Geomechanics and Engineering

  • 제30권1호
  • /
  • Pages.11-26
  • /
  • 2022
  • /
  • 2005-307X(pISSN)
  • /
  • 2092-6219(eISSN)
테크노프레스 (Techno-Press)
권호 표지
DOI QR코드

DOI QR Code

Prediction of squeezing phenomenon in tunneling projects: Application of Gaussian process regression

  • Mirzaeiabdolyousefi, Majid (Department of Mining, Petroleum & Geophysics Engineering, Shahrood University of Technology) ;
  • Mahmoodzadeh, Arsalan (Rock Mechanics Division, School of Engineering, Tarbiat Modares University) ;
  • Ibrahim, Hawkar Hashim (Department of Civil Engineering, College of Engineering, Salahaddin University-Erbil) ;
  • Rashidi, Shima (Department of Computer Science, College of Science and Technology, University of Human Development) ;
  • Majeed, Mohammed Kamal (Information Technology Department, Faculty of Science, Tishk International University (TIU)) ;
  • Mohammed, Adil Hussein (Department of Communication and Computer Engineering, Faculty of Engineering, Cihan University-Erbil)
  • 투고 : 2022.02.10
  • 심사 : 2022.05.30
  • 발행 : 2022.07.10
⟨ 이전 논문 다음 논문 ⟩

초록

One of the most important issues in tunneling, is the squeezing phenomenon. Squeezing can occur during excavation or after the construction of tunnels, which in both cases could lead to significant damages. Therefore, it is important to predict the squeezing and consider it in the early design stage of tunnel construction. Different empirical, semi-empirical and theoretical-analytical methods have been presented to determine the squeezing. Therefore, it is necessary to examine the ability of each of these methods and identify the best method among them. In this study, squeezing in a part of the Alborz service tunnel in Iran was estimated through a number of empirical, semi- empirical and theoretical-analytical methods. Among these methods, the most robust model was used to obtain a database including 300 data for training and 33 data for testing in order to develop a machine learning (ML) method. To this end, three ML models of Gaussian process regression (GPR), artificial neural network (ANN) and support vector regression (SVR) were trained and tested to propose a robust model to predict the squeezing phenomenon. A comparative analysis between the conventional and the ML methods utilized in this study showed that, the GPR model is the most robust model in the prediction of squeezing phenomenon. The sensitivity analysis of the input parameters using the mutual information test (MIT) method showed that, the most sensitive parameter on the squeezing phenomenon is the tangential strain (ε_θ^α) parameter with a sensitivity score of 2.18. Finally, the GPR model was recommended to predict the squeezing phenomenon in tunneling projects. This work's significance is that it can provide a good estimation of the squeezing phenomenon in tunneling projects, based on which geotechnical engineers can take the necessary actions to deal with it in the pre-construction designs.

