Abstract
When the new metro line crosses the existing metro line, its construction stage will have an adverse impact on the existing metro line, that is, settlement. In order to ensure the safety of metro line operation, it is necessary to obtain the variation law of settlement. In this paper, the four different machine learning methods (Radial Basis Function (RBF) neural network, the Back Propagation Neural Network (BPNN), Generalized Regression Neural Network (GRNN) and Gaussian Prior (GP) regression model) are established for settlement prediction. In which, the settlement data set is shared in the https://pan.baidu.com/s/1UuGnobkUljndzeGutlfdlg (Password: 1029). Based on the structural health monitoring (SHM) data of Nanjing Metro, the prediction performance of the RBF is the worst; In addition, the robustness of the RBF and BPNN is very poor, that is, for the settlement of different monitoring points, the required prediction model structure is also different, which will lead to the RBF and BPNN cannot be widely used in settlement prediction. On the contrary, the GRNN and GP prediction models have good robustness, in which the GP prediction model has the best robustness, but the GRNN model has poor prediction performance. Therefore, the GP model is recommended to predict the settlement of Nanjing metro in this paper.
Similar content being viewed by others
Data availability
Some or all data, models, or code that support the findings of this study are available from the corresponding author upon reasonable request. Data set: https://pan.baidu.com/s/1UuGnobkUljndzeGutlfdlg (password: 1029).
References
Alam MS, Gazder U (2020) Shear strength prediction of FRP reinforced concrete members using generalized regression neural network. Neural Comput Appl 32(10):6151–6158
Bajaj G, Singh P (2019) Understanding preferences of Delhi metro users using choice-based conjoint analysis. IEEE Trans Intell Transp Syst 22(1):384–393
Baziar MH, Saeedi Azizkandi A, Kashkooli A (2015) Prediction of pile settlement based on cone penetration test results: an ANN approach. KSCE J Civil Eng 19(1):98–106
Bullock Z, Karimi Z, Dashti S, Porter K, Liel AB, Franke KW (2019) A physics-informed semi-empirical probabilistic model for the settlement of shallow-founded structures on liquefiable ground. Géotechnique 69(5):406–419
Chen C, Liu Z, Wan S, Luan J, Pei Q (2020) Traffic flow prediction based on deep learning in internet of vehicles. IEEE Trans Intell Transp Syst 22(6):3776–3789
Chen S, Xiang Y (2006) A procedure for theoretical estimation of dewatering-induced pile settlement. Comput Geotech 33(4–5):278–282
Dasgupta S, Wheeler D, Khaliquzzaman M, Huq M (2021) Siting priorities for congestion-reducing projects in Dhaka: a spatiotemporal analysis of traffic congestion, travel times, air pollution, and exposure vulnerability. Int J Sustain Transp 16(12):1078–1096
Deng HS, Fu HL, Yue S, Huang Z, Zhao YY (2022) Ground loss model for analyzing shield tunneling-induced surface settlement along curve sections. Tunn Undergr Space Technol 119:104250
Ding, Y, Ye, XW, Guo Y (2023d) Wind load assessment with the JPDF of wind speed and direction based on SHM data. Structures 47(1):2074–2080
Ding Y, Ye, XW, Guo Y (2023b) A multistep direct and indirect strategy for predicting wind direction based on the EMD-LSTM model. Structural Control and Health Monitoring 4950487
Ding Y, Ye, XW, Guo Y, Zhang R, Ma Z (2023c) Probabilistic method for wind speed prediction and statistics distribution inference based on SHM data-driven. Probabilistic Engineering Mechanics 103475
Duan Y, Tan YJ (2006) On condition number of meshless collocation method using radial basis functions. Appl Math Comput 172(1):141–147
Han B, Geng F, Dai S, Gan G, Liu S, Yao L (2020) Statistically optimized back-propagation neural-network model and its application for deformation monitoring and prediction of concrete-face rockfill dams. J Perform Constr Facil 34(4):04020071
Harpham C, Dawson CW (2006) The effect of different basis functions on a radial basis function network for time series prediction: a comparative study. Neurocomputing 69(16–18):2161–2170
Jagan J, Samui P, Kim D (2019) Reliability analysis of simply supported beam using GRNN, ELM and GPR. Struct Eng Mech 71(6):000–000
Lai J, Qiu J, Feng Z, Chen J, Fan H (2016) Prediction of soil deformation in tunnelling using artificial neural networks. Comput Intell Neurosci 2016:6708183
Li H (2020) Analysis on the construction of sports match prediction model using neural network. Soft Comput 24(11):8343–8353
