Modeling of Digital Twin Workshop in Planning via a Graph Neural Network: The Case of an Ocean Engineering Manufacturing Intelligent Workshop
Source abstract
Abstract
In the era of Industry 4.0 to 5.0, the manufacturing industry is dedicated to improving its production efficiency, control capability and competitiveness with intelligent enhancement. As a typical discrete manufacturing industry, it is difficult for ocean engineering (OE) manufacturers to accurately control the entire production process, and the establishment of an integrated system supported by digital twin (DT) technology is a better solution. This paper proposes a comprehensive set of system architectures for the DT workshop. It focuses on planning, which is the main line of control, to establish a model based on graph neural networks (GNNs) and suggests five decision-support approaches associated with the model from a practical application perspective. The utilization of complete twin data for prediction and visual simulation effectively eliminates the problem of unexpected factors interfering with scheduling in enterprise production planning and achieves the goals of rapid processing and just-in-time completion. The planning model is based on the attention mechanism, which characterizes the disjunctive graph, extracts the input GNN, and outputs the scheduling decision by constructing the multi-attention network of operations and machines to deal with the complicated “operation–machine” combination relationship. The proposed method has been verified in the case of structural assembly and welding workshops, has validity and reliability, and is superior to the traditional priority scheduling rules and heuristics in terms of precision rate and rapidity. Furthermore, the DT system completes the production line application, and its proven reliability supports its full-scale application in future smart factories.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Digital Transformation in Industry · Manufacturing Process and Optimization · Flexible and Reconfigurable Manufacturing Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Mechanical and Electrical Engineering, Harbin Engineering University, Harbin 150001, China
Sanya Nanhai Innovation and Development Base of Harbin Engineering University, Harbin Engineering University, Sanya 572024, China
College of Shipbuilding Engineering, Harbin Engineering University, Harbin 150001, China
Tianjin Construction Company, Offshore Oil Engineering Co., Ltd., Tianjin 300461, China
Funding
Research on Intelligent Manufacturing Solutions and Key Technologies for the Upper Module of Offshore Oil and Gas Production Platforms · Research on Collaborative Design Technology of High-Tech Ocean-going Passenger Ships
References (46)
Show source-provided references
1. Make more digital twins10.1038/d41586-019-02849-1 ↗
2. Digital twin in industry: State-of-the-art10.1109/TII.2018.2873186 ↗
3. Bangsow, S. (2020). Tecnomatix Plant Simulation, Springer.10.1007/978-3-030-41544-0 ↗
4. Fourgeau, E., Gomez, E., Adli, H., Fernandes, C., and Hagege, M. (2016, January 24–26). System Engineering Workbench for Multi-views Systems Methodology with 3DEXPERIENCE Platform. Proceedings of the Second Asia-Pacific Conference on Complex Systems Design & Management, CSD&M Asia 2016, Singapore University of Technology, Singapore.10.1007/978-3-319-29643-2_21 ↗
5. Five-dimension digital twin model and its ten applications
6. Research and implementation of digital twin workshop based on real-time data driven
7. Data construction method for the applications of workshop digital twin system10.1016/j.jmsy.2020.02.003 ↗
8. Digital twin-driven manufacturing cyber-physical system for parallel controlling of smart workshop10.1007/s12652-018-0881-5 ↗
9. An application framework of digital twin and its case study10.1007/s12652-018-0911-3 ↗
10. Solving job shop scheduling problems via deep reinforcement learning10.1016/j.asoc.2023.110436 ↗
11. Flexible Job-Shop Scheduling via Graph Neural Network and Deep Reinforcement Learning10.1109/TII.2022.3189725 ↗
12. Learning to schedule job-shop problems: Representation and policy learning using graph neural network and reinforcement learning10.1080/00207543.2020.1870013 ↗
13. A multi-action deep reinforcement learning framework for flexible Job-shop scheduling problem10.1016/j.eswa.2022.117796 ↗
14. Lei, K., Guo, P., Wang, Y., Xiong, J., and Zhao, W. (2022, January 18–23). An End-to-end Hierarchical Reinforcement Learning Framework for Large-scale Dynamic Flexible Job-shop Scheduling Problem. Proceedings of the 2022 International Joint Conference on Neural Networks (IJCNN), Padua, Italy.10.1109/IJCNN55064.2022.9892005 ↗
15. A Deep Reinforcement Learning Framework Based on an Attention Mechanism and Disjunctive Graph Embedding for the Job-Shop Scheduling Problem10.1109/TII.2022.3167380 ↗
16. Research on adaptive job shop scheduling problems based on dueling double DQN10.1109/ACCESS.2020.3029868 ↗
17. PLM--beyond lean manufacturing
18. Glaessgen, E., and Stargel, D. (2012, January 23–26). The digital twin paradigm for future NASA and US Air Force vehicles. Proceedings of the 53rd AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics and Materials Conference, Honolulu, HI, USA.10.2514/6.2012-1818 ↗
19. Liu, X., Furrer, D., Kosters, J., and Holmes, J. (2018). Vision 2040: A Roadmap for Integrated, Multiscale Modeling and Simulation of Materials and Systems, NASA. No. E-19477.
