Adv Manuf Technol2018; 98(9–12): 3041–3059.
25.
FanYLiuCWangJ.Integrating multi-granularity model and similarity measurement for transforming process data into different granularity knowledge. Adv Eng Inf2018; 37: 88–102.
26.
ŠormazDSarkarA.SIMPM-upper-level ontology for manufacturing process plan network generation. Rob Comput Integr Manuf2019; 55(Part B): 183–198.
27.
EumKKangMKimG, et al. Ontology-based modeling of process selection knowledge for machining feature. Int J Precis Eng Manuf2013; 14(10): 1719–1726.
28.
KangMKimGLeeT, et al. Selection and sequencing of machining processes for prismatic parts using process ontology model. Int J Precis Eng Manuf2016; 17(3): 387–394.
29.
ChhimPChinnamRBSadawiN.Product design and manufacturing process based ontology for manufacturing knowledge reuse. J Intell Manuf2019; 30(2): 905–916.
30.
MaHZhouXLiuW, et al. A customizable process planning approach for rotational parts based on multi-level machining features and ontology. Int J Adv Manuf Technol2020; 108(3): 647–669.
31.
PaulheimH.Knowledge graph refinement: a survey of approaches and evaluation methods. Semant Web2017; 8(3): 489–508.
LiJLiuXYinW, et al. Empirical evaluation of multi-task learning in deep neural networks for natural language processing. Neural Comput Appl2021; 33(9): 4417–4428.
34.
WuXChenHWuG, et al. Knowledge engineering with big data. IEEE Intell Syst2015; 30(5): 46–55.
35.
ZhangXLiuXLiX, et al. MMKG: an approach to generate metallic materials knowledge graph based on DBpedia and Wikipedia. Comput Phys Commun2017; 211: 98–112.
36.
LiXZhangSHuangR, et al. Structured modeling of heterogeneous CAM model based on process knowledge graph. Int J Adv Manuf Technol2018; 96(9–12): 4173–4193.
37.
ZhouBBaoJLiJ, et al. A novel knowledge graph-based optimization approach for resource allocation in discrete manufacturing workshops. Rob Comput Integr Manuf2021; 71: 102160.
38.
GuoLYanFLiT, et al. An automatic method for constructing machining process knowledge base from knowledge graph. Rob Comput Integr Manuf2022; 73: 102222.
39.
KumarAStarlyB.FabNER: information extraction from manufacturing process science domain literature using named entity recognition. J Intell Manuf2022; 33(8): 2393–2407.
40.
ZhouBBaoJLiuY, et al. BA-IKG: BiLSTM embedded ALBERT for industrial knowledge graph generation and reuse. In: IEEE 18th international conference on industrial informatics (INDIN), Warwick, UK, 20–23 July 2020, pp.63–69. Piscataway: IEEE.
41.
DengTLiYLiuX, et al. Federated learning-based collaborative manufacturing for complex parts. J Intell Manuf2023; 34(7): 3025–3038.
42.
ElmesbahiABuj-CorralIEl MesbahiJ, et al. New STEP-NC-compliant system to automate process planning for the turning process. Int J Adv Manuf Technol2023; 128(5–6): 2419–2457.
43.
DevlinJChangMWLeeK, et al. BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, Minneapolis, MN, 2–7 June 2019, vol. 1, pp.4171–4186. Stroudsburg: ACL.
44.
MaXHovyE.End-to-end sequence labeling via bi-directional LSTM-CNNs-CRF. In: Proceedings of the 54th annual meeting of the association for computational linguistics, ACL 2016-long papers, Berlin, Germany, 7–12 August 2016, vol. 2, pp.1064–1074. Stroudsburg: ACL.
45.
BeutelDJTopalTMathurA, et al. Flower: a friendly federated learning research framework. arXiv Preprint arXiv:2007.14390, 2020.
