Geomechanics and Engineering

  • 제38권5호
  • /
  • Pages.517-528
  • /
  • 2024
  • /
  • 2005-307X(pISSN)
  • /
  • 2092-6219(eISSN)
테크노프레스 (Techno-Press)
권호 표지
DOI QR코드

DOI QR Code

Investigation of pile group response to adjacent twin tunnel excavation utilizing machine learning

  • Su-Bin Kim (Department of Civil Engineering, Seoul National University of Science and Technology) ;
  • Dong-Wook Oh (Department of Railroad Construction and Safety Engineering, Dongyang University) ;
  • Hyeon-Jun Cho (Department of Civil Engineering, Seoul National University of Science and Technology) ;
  • Yong-Joo Lee (Department of Civil Engineering, Seoul National University of Science and Technology)
  • 투고 : 2023.12.04
  • 심사 : 2024.02.02
  • 발행 : 2024.09.10
⟨ 이전 논문 다음 논문 ⟩

초록

For numerous tunnelling projects implemented in urban areas due to limited space, it is crucial to take into account the interaction between the foundation, ground, and tunnel. In predicting the deformation of piled foundations and the ground during twin tunnel excavation, it is essential to consider various factors. Therefore, this study derived a prediction model for pile group settlement using machine learning to analyze the importance of various factors that determine the settlement of piled foundations during twin tunnelling. Laboratory model tests and numerical analysis were utilized as input data for machine learning. The influence of each independent variable on the prediction model was analyzed. Machine learning techniques such as data preprocessing, feature engineering, and hyperparameter tuning were used to improve the performance of the prediction model. Machine learning models, employing Random Forest (RF), eXtreme Gradient Boosting (XGB), and Light Gradient Boosting Machine (LightGBM, LGB) algorithms, demonstrate enhanced performance after hyperparameter tuning, particularly with LGB achieving an R2 of 0.9782 and RMSE value of 0.0314. The feature importance in the prediction models was analyzed and PN was the highest at 65.04% for RF, 64.81% for XGB, and PCTC (distance between the center of piles) was the highest at 31.32% for LGB. SHAP was utilized for analyzing the impact of each variable. PN (the number of piles) consistently exerted the most influence on the prediction of pile group settlement across all models. The results from both laboratory model tests and numerical analysis revealed a reduction in ground displacement with varying pillar spacing in twin tunnels. However, upon further investigation through machine learning with additional variables, it was found that the number of piles has the most significant impact on ground displacement. Nevertheless, as this study is based on laboratory model testing, further research considering real field conditions is necessary. This study contributes to a better understanding of the complex interactions inherent in twin tunnelling projects and provides a reliable tool for predicting pile group settlement in such scenarios.

키워드

과제정보

This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korean government (MSIT) (No. 2021R1A2C2013162).

