Geomechanics and Engineering

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

EPB-TBM performance prediction using statistical and neural intelligence methods

  • Ghodrat Barzegari (Department of Earth Sciences, Faculty of Natural Sciences, University of Tabriz) ;
  • Esmaeil Sedghi (Department of Earth Sciences, Faculty of Natural Sciences, University of Tabriz) ;
  • Ata Allah Nadiri (Department of Earth Sciences, Faculty of Natural Sciences, University of Tabriz)
  • Received : 2022.07.06
  • Accepted : 2024.03.23
  • Published : 2024.05.10
⟨ Previous Next ⟩

Abstract

This research studies the effect of geotechnical factors on EPB-TBM performance parameters. The modeling was performed using simple and multivariate linear regression methods, artificial neural networks (ANNs), and Sugeno fuzzy logic (SFL) algorithm. In ANN, 80% of the data were randomly allocated to training and 20% to network testing. Meanwhile, in the SFL algorithm, 75% of the data were used for training and 25% for testing. The coefficient of determination (R2) obtained between the observed and estimated values in this model for the thrust force and cutterhead torque was 0.19 and 0.52, respectively. The results showed that the SFL outperformed the other models in predicting the target parameters. In this method, the R2 obtained between observed and predicted values for thrust force and cutterhead torque is 0.73 and 0.63, respectively. The sensitivity analysis results show that the internal friction angle (φ) and standard penetration number (SPT) have the greatest impact on thrust force. Also, earth pressure and overburden thickness have the highest effect on cutterhead torque.

Keywords

Acknowledgement

The authors are grateful to the site engineers for their kind cooperation and for providing field data.

