Intelligent Prediction of the Horizontal Deformation During the Excavation Process Based on Particle Swarm Optimisation and Support Vector Machine

Yu Zhang; Chen Zhang; Zhiduo Zhu; Liu Yang; Hao Tang

doi:10.7250/bjrbe.2025-20.657

Intelligent Prediction of the Horizontal Deformation During the Excavation Process Based on Particle Swarm Optimisation and Support Vector Machine

Authors

Yu Zhang School of Transportation, Southeast University, Nanjing, Jiangsu Province 211189, China and Jiangsu Key Laboratory of Low Carbon and Sustainable Geotechnical Engineering, Jiangsu Province 211189, China
Dr. Chen Zhang School of Transportation, Southeast University, Nanjing, Jiangsu Province 211189, China and Jiangsu Key Laboratory of Low Carbon and Sustainable Geotechnical Engineering, Jiangsu Province 211189, China
Professor Zhiduo Zhu School of Transportation, Southeast University, Nanjing, Jiangsu Province 211189, China and Jiangsu Key Laboratory of Low Carbon and Sustainable Geotechnical Engineering, Jiangsu Province 211189, China
Dr. Liu Yang School of Transportation, Southeast University, Nanjing, Jiangsu Province 211189, China and Jiangsu Key Laboratory of Low Carbon and Sustainable Geotechnical Engineering, Jiangsu Province 211189, China
Postgraduate Hao Tang School of Transportation, Southeast University, Nanjing, Jiangsu Province 211189, China and Jiangsu Key Laboratory of Low Carbon and Sustainable Geotechnical Engineering, Jiangsu Province 211189, China

DOI:

https://doi.org/10.7250/bjrbe.2025-20.657

Keywords:

deformation prediction, finite element simulation, highway tunnel pit, particle swarm optimisation, support vector machine

Abstract

The reasonable selection of soil layer parameters relates to the accurate prediction of the horizontal deformation of the foundation pit, which is the main problem of highway tunnel pit design. The aim of this paper is to obtain suitable soil layer parameters for finite element simulation of highway tunnel based on the particle swarm optimisation (PSO) and support vector machine (SVM). First, considering the overfitting problem of SVM in the inversion of soil parameters, the PSO was used to improve the SVM model. Second, the PSO- SVM model was trained with 25 groups of elastic modulus as input values and deformation as output values. Then, according to the monitored deformation data, the soil parameters were inverted by PSO-SVM model. Finally, the inversion parameters were substituted into the finite element model to predict the horizontal deformation of the foundation pit. The results showed that based on the inversion parameters of PSO-SVM model, the finite element method had a good accuracy in predicting the horizontal deformation of the foundation pit. The average relative error between the predicted value and monitored value was 2.95%. Therefore, the application of the parameter inversion method based on PSO-SVM had a reference value for tunnel pit design.

Supporting Agencies

Jiangsu Key Laboratory of Low Carbon and Sustainable Geotechnical Engineering

References

Amini, M., & Ardestani, A. (2019). Stability analysis of the North-Eastern slope of Daralou copper open pit mine against a secondary toppling failure. Engineering Geology, 249, 89−101. https://doi.org/10.1016/j.enggeo.2018.12.022 DOI: https://doi.org/10.1016/j.enggeo.2018.12.022

Chen, B., Fu, X., Guo, Y.X., & Shao, C.F. (2015). Zoning elastic modulus inversion for high arch dams based on the PSOGSA-SVM method. Advanced in Civil Engineering, 145–156. https://doi.org/10.1155/2019/7936513 DOI: https://doi.org/10.1155/2019/7936513

Cheng, Q.S., Yang Z.S., Qin S.W., Zhang, L., Miao, Q., & Zhang, Y. (2022). Application of soil parameters inversion based on PSO-MLSSVR in deep foundation pit engineering. Journal of Engineering Geology, 30(2), 520–532. https://doi.org/10.13544/j.cnki.jeg.2021-0143

Feng, T.G., Wang, C.R., Zhang, J., Wang, B., & Jin Y.F. (2022). An improved artificial bee colony-random forest (IABC-RF) model for predicting the tunnel deformation due to an adjacent foundation pit excavation. Underground Space, 7(4), 514–527. https://doi.org/10.1016/j.undsp.2021.11.004 DOI: https://doi.org/10.1016/j.undsp.2021.11.004

Gao, D.F., Zhou, A., Feng, Y.T., et al. (2020). Deformation monitoring and back analysis of soil parameters in the cut and cover installation of Taihu tunnel. Soil Engineering and Foundation, 34(3), 385–390.