참고문헌

  1. Ahn, C.Y., Park, D. and Moon, S.W. (2022), "Analysis of surface settlement troughs induced by twin shield tunnels in soil: A case study", Geomech. Eng., 30(4), 325-336. https://doi.org/10.12989/gae.2022.30.4.325.
  2. Alseid, B., Chen, J., Huang, H. and Seo, H. (2023), "RCF machine learning method to measure for geological structures in 3d point cloud of rock tunnel face", Available at SSRN 4503641. http://dx.doi.org/10.2139/ssrn.4503641.
  3. Ayasrah, M.M., Qiu, H. and Zhang, X. (2021), "Influence of cairo metro tunnel excavation on pile deep foundation of the adjacent underground structures: Numerical study", Symmetry, 13(3), 426. https://doi.org/10.3390/sym13030426.
  4. Chakeri, H., Hasanpour, R., Hindistan, M.A., and unver, B. (2011), "Analysis of interaction between tunnels in soft ground by 3D numerical modeling", Bull. Eng. Geol. Environ., 70, 439-448. https://doi.org/10.1007/s10064-010-0333-8.
  5. Choi, J.I. and Lee, S.W. (2010), "Influence of existing tunnel on mechanical behavior of new tunnel", KSCE J. Civil Eng., 14, 773-783. https://doi.org/10.1007/s12205-010-1013-8.
  6. Chu, B.L., Hsu, S.C., Chang, Y.L. and Lin, Y.S. (2007), "Mechanical behavior of a twin-tunnel in multi-layered formations", Tunn. Undergr. Sp. Tech., 22(3), 351-362. https://doi.org/10.1016/j.tust.2006.06.003.
  7. Das, B.M. (2011), Principles of Foundation Engineering, Cengage Learning, Boston, Massachusetts, USA.
  8. Do, N.A., Dias, D. and Oreste, P. (2016), "3D numerical investigation of mechanized twin tunnels in soft ground- Influence of lagging distance between two tunnel faces", Eng. Struct., 109, 117-125. https://doi.org/10.1016/j.engstruct.2015.11.053.
  9. Fang, Q., Zhang, D., Li, Q. and Wong, L.N.Y. (2015), "Effects of twin tunnels construction beneath existing shield-driven twin tunnels", Tunn. Undergr. Sp. Tech., 45, 128-137. https://doi.org/10.1016/j.tust.2014.10.001.
  10. Gordan, B., Koopialipoor, M., Clementking, A., Tootoonchi, H., and Tonnizam Mohamad, E. (2019), "Estimating and optimizing safety factors of retaining wall through neural network and bee colony techniques", Eng. with Comput., 35, 945-954. https://doi.org/10.1007/s00366-018-0642-2.
  11. Han, Y., Jiang, X., Wang, Y. and Wang, H. (2023), "Usage of coot optimization-based random forests analysis for determining the shallow foundation settlement", Geomech. Eng., 32(3), 271-291. https://doi.org/10.12989/gae.2023.32.3.271.
  12. Heama, N., Jongpradist, P., Lueprasert, P. and Suwansawat, S. (2017), "Investigation on tunnel responses due to adjacent loaded pile by 3D finite element analysis", Geomate J., 12(31), 63-70. https://doi.org/10.21660/2017.31.6542.
  13. Hong, S.K., Oh, D.W., Kong, S.M. and Lee, Y.J. (2020), "Investigation of divergence tunnel excavation according to horizontal offsets between tunnels", Geomech. Eng., 21(2), 111-122. https://doi.org/10.12989/gae.2020.21.2.111.
  14. Jeon, Y.J. and Lee, C.J. (2023), "Analysis of pile group behaviour to adjacent tunnelling considering ground reinforcement conditions with assessment of stability of superstructures", Geomech. Eng., 33(5), 463-475. https://doi.org/10.12989/gae.2023.33.5.463.
  15. Jung, H.S., Kim, J.H., Yoon, H.H., Sagong, M. and Lee, H.H. (2022), "Experimental study to determine the optimal tensile force of non-open cut tunnels using concrete modular roof method", Geomech. Eng., 29(3), 229-236. https://doi.org/10.12989/gae.2022.29.3.229.
  16. Kim, C.Y., Bae, G.J., Hong, S.W., Park, C.H., Moon, H.K. and Shin, H.S. (2001), "Neural network based prediction of ground surface settlements due to tunnelling", Comput. Geotech., 28(6-7), 517-547. https://doi.org/10.1016/S0266-352X(01)00011-8.
