DOI QR코드

DOI QR Code

Crowd jumping load simulation with generative adversarial networks

  • Xiong, Jiecheng (School of Civil Engineering, Zhengzhou University) ;
  • Chen, Jun (College of Civil Engineering and Architecture, Xinjiang University)
  • Received : 2020.03.07
  • Accepted : 2021.01.01
  • Published : 2021.04.25

Abstract

To mathematically represent crowd jumping loads, the features of the jumping load of each person, including pulse curve patterns, pulse interval sequences, and pulse energy sequences are considered. These features are essentially high-dimensional random variables. However, they have to be represented in a practically simplified model due to the lack of mathematical tools. The recently emerged generative adversarial networks (GANs) can model high-dimensional random variables well, as demonstrated in image synthesis and text generation. Therefore, this study adopts GANs as a new method for modelling crowd jumping loads. Conditional GANs (CGANs) combined with Wasserstein GANs with gradient penalty (WGANs-GP) are used in pulse curve pattern modelling, where a multi-layer perceptron and convolutional neural network are selected as the discriminator and generator, respectively. For the pulse energy sequence and pulse interval sequence modelling, similar GANs are used, where recurrent neural networks are selected as both the generator and discriminator. Finally, crowd jumping loads can be simulated by connected the pulse samples based on the pulse energy sequence samples and interval sequence samples, generated by the three proposed GANs. The experimental individual and crowd jumping load records are utilized in training GANs to ensure their output can simulate real load records well. Finally, the feasibility of the proposed GANs was verified by comparing the measured structural responses of an existing floor to the predicted structural responses.

Keywords

Acknowledgement

This work was supported by the National Natural Science Foundation of China (51778465, U1711264, 5200837) and Project ZYJKFW201811009. Moreover, the authors would like to thank all the test subjects for participating in the project and making the data collection possible.

