Prediction of Structural Vibration Induced by Subway Operations Using Hybrid Method Based on Improved LSTM and Spectral Analysis
Abstract
:1. Introduction
2. Framework of Proposed Hybrid Method
- (1)
- LSTM Model Improvement
- (2)
- Vibration Prediction by the Hybrid Method
3. Improvement of LSTM Model
3.1. RNNs and the Vanishing Gradient Problem
3.2. The LSTM Model
3.2.1. Memory Cell
3.2.2. Gates in LSTM
3.2.3. Evaluation Metrics
3.3. LSTM Model Improvement
3.3.1. Network Structure Improvement
- (1)
- Replacement of unidirectional LSTM with BiLSTM
- (2)
- Integration of attention mechanism
3.3.2. Parameter Optimization Using DBO Algorithm
3.4. Model Performance Validation
3.4.1. Simulation Signal Validation
- (1)
- Signal characteristics
- (2)
- Prediction results
3.4.2. Real-World Measured Signal Validation
- (1)
- Data collection for subway-induced vibrations
- (2)
- Prediction results
4. Validation of Hybrid Method
4.1. FE Model
4.2. Time-History Analysis
4.2.1. Train Dynamic Loads
4.2.2. Results
4.3. Spectral Analysis
4.3.1. Data Augmentation
4.3.2. Results
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Xu, D.; Zhao, Y.; Liu, H.; Zhu, H. Deformation monitoring of metro tunnel with a new ultrasonic-based system. Sensors 2017, 17, 1758. [Google Scholar] [CrossRef] [PubMed]
- Kurzweil, L.G. Ground-borne noise and vibration from underground rail systems. J. Sound Vib. 1979, 66, 363–370. [Google Scholar] [CrossRef]
- Melke, J. Noise and vibration from underground railway lines: Proposals for a prediction procedure. J. Sound Vib. 1988, 120, 391–406. [Google Scholar] [CrossRef]
- Madshus, C.; Kaynia, A.M. High-speed railway lines on soft ground: Dynamic behavior at critical train speed. J. Sound Vib. 2000, 231, 689–701. [Google Scholar] [CrossRef]
- Bahrekazemi, M. Train-Induced Ground Vibration and Its Prediction. Ph.D. Thesis, Royal Institute of Technology, Stockholm, Sweden, 2004. [Google Scholar]
- Tao, Z.; Moore, J.A.; Sanayei, M.; Wang, Y.; Zou, C. Train-induced floor vibration and structure-borne noise predictions in a low-rise over-track building. Eng. Struct. 2022, 255, 113914. [Google Scholar] [CrossRef]
- Kedia, N.K.; Kumar, A.; Singh, Y. Development of Empirical Relations to Predict Ground Vibrations due to Underground Metro Trains. KSCE J. Civ. Eng. 2023, 27, 251–260. [Google Scholar] [CrossRef]
- Gupta, S.; Degrande, G.; Lombaert, G. Experimental validation of a numerical model for subway induced vibrations. J. Sound Vib. 2009, 321, 786–812. [Google Scholar] [CrossRef]
- Amado-Mendes, P.; Costa, P.A.; Godinho, L.M.; Lopes, P. 2.5D MFS–FEM model for the prediction of vibrations due to underground railway traffic. Eng. Struct. 2015, 104, 141–154. [Google Scholar] [CrossRef]
- Bian, X.; Hu, J.; Thompson, D.; Powrie, W. Pore pressure generation in a poro-elastic soil under moving train loads. Soil Dyn. Earthq. Eng. 2019, 125, 105711. [Google Scholar] [CrossRef]
- Qu, S.; Yang, J.; Zhu, S.; Zhai, W.; Kouroussis, G. A hybrid methodology for predicting train-induced vibration on sensitive equipment in far-field buildings. Transp. Geotech. 2021, 31, 100682. [Google Scholar] [CrossRef]
- Wu, Z.; Zhang, N.; Bi, W.; Liu, J. Application of FEM–BEM–PEM Hybrid Random-Vibration Method on Low-Frequency Structure-Borne Noise Prediction of U-Shaped Girder in Urban Rail Transit. Int. J. Struct. Stab. Dyn. 2024. [Google Scholar] [CrossRef]
- Costa, P.A.; Calçada, R.; Cardoso, A.S. Track–ground vibrations induced by railway traffic: In-situ measurements and validation of a 2.5D FEM-BEM model. Soil Dyn. Earthq. Eng. 2012, 32, 111–128. [Google Scholar] [CrossRef]
- Liu, W.; Wu, Z.; Li, C.; Xu, L. Prediction of ground-borne vibration induced by a moving underground train based on excitation experiments. J. Sound Vib. 2022, 523, 116728. [Google Scholar] [CrossRef]
