RIME-VMD-BiLSTM: A surrogate model for seismic response prediction of nonlinear vehicle-track-bridge system

Abstract

This paper proposed a RIME-VMD-BiLSTM surrogate model to rapidly and precisely predict the seismic response of a nonlinear vehicle-track-bridge (VTB) system. The surrogate model employs the RIME algorithm to optimize the variational mode decomposition (VMD) parameters (k and α) and the architecture and hyperparameter of the bidirectional long- and short-term memory network (BiLSTM). After comparing different combinations and optimization algorithms, the surrogate model was trained and used to analyze a typical 9-span 32-m high-speed railway simply supported bridge system. A series of numerical examples considering the vehicle speed, bridge damping, seismic intensity, and training strategy on the prediction effect of the surrogate model were conducted on the extended OpenSees platform. The results show that the BiLSTM model performed better than the LSTM model, whereas the prediction effects of the single-LSTM and BiLSTM models were relatively poor. With the introduction of the VMD and RIME optimization techniques, the prediction effect of the proposed RIME-VMD-BiLSTM model was excellent. The abovementioned factors had a significant influence on the seismic response of a VTB system but little impact on the prediction effect of the surrogate model. The proposed surrogate model exhibits notable transferability and robustness for predicting the VTB’s nonlinear seismic response.

Keywords

seismic response prediction / vehicle-track-bridge system / surrogate model / BiLSTM neural network / OpenSees platform

References

[1] Jiang L-z, Zhang Y-t, Feng Y-l, et al. . Simplified calculation modeling method of multi-span bridges on high-speed railways under earthquake condition [J]. Bulletin of Earthquake Engineering, 2020, 18(5): 2303-2328.

[2] Jiang L-z, Zhou W-b, Wei B, et al. . Research progress of train-track-bridge system safety of highspeed railway under earthquake action [J]. China Civil Engineering Journal, 2020, 53(9): 1-13

[3] Wang W, Morgenthal G. Development and assessment of efficient models for barge impact processes based on nonlinear dynamic finite element analyses [J]. Engineering Structures, 2018, 175: 617-627.

[4] Wei B, Wang W-h, Wang P, et al. . Seismic responses of a high-speed railway (HSR) bridge and track simulation under longitudinal earthquakes [J]. Journal of Earthquake Engineering, 2022, 26(9): 4449-4470.

[5] Dang-Vu H, Nguyen Q D, Chung T, et al. . Frequency-based data-driven surrogate model for efficient prediction of irregular structure’s seismic responses [J]. Journal of Earthquake Engineering, 2022, 26(14): 7319-7336.

[6] Rezaei H, Zarfam P, Golafshani E M, et al. . Development of seismic demand prediction models for bridges based on probability approach using symbolic regression method [J]. Computers & Structures, 2023, 282: 106991.

[7] Li Y-j, Dai Z-h, Hu C-s, et al. . Optimisation of particle distribution and performance in three-layer tubular particleboards using response surface methodology [J]. Journal of Building Engineering, 2024, 82: 108256.

[8] Ren J-y, Zhang B, Zhu X-q, et al. . Damaged cable identification in cable-stayed bridge from bridge deck strain measurements using support vector machine [J]. Advances in Structural Engineering, 2022, 25(4): 754-771.

[9] Torky A A, Ohno S. Deep learning techniques for predicting nonlinear multi-component seismic responses of structural buildings [J]. Computers & Structures, 2021, 252: 106570.

[10] Jeng C H, Mo Y L. Quick seismic response estimation of prestressed concrete bridges using artificial neural networks [J]. Journal of Computing in Civil Engineering, 2004, 18(4): 360-372.

[11] Nguyen H D, Dao N D, Shin M. Prediction of seismic drift responses of planar steel moment frames using artificial neural network and extreme gradient boosting [J]. Engineering Structures, 2021, 242: 112518.

[12] Lu X-z, Xu Y-j, Tian Y, et al. . A deep learning approach to rapid regional post-event seismic damage assessment using time-frequency distributions of ground motions [J]. Earthquake Engineering & Structural Dynamics, 2021, 50(6): 1612-1627.

