Graph-DEM: A Graph Neural Network Model for Proxy and Acceleration Discrete Element Method
Source abstract
Abstract
The discrete element method (DEM) is widely employed in various fields for analyzing rock and soil movement. However, the traditional DEM involves a large number of calculations, which leads to reduced computational efficiency. Deep-learning presents a promising solution to this issue by utilizing neural networks to approximate DEM calculations. Moreover, the consistency between the arrangement of discrete particles and the structure presented in graph neural networks further reinforces the validity of this approach. In this study, we propose a novel model called Graph-DEM based on graph neural networks, which significantly enhances the speed of DEM calculations. Meanwhile, our model demonstrates the capability of adaptive learning across various constitutive relationships. To evaluate the model’s performance, we measure particle-trajectory prediction accuracy on three scenario datasets (dynamic, static, and principle experiments) and on two public datasets. In addition, the computational efficiency of the Graph-DEM model are compared against the traditional DEM. The experimental results demonstrate the superiority of the model in terms of accuracy, universality, and computational efficiency.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Infrastructure Maintenance and Monitoring · Mineral Processing and Grinding
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
SKLSDE and BDBC Lab, Beihang University, Beijing 100191, China
School of Transportation Science and Engineering, Beihang University, Beijing 100191, China
Faculty of Architecture, Civil and Transportation Engineering, Beijing University of Technology, Beijing 100124, China
Funding
National Key R&D Program of China · National Natural Science Foundation of China · Fundamental Research Funds for the Central Universities of China · Beijing Nova Program
References (58)
Show source-provided references
1. A discrete numerical model for granular assemblies10.1680/geot.1979.29.1.47 ↗
2. Liu, C. (2021). Matrix Discrete Element Analysis of Geological and Geotechnical Engineering, Springer.10.1007/978-981-33-4524-9 ↗
3. Finding structure in time10.1207/s15516709cog1402_1 ↗
4. Imagenet classification with deep convolutional neural networks10.1145/3065386 ↗
5. The graph neural network model10.1109/TNN.2008.2005605 ↗
6. Bruna, J., Zaremba, W., Szlam, A., and LeCun, Y. (2013). Spectral networks and locally connected networks on graphs. arXiv.
7. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł., and Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, Curran Associates Inc.
8. Displacement prediction of Jiuxianping landslide using gated recurrent unit (GRU) networks10.1007/s11440-022-01495-8 ↗
9. A maximum entropy method using fractional moments and deep learning for geotechnical reliability analysis10.1007/s11440-021-01326-2 ↗
10. Intelligent assistant driving method for tunnel boring machine based on big data10.1007/s11440-021-01327-1 ↗
11. Kipf, T.N., and Welling, M. (2016). Semi-supervised classification with graph convolutional networks. arXiv.
12. Gilmer, J., Schoenholz, S.S., Riley, P.F., Vinyals, O., and Dahl, G.E. (2017, January 6–11). Neural message passing for quantum chemistry. Proceedings of the International Conference on Machine Learning, Sydney, Australia.
13. Multilayer feedforward networks are universal approximators10.1016/0893-6080(89)90020-8 ↗
14. Deep learning10.1038/nature14539 ↗
15. DEM analysis of bonded granular geomaterials10.1002/nag.728 ↗
16. Krzaczek, M., Nitka, M., and Tejchman, J. (2022). Modelling of Hydraulic Fracturing in Rocks in Non-isothermal Conditions Using Coupled DEM/CFD Approach with Two-Phase Fluid Flow Model. Multiscale Processes of Instability, Deformation and Fracturing in Geomaterials, Proceedings of the 12th International Workshop on Bifurcation and Degradation in Geomechanics, Springer.10.1007/978-3-031-22213-9_12 ↗
17. Modeling granular soils liquefaction using coupled lattice Boltzmann method and discrete element method10.1016/j.soildyn.2014.09.004 ↗
18. FLAC/PFC coupled numerical simulation of AE in large-scale underground excavations10.1016/j.ijrmms.2006.09.013 ↗
19. O’Sullivan, C. (2011). Particulate Discrete Element Modelling: A Geomechanics Perspective, CRC Press.10.1201/9781482266498 ↗
20. Wang, X., Ji, H., Shi, C., Wang, B., Ye, Y., Cui, P., and Yu, P.S. (2019, January 13–17). Heterogeneous graph attention network. Proceedings of the World Wide Web Conference, San Francisco, CA, USA.10.1145/3308558.3313562 ↗
21. Qu, L., Zhu, H., Duan, Q., and Shi, Y. (2020, January 20–24). Continuous-time link prediction via temporal dependent graph neural network. Proceedings of the Web Conference 2020, Taipei, Taiwan.10.1145/3366423.3380073 ↗
22. Velickovic, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., and Bengio, Y. (2017). Graph attention networks. arXiv.
23. Wu, Z., Pan, S., Long, G., Jiang, J., Chang, X., and Zhang, C. (2020, January 6–10). Connecting the dots: Multivariate time series forecasting with graph neural networks. Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Virtual Event.10.1145/3394486.3403118 ↗
24. Zhang, M., and Chen, Y. (2018). Link prediction based on graph neural networks. Advances in Neural Information Processing Systems, Curran Associates Inc.