20. Digital twin modeling10.1016/j.jmsy.2022.06.015 ↗
21. Digital twin shop-floor: A new shop-floor paradigm towards smart manufacturing10.1109/ACCESS.2017.2756069 ↗
22. Modular based flexible digital twin for factory design10.1007/s12652-018-0953-6 ↗
23. Digital twin-based opti-state control method for a synchronized production operation system10.1016/j.rcim.2019.101892 ↗
24. Predictive manufacturing system-Trends of next-generation production systems10.3182/20130522-3-BR-4036.00107 ↗
25. Shaping the digital twin for design and production engineering10.1016/j.cirp.2017.04.040 ↗
26. A digital twin-driven approach for the assembly-commissioning of high precision products10.1016/j.rcim.2019.101839 ↗
27. Graph neural networks: A review of methods and applications10.1016/j.aiopen.2021.01.001 ↗
28. A comprehensive survey on graph neural networks10.1109/TNNLS.2020.2978386 ↗
29. Gori, M., Monfardini, G., and Scarselli, F. (August, January 31). A new model for learning in graph domains. Proceedings of the 2005 IEEE International Joint Conference on Neural Networks, Montreal, QC, Canada.
30. Bruna, J., Zaremba, W., Szlam, A., and LeCun, Y. (2013). Spectral networks and locally connected networks on graphs. arXiv.
31. Convolutional neural networks on graphs with fast localized spectral filtering
32. Kipf, T.N., and Welling, M. (2016). Semi-supervised classification with graph convolutional networks. arXiv.
33. Li, Y., Tarlow, D., Brockschmidt, M., and Zemel, R. (2015). Gated graph sequence neural networks. arXiv.
34. Veličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., and Bengio, Y. (2017). Graph attention networks. arXiv.
35. Inductive representation learning on large graphs
36. Gilmer, J., Schoenholz, S., Riley, P., Vinyals, O., and Dahl, G. (2017, January 6–11). Neural Message Passing for Quantum Chemistry. Proceedings of the 34th International Conference on Machine Learning, Sydney, NSW, Australia.
37. Zhu, J., Wu, M., and Liu, C. (2020, January 27–29). Research on the Application Mode of Blockchain Technology in the Field of Shipbuilding. Proceedings of the 2020 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA), Dalian, China.10.1109/ICAICA50127.2020.9182592 ↗
38. Method of digital twin logic model oriented to production line simulation
39. Model-based test case generation from UML sequence diagrams using extended finite state machines10.1007/s11219-020-09531-0 ↗
40. Wang, R., Wang, G., Sun, J., Deng, F., and Chen, J. (2023). Flexible Job Shop Scheduling via Dual Attention Network Based Reinforcement Learning. arXiv.10.1109/TNNLS.2023.3306421 ↗
41. Schulman, J., Wolski, F., Dhariwal, P., Radford, A., and Klimov, O. (2017). Proximal policy optimization algorithms. arXiv.
42. A knowledge discovery and reuse method for time estimation in ship block manufacturing planning using DEA10.1016/j.aei.2018.11.005 ↗
43. Su, X., Lu, J., Chen, C., Yu, J., and Ji, W. (2022). Dynamic Bottleneck Identification of Manufacturing Resources in Complex Manufacturing System. Appl. Sci., 12.10.3390/app12094195 ↗
44. Green scheduling optimization of ship plane block flow line considering carbon emission and noise10.1016/j.cie.2020.106680 ↗
45. A Multitime Window Parallel Scheduling System for Large-Scale Offshore Platform Project10.1155/2022/2352651 ↗
46. Research on Welding Quality Traceability Model of Offshore Platform Block Construction Process