Dimensionality Reduction of a Moving Particle System Using Convolutional Neural Networks
DOI:
https://doi.org/10.70567/mc.v41i19.100Keywords:
Autoencoders, Convolutional Networks, Dimensionality Reduction, Granular MatterAbstract
In the field of machine learning, an innovative approach has been developed in recent years for modeling complex systems by identifying intrinsic dimensions and neural state variables (NSVs) using convolutional neural networks (CNNs). This technique has proven effective for long-term stable prediction of complex dynamic systems, such as those encountered in industrial applications involving granular matter flows. The present work focuses on the use of convolutional autoencoders to predict images in two-dimensional particle systems in motion. The data, generated through simulations, are used to train the network, decomposing and reconstructing video sequences that capture the system’s dynamics. The decomposition process involves a reduction of the system’s dimensionality, which is crucial for obtaining a more efficient and simplified representation of its dynamic behavior. This facilitates the understanding and prediction of the system in industrial environments. The results are expected to contribute to the development of future simplified models of the system.
References
Baldi P. y Hornik K. Neural networks and principal component analysis: Learning from examples without local minima. Neural Networks, 2(1):53-58, 1989. https://doi.org/10.1016/0893-6080(89)90014-2
Berkooz G., Holmes P., y Lumley J.L. The proper orthogonal decomposition in the analysis of turbulent flows. Annual Review of Fluid Mechanics, 25(1):539-575, 1993. https://doi.org/10.1146/annurev.fl.25.010193.002543
Brunton S.L., Proctor J.L., y Kutz J.N. Proceedings of the national academy of sciences. Proceedings of the National Academy of Sciences, 113(14):3932-3939, 2016. https://doi.org/10.1073/pnas.1517384113
Champion K., Lusch B., Kutz J.N., y Brunton S.L. Proceedings of the national academy of sciences. Proceedings of the National Academy of Sciences, 116(45):22445-22454, 2019. https://doi.org/10.1073/pnas.1906995116
Chen B., Huang K., Raghupathi S., Chandratreya I., Du Q., y Lipson H. Discovering state variables hidden in experimental data. 2021. doi:10.48550/arXiv.2112.10755.
Chollet F. Keras. GitHub repository, 2015.
Cundall P. y Strack O. A discrete numerical model for granular assemblies. Geotechnique, 29:47-65, 1979. https://doi.org/10.1680/geot.1979.29.1.47
Goodfellow I., Bengio Y., Courville A., y Bengio Y. Deep Learning, volumen 1. MIT Press, Cambridge, 2016.
Holmes P.J., Lumley J.L., Berkooz G., y Rowley C.W. Turbulence, coherent structures, dynamical systems and symmetry. Cambridge Monographs in Mechanics. Cambridge University Press, Cambridge, England, 2nd edición, 2012. https://doi.org/10.1017/CBO9780511919701
Nedderman R. Statics and kinematics of granular materials. Cambridge University Press, London, 1992. https://doi.org/10.1017/CBO9780511600043
Pearson K. On lines and planes of closest fit to systems of points in space. Philosophical Magazine, 2(7-12):559-572, 1901. https://doi.org/10.1080/14786440109462720
Taira K., Brunton S.L., Dawson S.T.M., Rowley C.W., Colonius T., McKeon B.J., Schmidt O.T., Gordeyev S., Theofilis V., y Ukeiley L.S. Modal analysis of fluid flows: An overview. AIAA Journal, 55(12):4013-4041, 2017. https://doi.org/10.2514/1.J056060
Udrescu S.M. y Tegmark M. Science advances. Science Advances, 6(23):eaay2631, 2020. https://doi.org/10.1126/sciadv.aay2631
Wang Z. Image quality assessment: Form error visibility to structural similarity. IEEE Trans. Image Process., 13(4):604-606, 2004. https://doi.org/10.1109/TIP.2003.819861
Zhu H., Zhou Z., Yang R., y Yu A. Discrete particle simulation of particulate systems: theoretical developments. Chemical Engineering Science, 62(13):3378-3396, 2007. https://doi.org/10.1016/j.ces.2006.12.089
Zhu H., Zhou Z., Yang R., y Yu A. Discrete particle simulation of particulate systems: a review of major applications and findings. Chemical Engineering Science, 63(23):5728-5770, 2008. https://doi.org/10.1016/j.ces.2008.08.006
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Argentine Association for Computational Mechanics
This work is licensed under a Creative Commons Attribution 4.0 International License.
This publication is open access diamond, with no cost to authors or readers.
Only those papers that have been accepted for publication and have been presented at the AMCA congress will be published.