  17. Kim, Y.S., Ko, H.W., Kim, J.H. and Lee, J.G. (2012), "Dynamic deformation characteristics of Joomunjin standard sand using cyclic triaxial test", J. Korean Geotech. Soc., 28(12), 53-64. https://doi.org/10.7843/kgs.2012.28.12.53.
  18. Kong, S.M., Jung, H.S. and Lee, Y.J. (2017), "Investigation of ground behaviour adjacent to an embedded pile according to various tunnel volume losses", Int. J. Geo-Eng., 8, 1-15. https://doi.org/10.1186/s40703-017-0043-1.
  19. Kong, S.M., Oh, D.W., Ahn, H.Y., Lee, H.G. and Lee, Y.J. (2016), "Investigation of ground behaviour between plane-strain grouped pile and 2-arch tunnel station excavation", J. Korean Tunn. Undergr. Sp. Assoc., 18(6), 535-544. https://doi.org/10.9711/KTAJ.2016.18.6.535.
  20. Korean Geotechnical Society (2016), Design Criteria for Structure Foundation, Korean Geotechnical Society, Seoul, Republic of Korea.
  21. Lambe, T.W. and Whitman, R.V. (1979), Soil mechanics, John Wiley & Son, Hoboken, New Jersey, USA.
  22. Liu, X., Suliman, L., Zhou, X., Zhang, J., Xu, B., Xiong, F. and Abd Elmageed, A. (2022), "The difference in the slope supported system when excavating twin tunnels: Model test and numerical simulation", Geomech. Eng., 31(1), 15-30. https://doi.org/10.12989/gae.2022.31.1.015.
  23. Marshall, A.M. and Haji, T. (2015), "An analytical study of tunnel-pile interaction", Tunn. Undergr. Sp. Tech., 45, 43-51. https://doi.org/10.1016/j.tust.2014.09.001.
  24. Mirhabibi, A. and Soroush, A. (2012), "Effects of surface buildings on twin tunnelling-induced ground settlements", Tunn. Undergr. Sp. Tech., 29, 40-51. https://doi.org/10.1016/j.tust.2011.12.009.
  25. Mroueh, H., and Shahrour, I. (2002), "Three-dimensional finite element analysis of the interaction between tunneling and pile foundations", Int. J. Numer. Anal. Method. Geomech., 26(3), 217-230. https://doi.org/10.1002/nag.194.
  26. Nejad, F.P., Jaksa, M.B., Kakhi, M. and McCabe, B.A. (2009), "Prediction of pile settlement using artificial neural networks based on standard penetration test data", Comput. Geotech., 36(7), 1125-1133. https://doi.org/10.1016/j.compgeo.2009.04.003.
  27. Ng, C.W.W. and Lu, H. (2014), "Effects of the construction sequence of twin tunnels at different depths on an existing pile", Can. Geotech. J., 51(2), 173-183. https://doi.org/10.1139/cgj2012-0452.
  28. Ng, C.W.W., Lu, H. and Peng, S.Y. (2013), "Three-dimensional centrifuge modelling of the effects of twin tunnelling on an existing pile", Tunn. Undergr. Sp. Tech., 35, 189-199. https://doi.org/10.1016/j.tust.2012.07.008.
  29. Oh, D.W., Kong, S.M., Kim, S.B. and Lee, Y.J. (2023), "Prediction and analysis of axial stress of piles for piled raft due to adjacent tunneling using explainable AI", Appl. Sci., 13(10), 6074. https://doi.org/10.3390/app13106074.
  30. Oh, D.W., Kong, S.M., Lee, Y.J. and Park, H.J. (2021), "Prediction of change rate of settlement for piled raft due to adjacent tunneling using machine learning", Appl. Sci., 11(13), 6009. https://doi.org/10.3390/app11136009.
  31. PLXIS (2023), Manuals-PLAXIS; Bentley Systems, Pennsylvania, USA. https://communities.bentley.com/products/geotech-analysis/w/wiki/46137/manuals---plaxis
  32. Potts, D.M. and Zdravkovic, L. (2001), Finite Element Analysis in Geotechnical Engineering: Application, Thomas Telford, London, United Kingdom.
  33. Sou-Sen, L. and Hsien-Chuang, L. (2004), "Neural-network-based regression model of ground surface settlement induced by deep excavation", Automat. Constr., 13(3), 279-289. https://doi.org/10.1016/S0926-5805(03)00018-9.
  34. Xiang, Y. and Feng, S. (2013), "Theoretical prediction of the potential plastic zone of shallow tunneling in vicinity of pile foundation in soils", Tunn. Undergr. Sp. Tech., 38, 115-121. https://doi.org/10.1016/j.tust.2013.05.006.