Gioda, G, & Maier, G. (1981). Direct search solution of an inverse problem in elastoplasticity: identification angle and in-situ stress by pressure tunnel tests. International Journal of Rock Mechanics and Mining Sciences and Geomechanics Abstracts, 18(2), 1823–1848. https://doi.org/10.1002/nme.1620151207 DOI: https://doi.org/10.1016/0148-9062(81)90749-X

Guo, Q., Li, G.Q., Deng, C., Wu, J., Chen, Z.Y., & Xu, X.B. (2020). Rolling bearing fault diagnosis based on wavelet packet transform and convolutional neural network. Applied Sciences, 10(3), Article 770. https://doi.org/10.3390/app10030770 DOI: https://doi.org/10.3390/app10030770

Jiang, A.N., Wang, S.Y., & Tang S.L. (2011). Feedback analysis of tunnel construction using a hybrid arithmetic based on Support Vector Machine and Particle Swarm Optimisation. Automation in Construction, 20(4), 482–489. https://doi.org/10.1016/j.autcon.2010.11.016 Jiang, P. (2013). Back analysis method of foundation pit soil mechanical parameters based on DOI: https://doi.org/10.1016/j.autcon.2010.11.016

GA-BP neural network. Journal of Applied Sciences, 13(15), 3099–3103. https://doi.org/10.3923/jas.2013.3099.3103 DOI: https://doi.org/10.3923/jas.2013.3099.3103

Kavanagh, K.T., & Clough, R.W. (1971). Finite element applications in the characterization of elastic solids. International Journal of Solids & Structures, 7(1), 11–23. https://doi.org/10.1016/0020-7683(71)90015-1 DOI: https://doi.org/10.1016/0020-7683(71)90015-1

Kirsten, H.A.D. (1976). Determination of rock mass elastic moduli by back analysis of deformation measurement. Proc. Symp. on Exploration for Rock Eng. Johannesburg, 1154–1160.

Li, J., Zhou, S.C., Wang, L., et al. (2017). Methods for calculating the elastic modulus in numerical analysis of soft soil area. China Water Transport, 17(5), 324–328.

Li, S., Yuan, Z.G., Wang, C., et al. (2018). Optimization of support vector machine parameters based on group intelligence algorithm. CAAI Transactions on Intelligent Systems, 13(1), 70–84.

Li, Y.J., Xue, Y.D., Yue, L., & Chen B. (2015). Displacement prediction of deep foundation pit based on genetic algorithms and BP neural Network. Chinese Journal of Underground Space and Engineering, 11(S2), 741–749.

Li, B.Y., & Sima, J. (2021). Inverse analysis of horizontal displacement of foundation pit based on MEC-BP neural network. J. Railw. Sci. Eng., 18, 1764–1772. https://doi.org/10.19713/j.cnki.43-1423/u.t20210086

Li, H., Zhao, Z., & Du, X. (2022). Research and application of deformation prediction model for deep foundation pit based on LSTM. Wireless Communications and Mobile Computing, 463–478. https://doi.org/10.1155/2022/9407999 DOI: https://doi.org/10.1155/2022/9407999

Li, Q., Cheng, F., & Zhang, X. (2024). Numerical simulation and deformation prediction of deep pit based on PSO-BP neural network inversion of soil parameters. Sensors, 24(10), Article 2959. https://doi.org/10.3390/s24102959 DOI: https://doi.org/10.3390/s24102959

Ling, T.H., Qin, J., Song, Q., & Hua, F. (2020). Intelligent displacement inverse analysis method based on improved particle swarm optimization and neural network and its application. J. Railw. Sci. Eng., 17, 2181–2190. https://doi.org/10.19713/j.cnki.43-1423/u.T20191119

Liu, H., Zhang, H.Q., & Liu, B. (2014). A prediction method for the deformation of excavations based on the particle Swarm optimization neural network. Journal of Jilin University (Earth Science Edition), 5, 1609−1614. https://doi.org/10.13278/j.cnki.jjuese.201405204

Liu, Q., Yang, C.Y., & Lin, L. (2021). Deformation prediction of a deep foundation pit based on the combination model of wavelet transform and Gray BP neural network. Mathematical Problems in Engineering, 102–115. https://doi.org/10.1155/2021/2161254 DOI: https://doi.org/10.1155/2021/2161254

