Abstract
For sequences of complex 3D shapes in time we present a general approach to detect patterns for their analysis and to predict the deformation by making use of structural components of the complex shape. We incorporate long short-term memory (LSTM) layers into an autoencoder to create low dimensional representations that allow the detection of patterns in the data and additionally detect the temporal dynamics in the deformation behavior. This is achieved with two decoders, one for reconstruction and one for prediction of future time steps of the sequence. In a preprocessing step the components of the studied object are converted to oriented bounding boxes which capture the impact of plastic deformation and allow reducing the dimensionality of the data describing the structure. The architecture is tested on the results of 196 car crash simulations of a model with 133 different components, where material properties are varied. In the latent representation we can detect patterns in the plastic deformation for the different components. The predicted bounding boxes give an estimate of the final simulation result and their quality is improved in comparison to different baselines.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
- 2.
Computed with LS-DYNa http://www.lstc.com/products/ls-dyna.
- 3.
Implemented in Keras [5], no peephole connections.
References
Bohn, B., Garcke, J., Griebel, M.: A sparse grid based method for generative dimensionality reduction of high-dimensional data. J. Comput. Phys. 309, 1–17 (2016)
Bohn, B., et al.: Analysis of car crash simulation data with nonlinear machine learning methods. Procedia Comput. Sci. 18, 621–630 (2013)
Bronstein, M.M., Bruna, J., LeCun, Y., Szlam, A., Vandergheynst, P.: Geometric deep learning: going beyond euclidean data. IEEE Signal Process. Mag. 34(4), 18–42 (2017)
Chang, C.T., Gorissen, B., Melchior, S.: Fast oriented bounding box optimization on the rotation group \(SO(3,\mathbb{R})\). ACM TOG 30(5), 122 (2011)
Chollet, F., et al.: Keras (2015). https://keras.io
Dimitrov, D., Knauer, C., Kriegel, K., Rote, G.: Bounds on the quality of the PCA bounding boxes. Comput. Geom. 42(8), 772–789 (2009)
Gao, L., Lai, Y.K., Yang, J., Ling-Xiao, Z., Xia, S., Kobbelt, L.: Sparse data driven mesh deformation. IEEE Trans. Vis. Comput. Graph. 1 (2019). https://doi.org/10.1109/TVCG.2019.2941200
Goldberg, D.E.: Genetic Algorithms in Search, Optimization and Machine Learning. Addison-Wesley Longman Publishing Co., Inc., Boston (1989)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)
Graening, L., Sendhoff, B.: Shape mining: a holistic data mining approach for engineering design. Adv. Eng. Inform. 28(2), 166–185 (2014)
Graves, A.: Generating sequences with recurrent neural networks. arXiv:1308.0850 (2013)
Guennec, Y.L., Brunet, J.P., Daim, F.Z., Chau, M., Tourbier, Y.: A parametric and non-intrusive reduced order model of car crash simulation. Comput. Methods Appl. Mech. Eng. 338, 186–207 (2018)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Holland, J.H.: Adaptation in Natural and Artificial Systems. University of Michigan Press, Ann Arbor (1975). Second edition (1992)
Iza-Teran, R., Garcke, J.: A geometrical method for low-dimensional representations of simulations. SIAM/ASA J. Uncertain. Quantif. 7(2), 472–496 (2019)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015). arXiv:1412.6980
Litany, O., Remez, T., Rodola, E., Bronstein, A., Bronstein, M.: Deep functional maps: structured prediction for dense shape correspondence. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5659–5667 (2017)
van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579–2605 (2008)
Monti, F., Boscaini, D., Masci, J., Rodola, E., Svoboda, J., Bronstein, M.M.: Geometric deep learning on graphs and manifolds using mixture model CNNs. In: CVPR, pp. 5115–5124 (2017)
Nelder, J.A., Mead, R.: A simplex method for function minimization. Comput. J. 7(4), 308–313 (1965)
O’Rourke, J.: Finding minimal enclosing boxes. Int. J. Comput. Inf. Sci. 14(3), 183–199 (1985)
Qiao, Y.L., Gao, L., Lai, Y.K., Xia, S.: Learning bidirectional LSTM networks for synthesizing 3D mesh animation sequences. arXiv:1810.02042 (2018)
von Rueden, L., Mayer, S., Sifa, R., Bauckhage, C., Garcke, J.: Combining machine learning and simulation to a hybrid modelling approach: current and future directions. In: Berthold, M.R., Feelders, A., Krempl, G. (eds.) IDA 2020. LNCS, vol. 12080, pp. 548–560. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-44584-3_43
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323, 533–536 (1986)
Sprügel, T., Schröppel, T., Wartzack, S.: Generic approach to plausibility checks for structural mechanics with deep learning. In: DS 87-1 Proceedings of the 21st International Conference on Engineering Design, vol. 1, pp. 299–308 (2017)
Srivastava, N., Mansimov, E., Salakhudinov, R.: Unsupervised learning of video representations using LSTMs. In: ICML, Lille, France, vol. 37, pp. 843–852 (2015)
Steffes-lai, D.: Approximation Methods for High Dimensional Simulation Results-Parameter Sensitivity Analysis and Propagation of Variations for Process Chains. Logos Verlag Berlin GmbH (2014)
Söderkvist, I., Wedin, P.Å.: On condition numbers and algorithms for determining a rigid body movement. BIT Numer. Math. 34(3), 424–436 (1994)
Tan, Q., Gao, L., Lai, Y.K., Xia, S.: Variational autoencoders for deforming 3D mesh models. In: CVPR, pp. 5841–5850 (2018)
Thole, C.A., Nikitina, L., Nikitin, I., Clees, T.: Advanced mode analysis for crash simulation results. In: Proceedings of 9th LS-DYNA Forum (2010)
Wan, J., Escalera, S., Perales, F.J., Kittler, J.: Articulated motion and deformable objects. Pattern Recogn. 79, 55–64 (2018)
Zhao, Z., Xianlong, J., Cao, Y., Wang, J.: Data mining application on crash simulation data of occupant restraint system. Expert Syst. Appl. 37, 5788–5794 (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Hahner, S., Iza-Teran, R., Garcke, J. (2020). Analysis and Prediction of Deforming 3D Shapes Using Oriented Bounding Boxes and LSTM Autoencoders. In: Farkaš, I., Masulli, P., Wermter, S. (eds) Artificial Neural Networks and Machine Learning – ICANN 2020. ICANN 2020. Lecture Notes in Computer Science(), vol 12396. Springer, Cham. https://doi.org/10.1007/978-3-030-61609-0_23
Download citation
DOI: https://doi.org/10.1007/978-3-030-61609-0_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-61608-3
Online ISBN: 978-3-030-61609-0
eBook Packages: Computer ScienceComputer Science (R0)