References

  1. Arjovsky, M. and Bottou, L. (2017), "Towards principled methods for training generative adversarial networks", arXiv, 1701.04862.
  2. Bengio, Y., Louradour, J., Collobert, R. and Weston, J. (2009), "Curriculum learning", Proceedings of the 26th Annual International Conference on Machine Learning, Quebec, Canada, June.
  3. Chen, J., Wang, H. and Wang, L. (2015a), "Experimental investigation on single person's jumping load model", Earthq. Eng. Eng. Vib., 14(4), 703-714. https://doi.org/10.1007/s11803-015-0055-9
  4. Chen, J., Zhang, M. and Liu, W. (2015b), "Vibration serviceability performance of an externally prestressed concrete floor during daily use and under controlled human activities", J. Perform Constr. Fac., 30(2), 4015007. https://doi.org/10.1061/(asce)cf.1943-5509.0000738
  5. Chen, J., Tan, H. and Pan, Z. (2016), "Experimental validation of smartphones for measuring human-induced loads", Smart Struct. Syst., Int. J., 18(3), 625-642. https://doi.org/10.12989/sss.2016.18.3.625
  6. Chen, J., Li, G. and Racic, V. (2018), "A data-driven wavelet-based approach for generating jumping loads", Mech. Syst. Signal Pr., 106, 49-61. https://doi.org/10.1016/j.ymssp.2017.12.013
  7. Cho, K., Van Merrienboer, B., Bahdanau, D. and Bengio, Y. (2014), "On the properties of neural machine translation: Encoder-decoder approaches", arXiv, 1409.1259.
  8. de Brito, V.L. and Pimentel, R.L. (2009), "Cases of collapse of demountable grandstands", J. Perform Constr. Fac., 23(3), 151-59. https://doi.org/10.1061/(asce)cf.1943-5509.0000006
  9. Duan, Y., Chen, Q., Zhang, H., Yun, C.B., Wu, S. and Zhu, Q. (2019), "CNN-based damage identification method of tied-arch bridge using spatial-spectral information", Smart Struct. Syst., Int. J., 23(5), 507-520. https://doi.org/10.12989/sss.2019.23.5.507
  10. Ellis, B.R. and Ji, T. (2004), "Loads generated by jumping crowds: Numerical modelling", Struct. Eng., 82(17), 35-40.
  11. Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A. and Bengio, Y. (2014), "Generative adversarial nets", Proceedings of the 27th International Conference on Neural Information Processing Systems, Quebec, Canada, December.
  12. Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V. and Courville, A.C. (2017), "Improved training of wasserstein gans", Proceedings of the 31st International Conference on Neural Information Processing Systems, CA, USA, December.
  13. Jimenez-Alonso, J.F. and Saez, A. (2018), "Motion-based design of TMD for vibrating footbridges under uncertainty conditions", Smart Struct. Syst., Int. J., 21(6), 727-740. https://doi.org/10.12989/sss.2018.21.6.727
  14. Kasperski, M. and Agu, E. (2005), "Prediction of crowd-induced vibrations via simulation", Proceeding of 23rd International Modal Analysis Conference, FL, USA, February.
  15. Kingma, D.P. and Ba, J. (2014), "Adam: A method for stochastic optimization", arXiv: 1412.6980.
  16. Krizhevsky, A., Sutskever, I. and Hinton, G.E. (2012), "Imagenet classification with deep convolutional neural networks", Conference on Neural Information Processing Systems, NV, USA, December.
  17. LeCun, Y., Bengio, Y. and Hinton, G. (2015), "Deep learning", Nature, 521(7553), 436-444. https://doi.org/10.1038/nature14539
  18. Lee, S.H., Lee, K.K., Woo, S.S. and Cho, S.H. (2013), "Global vertical mode vibrations due to human group rhythmic movement in a 39 story building structure", Eng. Struct., 57, 296-305. https://doi.org/10.1016/j.engstruct.2013.09.035
  19. Li, G., Ji, T. and Chen, J. (2018), "Determination of the dynamic load factors for crowd jumping using motion capture technique", Eng. Struct., 174, 1-9. https://doi.org/10.1016/j.engstruct.2018.07.056
  20. Mirza, M. and Osindero, S. (2014), "Conditional generative adversarial nets", arXiv: 1411.1784.
  21. Parkhouse, J.G. and Ewins, D.J. (2006), "Crowd-induced rhythmic loading", P. I. Civil Eng-Str. B., 159(5), 247-259. https://doi.org/10.1680/stbu.2006.159.5.247
  22. Press, O., Bar, A., Bogin, B., Berant, J. and Wolf, L. (2017), "Language generation with recurrent generative adversarial networks without pre-training", arXiv: 1706.01399.
  23. Racic, V. and Pavic, A. (2010a), "Mathematical model to generate near-periodic human jumping force signals", Mech. Syst. Signal Pr., 24(1), 138-152. https://doi.org/10.1016/j.ymssp.2009.07.001
  24. Racic, V. and Pavic, A. (2010b), "Stochastic approach to modelling of near-periodic jumping loads", Mech. Syst. Signal Pr., 24(8), 3037-3059. https://doi.org/10.1016/j.ymssp.2010.05.019
  25. Rumelhart, D.E., Hinton, G.E. and Williams, R.J. (1986), "Learning representations by back-propagating errors", Nature, 323(6088), 533-536. https://doi.org/10.1038/323533a0
  26. Sim, J., Blakeborough, A., Williams, M.S. and Parkhouse, G. (2008), "Statistical model of crowd jumping loads", J. Struct. Eng., 134(12), 1852-1861. https://doi.org/10.1061/(asce)0733-9445(2008)134:12(1852)
  27. Van Nimmen, K., Lombaert, G., De Roeck, G. and Van den Broeck, P. (2014), "Vibration serviceability of footbridges: Evaluation of the current codes of practice", Eng. Struct., 59, 448-461. https://doi.org/10.1016/j.engstruct.2013.11.006
  28. Wang, X., Pereira, E., Diaz, I.M. and Garcia-Palacios, J.H. (2018), "Velocity feedback for controlling vertical vibrations of pedestrian-bridge crossing. Practical guidelines", Smart Struct. Syst., Int. J., 22(1), 95-103. https://doi.org/10.12989/sss.2018.22.1.095
  29. Wu, J., Zhang, C., Xue, T., Freeman, B. and Tenenbaum, J. (2016), "Learning a probabilistic latent space of object shapes via 3d generative-adversarial modeling", Proceedings of the 30th International Conference on Neural Information Processing Systems, Barcelona, Spain, December.
  30. Xiong, J. and Chen, J. (2018), "Power spectral density function for individual jumping load", Int. J. Struct. Stab. Dy., 18(2), 1850023. https://doi.org/10.1142/s0219455418500232
  31. Xiong, J. and Chen, J. (2019), "Random field model for crowd jumping loads", Struct. Saf., 76, 197-209. https://doi.org/10.1016/j.strusafe.2018.10.001
  32. Xiong, J. and Chen, J. (2021), "Open access and updated human-induced load data set", J. Struct. Eng., 147(3), 04720003. https://doi.org/10.1061/(ASCE)ST.1943-541X.0002932
  33. Xiong, J., Chen, J. and Caprani, C. (2021), "Spectral analysis of human-structure interaction during crowd jumping", Appl. Math. Model., 89, 610-626. https://doi.org/10.1016/j.apm.2020.07.030
  34. Ye, X.W., Dong, C.Z. and Liu, T. (2016), "Image-based structural dynamic displacement measurement using different multi-object tracking algorithms", Smart Struct. Syst., Int. J., 17(6), 935-956. https://doi.org/10.12989/sss.2016.17.6.935