References

  1. Alvisi, S., Mascellani, G., Franchini, M. and Bardossy, A. (2006), "Water level forecasting through fuzzy logic and artificial neural network approaches", Hydrol. Earth Syst. Sci., 10(1), 1-17. https://doi.org/10.5194/hessd-2-1107-2005.
  2. Avunduk, E. and Copur, H. (2018), "Empirical modeling for predicting excavation performance of EPB TBM based on soil properties", Tunn. Undergr. Sp. Tech., 71, 340-353. https://doi.org/10.1016/j.tust.2017.09.016.
  3. Ates, U., Bilgin, N. and Copur, H. (2014), "Estimating torque, thrust and other design parameters of different type TBMs with some criticism to TBMs used in Turkish tunneling projects", Tunn. Undergr. Sp. Tech., 40, 46-63. https://doi.org/10.1016/j.tust.2013.09.004.
  4. Barzegari, G., Shayan, F. and Chakeri, H. (2018), "Investigations on Geotechnical Aspects for TBM Specification on the Tabriz Metro Line 3, Iran", Geotech. Geol. Eng., 36(6), 3639-3663. https://doi.org/10.1007/s10706-018-0563-2.
  5. Barzegari, G. and Uromeihy, A. (2016), "Study of soil abrasivity impact on TBM tunnelling efficiency at the Tabriz metro L1", Iran J. Min. Eng., 10(29), 67-79. http://dori.net/dor/20.1001.1.17357616.1394.10.29.6.3. 1001.1.17357616.1394.10.29.6.3
  6. Barzegari, G., Uromeihy, A. and Zhao, J. (2014), "EPB tunneling challenges in bouldery ground: a new experience on the Tabriz metro line 1, Iran", Bull. Eng. Geol. Environ., 73(2), 429-440. https://doi.org/10.1007/s10064-013-0490-7.
  7. Basheer, I.A .(2000), "Selection of methodology for neural network modeling of constitutive hysteresis behavior of soils", Comput.-Aided Civ. Infrastruct. Eng., 15(6), 445-463. https://doi.org/10.1111/0885-9507.00206.
  8. Bilgin, N. and Algan, M. (2012), "The performance of a TBM in a squeezing ground at Uluabat, Turkey", Tunn. Undergr. Sp. Tech., 32, 58-65. https://doi.org/10.1016/j.tust.2012.05.004.
  9. Cho, K.H., Sthiannopkao, S., Pachepsky, Y.A., Kim, K.W. and Kim, J. (2011), "Prediction of contamination potential of groundwater arsenic in Cambodia, Laos, and Thailand using artificial neural network", Water Res., 45(17), 5535-5544. https://doi.org/10.1016/j.watres.2011.08.010.
  10. Copur, H., Aydin, H., Bilgin, N., Balci, C., Tumac, D. and Dayanc, C. (2014), "Predicting performance of EPB TBMs by using a stochastic model implemented into a deterministic model", Tunn. Undergr. Sp. Tech., 42, 1-14. https://doi.org/10.1016/j.tust.2014.01.006.
  11. Darbor, M., Chakeri, H. and Asgharzadeh Dizaj, M. (2020), "Investigation of the effect of different parameters on the penetration rate of earth pressure balance boring machine using fuzzy and neuro-fuzzy methods, and metaheuristic algorithms (A case study: Tabriz metro line 2)", J. Anal. Numer. Method. Min. Eng., 10(2), 43-60. https://doi.org/10.29252/ANM.2020.13347.1430.
  12. Demuth, H., Beale, M. and Hagan, M. (1992), "Neural network toolbox. For Use with MATLAB", the Math Works Inc, 2000.
  13. Elbaz, K., Shen, S.L., Zhou, A., Yuan, D.J. and Xu, Y.S. (2019), "Optimization of EPB shield performance with adaptive neuro-fuzzy inference system and genetic algorithm", Appl. Sci., 9(4). 780. https://doi.org/10.3390/app9040780.
  14. Gelman, A. and Hill, J. (2006), "Data analysis using regression and multilevel/hierarchical models", Cambridge University Press.
  15. Herrenknech, M. and Bappler, K (2007), "Latest technologies in mechanized tunneling", Proceedings of the TBM Conference Organized by BASF, Istanbul-Turkey.
  16. Jammalamadaka, S.R. (2003), "Introduction to linear regression analysis", Am. Stat., 57, 67.
  17. Kasper, T. and Meschke, G. (2004), "A 3D finite element simulation model for TBM tunneling in soft ground", Int. J. Numer. Anal. Method. Geomech., 28(14), 1441-1460. https://doi.org/10.1002/nag.395.
  18. Kim, K.Y., Jo, S.A., Ryu, H.H. and Cho, G.C. (2020), "Prediction of TBM performance based on specific energy", Geomech. Eng., 22(6), 489-496. https://doi.org/10.12989/gae.2020.22.6.489.
  19. Lallahem, S., Mania, J., Hani, A. and Najjar, Y. (2005), "On the use of neural networks to evaluate groundwater levels in fractured media", J. Hydrol., 307(1-4), 92-111. https://doi.org/10.1016/j.jhydrol.2004.10.005.
  20. Li, C., Zhou, J., Tao, M., Du, K., Wang, S., Armaghani, D.J. and Mohamad, E.T. (2022), "Developing hybrid ELM-ALO, ELMLSO and ELM-SOA models for predicting advance rate of TBM", Transp. Geotech., 36, 100819. https://doi.org/10.1016/j.trgeo.2022.100819.
  21. Lin, S.S., Zhang, N., Zhou, A. and Shen, S.L. (2022), "Time-series prediction of shield movement performance during tunneling based on hybrid model", Tunn. Undergr. Sp. Tech., 119, 104245. https://doi.org/10.1016/j.tust.2021.104245.
  22. Lovat, R.P. and Eng, P. (2007), "TBM design considerations: selection of earth pressure balance or slurry pressure balance tunnel boring machines", Proceedings of the International Symposium on Utilization of Underground Space in Urban Areas.
  23. Mahmoodzadeh, A., Nejati, H., Ibrahim, H., Ali, H.F.H., Mohammed, A., Rashidi, S. and Majeed, M.K. (2022) , "Several models for tunnel boring machine performance prediction based on machine learning", Geomech. Eng., 30(1), 75-91. https ://doi.org/10.12989/gae.2022.30.1.075.
  24. Mamdani, E.H. and Assilian, S. (1975), "An experiment in linguistic synthesis with a fuzzy logic controller", Int. J. Man-Mach. Stud., 7(1), 1-13. https://doi.org/10.1016/S0020-7373(75)80002-2.
  25. Marinos, P.G., Novack, M., Benissi, M., Panteliadou, M., Papouli, D., Stoumpos, G., Marinos, V. and Korkaris, K. (2008), "Ground information and selection of TBM for the Thessaloniki Metro, Greece", Environ. Eng. Geosci., 14(1). 17-30. https://doi.org/10.2113/gseegeosci.14.1.17.
  26. Menhaj, M.B. (2012), "Fundamentals of Neural Networks", 1st Ed., Amir-kabir University of Technology Publishing Center, 476.
  27. Meyers, L.S., Gamst, G. and Guarino, A.J. (2016), "Applied multivariate research: Design and Interpretation", Sage Publications.
  28. Nadiri, A.A. (2013), "Comparison of the efficiency of numerical and artificial intelligence models in the management of aquifers (Case study: Tasuj plain)", Ph.D. Dissertation, University of Tabriz, Tabriz.
  29. Qin, C., Shi, G., Tao, J., Yu, H., Jin, Y., Lei, J. and Liu, C. (2020), "Precise cutterhead torque prediction for shield tunneling machines using a novel hybrid deep neural network", Mech. Syst. Signal Pr., 151. https://doi.org/10.1016/j.ymssp.2020.107386.
  30. Shi, H., Yang, H.Y., Gong, G.F. and Wang, L.T. (2011), "Determination of the cutterhead torque for EPB shield tunneling machine", Automat. Constr., 20, 1087-1095. https://doi.org/10.1016/j.autcon.2011.04.010.
  31. Sugeno, M. (1985), "Industrial applications of fuzzy control", Elsevier Science Pub. Co., Japan.
  32. Wang, S., Zhou, J., Li, C., Armaghani, D.J., Li, X. and Mitri, H.S. (2021), "Rockburst prediction in hard rock mines developing bagging and boosting tree-based ensemble techniques", J. Cent. South Univ., 28, 527-542. https://doi.org/10.1007/s11771-021-4619-8.
  33. Yagiz, S. (2008), "Utilizing rock mass properties for predicting TBM performance in hard rock condition", Tunn. Undergr. Sp. Tech., 23(3), 326-339. https://doi.org/10.1016/j.tust.2007.04.011.
  34. Zadeh, L.A. (1996), "Fuzzy sets. In Fuzzy sets, fuzzy logic, and fuzzy systems: selected papers by Lotfi Zadeh", Adv. Fuzzy Syst. - Appl. Theory., 1, 394-432. https://doi.org/10.1142/2895.
  35. Zeng, J., Roy, B., Mohammed, A.S., Armaghani, D.J., Zhou, J. and Mohamad, E.T. (2022), "Proposing several hybrid PSO-extreme learning machine techniques to predict TBM performance", Eng. Comput., 38, 3811-3827. https://doi.org/10.1007/s00366-020-01225-2.
  36. Zhang, Q., Hou, Z., Huang, G., Cai, Z. and Kang, Y. (2015), "Mechanical characterization of the load distribution on the cutterhead-ground interface of shield tunneling machines", Tunn. Undergr. Sp. Tegh., 47:106-113. https://doi.org/10.1016/j.tust.2014.12.009