Geomechanics and Engineering

  • 제37권6호
  • /
  • Pages.629-641
  • /
  • 2024
  • /
  • 2005-307X(pISSN)
  • /
  • 2092-6219(eISSN)
테크노프레스 (Techno-Press)
권호 표지
DOI QR코드

DOI QR Code

Optimizing shallow foundation design: A machine learning approach for bearing capacity estimation over cavities

  • Kumar Shubham (Department of Civil Engineering, National Institute of Technology Jamshedpur) ;
  • Subhadeep Metya (Department of Civil Engineering, National Institute of Technology Jamshedpur) ;
  • Abdhesh Kumar Sinha (Department of Civil Engineering, National Institute of Technology Jamshedpur)
  • 투고 : 2023.05.30
  • 심사 : 2024.06.12
  • 발행 : 2024.06.25
⟨ 이전 논문 다음 논문 ⟩

초록

The presence of excavations or cavities beneath the foundations of a building can have a significant impact on their stability and cause extensive damage. Traditional methods for calculating the bearing capacity and subsidence of foundations over cavities can be complex and time-consuming, particularly when dealing with conditions that vary. In such situations, machine learning (ML) and deep learning (DL) techniques provide effective alternatives. This study concentrates on constructing a prediction model based on the performance of ML and DL algorithms that can be applied in real-world settings. The efficacy of eight algorithms, including Regression Analysis, k-Nearest Neighbor, Decision Tree, Random Forest, Multivariate Regression Spline, Artificial Neural Network, and Deep Neural Network, was evaluated. Using a Python-assisted automation technique integrated with the PLAXIS 2D platform, a dataset containing 272 cases with eight input parameters and one target variable was generated. In general, the DL model performed better than the ML models, and all models, except the regression models, attained outstanding results with an R2 greater than 0.90. These models can also be used as surrogate models in reliability analysis to evaluate failure risks and probabilities.