25. Nasiri, E., Berahmand, K., Rostami, M., and Dabiri, M. (2021). A novel link prediction algorithm for protein-protein interaction networks by attributed graph embedding. Comput. Biol. Med., 137.10.1016/j.compbiomed.2021.104772 ↗
26. Graph neural networks: A review of methods and applications10.1016/j.aiopen.2021.01.001 ↗
27. Li, Y., Yu, R., Shahabi, C., and Liu, Y. (2017). Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. arXiv.
28. Yu, B., Yin, H., and Zhu, Z. (2017). Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. arXiv.10.24963/ijcai.2018/505 ↗
29. Duvenaud, D.K., Maclaurin, D., Iparraguirre, J., Bombarell, R., Hirzel, T., Aspuru-Guzik, A., and Adams, R.P. (2015). Convolutional networks on graphs for learning molecular fingerprints. Advances in Neural Information Processing Systems, MIT Press.
30. Schlichtkrull, M., Kipf, T.N., Bloem, P., Van Den Berg, R., Titov, I., and Welling, M. (2018). Modeling relational data with graph convolutional networks. The Semantic Web: 15th International Conference, ESWC 2018, Heraklion, Crete, Greece, 3–7 June 2018; Proceedings 15, Springer.
31. Ying, R., He, R., Chen, K., Eksombatchai, P., Hamilton, W.L., and Leskovec, J. (2018, January 19–23). Graph convolutional neural networks for web-scale recommender systems. Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, London, UK.10.1145/3219819.3219890 ↗
32. He, X., Deng, K., Wang, X., Li, Y., Zhang, Y., and Wang, M. (2020, January 25–30). Lightgcn: Simplifying and powering graph convolution network for recommendation. Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, Virtual Event.10.1145/3397271.3401063 ↗
33. Grzeszczuk, R., Terzopoulos, D., and Hinton, G. (1998, January 19–24). Neuroanimator: Fast neural network emulation and control of physics-based models. Proceedings of the 25th Annual Conference on Computer Graphics and Interactive Techniques, Orlando, FL, USA.10.1145/280814.280816 ↗
34. Inside fluids: Clebsch maps for visualization and processing10.1145/3072959.3073591 ↗
35. Fast fluid simulations with sparse volumes on the GPU10.1111/cgf.13350 ↗
36. Wave curves: Simulating lagrangian water waves on dynamically deforming surfaces10.1145/3386569.3392466 ↗
37. CD-MPM: Continuum damage material point methods for dynamic fracture animation10.1145/3306346.3322949 ↗
38. A multi-scale model for simulating liquid-fabric interactions10.1145/3197517.3201392 ↗
39. Solid-fluid interaction with surface-tension-dominant contact10.1145/3450626.3459862 ↗
40. Data-driven fluid simulations using regression forests
41. Li, Y., Wu, J., Tedrake, R., Tenenbaum, J.B., and Torralba, A. (2018). Learning particle dynamics for manipulating rigid bodies, deformable objects, and fluids. arXiv.
42. Ummenhofer, B., Prantl, L., Thuerey, N., and Koltun, V. (2020, January 26–30). Lagrangian fluid simulation with continuous convolutions. Proceedings of the International Conference on Learning Representations, Addis Ababa, Ethiopia. Available online: https://openreview.net/forum?id=B1lDoJSYDH.
43. Sanchez-Gonzalez, A., Godwin, J., Pfaff, T., Ying, R., Leskovec, J., and Battaglia, P. (2020, January 13–18). Learning to simulate complex physics with graph networks. Proceedings of the International Conference on Machine Learning, Virtual.
44. Rubanova, Y., Sanchez-Gonzalez, A., Pfaff, T., and Battaglia, P. (2021). Constraint-based graph network simulator. arXiv.
45. Wu, T., Wang, Q., Zhang, Y., Ying, R., Cao, K., Sosic, R., Jalali, R., Hamam, H., Maucec, M., and Leskovec, J. (2022, January 14–18). Learning large-scale subsurface simulations with a hybrid graph network simulator. Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Washington, DC, USA.10.1145/3534678.3539045 ↗
46. Cranmer, M., Greydanus, S., Hoyer, S., Battaglia, P., Spergel, D., and Ho, S. (2020). Lagrangian neural networks. arXiv.
47. Learning articulated rigid body dynamics with lagrangian graph neural network
48. Satorras, V.G., Hoogeboom, E., and Welling, M. (2021, January 18–24). E(n) equivariant graph neural networks. Proceedings of the International Conference on Machine Learning, Virtual.
49. Huang, W., Han, J., Rong, Y., Xu, T., Sun, F., and Huang, J. (2022). Equivariant graph mechanics networks with constraints. arXiv.
50. Equivariant spatio-temporal attentive graph networks to simulate physical dynamics
51. Learning physical dynamics with subequivariant graph neural networks
52. Learning solid dynamics with graph neural network10.1016/j.ins.2024.120791 ↗
53. Glorot, X., and Bengio, Y. (2010, January 13–15). Understanding the difficulty of training deep feedforward neural networks. Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, Sardinia, Italy. Available online: http://proceedings.mlr.press/v9/glorot10a.
54. Ba, J.L., Kiros, J.R., and Hinton, G.E. (2016). Layer normalization. arXiv.
55. Machine-learning nonconservative dynamics for new-physics detection10.1103/PhysRevE.104.055302 ↗
56. An optimal algorithm for approximate nearest neighbor searching fixed dimensions10.1145/293347.293348 ↗
57. Learning representations by back-propagating errors10.1038/323533a0 ↗
58. Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv.