Steel and Composite Structures

  • 제53권4호
  • /
  • Pages.377-399
  • /
  • 2024
  • /
  • 1229-9367(pISSN)
  • /
  • 1598-6233(eISSN)
테크노프레스 (Techno-Press)
권호 표지
DOI QR코드

DOI QR Code

Hybrid predictive machine learning models to evaluate the bearing capacity of concrete and steel piles

  • Mesut Gor (Department of Civil Engineering, Engineering Faculty, Firat University)
  • 투고 : 2024.03.15
  • 심사 : 2024.10.21
  • 발행 : 2024.11.25
⟨ 이전 논문 다음 논문 ⟩

초록

Accurately predicting the bearing capacity of steel and concrete piles is a critical factor in the design and safety of deep foundations. This study presents a novel application of hybrid machine learning models, specifically Invasive Weed Optimization with Multilayer Perceptron (IWOMLP) and Harris Hawks Optimization with Multilayer Perceptron (HHOMLP), for enhancing the prediction of pile bearing capacity. These hybrid models integrate evolutionary optimization algorithms with neural networks, aiming to improve prediction accuracy by addressing the nonlinearities and complexities in pile-soil interaction. The study compares the performance of IWOMLP and HHOMLP against conventional machine learning methods such as Simple Linear Regression, Gaussian Processes, Random Forest, and others. The training and testing phases evaluate the models based on various error metrics, including R2, RMSE, MAE, and additional advanced metrics. The key innovation in this research lies in combining optimization techniques with neural networks, which significantly enhances the model's ability to predict complex geotechnical properties. The primary goal of this work is to develop a reliable, data-driven approach for accurate pile capacity prediction, providing a more precise tool for geotechnical engineers to improve decision-making in foundation design. Results indicate that the hybrid models, particularly IWOMLP, outperform traditional approaches, achieving higher R2 and lower RMSE values. This research demonstrates the potential of hybrid models to advance geotechnical engineering practices by delivering more accurate and reliable predictions.