Ma, H.H., Yuan, S., Zhang, Z., Tian, Y.H., & Dong, S.S. (2023). Application of soil parameter inversion method based on BP neural network in foundation pit deformation prediction. Appl. Geophys., 20, 299–309. https://doi.org/10.1007/s11770-023-1029-8 DOI: https://doi.org/10.1007/s11770-023-1029-8

Ruan, Y.F., Gao, C.Q., Liu, K.W., et al. (2019). Inversion of rock and soil mechanics parameters based on particle swarm optimization wavelet support vector machine. Rock and Soil Mechanics, 40(9), 3662–3669. https://doi.org/10.16285/j.rsm.2018.1055

Ruan, Y.F., Yu, D.X., Wu, L., et al. (2021). DE-GWO algorithm to optimize SVM inversion mechanical parameters of soft soil. Chinese Journal of Geotechnical Engineering, 43(S1), 166–170.

Sha, Y.H., & Chen, Z.J. (2017). Application of PSO-SVM algorithm in soil parameters inversion.

Site Investigation Science and Technology, 3, 45–49.

Shen, Y.S., Wang, P., Li, M.P. & Mei, Q.W. (2019). Application of subway foundation pit engineering risk assessment: A case study of Qingdao rock area, China. KSCE J. Civ. Eng., 23(11), 4621–4630. https://doi.org/10.1007/s12205-019-1854-8 DOI: https://doi.org/10.1007/s12205-019-1854-8

Wang, Z.L., Li, Y.C., & Shen, R.F. (2007). Correction of soil parameters in calculation of embankment settlement using a BP network back-analysis model. Engineering Geology, 91(2–4), 168–177. https://doi.org/10.1016/j.enggeo.2007.01.007 DOI: https://doi.org/10.1016/j.enggeo.2007.01.007

Wang, Z.Y., Yang, Z.F., & Wang, S.J. (1998). A review on inverse analyses of displacements in rock mechanics. Advances in Mechanics, 28(4), 488–498.

Xiao, M.Q., Liu, H., Peng, C.S., et al. (2017). Back analysis of deep soft soil parameters based on neural network. Chinese Journal of Underground Space and Engineering, 13(1), 279–286.

Xu, Y., Zhao, Y., Jiang, Q., Sun, J., Tian, C., & Jiang, W. (2024). Machine-learning-based deformation prediction method for deep foundation-pit enclosure structure. Applied Sciences, 14(3), Article 1273. https://doi.org/10.3390/app14031273 DOI: https://doi.org/10.3390/app14031273

Yang, W., & Li, Q.Q. (2004). Survey on particle Swarm optimization algorithm. Strategic Study of CAE, 6(5), 87–94.

Zhang, Z.H., Zhou, C.B., Xiao, Z., & Miao, G. (2013). Sensitivity analysis and orthogonal backward analysis of soil parameters for subway tunnel. Journal of Central South University (Science and Technology), 44(6), 2488–2493.

Zhao, J., Li, W., & Peng, Y. (2023). Analysis on intelligent deformation prediction of deep foundation pit with internal support based on optical fiber monitoring and HSS model. Front. Mater., 10, Article 1231303. https://doi.org/10.3389/fmats.2023.1231303 DOI: https://doi.org/10.3389/fmats.2023.1231303

Zheng, G., Du, Y.M., Diao, Y.N., Deng, X., Zhu, G.P., & Zhang, L.M. (2016). Influenced zones for deformation of existing tunnels adjacent to excavations. Chinese Journal of Geotechnical Engineering. 38(4), 599–612. https://doi.org/10.11779/CJGE201604003

Zhou, A., Wang, B., Li, J.T., Zhou, X., & Xia, W.J. (2022). Long-term stability analysis and deformation prediction of soft soil foundation pit in Taihu tunnel. Journal of ZheJiang University (Engineering Science), 56(4), 692–701.

Zhou, Y., Su, W. J., Ding, L.Y., Luo, H.B., & Peter, E.D.L. (2017). Predicting safety risks in deep foundation pits in subway infrastructure projects: Support Vector Machine approach. Journal of Computing in Civil Engineering, 31(5), 292–300. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000700 DOI: https://doi.org/10.1061/(ASCE)CP.1943-5487.0000700