Abstract
Modular buildings are made up of standardized building sections manufactured in a controlled environment. Their advantages include speedy construction process, cost-effectiveness, and higher quality. Further, it provides an opportunity to perform data-driven numerical simulations through a standardized process. Due to its capability of topological generalization, a Graph Neural Network (GNN) based approach is proposed in this study as an innovative structural dynamics simulation tool. The proposed approach can predict the dynamic response of structures with different topologies by changing the relationship matrix. To demonstrate its effectiveness, three spring-mass systems, with 3-DOF, 6-DOF, and 10-DOF, are used as examples of modular buildings. The dynamic response data of the 3-DOF system are used to train a GNN model. After necessary topological adaptation, the model is then used to predict the dynamic response of the 6-DOF system and the 10-DOF system, without any new training process. The results show that the proposed approach can predict the dynamic responses of structures with different topologies with a very low peak mean square error (PMSE), which is less than 0.01. It has the potential to enhance the generalization capabilities of data-driven numerical simulation methods.
J. Zhang and T. Zhang—Contributed equally to this work.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Lacey, A.W., Chen, W.S., Hao, H., Bi, K.: Review of bolted inter-module connections in modular steel buildings. J. Build. Eng. 23(2019), 207–219 (2019)
Biswal, S., Chryssanthopoulos, M.K., Wang, Y.: Condition identification of bolted connections using a virtual viscous damper. Struct. Health Monit. 21(2), 731–752 (2022)
Zhang, T., Biswal, S., Wang, Y.: SHMnet: condition assessment of bolted connection with beyond human-level performance. Struct. Health Monit. 19(4), 1188–1201 (2019)
Wang, Y., Li, H., Wang, C., Zhao, R.D.: Artificial neural network prediction for seismic response of bridge structure. In: 2009 International Conference on Artificial Intelligence and Computational Intelligence, pp. 503–506 (2009)
Lagaros, N.D., Papadrakakis, M.: Neural network based prediction schemes of the non-linear seismic response of 3D buildings. Adv. Eng. Softw. 44, 92–115 (2012)
Wu, R.T., Jahanshahi, M.R., A.M.ASCE: Deep convolutional neural network for structural dynamic response estimation and system identification. J. Eng. Mech. 145(1), 1–25 (2019)
Zhang, R.Y., Chen, Z., Chen, S., Zheng, J.W., Buyukozturk, O., Sun, H.: Deep long short-term memory networks for nonlinear structural seismic response prediction. Comput. Struct. 220, 55–68 (2019)
Yu, Y., Yao, H.P., Liu, Y.M.: Structural dynamics simulation using a novel physics-guided machine learning method. Eng. Appl. Artif. Intell. 96, 1–14 (2020)
Peng, H., Yan, J.W., Yu, Y., Luo, Y.Z.: Time series estimation based on deep learning for structural dynamic nonlinear prediction. Structures 29, 1016–1031 (2021)
Battaglia, P.W., Pascanu, R., Lai, M., Rezende, D., Kavukcuoglu, K.: Interaction networks for learning about objects. In: Proceedings of the 30th International Conference on Neural Information Processing Systems, pp. 4509–451 NIPS, Barcelona (2016)
Li, Y.Z., Wu, J.J., Zhu, J.Y., Tenenbaum, J.B., Torralba, A., Tedrake, R.: Propagation networks for model-based control under partial observation. In: 2019 International Conference on Robotics and Automation (ICRA) (2019)
Alvaro, S.G., Godwin, J., Pfaff, T., Ying, R., Leskovec, J., Battaglia, P.W.: Learning to simulate complex physics with graph networks. In: arXiv:2002.09405 (2020)
Toussaint, M.A., Allen, K.R., Smith, K.A., Tenenbaum, J.B.: Differentiable physics and stable modes for tool-use and manipulation planning. In: Robotics: Science and Systems (2018)
Gao, Y.Q., Mosalam, K.M.: Deep transfer learning for image-based structural damage recognition. Comput.-Aided Civil Infrastruct. Eng. 33, 748–768 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, J., Zhang, T., Wang, Y. (2022). GNN-Based Structural Dynamics Simulation for Modular Buildings. In: Yu, S., et al. Pattern Recognition and Computer Vision. PRCV 2022. Lecture Notes in Computer Science, vol 13536. Springer, Cham. https://doi.org/10.1007/978-3-031-18913-5_19
Download citation
DOI: https://doi.org/10.1007/978-3-031-18913-5_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-18912-8
Online ISBN: 978-3-031-18913-5
eBook Packages: Computer ScienceComputer Science (R0)