키워드

References

  1. Al-Jeznawi, D., Khatti, J., Al-Janabi, M.A.Q., Grover, K.S., Jais, I.B.M., Albusoda, B.S. and Khalid, N. (2023), "Seismic performance assessment of single pipe piles using three-dimensional finite element modeling considering different parameters", Earthq. Struct., 24(6), 455-475. https://doi.org/10.12989/eas.2023.24.6.455.
  2. Amjad, M., Ahmad, I., Ahmad, M., Wroblewski, P., Kaminski, P. and Amjad, U. (2022), "Prediction of pile bearing capacity using XGBoost algorithm: Modeling and performance evaluation", Appl. Sci., 12(4), 2126. https://doi.org/10.3390/app12042126.
  3. Badgujar, C., Das, S., Figueroa, D.M. and Flippo, D. (2023), "Application of computational intelligence methods in agricultural soil-machine interaction: A review", Agriculture, 13(2), 357. https://doi.org/10.3390/agriculture13020357.
  4. Badhon, F.F. (2021), Performance of Recycled Plastic Pins for Increasing Bearing Capacity of Foundation Soil, The University of Texas at Arlington.
  5. Bao, X., Jia, H. and Lang, C. (2019), "A novel hybrid harris hawks optimization for color image multilevel thresholding segmentation", IEEE Access, 7, 76529-76546. https://doi.org/10.1109/ACCESS.2019.2921545.
  6. Bardhan, A., Manna, P., Kumar, V., Burman, A., Zlender, B. and Samui, P. (2021), "Reliability analysis of piled raft foundation using a novel hybrid approach of ANN and equilibrium optimizer", CMES-Comput. Modeling Eng. Sci., 128(3), https://doi.org/10.32604/cmes.2021.015885.
  7. Benali, A., Hachama, M., Bounif, A., Nechnech, A. and Karray, M. (2021), "A TLBO-optimized artificial neural network for modeling axial capacity of pile foundations", Eng. Comput., 37(1), 675-684. https://doi.org/10.1007/s00366-019-00847-5.
  8. Berke, L. and Hajela, P. (1993), Optimization of Large Structural Systems. Springer, 731-745.
  9. Bloodworth, A. and Su, J. (2018), "Numerical analysis and capacity evaluation of composite sprayed concrete lined tunnels", Underg. Space 3(2), 87-108. https://doi.org/10.1016/j.undsp.2017.12.001.
  10. Change, I.C. (2007), The Physical Science Ba-sis. Contribution of Working Group 1 to the Fourth Assessment Report ofthe Intergovernmental Panel on Climate Change. Cambridge. UK.
  11. Chen, S., Zhang, H., Zykova, K.I., Touchaei, H.G., Yuan, C., Moayedi, H. and Le, B.N. (2023), "Computational intelligence models for predicting the frictional resistance of driven pile foundations in cold regions", Comput. Concrete, 32(2), 217-232. https://doi.org/10.12989/cac.2023.32.2.217.
  12. Daniel, C., Khatti, J. and Grover, K.S. (2024), "Assessment of compressive strength of high-performance concrete using soft computing approaches", Comput. Concrete, 33(1), 55. https://doi.org/10.12989/cac.2024.33.1.055.
  13. Dutta, S., Samui, P. and Kim, D. (2018), "Comparison of machine learning techniques to predict compressive strength of concrete", Comput. Concr 21(4), 463-470. https://doi.org/10.12989/cac.2018.21.4.463.
  14. Ehteram, M., Ferdowsi, A., Faramarzpour, M., Al-Janabi, A.M.S., Al-Ansari, N., Bokde, N.D. and Yaseen, Z.M. (2021), "Hybridization of artificial intelligence models with nature inspired optimization algorithms for lake water level prediction and uncertainty analysis", Alexandria Eng. J., 60(2), 2193-2208. https://doi.org/10.1016/j.aej.2020.12.034.
  15. Fan, S., He, T., Li, W., Zeng, C., Chen, P., Chen, L. and Shu, J. (2024), "Machine learning-based classification of quality grades for concrete vibration behaviour", Automation Construct., 167, 105694. https://doi.org/10.1016/j.autcon.2024.105694.
  16. Fang, H.-Y. (2013), Foundation Engineering Handbook. Springer Science & Business Media.
  17. Firoozi, A.A. and Firoozi, A.A. (2023), "Application of machine learning in geotechnical engineering for risk assessment", https://doi.org/10.5772/intechopen.113218.
  18. Ghasemi, M., Ghavidel, S., Akbari, E. and Vahed, A.A. (2014), "Solving non-linear, non-smooth and non-convex optimal power flow problems using chaotic invasive weed optimization algorithms based on chaos", Energy, 73, 340-353. https://doi.org/10.1016/j.energy.2014.06.026.
  19. Heidari, A.A., Mirjalili, S., Faris, H., Aljarah, I., Mafarja, M. and Chen, H. (2019), "Harris hawks optimization: Algorithm and applications", Future Generation Comput. Syst., 97, 849-872. https://doi.org/10.1016/j.future.2019.02.028.
  20. Huang, H., Li, M., Yuan, Y. and Bai, H. (2023), "Experimental research on the seismic performance of precast concrete frame with replaceable artificial controllable plastic hinges", J. Struct. Eng., 149(1), 04022222. https://doi.org/10.1061/JSENDH.STENG-11648.
  21. Hussein, F. (2022), "Deep foundations: A survey on methods of construction, methods of calculation and a real-life design calculation", Ph.D. Dissertation, Altinbas universitesi/Lisansustu Egitim Enstitusu.
  22. Isbuga, V. (2020), "Modeling of pile-soil-pile interaction in laterally loaded pile groups embedded in linear elastic soil layers", Arab. J. Geosci., 13, 1-17. https://doi.org/10.1007/s12517-020-5229-8.
  23. Izadi, A., Nazemi Sabet Soumehsaraei, M., Jamshidi Chenari, R., Moallemi, S. and Javankhoshdel, S. (2021), "Spectral bearing capacity analysis of strip footings under pseudo-dynamic excitation", Geomech. Geoeng., 16(5), 359-378. https://doi.org/10.1080/17486025.2019.1670873.
  24. Jebur, A.A., Atherton, W., Al Khaddar, R.M. and Loffill, E. (2021), "Artificial neural network (ANN) approach for modelling of pile settlement of open-ended steel piles subjected to compression load", Europ. J. Environ. Civil Eng., 25(3), 429-451. https://doi.org/10.1080/19648189.2018.1531269.
  25. Kiany, K., Baghbani, A., Abuel-Naga, H., Baghbani, H., Arabani, M. and Shalchian, M.M. (2023), "Enhancing ultimate bearing capacity prediction of cohesionless soils beneath shallow foundations with grey box and hybrid AI models", Algorithms, 16(10), 456. https://doi.org/10.3390/a16100456.
  26. Kouchami-Sardoo, I., Shirani, H., Esfandiarpour-Boroujeni, I., Besalatpour, A. and Hajabbasi, M. (2020), "Prediction of soil wind erodibility using a hybrid Genetic algorithm-Artificial neural network method", Catena, 187, 104315. https://doi.org/10.1016/j.catena.2019.104315.
  27. Kumar, M., Kumar, V., Rajagopal, B.G., Samui, P. and Burman, A. (2023), "State of art soft computing based simulation models for bearing capacity of pile foundation: a comparative study of hybrid ANNs and conventional models", Modeling Earth Syst. Environ., 9(2), 2533-2551. https://doi.org/10.1007/s40808-022-01637-7.
  28. Li, H., Zeng, J., Almadhor, A., Riahi, A., Almujibah, H., Abbas, M., Ponnore, J.J. and Assilzadeh, H. (2024), "A study on improving energy flexibility in building engineering through generalized prediction models: Enhancing local bearing capacity of concrete for engineering structures", Eng. Struct., 303, 117051. https://doi.org/10.1016/j.engstruct.2023.117051.
  29. Lu, D., Wang, G., Du, X. and Wang, Y. (2017), "A nonlinear dynamic uniaxial strength criterion that considers the ultimate dynamic strength of concrete", Int. J. Impact Eng., 103, 124-137. https://doi.org/10.1016/j.ijimpeng.2017.01.011.
  30. MacKay, D.J. (1998), "Introduction to Gaussian processes", NATO ASI Series F Comput. Syst. Sci., 168, 133-166.
  31. Mahesh, B. (2020), "Machine learning algorithms-a review", Int. J. Sci. Res., (IJSR).[Internet], 9(1), 381-386. https://doi.org/10.21275/ART20203995.
  32. Marill, K.A. (2004), "Advanced statistics: linear regression, part I: simple linear regression", Academic Emergency Medicine, 11(1), 87-93.
  33. Mehrabian, A.R. and Lucas, C. (2006), "A novel numerical optimization algorithm inspired from weed colonization", Ecological Informatics, 1(4), 355-366. https://doi.org/10.1016/j.ecoinf.2006.07.003.
  34. Milad, F., Kamal, T., Nader, H. and Erman, O.E. (2015), "New method for predicting the ultimate bearing capacity of driven piles by using Flap number", KSCE J. Civil Eng., 19(3), 611-620. https://doi.org/10.1007/s12205-013-0315-z.
  35. 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(2), 347-356. https://doi.org/10.1007/s00366-017-0545-7.
  36. Moayedi, H., Mosallanezhad, M., Rashid, A.S.A., Jusoh, W.A.W. and Muazu, M.A. (2020), "A systematic review and meta-analysis of artificial neural network application in geotechnical engineering: theory and applications", Neural Comput. Appl., 32, 495-518. https://doi.org/10.1007/s00521-019-04109-9.
  37. Moayedi, H., Varamini, N., Mosallanezhad, M., Foong, L.K. and Le, B.N. (2022), "Applicability and comparison of four nature-inspired hybrid techniques in predicting driven piles' friction capacity", Transport. Geotech., 37, 100875. https://doi.org/10.1016/j.trgeo.2022.100875.
  38. Mohajerani, A., Bosnjak, D. and Bromwich, D. (2016), "Analysis and design methods of screw piles: A review". Soils Found., 56(1), 115-128. https://doi.org/10.1016/j.sandf.2016.01.009.
  39. Murlidhar, B.R., Sinha, R.K., Mohamad, E.T., Sonkar, R. and Khorami, M. (2020), "The effects of particle swarm optimisation and genetic algorithm on ANN results in predicting pile bearing capacity", Int. J. Hydromechatronic., 3(1), 69-87. https://doi.org/10.1504/IJHM.2020.105484.
  40. Naidu, Y.R. and Ojha, A.K. (2015), "A hybrid version of invasive weed optimization with quadratic approximation", Soft Comput., 19(12), 3581-3598. https://doi.org/10.1007/s00500-015-1896-x.
  41. Nguyen, Q.V., Fatahi, B. and Hokmabadi, A.S. (2017), "Influence of size and load-bearing mechanism of piles on seismic performance of buildings considering soil-pile-structure interaction", Int. J. Geomech., 17(7), 04017007. https://doi.org/10.1061/(ASCE)GM.1943-5622.0000869.
  42. Nguyen, T., Ly, K.-D., Nguyen-Thoi, T., Nguyen, B.-P. and Doan, N.-P. (2022), "Prediction of axial load bearing capacity of PHC nodular pile using Bayesian regularization artificial neural network", Soils Found., 62(5), 101203. https://doi.org/10.1016/j.sandf.2022.101203.
  43. Niranjan, A., Nutan, D., Nitish, A., Shenoy, P.D. and Venugopal, K. (2018), "ERCR TV: Ensemble of random committee and random tree for efficient anomaly classification using voting", 2018 3rd International Conference for Convergence in Technology (I2CT) 1-5.
  44. Oluwatuyi, O.E., Ng, K. and Wulff, S.S. (2023), "Improved resistance prediction and reliability for bridge pile foundation in shales through optimal site investigation plans", Reliability Eng. Sys. Safety, 239, 109476. https://doi.org/10.1016/j.ress.2023.109476.
  45. Onyelowe, K.C., Mojtahedi, F.F., Azizi, S., Mahdi, H.A., Sujatha, E.R., Ebid, A.M., Darzi, A.G. and Aneke, F.I. (2022), "Innovative overview of SWRC application in modeling geotechnical engineering problems", Designs, 6(5), 69. https://doi.org/10.3390/designs6050069.
  46. Pham, T.A., Ly, H.-B., Tran, V.Q., Giap, L.V., Vu, H.-L.T. and Duong, H.-A.T. (2020), "Prediction of pile axial bearing capacity using artificial neural network and random forest", Appl. Sci., 10(5), 1871. https://doi.org/10.3390/app10051871.
  47. Phoon, K.-K. (2023), "What geotechnical engineers want to know about reliability", ASCE-ASME J. Risk Uncertainty Eng. Syst., Part A: Civil Eng., 9(2), 03123001. https://doi.org/10.1061/AJRUA6.RUENG-1002.
  48. Phoon, K.-K. and Tang, C. (2019), "Characterisation of geotechnical model uncertainty", Georisk: Assessment Manage. Risk Eng. Syst. Geohaz., 13(2), 101-130. https://doi.org/10.1080/17499518.2019.1585545.
  49. Phoon, K.-K., Cao, Z.-J., Ji, J., Leung, Y.F., Najjar, S., Shuku, T., Tang, C., Yin, Z.-Y., Ikumasa, Y. and Ching, J. (2022), "Geotechnical uncertainty, modeling, and decision making", Soils Found., 62(5), 101189. https://doi.org/10.1016/j.sandf.2022.101189.
  50. Qiao, W., Moayedi, H. and Foong, L.K. (2020), "Nature-inspired hybrid techniques of IWO, DA, ES, GA, and ICA, validated through a k-fold validation process predicting monthly natural gas consumption", Energy Build., 217, 110023. https://doi.org/10.1016/j.enbuild.2020.110023.
  51. Rabiei, M. and Choobbasti, A.J. (2020), "Innovative piled raft foundations design using artificial neural network", Front. Struct. Civil Eng., 14(1), 138-146. https://doi.org/10.1007/s11709-019-0585-8.
  52. Rigatti, S.J. (2017), "Random forest", J. Insurance Medicine, 47(1), 31-39.
  53. Skurichina, M. and Duin, R.P. (2002), "Bagging, boosting and the random subspace method for linear classifiers", Pattern Anal. Appl., 5, 121-135. https://doi.org/10.1007/s100440200011
  54. Taylor, K.E. (2001), "Summarizing multiple aspects of model performance in a single diagram", J. Geophy. Res. Atmos., 106(D7), 7183-7192. https://doi.org/10.1029/2000JD900719.
  55. Wang, A.X., Chukova, S.S. and Nguyen, B.P. (2022), "Implementation and analysis of centroid displacement-based k-nearest neighbors", International Conference on Advanced Data Mining and Applications, 431-443.
  56. Wang, F. and Liu, Y. (2022), "A mechanism-based simulation algorithm for crack propagation in non-uniform geomaterials", Comput. Geotech., 151, 104994. https://doi.org/10.1016/j.compgeo.2022.104994.
  57. Zhang, J. and Morris, A.J. (1998), "A sequential learning approach for single hidden layer neural networks", Neural Networks, 11(1), 65-80. https://doi.org/10.1016/S0893-6080(97)00111-1.
  58. 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.
  59. Zhang, X., Wang, S., Liu, H., Cui, J., Liu, C. and Meng, X. (2024), "Assessing the impact of inertial load on the buckling behavior of piles with large slenderness ratios in liquefiable deposits", Soil Dyn. Earthq. Eng., 176, 108322. https://doi.org/10.1016/j.soildyn.2023.108322.