A seismic response prediction method based on a self-optimized Bayesian Bi-LSTM mixed network for high-speed railway track-bridge system

Abstract

The construction of China’s high-speed railway (HSR) network has reached earthquake-prone regions, necessitating a timely and accurate post-disaster quick prediction approach to ensure the safety of the HSR systems’ transportation lifeline. This study proposes a fast prediction method utilizing a Bayesian self-optimized bi-directional long short-term memory (Bi-LSTM) network to develop a fast prediction framework for the seismic response of the HSR track-bridge system. It describes a hierarchical clustering algorithm based on discrete wavelet decomposition. The results indicated that the proposed framework effectively predicts the nonlinear seismic response of HSR bridge structures. The model also showed the performance of the work migrate ability and robustness. In addition, the impact of different prediction locations on the HSR track-bridge system is minimal. The hierarchical clustering method based on wavelet decomposition can effectively reduce the number of inputs to the seismic training dataset while ensuring prediction accuracy.

Keywords

high-speed railway track-bridge system / Bayesian optimization / Bi-LSTM neural network / wavelet clustering

References

[1] JiangL-z, PengK, YuJ, et al. . The influence of trains on the seismic response of simply-supported beam bridges with different pier heights expressed through an impact factor. Bulletin of Earthquake Engineering, 2022, 20(5): 2795-2814 J]

[2] XuY-j, LuX-z, CetinerB, et al. . Real-time regional seismic damage assessment framework based on long short-term memory neural network. Computer-Aided Civil and Infrastructure Engineering, 2021, 36(4): 504-521 J]

[3] LiuY, RenY-f, WangD-r, et al. . Research on co-seismic displacement of ground surface at Liuhuanggou Bridge of Lanzhou-Xinjiang high-speed railway caused by the 2022 Menyuan Earthquake in Qinghai Province. China Railway Science, 2022, 43(5): 42-50[J]

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

[5] LiY, AstrozaR, ConteJ P, et al. . Nonlinear FE model updating and reconstruction of the response of an instrumented seismic isolated bridge to the 2010 Maule Chile earthquake. Earthquake Engineering & Structural Dynamics, 2017, 46(15): 2699-2716 J]

[6] ZhangY-t, JiangL-z, ZhouW-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. Construction and Building Materials, 2020, 241: 118026 J]

[7] ZhangY-t, JiangL-z, ZhouW-b, et al. . Study of resonance condition of railway bridge subjected to train loads with a four-beam system. Mechanics Based Design of Structures and Machines, 2023, 51(3): 1468-1488 J]

[8] LaiZ-p, JiangL-z, ZhouW-bao. An analytical study on dynamic response of multiple simply supported beam system subjected to moving loads. Shock and Vibration, 2018, 20182149251 J]

[9] YuJ, ZhouW-b, JiangL-zhong. Study on the estimate for seismic response of high-speed railway bridgetrack system. Engineering Structures, 2022, 267114711 J]

[10] YuJ, JiangL-z, ZhouW-b, et al. . Component damage and failure sequence of track-bridge system for high-speed railway under seismic action. Journal of Earthquake Engineering, 2023, 27(3): 656-678 J]

[11] ZhangR-y, ChenZ, ChenS, et al. . Deep long short-term memory networks for nonlinear structural seismic response prediction. Computers and Structures, 2019, 220(C): 55-68 J]

[12] Dang-VuH, NguyenQ D, ChungT, et al. . Frequency-based data-driven surrogate model for efficient prediction of irregular structure’s seismic responses. Journal of Earthquake Engineering, 2022, 26(14): 7319-7336 J]

[13] KrizhevskyA, SutskeverI, HintonG E. ImageNet classification with deep convolutional neural networks. Communications of the ACM, 2017, 60(6): 84-90 J]

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

[15] ZAREMBA W, SUTSKEVER I, VINYALS O. Recurrent neural network regularization [EB/OL]. 2014: arXiv:1409.2329. http://arxiv.org/abs/1409.2329.pdf.

[16] Perez-RamirezC A, Amezquita-SanchezJ P, Valtierra-RodriguezM, et al. . Recurrent neural network model with Bayesian training and mutual information for response prediction of large buildings. Engineering Structures, 2019, 178603-615 J]

[17] SHI Xing-jian, CHEN Zhou-rong, WANG Hao, et al. Convolutional LSTM network: A machine learning approach for precipitation nowcasting [EB/OL]. 2015: arXiv: 1506.04214. http://arxiv.org/abs/1506.04214.pdf.

[18] BhandarkarT, VardaanK, SatishN, et al. . Earthquake trend prediction using long short-term memory RNN. International Journal of Electrical and Computer Engineering (IJECE), 2019, 9(2): 1304 J]

[19] YuJ, ZhouW-b, JiangL-zhong. Response spectra of fitted post-seismic residual track irregularity for high-speed railway. Earthquake Engineering & Structural Dynamics, 2023, 522350-369 J]

[20] HUANG Zhi-heng, XU Wei, YU Kai. Bidirectional LSTM-CRF models for sequence tagging [EB/OL]. 2015: arXiv: 1508.01991. http://arxiv.org/abs/1508.01991.pdf.

[21] ChenY, ChenH-r, ZengH, et al. . Structural optimization design of sinusoidal wavy plate fin heat sink with crosscut by Bayesian optimization. Applied Thermal Engineering, 2022, 213: 118755 J]

[22] DingZ-h, LiJ, HaoHong. Simultaneous identification of structural damage and nonlinear hysteresis parameters by an evolutionary algorithm-based artificial neural network. International Journal of Non Linear Mechanics, 2022, 142103970 J]

[23] ShahriariB, SwerskyK, WangZ-y, et al. . Taking the human out of the loop: A review of Bayesian optimization. Proceedings of the IEEE, 2016, 104(1): 148-175 J]

[24] ElsaidA, El JamiyF, HigginsJ, et al. . Optimizing long short-term memory recurrent neural networks using ant colony optimization to predict turbine engine vibration. Applied Soft Computing, 2018, 73969-991 J]

[25] KavianpourP, KavianpourM, JahaniE, et al. . A CNN-BiLSTM model with attention mechanism for earthquake prediction. The Journal of Supercomputing, 2023, 79(17): 19194-19226 J]

[26] MangalathuS, HwangS H, ChoiE, et al. . Rapid seismic damage evaluation of bridge portfolios using machine learning techniques. Engineering Structures, 2019, 201109785 J]

[27] OhB K, GlisicB, ParkS W, et al. . Neural network-based seismic response prediction model for building structures using artificial earthquakes. Journal of Sound and Vibration, 2020, 468115109 J]