Application of a Bi-Mamba Model for Railway Subgrade Settlement Prediction During Pipe-Jacking Tunneling
Source abstract
Abstract
To explore a more accurate prediction method for subgrade settlement induced by underpass construction, this study takes the existing railway project of Ningbo Yuanyi Road underpass as a case to construct a subgrade settlement prediction model based on the Mamba neural network. Using monitoring data collected using on-site automated monitoring robots as the data foundation, the prediction results of the improved transformer, long short-term memory (LSTM), time-series dense encoder (Tide), and decomposition-linear (Dlinear) neural networks are compared. The research results show that the Mean Squared Error (MSE) and Mean Absolute Error (MAE) of the proposed Bi-Mamba model are 0.279 and 0.276, respectively, demonstrating higher prediction accuracy than comparative models such as iTransformer and LSTM. Additionally, ablation experiments verify that the attention gating module in the model reduces the MSE by 9.1%, serving as a key component for improving accuracy. This study provides an advanced data-driven prediction method for subgrade settlement forecasting, offering technical references for similar engineering projects.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Geotechnical Engineering and Analysis · Geotechnical Engineering and Underground Structures · Civil and Geotechnical Engineering Research
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Civil Engineering, Central South University, Changsha 410075, China
References (29)
Show source-provided references
1. Risk assessment for shield tunneling beneath buildings based on interval improved TOPSIS method and FAHP method
2. Analysis of the settlement of an existing tunnel induced by shield tunneling underneath10.1016/j.tust.2018.06.035 ↗
3. The Prediction of Ground Settlement of a Box Culvert Jacked Under the Action of an Ultra-Shallow Buried Pipe Curtain10.1007/s13369-021-06417-6 ↗
4. Li, J., Yan, B., and Shi, Y. (2013, January 5–7). The monitoring and analysis of surface subsidence of Soft soil rock large section of subway tunnel shield construction. Proceedings of the 2nd International Conference on Energy Materials and Material Application, Changsha, China.
5. Ground movements due to the construction of cut-and-cover structures and slurry shield tunnel of the Cairo Metro10.1016/S0886-7798(99)00044-9 ↗
6. Stability of plane strain tunnel headings in soils with tensile strength cut-off10.1016/j.tust.2019.103138 ↗
7. Ding, D., Yang, X., Lu, W., Liu, W., and Yan, M. (November, January 31). Numerical Analysis on Deformation of Adjacent Structures due to Metro Station Construction by Enlarging Large-diameter Shield Tunnel. Proceedings of the International Conference on Civil Engineering and Building Materials, Kunming, China.
8. Support vector machine model of settlement prediction of road soft foundation
9. Settlement prediction using support vector machine (SVM)-based compressibility models: A case study10.1007/s40999-019-00421-6 ↗
10. Artificial neural networks analysis of São Paulo subway tunnel settlement data10.1016/j.tust.2007.07.002 ↗
11. Prediction of shield tunneling-induced ground settlement using machine learning techniques10.1007/s11709-019-0561-3 ↗
12. Surface settlement prediction of subway tunnels constructed by step method based on VMD-GRU
13. Hu, Y., Gu, C., Meng, Z., Shao, C., and Min, Z. (2022). Prediction for the Settlement of Concrete Face Rockfill Dams Using Optimized LSTM Model via Correlated Monitoring Data. Water, 14.10.3390/w14142157 ↗
14. Prediction of ground surface settlement by shield tunneling using XGBoost and Bayesian Optimization10.1016/j.engappai.2022.105020 ↗
15. Prediction of maximum surface settlement caused by earth pressure balance (EPB) shield tunneling with ANN methods10.1016/j.sandf.2018.11.005 ↗
16. Determination of earth pressure balance tunnel-related maximum surface settlement: A multivariate adaptive regression splines approach10.1007/s10064-016-0937-8 ↗
17. Wang, C., Tsepa, O., Ma, J., and Wang, B. (2024). Graph-mamba: Towards long-range graph sequence modeling with selective state spaces. arXiv.
18. Rs 3 mamba: Visual state space model for remote sensing image semantic segmentation10.1109/LGRS.2024.3414293 ↗
19. Rsmamba: Remote sensing image classification with state space model
20. Rs-mamba for large remote sensing image dense prediction
21. Mambads: Near-surface meteorological field downscaling with topography constrained selective state space modeling10.1109/TGRS.2024.3496895 ↗
22. Liu, Y., Hu, T., Zhang, H., Wu, H., Wang, S., Ma, L., and Long, M. (2023). iTransformer: Inverted Transformers Are Effective for Time Series Forecasting. arXiv.
23. Gu, A., and Dao, T. (2023). Mamba: Linear-time sequence modeling with selective state spaces. arXiv.
24. Is mamba effective for time series forecasting?10.1016/j.neucom.2024.129178 ↗
25. Wang, F., Jiang, M., Qian, C., Yang, S., Li, C., Zhang, H., Wang, X., and Tang, X. (2017, January 21–26). Residual attention network for image classification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.683 ↗
26. Raffel, C., and Ellis, D.P.W. (2015). Feed-forward networks with attention can solve some long-term memory problems. arXiv.
27. Li, Z., Peng, Y., Li, J., and Tang, Z. (2024). Composite Foundation Settlement Prediction Based on LSTM-Transformer Model for CFG. Appl. Sci., 14.10.3390/app14020732 ↗
28. Das, A., Kong, W., Leach, A., Mathur, S.K., Sen, R., and Yu, R. (2023). Long-term forecasting with tide: Time-series dense encoder. Trans. Mach. Learn. Res.
29. Are transformers effective for time series forecasting?