키워드

참고문헌

  1. Alzabeebee, S. and Al-Taie, A. (2022), "Development of new models to predict the compressibility parameters of alluvial soils", Geomech. Eng., 30(5), 437-448. https://doi.org/10.12989/gae.2022.30.5.437. 
  2. Badie, A. and Wang, M.C. (1984), "Stability of spread footing above void in clay", J. Geotech. Eng., 110, 1591-1605. https://doi.org/10.1061/(ASCE)0733-9410(1984)110:11(1591). 
  3. Bong, T., Kim, S.R. and Kim, B.I. (2020), "Prediction of ultimate bearing capacity of aggregate pier reinforced clay using multiple regression analysis and deep learning", Appl. Sci., 10(13), 4580. https://doi.org/10.3390/app10134580. 
  4. Broere, W. (2016), "Urban underground space: Solving the problems of today's cities", Tunn. Undergr. Sp. Tech., 55, 245-248. https://doi.org/10.1016/j.tust.2015.11.012. 
  5. Chowdhury, R., Bhattacharya, G. and Metya, S. (2023), Geotechnical Slope Analysis, 2nd Ed., CRC Press, Balkema. 
  6. Dadhich, S., Sharma, J.K. and Madhira, M. (2021), "Prediction of ultimate bearing capacity of aggregate pier reinforced clay using machine learning", Int. J. Geosynth. Ground Eng., 7, 1-16. https://doi.org/10.1007/s40891-021-00282-x. 
  7. Debbarma, S. and Ransinchung, G.D. (2022), "Using artificial neural networks to predict the 28-day compressive strength of roller-compacted concrete pavements containing RAP aggregates", Road Mater. Pavement Des., 23, 149-167. https://doi.org/10.1080/14680629.2020.1822202. 
  8. Faherty, R., Acikgoz, S., Wong, E.K.L., Hewitt, P. and Viggiani, G.M.B. (2022), "Tunnel-soil-structure interaction mechanisms in a metallic arch bridge", Tunn. Undergr. Sp. Tech., 123, 104429. https://doi.org/10.1016/j.tust.2022.104429. 
  9. Fan, S., Song, Z., Xu, T., Wang, K. and Zhang, Y. (2021), "Tunnel deformation and stress response under the bilateral foundation pit construction: A case study", Arch. Civil Mech. Eng., 21. https://doi.org/10.1007/s43452-021-00259-7. 
  10. Fathima Sana, V.K., Nazeeh, K.M., Dilip, D.M. and Sivakumar Babu, G.L. (2022), "Reliability-based design optimization of shallow foundation on cohesionless soil based on surrogate-based numerical Mmodeling", Int. J. Geomech., 22, 1-8. https://doi.org/10.1061/(asce)gm.1943-5622.0002274. 
  11. Goel, R.K. (2015), Use of underground space for the development of cities in India, Water and Energy International 58RNI:41-45. 
  12. Habibagahi, K. (1984), "Bearing capacity of strip footing above void", J. Geotech. Eng., 110, 137. https://doi.org/10.1061/(ASCE)0733-9410(1984)110:1(137). 
  13. Jabbar, S.F., Hamed, R.I. and Alwan, A.H. (2018), "The potential of nonparametric model in foundation bearing capacity prediction", Neural Comput. Appl., 30, 3235-3241. https://doi.org/10.1007/s00521-017-2916-9. 
  14. Kardani, N., Zhou, A., Nazem, M. and Shen, S.L. (2020), "Estimation of bearing capacity of piles in cohesionless soil using optimised machine learning approaches", Geotech. Geol. Eng., 38, 2271-2291. https://doi.org/10.1007/s10706-019-01085-8. 
  15. Keawsawasvong, S. (2021), "Limit analysis solutions for spherical cavities in sandy soils under overloading", Innov. Infrastruct. Solutions, 6, 1-8. https://doi.org/10.1007/s41062-020-00398-5. 
  16. Kioumarsi, M., Dabiri, H., Kandiri, A. and Farhangi, V. (2023), "Compressive strength of concrete containing furnace blast slag; optimized machine learning-based models", Clean Eng. Technol., 13, 100604. https://doi.org/10.1016/j.clet.2023.100604. 
  17. Kohestani, V.R., Vosoughi, M., Hassanlourad, M. and Fallahnia, M. (2017), "Bearing capacity of shallow foundations on cohesionless soils: A random forest based approach", Civil Eng. Infrastruct. J., 50, 35-49. https://doi.org/10.7508/ceij.2017.01.003. 
  18. Kumar, D.R., Wipulanusat, W., Kumar, M., Keawsawasvong, S. and Samui, P. (2024), "Optimized neural network-based state-of-the-art soft computing models for the bearing capacity of strip footings subjected to inclined loading", Intell. Syst. Appl., 21, 200314. https://doi.org/10.1016/j.iswa.2023.200314. 
  19. Kumar, P., Metya, S., Shubham, K. and Prashad, D. (2022), "Behaviour of strip footing over cavity subjected to inclined and eccentric loads", Arabian J. Geosci., 15. https://doi.org/10.1007/s12517-022-10739-6. 
  20. Kumar, P. and Samui, P. (2024), "Reliability-based load and resistance factor design of an energy pile with CPT data using machine learning techniques", Arab. J. Sci. Eng., 49, 4831-4860. https://doi.org/10.1007/s13369-023-08253-2. 
  21. Li, M.G., Xiao, X., Wang, J.H. and Chen, J.J. (2019), "Numerical study on responses of an existing metro line to staged deep excavations", Tunn. Undergr. Sp. Tech., 85, 268-281. https://doi.org/10.1016/j.tust.2018.12.005. 
  22. Lo, K.Y. and Ramsay, J.A. (1991), "The effect of construction on existing subway tunnels-a case study from Toronto", Tunnelling and Underground Space Technology incorporating Trenchless 6, 287-297. https://doi.org/10.1016/0886-7798(91)90140-Y. 
  23. Malhotra, M., Sahu, V., Srivastava, A. and Misra, A.K. (2020), "Experimental and numerical investigation of the effect of pre-existing utility tunnel on the bearing capacity of shallow footing in sandy soils", J. Eng. Design Tech., 18, 513-529. https://doi.org/10.1108/JEDT-04-2019-0102. 