[13] Perez-Ramirez C A, Amezquita-Sanchez J P, Valtierra-Rodriguez M, et al. . Recurrent neural network model with Bayesian training and mutual information for response prediction of large buildings [J]. Engineering Structures, 2019, 178: 603-615.

[14] Zhang R-y, Chen Z, Chen S, et al. . Deep long short-term memory networks for nonlinear structural seismic response prediction [J]. Computers & Structures, 2019, 220: 55-68.

[15] Xu Y-j, Lu X-z, Cetiner B, et al. . Real-time regional seismic damage assessment framework based on long short-term memory neural network [J]. Computer-Aided Civil and Infrastructure Engineering, 2021, 36(4): 504-521.

[16] Zhang Y-t, Jiang L-z, Zhou W-b, et al. . Study of bridge-subgrade longitudinal constraint range for high-speed railway simply-supported beam bridge with CRTSII ballastless track under earthquake excitation [J]. Construction and Building Materials, 2020, 241: 118026.

[17] Huang Z, Xu W, Yu K. Bidirectional LSTM-CRF models for sequence tagging [OL], 2015arXiv: 1508.01991

[18] Pang X-miao. Prediction of wheel-rail force based on artificial neural network [D], 2012, Nanjing. Nanjing University of Science and Technology(in Chinese)

[19] Lei L, Shao S-l, Liang L-xia. An evolutionary deep learning model based on EWKM, random forest algorithm, SSA and BiLSTM for building energy consumption prediction [J]. Energy, 2024, 288: 129795.

[20] Sekhar C, Dahiya R. Robust framework based on hybrid deep learning approach for short term load forecasting of building electricity demand [J]. Energy, 2023, 268: 126660.

[21] Song B-y, Liu Y-y, Fang J-z, et al. . An optimized CNN-BiLSTM network for bearing fault diagnosis under multiple working conditions with limited training samples [J]. Neurocomputing, 2024, 574: 127284.

[22] Su H, Zhao D, Heidari A A, et al. . RIME: A physics-based optimization [J]. Neurocomputing, 2023, 532: 183-214.

[23] Dragomiretskiy K, Zosso D. Variational mode decomposition [J]. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544.

[24] Yao X-y, Zhou Q-z, Wang C, et al. . An adaptive seismic signal denoising method based on variational mode decomposition [J]. Measurement, 2021, 177: 109277.

[25] Gu Q, Liu Y-d, Guo W, et al. . A practical wheel-rail interaction element for modeling vehicle-track-bridge systems [J]. International Journal of Structural Stability and Dynamics, 2019, 19(2): 1950011

[26] Liu H-y, Yu Z-w, Guo W, et al. . A rapid simulation technique of the train-track-bridge interaction based on OpenSEES [J]. Journal of Railway Science and Engineering, 2021, 18(4): 957-965(in Chinese)

[27] Zheng X-l, Xu X-y, Chen L, et al. . Comparison of application of track spectrum of high speed railway between China and Germany in vehicle bridge coupling [J]. Journal of Railway Science and Engineering, 2021, 18(5): 1090-1097(in Chinese)

[28] GB 50111-2006. Code for seismic design of railway engineering (2009 edition) [S]. (in Chinese)

[29] Hochreiter S, Schmidhuber J. Long short-term memory [J]. Neural Computation, 1997, 9(8): 1735-1780.

[30] Srivastava N, Hinton G, Krizhevsky A, et al. . Dropout: A simple way to prevent neural networks from overfitting [J]. Journal of Machine Learning Research, 2014, 15(1): 1929-1958. DOI:

[31] Zhang S, Ding J-h, Ding X-x, et al. . Noise reduction and feature extraction of acoustic emission signals from floating ring seals based on IA-VMD [J]. Journal of Vibration and Shock, 2024, 43(4): 222-229(in Chinese)

RIGHTS & PERMISSIONS

Central South University