Geomechanics and Engineering

  • 제31권6호
  • /
  • Pages.545-556
  • /
  • 2022
  • /
  • 2005-307X(pISSN)
  • /
  • 2092-6219(eISSN)
테크노프레스 (Techno-Press)
권호 표지
DOI QR코드

DOI QR Code

Tunnel wall convergence prediction using optimized LSTM deep neural network

  • Arsalan, Mahmoodzadeh (Rock Mechanics Division, School of Engineering, Tarbiat Modares University) ;
  • Mohammadreza, Taghizadeh (Department of Civil engineering, Faculty of engineering, University of Kashan) ;
  • Adil Hussein, Mohammed (Department of Communication and Computer Engineering, Faculty of Engineering, Cihan University-Erbil) ;
  • Hawkar Hashim, Ibrahim (Department of Civil Engineering, College of Engineering, Salahaddin University-Erbil) ;
  • Hanan, Samadi (School of Geology, College of Science, University of Tehran) ;
  • Mokhtar, Mohammadi (Department of Information Technology, College of Engineering and Computer Science, Lebanese French University) ;
  • Shima, Rashidi (Department of Computer Science, College of Science and Technology, University of Human Development)
  • 투고 : 2022.04.27
  • 심사 : 2022.09.08
  • 발행 : 2022.12.25
⟨ 이전 논문 다음 논문 ⟩

초록

Evaluation and optimization of tunnel wall convergence (TWC) plays a vital role in preventing potential problems during tunnel construction and utilization stage. When convergence occurs at a high rate, it can lead to significant problems such as reducing the advance rate and safety, which in turn increases operating costs. In order to design an effective solution, it is important to accurately predict the degree of TWC; this can reduce the level of concern and have a positive effect on the design. With the development of soft computing methods, the use of deep learning algorithms and neural networks in tunnel construction has expanded in recent years. The current study aims to employ the long-short-term memory (LSTM) deep neural network predictor model to predict the TWC, based on 550 data points of observed parameters developed by collecting required data from different tunnelling projects. Among the data collected during the pre-construction and construction phases of the project, 80% is randomly used to train the model and the rest is used to test the model. Several loss functions including root mean square error (RMSE) and coefficient of determination (R2) were used to assess the performance and precision of the applied method. The results of the proposed models indicate an acceptable and reliable accuracy. In fact, the results show that the predicted values are in good agreement with the observed actual data. The proposed model can be considered for use in similar ground and tunneling conditions. It is important to note that this work has the potential to reduce the tunneling uncertainties significantly and make deep learning a valuable tool for planning tunnels.

