Structural Engineering and Mechanics

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Predicting the CPT-based pile set-up parameters using HHO-RF and PSO-RF hybrid models

  • Yun Dawei (Department of Information Engineering, Hainan Vocational University of Science and Technology) ;
  • Zheng Bing (Department of Information Engineering, Hainan Vocational University of Science and Technology) ;
  • Gu Bingbing (Department of Information Engineering, Hainan Vocational University of Science and Technology) ;
  • Gao Xibo (Department of Information Engineering, Hainan Vocational University of Science and Technology) ;
  • Behnaz Razzaghzadeh (Civil Engineering Department, University of Mohaghegh Ardabili)
  • Received : 2021.10.03
  • Accepted : 2023.04.28
  • Published : 2023.06.10
⟨ Previous Next ⟩

Abstract

Determining the properties of pile from cone penetration test (CPT) is costly, and need several in-situ tests. At the present study, two novel hybrid learning models, namely PSO-RF and HHO-RF, which are an amalgamation of random forest (RF) with particle swarm optimization (PSO) and Harris hawks optimization (HHO) were developed and applied to predict the pile set-up parameter "A" from CPT for the design aim of the projects. To forecast the "A," CPT data along were collected from different sites in Louisiana, where the selected variables as input were plasticity index (PI), undrained shear strength (Su), and over consolidation ratio (OCR). Results show that both PSO-RF and HHO-RF models have acceptable performance in predicting the set-up parameter "A," with R2 larger than 0.9094, representing the admissible correlation between observed and predicted values. HHO-RF has better proficiency than the PSO-RF model, with R2 and RMSE equal to 0.9328 and 0.0292 for the training phase and 0.9729 and 0.024 for testing data, respectively. Moreover, PI and OBJ indices are considered, in which the HHO-RF model has lower results which leads to outperforming this hybrid algorithm with respect to PSO-RF for predicting the pile set-up parameter "A," consequently being specified as the proposed model. Therefore, the results demonstrate the ability of the HHO algorithm in determining the optimal value of RF hyperparameters than PSO.

Keywords

Acknowledgement

Hainan Natural Science Foundation of 2021 High-level Talents project "Research and application of Student Service Group Clustering and community Model based on Big Data mode" (No. 621RC611).