키워드

참고문헌

  1. Aydan, O., Akagi, T. and Kawamoto, T. (1993), "The squeezing potential of rocks around tunnels; theory and prediction", Rock Mech. Rock Eng., 26(2), 137-163. https://doi.org/10.1007/BF01023620.
  2. Barton, N., Lien, R. and Lunde, J. (1974), "Engineering classification of rock masses for the design of tunnel support", Rock Mech., 6, 189-236. https://doi.org/10.1007/BF01239496.
  3. Bai, X., Cheng, W.C., Ong, D.E.L. and Li, G. (2021), "Evaluation of geological conditions and clogging of tunneling using machine learning", Geomech. Eng., 25(1), 59-73. https://doi.org/10.12989/gae.2021.25.1.059.
  4. Fatemi Aghda, S.M., Ganjalipour, K. and Esmaeil Zadeh, M. (2016), "Comparison of squeezing prediction methods: A case study on Nowsoud tunnel", Geotech. Geol. Eng., 34(5), 1487-1512. https://doi.org/10.1007/s10706-016-0056-0.
  5. Feng, X.T., Zhao, H.B. and Li, S.J. (2004), "Modeling non-linear displacement time series of geo-materials using evolutionary support vector machines", Int. J. Rock Mech. Min. Sci., 41(7), 1087-1107. https://doi.org/10.1016/J.IJRMMS.2004.04.003.
  6. Ghasemi, E. and Gholizadeh, H. (2018), "Prediction of squeezing potential in tunneling projects using data mining-based techniques", Geotech. Geol. Eng., 1-10. https://doi.org/10.1007/s10706-018-0705-6.
  7. Grelle, G. and Guadagno, F.M. (2012), "Regression analysis for seismic slope instability based on a double phase viscoplastic sliding model of the rigid block", Landslides, 10(5), 583-597. https://doi.org/10.1007/s10346-012-0350-8.
  8. Goel, R.K. (1995), "Correlations for predicting support pressures and closures in tunnels", Ph.D. Thesis, University of Nagpur, India, 310p.
  9. Hoek, E. (1998), "Tunnel support in weak rock", In: Proceeding of regional symposium on sedimentary rock engineering", Keynote address, Symposium of Sedimentary Rock Engineering, Taipei, Taiwan, November 20-22, 1998.
  10. Hoek, E. and Marinos, P. (2000), "Predicting tunnel squeezing problems in weak heterogeneous rock masses", Tunn. Tunn. Int., 32(11), 45-51. Corpus ID: 130823387
  11. Hoek, E. (2001), "Big tunnels in bad rock", J. Geotech. Geoenviron. Eng., 127(9), 726-740. https://doi.org/10.1061/(ASCE)1090-0241(2001)127:9(726).
  12. Jethwa, J.L, Singh., B. and Singh, B. (1984), "Estimation of ultimate rock pressure for tunnel linings under squeezing rock conditions-a new approach", (Eds., Brown, E.T. and Hudson, J.A.), Proceedings of ISRM symposium on design and performance of underground excavations, Cambridge, 231-238. https://www.icevirtuallibrary.com/doi/abs/10.1680/dapoue.35652.0028
  13. Kang, F., Han, S.X., Salgado, R. and Li, J.J. (2015), "System probabilistic stability analysis of soil slopes using Gaussian process regression with Latin hypercube sampling", Comput. Geotech., 63(1), 13-25. https://doi.org/10.1016/j.compgeo.2014.08.010.
  14. Khishe, M. and Mosavi, M.R. (2020). "Chimp optimization algorithm", Exp. Syst. with Appl., 149, 113338. https://doi.org/10.1016/j.eswa.2020.113338.
  15. Khishe, M. and Mosavi, M.R. (2019), "Improved whale trainer for sonar datasets classification using neural network", Appl. Acoust., 154, 176-192. https://doi.org/10.1016/j.apacoust.2019.05.006.
  16. Li, L.P., Shi, S.S., Zhang, Q.Q., Zhang, J. and Hu, J. (2017), "Gaussian process model of water in flow prediction in tunnel construction and its engineering applications", Tunn. Undergr. Sp. Tech., 69, 155-161. https://doi.org/10.1016/j.tust.2017.06.018.
  17. Liu, R., Liu, E., Yang, J., Li, M. and Wang, F. (2006), "Optimizing the hyper-parameters for SVM by combining evolution strategies with a grid search", In: International conference on intelligent computing, Kunming, China, 44, 712-721. https://doi.org/10.1007/978-3-540-37256-1_87.
  18. Liu, Z.B., Shao, J.F., Xu, W.Y., Chen, H.J. and Shi, C. (2014), "Comparison on landslide non-linear displacement analysis and prediction with computational intelligence approaches", Landslides, 11(5), 889-896. https://doi.org/10.1007/s10346-013-0443-z.