- He, C.; Zhou, S.; Di, H.; Zhang, X. An efficient prediction model for vibrations induced by underground railway traffic and experimental validation. Transp. Geotech. 2021, 31, 100646. [Google Scholar] [CrossRef]
- Colaço, A.; Castanheira-Pinto, A.; Costa, P.A.; Ruiz, J.F. Combination of experimental measurements and numerical modelling for prediction of ground-borne vibrations induced by railway traffic. Constr. Build. Mater. 2022, 343, 127928. [Google Scholar] [CrossRef]
- Shu, J.; Yu, H.; Liu, G. DF-CDM: Conditional diffusion model with data fusion for bridge dynamic response reconstruction. Mech. Syst. Signal Process. 2024, 222, 111783. [Google Scholar] [CrossRef]
- Wang, S.; Lin, S.; Yang, R. A lightweight convolutional neural network for multipoint displacement measurements on bridge structures. Nonlinear Dyn. 2024, 112, 11745–11763. [Google Scholar] [CrossRef]
- Sun, R.; Wang, S.; Li, M.; Zhu, Y. An algorithm for large-span flexible bridge pose estimation and multi-key point vibration displacement measurement. Measurement 2024, 240, 115582. [Google Scholar] [CrossRef]
- Wang, S.; He, J.; Fan, J.; Sun, P.; Wang, D. A time-domain method for free vibration responses of an equivalent viscous damped system based on a complex damping model. J. Low Freq. Noise Vib. Act. Control. 2023, 42, 1531–1540. [Google Scholar] [CrossRef]
- He, Y.; Zhang, Y.; Yao, Y.; He, Y.; Sheng, X. Review on the Prediction and Control of Structural Vibration and Noise in Buildings Caused by Rail Transit. Buildings 2023, 13, 2310. [Google Scholar] [CrossRef]
- Liang, R.; Liu, W.; Li, C.; Li, W.; Wu, Z. A novel efficient probabilistic prediction approach for train-induced ground vibrations based on transfer learning. J. Vib. Control 2024, 30, 576–587. [Google Scholar] [CrossRef]
- Abbas, N.; Umar, T.; Salih, R.; Akbar, M.; Hussain, Z.; Haibei, X. Structural Health Monitoring of Underground Metro Tunnel by Identifying Damage Using ANN Deep Learning Auto-Encoder. Appl. Sci. 2023, 13, 1332. [Google Scholar] [CrossRef]
- Siłka, J.; Wieczorek, M.; Woźniak, M. Recurrent neural network model for high-speed train vibration prediction from time series. Neural Comput. Applic 2022, 34, 13305–13318. [Google Scholar] [CrossRef]
- Zhang, Y.; Xie, X.; Li, H.; Zhou, B.; Wang, Q.; Shahrour, I. Subway tunnel damage detection based on in-service train dynamic response, variational mode decomposition, convolutional neural networks and long short-term memory. Autom. Constr. 2022, 139, 104293. [Google Scholar] [CrossRef]
- Xin, T.; Yang, Y.; Zheng, X.; Lin, J.; Wang, S.; Wang, P. Time Series Recovery Using Adjacent Channel Data Based on LSTM: A Case Study of Subway Vibrations. Appl. Sci. 2022, 12, 11497. [Google Scholar] [CrossRef]
- Li, S.; Qiu, Y.; Jiang, J.; Wang, H.; Nan, Q.; Sun, L. Identification of Abnormal Vibration Signal of Subway Track Bed Based on Ultra-Weak FBG Sensing Array Combined with Unsupervised Learning Network. Symmetry 2022, 14, 1100. [Google Scholar] [CrossRef]
- Jie, L.; Fang, L.; Weiping, X.; Xiaoxiong, J. Track vibration sequence anomaly detection algorithm based on LSTM. Adv. Struct. Eng. 2023, 26, 1682–1695. [Google Scholar] [CrossRef]
- Hochreiter, S.; Schmidhuber, J. Long short-term memory. Neural Comput. 1997, 9, 1735–1780. [Google Scholar] [CrossRef] [PubMed]
- Hao, X.; Liu, Y.; Pei, L.; Li, W.; Du, Y. Atmospheric Temperature Prediction Based on a BiLSTM Attention Model. Symmetry 2022, 14, 2470. [Google Scholar] [CrossRef]
- Kim, T.Y.; Cho, S.B. Predicting residential energy consumption using CNN-LSTM neural networks. Energy 2019, 182, 72–81. [Google Scholar] [CrossRef]