키워드

참고문헌

  1. Adoko, A.C. and Wu, L. (2012), "Estimation of convergence of a high-speed railway tunnel in weak rocks using an adaptive neuro-fuzzy inference system (ANFIS) approach", J. Rock Mech.. Geotech. Eng., 4(1), 11-18. https://doi.org/https://doi.org/10.3724/SP.J.1235.2012.00011.
  2. Adoko, A.C., Jiao, Y.Y., Wu, L., Wang, H. and Wang, Z.H. (2013), "Predicting tunnel convergence using multivariate adaptive regression spline and artificial neural network", Tunn. Undergr. Sp. Tech., 38, 368-376. https://doi.org/https://doi.org/10.1016/j.tust.2013.07.023.
  3. Asadollahpour, E., Rahmannejad, R., Asghari, A. and Abdollahipour, A. (2014), "Back analysis of closure parameters of Panet equation and Burger׳s model of Babolak water tunnel conveyance", Int. J. Rock Mech. Min. Sci., 68, 159-166. https://doi.org/https://doi.org/10.1016/j.ijrmms.2014.02.017.
  4. Bai, X.D., Cheng, W.C., Ong, D.E.L. and Ge, L. (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.
  5. Debernardi, D. and Barla, G. (2009), "New viscoplastic model for design analysis of tunnels in squeezing conditions", Rock Mech. Rock Eng., 42(2), 259. https://doi.org/10.1007/s00603-009-0174-6.
  6. Fahimifar, A., Tehrani, F.M., Hedayat, A. and Vakilzadeh, A. (2010), "Analytical solution for the excavation of circular tunnels in a visco-elastic Burger's material under hydrostatic stress field", Tunn. Undergr. Sp. Tech., 25(4), 297-304. https://doi.org/https://doi.org/10.1016/j.tust.2010.01.002.
  7. Fakhri, D., Khodayari, A., Mahmoodzadeh, A., Hosseini, M., Ibrahim, H. and Mohammed, A. (2022), "Prediction of mixed-mode I and II effective fracture toughness of several types of concrete using the extrema gradient boosting method and metaheuristic optimization algorithms", Eng. Fract. Mech., In press, https://doi.org/10.1016/j.engfracmech.2022.108916.
  8. Feng, X., Jimenez, R., Zeng, P. and Senent, S. (2019), "Prediction of time-dependent tunnel convergences using a Bayesian updating approach", Tunn. Undergr. Sp. Tech., 94, 103118. https://doi.org/https://doi.org/10.1016/j.tust.2019.103118.
  9. Gonzalez el A lamo, J.A. and Jimenez, R. (2011), "Prediction of convergences in rock tunnels excavated by conventional methods", Proceedings of the 12th ISRM Congress, Beijing, China.
  10. Guan, Z., Jiang, Y. and Tanabashi, Y. (2009), "Rheological parameter estimation for the prediction of long-term deformations in conventional tunnelling", Tunn. Undergr. Sp. Tech., 24(3), 250-259. https://doi.org/https://doi.org/10.1016/j.tust.2008.08.001.
  11. Hajihassani, M., Abdullah, S.S., Asteris, P.G. and Jahed Armaghani, D. (2019), "A gene expression programming model for predicting tunnel convergence", Appl. Sci., 9(21), 4650. https://doi.org/10.3390/app9214650.
  12. Kontogianni, V., Psimoulis, P. and Stiros, S. (2006), "What is the contribution of time-dependent deformation in tunnel convergence?", Eng. Geol., 82(4), 264-267. https://doi.org/https://doi.org/10.1016/j.enggeo.2005.11.001.
  13. Liu, J., Jiang, Y., Zhang, Y. and Sakaguchi, O. (2021a), "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.
  14. Liu, L.L., Yang, C. and Wang, X.M. (2021b), "Landslide susceptibility assessment using feature selection-based machine learning models", Geomech. Eng., 25(1), 1-16. https://doi.org/10.12989/gae.2021.25.1.001.
  15. Luat, N.V., Lee, K. and Thai, D.K. (2020), "Application of artificial neural networks in settlement prediction of shallow foundations on sandy soils", Geomech. Eng., 20(5), https://doi.org/10.12989/gae.2020.20.5.385.
  16. Mahdevari, S. and Torabi, S.R. (2012), "Prediction of tunnel convergence using artificial neural networks", Tunn. Undergr. Sp. Tech., 28, 218-228. https://doi.org/https://doi.org/10.1016/j.tust.2011.11.002 .
  17. Mahdevari, S., Shirzad Haghighat, H. and Torabi, S.R. (2013), "A dynamically approach based on SVM algorithm for prediction of tunnel convergence during excavation", Tunn. Undergr. Sp. Tech., 38, 59-68. https://doi.org/https://doi.org/10.1016/j.tust.2013.05.002.
  18. Mahdevari, S., Torabi, S.R. and Monjezi, M. (2012), "Application of artificial intelligence algorithms in predicting tunnel convergence to avoid TBM jamming phenomenon", Int. J. Rock Mech. Min. Sci., 55, 33-44. https://doi.org/https://doi.org/10.1016/j.ijrmms.2012.06.005.
  19. Mahmoodzadeh, A., Nejati, H.R., Mohammadi, M., Mohammed, A., Ibrahim, H. and Rashidi, S. (2022a), "Numerical and Machine learning modeling of hard rock failure induced by structural planes around deep tunnels", Eng. Fract. Mech., 271, 108648. https://doi.org/10.1016/j.engfracmech.2022.108648.
  20. Mahmoodzadeh, A., Rashidi, S., Mohammed, A., Hama Ali, H. and Ibrahim, H. (2022b), Machine learning approaches to enable resource forecasting process of road tunnels construction. Communication Engineering and Computer Science, North America, mar. 2022. Available at: . Date accessed: 21 Sep. 2022. http://doi.org/10.24086/cocos2022/paper.718.
  21. Mirzaeiabdolyousefi, M., Mahmoodzadeh, A., Ibrahim, H., Rashidi, S., Majeed, M. and Mohammed, A. (2022), "Prediction of squeezing phenomenon in tunneling projects: Application of Gaussian process regression", Geomech. Eng., 30(1), 11-26. https://doi.org/10.12989/gae.2022.30.1.011.
  22. Nadimi, S., Shahriar, K., Sharifzadeh, M. and Moarefvand, P. (2011), "Triaxial creep tests and back analysis of time-dependent behavior of Siah Bisheh cavern by 3-Dimensional Distinct Element Method", Tunn. Undergr. Sp. Tech., 26(1), 155-162. https://doi.org/https://doi.org/10.1016/j.tust.2010.09.002. Nomikos, P., Rahmannejad, R. and Sofianos, A. (2011),
  23. "Supported axisymmetric tunnels within linear viscoelastic burgers rocks", Rock Mech. Rock Eng., 44(5), 553-564. https://doi.org/10.1007/s00603-011-0159-0.
  24. Rafiai, H. and Moosavi, M. (2012), "An approximate ANN-based solution for convergence of lined circular tunnels in elasto-plastic rock masses with anisotropic stresses", Tunn. Undergr. Sp. Tech., 27(1), 52-59. https://doi.org/https://doi.org/10.1016/j.tust.2011.06.008.
  25. Sakurai, S. (1978), "Approximate time-dependent analysis of tunnel support structure considering progress of tunnel face", Int. J. Numer. Anal. Method. Geomech., 2(2), 159-175. https://doi.org/10.1002/nag.1610020205.
  26. Sharifzadeh, M., Tarifard, A. and Moridi, M.A. (2013), "Time-dependent behavior of tunnel lining in weak rock mass based on displacement back analysis method", Tunn. Undergr. Sp. Tech., 38, 348-356. https://doi.org/https://doi.org/10.1016/j.tust.2013.07.014.
  27. Sterpi, D. and Gioda, G. (2009), "Visco-plastic behaviour around advancing tunnels in squeezing rock", Rock Mech. Rock Eng., 42(2), 319-339. https://doi.org/10.1007/s00603-007-0137-8.
  28. Torabi-Kaveh, M. and Sarshari, B. (2020), "Predicting convergence rate of namaklan twin tunnels using machine learning methods", Arabian J. Sci. Eng., 45(5), 3761-3780. https://doi.org/10.1007/s13369-019-04239-1.
  29. Vu, T.M., Sulem, J., Subrin, D., Monin, N. and Lascols, J. (2013), "Anisotropic closure in squeezing rocks: The example of Saint-Martin-la-Porte access gallery", Rock Mec. Rock Eng., 46(2), 231-246. https://doi.org/10.1007/s00603-012-0320-4.
  30. Xiang, G., Yin, D., Cao, 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.