  19. Li, B., Fu, Y., Hong, Y. and Gao, Z (2021), "Deterministic and probabilistic analysis of tunnel face stability using support vector machine", Geomech. Eng., 25(1), 17-30. https://doi.org/10.12989/gae.2021.25.1.017.
  20. Liu, J., Jiang, Y., Zhang, Y. and Sakaguchi, O. (2021), "Influence of different combinations of measurement while drilling parameters by artificial neural network on estimation of tunnel support patterns", Geomech. Eng., 25(6), 439-454. https://doi.org/10.12989/gae.2021.25.6.439.
  21. Mahmoodzadeh, A., Mohammadi, M., Abdulhamid, S.N., HIbrahim, H.H., Hama-Ali, H.H., Nejati, H.R. and Rashidi S. (2022). "Prediction of duration and construction cost of road tunnels using Gaussian process regression", Geomech. Eng., 28(1), 65-75. https://doi.org/10.12989/gae.2021.28.1.065.
  22. Mosavi, M., Kaveh, M., Khishe, M. and Aghababaie, M. (2018), "Design and implementation a sonar data set classifier using multi-layer perceptron neural network trained by elephant herding optimization", Iran. J. Marine Tech., 5(1), 1-12. http://ijmt.iranjournals.ir/article_31015.html?lang=en.
  23. Mosavi, M., Khishe, M. and Moridi, A. (2016). "Classification of sonar target using hybrid particle swarm and gravitational search", Iran. J. Marine Tech., 3(1), 1-13. http://ijmt.iranjournals.ir/article_19580.html?lang=en
  24. Mosavi, M.R. and Khishe, M., Hatam Khani, Y. and Shabani, M. (2017), "Training radial basis function neural network using stochastic fractal search algorithm to classify sonar dataset", Iran. J. Elec. Electronic Eng., 13(1), 100-111. http://ijeee.iust.ac.ir/article-1-959-en.html.
  25. Pal, M. and Deswal, S. (2010), "Modelling pile capacity using Gaussian process regression", Comput. Geotech., 37, 942-947. https://doi.org/10.1016/j.compgeo.2010.07.012.
  26. Quinonero-Candela, J. and Rasmussen, C.E. (2005), "A unifying view of sparse approximate Gaussian process regression", J. Mach. Learn. Res., 6, 1939-1959. https://doi.org/10.5555/1046920.1194909.
  27. Rohmer, J. and Foerster, E. (2011), "Global sensitivity analysis of large-scale numerical land-slide models based on Gaussian-Process metamodeling", Comput. Geosci., 37(7), 91-927. https://doi.org/10.1016/j.cageo.2011.02.020.
  28. Sakurai, S. (1983), "Displacement measurements associated with the design on underground openings", (Ed., Kova'ri, K.) Proceedings of the international symposium on field measurements in geomechanics, Balkema, Zurich.
  29. Schulz, E., Speekenbrink, M. and Krause, A. (2018), "A tutorial on Gaussian process regression: Modelling, exploring, and exploiting functions", J. Math. Psychology, 85, 1-16. https://doi.org/10.1016/j.jmp.2018.03.001.
  30. Singh, B., Jethwa, J.L., Dube, A.K. and Singh, B. (1992), "Correlation between observed support pressure and rock mass quality", Tunn. Undergr. Sp. Tech., 7, 59-74. https://doi.org/10.1016/0886-7798(92)90114-W.
  31. Wang, D.D., Qiu, G.Q., Xie, W.B. and Wang, Y. (2012), "Deformation prediction model of surrounding rock based on GA-LSSVM-markov", Nat. Sci., 4(2), 85-90. https://doi.org/10.4236/ns.2012.42013.
  32. Wenner, D. and Wannenmacher, H. (2008), "Technical challenges during construction of Alborz service tunnel, Iran", Geomechanik und Tunnelbau, 1(6), 537-542. https://doi.org/10.1002/geot.200800065.
  33. Xiang, G., Ying, D., Gao, C. and Yuan, L. (2021), "Application of artificial neural network for prediction of flow ability of soft soil subjected to vibrations', Geomech. Eng., 25(5), 395-403. https://doi.org/10.12989/gae.2021.25.5.395.
  34. Yuan, J., Wang, K., Yu, T. and Fang, M. (2008), "Reliable multi-objective optimization of high-speed WEDM process based on Gaussian process regression", Int. J. Mach. Tools Manuf., 48, 47-60. https://doi.org/10.1016/j.ijmachtools.2007.07.011.