- Shen, B.; Liu, Y.; Chen, H.; Yu, Y. Dung Beetle Optimizer: A New Swarm Intelligence Algorithm for Global Optimization. Appl. Soft Comput. 2022, 130, 109703. [Google Scholar]
- Wang, D.; Liang, Q.; Zhou, Y.; Li, J.; Ke, X.; Ling, H.; Ding, C. Study on vertical shaking table model test of super high-rise structure over subway: Engineering background and model verification. Build. Struct. 2022, 52, 1–8, 28. (In Chinese) [Google Scholar]
- Pan, C.; Pande, G.N. Preliminary deterministic finite element study on a tunnel driven in loess subjected to train loading. China Civ. Eng. J. 1984, 17, 19–28. (In Chinese) [Google Scholar]
- Lai, J.; Zhou, H.; Wang, K.; Qiu, J.; Wang, L.; Wang, J.; Feng, Z. Shield-driven induced ground surface and Ming Dynasty city wall settlement of Xi’ an metro. Tunn. Undergr. Space Technol. 2020, 97, 103220. [Google Scholar] [CrossRef]
Scenario | Model | RMSE | MAE | R2 |
---|---|---|---|---|
Scenario 1 | LSTM | 0.20265 | 0.16934 | 95.5706% |
BiLSTM | 0.19892 | 0.16322 | 95.7329% | |
DBO–BiLSTM–attention | 0.08936 | 0.07265 | 99.1386% | |
Scenario 2 | LSTM | 0.22865 | 0.19105 | 94.4016% |
BiLSTM | 0.25781 | 0.2053 | 92.8830% | |
DBO–BiLSTM–attention | 0.14098 | 0.11355 | 97.8718% | |
Scenario 3 | LSTM | 0.26557 | 0.21639 | 92.7666% |
BiLSTM | 0.2685 | 0.21663 | 92.6061% | |
DBO–BiLSTM–attention | 0.20163 | 0.16431 | 95.8305% | |
Scenario 4 | LSTM | 0.29656 | 0.23619 | 90.9074% |
BiLSTM | 0.33442 | 0.26141 | 91.0375% | |
DBO–BiLSTM–attention | 0.25766 | 0.20612 | 94.1024% |
Model | RMSE | MAE |
---|---|---|
LSTM | 0.00240 | 0.00187 |
BiLSTM | 0.00122 | 0.00095 |
DBO–BiLSTM–attention | 0.00078 | 0.00060 |
Component | Unit Weight (KN/m3) | Modulus of Elasticity (MPa) | Cohesion Force (kPa) | Interior Friction Angle (°) | Poisson Ratio |
---|---|---|---|---|---|
Soil | 15 | 10 | 16.1 | 26.3 | 0.15 |
Structure | 24 | 30,000 | - | - | 0.2 |
Lining | 24 | 36,500 | - | - | 0.167 |
Unilateral Wheel Weight, A0/kN | Unsprung Mass, m/kg | Geometric Irregularity Vector Height, αi/mm | Basic Vibration Wavelength, Li/m | ||||
---|---|---|---|---|---|---|---|
i | i | i | |||||
70 | 750 | 3.5 | 0.4 | 0.08 | 8 | 2 | 0.5 |
Fs | RMSE (×10−4) | MAE (×10−4) | R2 |
---|---|---|---|
100 Hz | 3.2214 | 2.6347 | 97.789% |
200 Hz | 2.3334 | 1.9512 | 98.856% |
300 Hz | 1.7433 | 1.4141 | 99.376% |
Scenarios | Excitation Signal | Point 2# | Point 3# | Point 4# |
---|---|---|---|---|
Scenario 1 | baseline | 0.02680 | 0.04978 | 0.08739 |
original | 0.01833 | 0.03673 | 0.07216 | |
augmented | 0.02242 | 0.04293 | 0.07844 | |
Scenario 2 | baseline | 0.02790 | 0.05297 | 0.10049 |
original | 0.02714 | 0.04733 | 0.08756 | |
augmented | 0.02756 | 0.04805 | 0.08860 | |
Scenario 3 | baseline | 0.02980 | 0.06636 | 0.12235 |
original | 0.03856 | 0.06723 | 0.10953 | |
augmented | 0.03398 | 0.06521 | 0.11598 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Liu, X.; Xu, G.; Ye, X. Prediction of Structural Vibration Induced by Subway Operations Using Hybrid Method Based on Improved LSTM and Spectral Analysis. Symmetry 2025, 17, 75. https://doi.org/10.3390/sym17010075
Liu X, Xu G, Ye X. Prediction of Structural Vibration Induced by Subway Operations Using Hybrid Method Based on Improved LSTM and Spectral Analysis. Symmetry. 2025; 17(1):75. https://doi.org/10.3390/sym17010075
Chicago/Turabian StyleLiu, Xiaolin, Guoyuan Xu, and Xijun Ye. 2025. "Prediction of Structural Vibration Induced by Subway Operations Using Hybrid Method Based on Improved LSTM and Spectral Analysis" Symmetry 17, no. 1: 75. https://doi.org/10.3390/sym17010075
APA StyleLiu, X., Xu, G., & Ye, X. (2025). Prediction of Structural Vibration Induced by Subway Operations Using Hybrid Method Based on Improved LSTM and Spectral Analysis. Symmetry, 17(1), 75. https://doi.org/10.3390/sym17010075