Li B, Ding J, Yin Z, Li K, Zhao X, Zhang L (2021) Optimized neural network combined model based on the induced ordered weighted averaging operator for vegetable price forecasting. Expert Syst Appl 168:114232
Liu J, Qi T, Wu Z (2012) Analysis of ground movement due to metro station driven with enlarging shield tunnels under building and its parameter sensitivity analysis. Tunn Undergr Space Technol 28:287–296
Mazek SA (2014) Evaluation of surface displacement equation due to tunneling in cohesionless soil. Geomech Eng 7(1):55–73
Powell MJ (1992) The theory of radial basis function approximation in 1990. Advances in numerical analysis. Springer, pp 105–210
Samui P (2008) Support vector machine applied to settlement of shallow foundations on cohesionless soils. Comput Geotech 35(3):419–427
Wan HP, Ni YQ (2018) Bayesian modeling approach for forecast of structural stress response using structural health monitoring data. J Struct Eng 144(9):04018130
Wan HP, Ni YQ (2019) Bayesian multi-task learning methodology for reconstruction of structural health monitoring data. Struct Health Monit 18(4):1282–1309
Wang F, Gou B, Qin Y (2013) Modeling tunneling-induced ground surface settlement development using a wavelet smooth relevance vector machine. Comput Geotech 54:125–132
Wang F, Gou B, Zhang Q, Qin Y, Li B (2016) Evaluation of ground settlement in response to shield penetration using numerical and statistical methods: a metro tunnel construction case. Struct Infrastruct Eng 12(9):1024–1037
Wang W, Tang R, Li C, Liu P, Luo L (2018) A BP neural network model optimized by mind evolutionary algorithm for predicting the ocean wave heights. Ocean Eng 162:98–107
Wang Z, Zhang KW, Wei G, Li B, Li Q, Yao WJ (2018) Field measurement analysis of the influence of double shield tunnel construction on reinforced bridge. Tunn Undergr Space Technol 81:252–264
Wu HN, Shen SL, Yang J (2017) Identification of tunnel settlement caused by land subsidence in soft deposit of Shanghai. J Perform Constr Facil 31(6):04017092
Ding, Y, Ye, XW, Guo Y (2023a) Data set from wind temperature humidity and cable acceleration monitoring of the Jiashao bridge Journal of Civil. Structural Health Monitoring 13(2–3):579–589
Ye XW, Ding Y, Wan HP (2019) Machine learning approaches for wind speed forecasting using long-term monitoring data: a comparative study. Smart Struct Syst 24(6):733–744
Ye XW, Ding Y, Wan HP (2020) Statistical evaluation of wind properties based on long-term monitoring data. J Civil Struct Heal Monit 10(5):987–1000
Ye XW, Ding Y, Wan HP (2021) Probabilistic forecast of wind speed based on Bayesian emulator using monitoring data. Struct Control Health Monit 28(1):e2650
Zemouri R, Zerhouni N (2012) Autonomous and adaptive procedure for cumulative failure prediction. Neural Comput Appl 21(2):319–331
Zhang E, Hou L, Shen C, Shi Y, Zhang Y (2015) Sound quality prediction of vehicle interior noise and mathematical modeling using a back propagation neural network (BPNN) based on particle swarm optimization (PSO). Meas Sci Technol 27(1):015801
Zhang P, Wu HN, Chen RP, Chan TH (2020) Hybrid meta-heuristic and machine learning algorithms for tunneling-induced settlement prediction: a comparative study. Tunn Undergr Space Technol 99:103383
Zhang L, Wu X, Ji W, AbouRizk SM (2017) Intelligent approach to estimation of tunnel-induced ground settlement using wavelet packet and support vector machines. J Comput Civil Eng 31(2):04016053
Zhou Z, Chen Y, Liu Z, Miao L (2020) Theoretical prediction model for deformations caused by construction of new tunnels undercrossing existing tunnels based on the equivalent layered method. Comput Geotech 123:103565
Zhou X, Shi P, Xu X, Liu W (2021) Theoretical prediction models for ground settlement during box jacking. Mech Adv Mater Struct 29(26):5588–5595
Acknowledgements
This work was supported by the Scientific Research Project of Zhejiang Provincial Department of Education (Grant No. Y202248682), the Educational Science Planning Project of Zhejiang Province (Grant No. 2023SCG222), and the Natural Science Foundation of China (Grant nos. 51968022 and 52163034).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Ding, Y., Hang, D., Wei, YJ. et al. Settlement prediction of existing metro induced by new metro construction with machine learning based on SHM data: a comparative study. J Civil Struct Health Monit 13, 1447–1457 (2023). https://doi.org/10.1007/s13349-023-00714-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13349-023-00714-4