  24. Maria, A. and Naggar, E. (2015), Effects of tunnelling on the bearing capacity of shallow foundations. In: GeoQuebec 2015. 
  25. Metya, S., Mukhopadhyay, T., Adhikari, S. and Bhattacharya, G. (2017), "System reliability analysis of soil slopes with general slip surfaces using multivariate adaptive regression splines", Comput. Geotech., 87, 212-228. https://doi.org/10.1016/j.compgeo.2017.02.017. 
  26. Miliziano, S. and de Lillis, A. (2019), "Predicted and observed settlements induced by the mechanized tunnel excavation of metro line C near S. Giovanni station in Rome", Tunn. Undergr. Sp. Tech., 86, 236-246. https://doi.org/10.1016/j.tust.2019.01.022. 
  27. Mirzaeiabdolyousefi, M., Mahmoodzadeh, A., Ibrahim, H.H., Rashidi, S., Kamal Majeed, M. and Mohammed, A.H. (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. 
  28. Moayedi, H. and Jahed Armaghani, D. (2018), "Optimizing an ANN model with ICA for estimating bearing capacity of driven pile in cohesionless soil", Eng. Comput., 34, 347-356. https://doi.org/10.1007/s00366-017-0545-7. 
  29. Nazeeh, K.M., Dilip, D.M. and Sivakumar Babu, G.L. (2023), "Quantile-based design and optimization of shallow foundation on cohesionless soil using adaptive Kriging surrogates", Int. J. Geomech., 23. https://doi.org/10.1061/ijgnai.gmeng-8226. 
  30. Pribyl, O., Pribyl, P. and Svitek, M. (2021), Interdisciplinary urban tunnel control within smart cities, Applied Sciences (Switzerland), 11. https://doi.org/10.3390/app112210950. 
  31. Rabbani, A., Muslih, J.A., Saxena, M., Patil, S.K., Mulay, B.N., Tiwari, M., Usha, A., Kumari, S. and Samui, P. (2024), "Utilization of tree-based ensemble models for predicting the shear strength of soil", Transport. Infrastruct. Geotech., https://doi.org/10.1007/s40515-024-00379-6. 
  32. Rajabi, A.M., Saadati, M., Mahmoudi, M. and Fijani, E. (2022), "Effect of the circular cavity on the undrained bearing capacity of shallow strip footing", Arabian J. Geosci., 15, 1-10. https://doi.org/10.1007/s12517-022-10503-w. 
  33. Sabouni, R. and Airan Eng, M. (2018), "Evaluation of foundation on soil with cavities: A case study from the UAE", Int. J. Struct. Civil Eng. Res., 358-363. https://doi.org/10.18178/ijscer.7.4.358-363. 
  34. Shahin, H.M., Nakai, T., Ishii, K., Iwata, T. and Kuroi, S. (2016), "Investigation of influence of tunneling on existing building and tunnel: Model tests and numerical simulations", Acta Geotech., 11, 679-692. https://doi.org/10.1007/s11440-015-0428-2. 
  35. Shubham, K., Metya, S. and Bhattacharya, G. (2022), "Reliability analysis of settlement of a foundation resting over a circular void", (Eds., Satyanarayana Reddy, C.N.V., Krishna, A.M. and Satyam, N.), Dynamics of Soil and Modelling of Geotechnical Problems. Lecture Notes in Civil Engineering, 186th edn. Springer, Singapore. 
  36. Shubham, K., Metya, S. and Sinha, A.K. (2023a), "Surrogate model-based prediction of settlement in foundation over cavity for reliability analysis", Transport. Infrastruct. Geotech.,. https://doi.org/10.1007/s40515-023-00329-8. 
  37. Shubham, K., Rout, M.K.D. and Sinha, A.K. (2023b), "Efficient compressive strength prediction of concrete incorporating industrial wastes using deep neural network", Asian J. Civil Eng., https://doi.org/10.1007/s42107-023-00726-x. 
  38. Sohaei, H., Namazi, E., Hajihassani, M. and Marto, A. (2020), "A review on tunnel-pile interaction applied by physical modeling", Geotech. Geol. Eng., 38, 3341-3362. https://doi.org/10.1007/s10706-020-01240-6. 
  39. Srivastava, A., Kothari, S. and Jawaid, S. (2024), "Numerical simulation-based performance assessment of pile group placed over buried utility tunnel", Iranian J. Sci. Tech. T. Civil Eng., https://doi.org/10.1007/s40996-023-01321-5. 
  40. Wang, M.C. and Hsieh, C.W. (1987), Collapse Load of Strip Footing Above Circular Void., 113, 511-515.  https://doi.org/10.1061/(ASCE)0733-9410(1987)113:5(511)
  41. Wu, G., Zhao, M., Zhao, H. and Xiao, Y. (2020), "Effect of eccentric load on the undrained bearing capacity of strip footings above voids", Int. J. Geomech., 20, 04020078. https://doi.org/10.1061/(asce)gm.1943-5622.0001710. 
  42. Xue, Y., Li, X., Li, G., Qiu, D., Gong, H. and Kong, F. (2020), "An analytical model for assessing soft rock tunnel collapse risk and its engineering application", Geomech. Eng., 23(5), 441-454. https://doi.org/10.12989/gae.2020.23.5.441. 
  43. Yu, Z.T., Wang, H.Y., Wang, W., Ling, D.S., Zhang, X.D., Wang, C. and Qu, Y.H. ( 2021), "Experimental and numerical investigation on the effects of foundation pit excavation on adjacent tunnels in soft soil", Math. Probl. Eng., https://doi.org/10.1155/2021/5587857. 
  44. Zhang, W., Gu, X., Tang, L., Yin, Y., Liu, D. and Zhang, Y. (2022), "Application of machine learning, deep learning and optimization algorithms in geoengineering and geoscience: Comprehensive review and future challenge", Gondwana Res., 109, 1-17. https://doi.org/10.1016/j.gr.2022.03.015.