References

  1. Abdelsalam, M., Diab, H.Y. and El-Bary, A.A. (2021), "A metaheuristic harris hawk optimization approach for coordinated control of energy management in distributed generation based microgrids", Appl. Sci., 11(9), 4085. https://doi.org/10.3390/app11094085. 
  2. Abu-Farsakh, M.Y. and Mojumder, M.A.H. (2020), "Exploring Artificial Neural Network to evaluate the undrained shear strength of soil from cone penetration test data", Transp. Res. Record, 2674(4), 11-22. https://doi.org/10.1177/0361198120912426. 
  3. Ahmad, M.W., Mourshed, M. and Rezgui, Y. (2017), "Trees vs neurons: Comparison between random forest and ANN for high-resolution prediction of building energy consumption", Energy Build., 147, 77-89. https://doi.org/10.1016/j.enbuild.2017.04.038. 
  4. Aghayari Hir, M., Zaheri, M. and Rahimzadeh, N. (2022), "Prediction of rural travel demand by spatial regression and artificial neural network methods (Tabriz County)", J. Transp. Res., https://doi.org/10.22034/TRI.2022.312204.2970. 
  5. ASTM D2850-03 (2017), Standard Test Method for Unconsolidated-Undrained Triaxial CompressionTest on Cohesive Soils, https://doi.org/10.1520/D2850-03. 
  6. ASTM D3441-16 (2018), Standard Test Method for Mechanical Cone Penetration Testing of Soils, https://doi.org/10.1520/D3441-16. 
  7. Archer, K.J. and Kimes, R.V. (2008), "Empirical characterization of random forest variable importance measures", Comput. Stat. Data Anal., 52(4), 2249-2260. https://doi.org/10.1016/j.csda.2007.08.015. 
  8. Axelsson, G. (1998), "Long-term set-up of driven piles in non-cohesive soils evaluated from dynamic tests on penetration rods", Geotechnical Site Characterization, 895-900. 
  9. Babbar, A., Prakash, C., Singh, S., Gupta, M.K., Mia, M. and Pruncu, C.I. (2020), "Application of hybrid nature-inspired algorithm: Single and bi-objective constrained optimization of magnetic abrasive finishing process parameters", J. Mater. Res. Technol., 9(4), 7961-7974. https://doi.org/10.1016/j.jmrt.2020.05.003. 
  10. Bednarz, J.C. (1988), "Cooperative Hunting Harris' Hawks (Parabuteo unicinctus)", Sci., 239(4847), 1525-1527.  https://doi.org/10.1126/science.239.4847.1525
  11. Benemaran, R.S. and Esmaeili-Falak, M. (2020), "Optimization of cost and mechanical properties of concrete with admixtures using MARS and PSO", Comput. Concrete, 26(4), 309-316. https://doi.org/10.12989/cac.2020.26.4.309. 
  12. Bergahl, U. (1981), "Load tests on friction piles in clay", Proc. 10th Int. Conf. on SMFE, 625-630. 
  13. Biau, G., Devroye, L. and Lugosi, G. (2008), "Consistency of random forests and other averaging classifiers", J. Mach. Learn. Res., 9(9), 2015-2033. 
  14. Bond, A.J. and Jardine, R.J. (1991), "Effects of installing displacement piles in a high OCR clay", Geotechniq., 41(3), 341-363. https://doi.org/10.1680/geot.1991.41.3.341. 
  15. Breiman, L. (2001), "Random forests", Mach. Learn., 45(1), 5-32. https://doi.org/10.1023/A:1010933404324. 
  16. Bullock, P.J. (2008), "The easy button for driven pile setup: dynamic testing", From Research to Practice in Geotechnical Engineering, 471-488. https://doi.org/10.1061/40962(325)17. 
  17. Bullock, P.J., Schmertmann, J.H., McVay, M.C. and Townsend, F.C. (2005), "Side shear setup. I: Test piles driven in Florida", J. Geotech. Geoenviron. Eng., 131(3), 292-300. https://doi.org/10.1061/(ASCE)1090-0241(2005)131:3(292). 
  18. Bullock, P.J. (1999). Pile Friction Freeze: A Field and Laboratory Study, University of Florida. 
  19. Camp III, W.M. and Parmar, H.S. (1999), "Characterization of pile capacity with time in the cooper marl: Study of applicability of a past approach to predict long-term pile capacity", Transp. Res. Record, 1663(1), 16-24. https://doi.org/10.3141/1663-03. 
  20. Chen, L., Li, Y., Zhao, G., Zhang, C. and Gao, F. (2020), "Multi-objective optimization and experimental investigation on hot extruded plate of high strength Al-Zn-Mg alloy", J. Mater. Res. Technol., 9(1), 507-519. https://doi.org/10.1016/j.jmrt.2019.10.080. 
  21. Chen, W., Xie, X., Wang, J., Pradhan, B., Hong, H., Bui, D.T., ... & Ma, J. (2017), "A comparative study of logistic model tree, random forest, and classification and regression tree models for spatial prediction of landslide susceptibility", Catena, 151, 147-160. https://doi.org/10.1016/j.catena.2016.11.032. 
  22. Chen, W., Wang, Y., Cao, G., Chen, G. and Gu, Q. (2014), "A random forest model based classification scheme for neonatal amplitude-integrated EEG", Biomed. Eng. Online, 13(2), 1-13. https://doi.org/10.1186/1475-925X-13-S2-S4. 
  23. Chow, F.C., Jardine, R.J., Brucy, F. and Nauroy, J.F. (1998), "Effects of time on capacity of pipe piles in dense marine sand", J. Geotech. Geoenviron. Eng., 124(3), 254-264. https://doi.org/10.1061/(ASCE)1090-0241(1998)124:3(254). 
  24. Duan, L., Wu, M. and Wang, Q. (2022), "Predicting the CPT-based pile set-up parameters using HHO-RF and WOA-RF hybrid models", Arab. J. Geosci., 15(7), 602. https://doi.org/10.1007/s12517-022-09843-4. 
  25. Elias, M.B. (2008), Numerical Simulation of Pile Installation and Setup. 
  26. Elsheikh, A.H., Abd Elaziz, M., Ramesh, B., Egiza, M. and Alqaness, M.A. (2021), "Modeling of drilling process of GFRP composite using a hybrid random vector functional link network/parasitism-predation algorithm", J. Mater. Res. Technol., 14, 298-311. https://doi.org/10.1016/j.jmrt.2021.06.033. 
  27. Esmaeili-Falak, M. and Hajialilue-Bonab, M. (2012), "Numerical studying the effects of gradient degree on slope stability analysis using limit equilibrium and finite element methods", Int. J. Acad. Res., 4(4), 216-22. https://doi.org/10.7813/2075-4124.2012/4-4/A.30. 
  28. Esmaeili-Falak, M., Katebi, H. and Javadi, A. (2018), "Experimental study of the mechanical behavior of frozen soils-A case study of tabriz subway", Periodica Polytechnica Civil Eng., 62(1), 117-125. https://doi.org/10.3311/PPci.10960. 
  29. Esmaeili-Falak, M., Katebi, H., Vadiati, M. and Adamowski, J. (2019), "Predicting triaxial compressive strength and Young's modulus of frozen sand using artificial intelligence methods", J. Cold Region. Eng., 33(3), 4019007. https://doi.org/10.1061/(ASCE)CR.1943-5495.0000188. 
  30. Esmaeili Falak, M. and Sarkhani Benemaran, R. (2022), "Investigating the stress-strain behavior of frozen clay using triaxial test", J. Struct. Constr. Eng., 10(1), 1. https://doi.org/10.22065/JSCE.2022.332406.2747. 
  31. Esmaeili-Falak, M. and Benemaran, R.S. (2023), "Ensemble deep learning-based models to predict the resilient modulus of modified base materials subjected to wet-dry cycles", Geomech. Eng., 32(6), 583-600. https://doi.org/10.12989/gae.2023.32.6.583. 
  32. Ge, D.M., Zhao, L.C. and Esmaeili-Falak, M. (2023), "Estimation of rapid chloride permeability of SCC using hyperparameters optimized random forest models", J. Sustain. Cement-Bas. Mater., 12(5), 542-560. https://doi.org/10.1080/21650373.2022.2093291. 
  33. Guang-Yu, Z. (1988), "Wave equation applications for piles in soft ground", Proceeding Third International Conference on the Application of Stress-Wave Theory to Piles, Ottawa, Canada.
  34. Hammerstrom, D. (1993), "Neural networks at work", IEEE Spectrum, 30(6), 26-32. https://doi.org/10.1109/6.214579. 
  35. Haque, M.N., Abu-Farsakh, M.Y., Chen, Q. and Zhang, Z. (2014), "Case study on instrumenting and testing full-scale test piles for evaluating setup phenomenon", Transp. Res. Record, 2462(1), 37-47. https://doi.org/10.3141/2462-05. 
  36. Haque, M.N. (2015), "Field instrumentation and testing to study set-up phenomenon of driven piles and its implementation in LRFD design methodology", Louisiana State University and Agricultural & Mechanical College. 
  37. Heidari, A.A., Mirjalili, S., Faris, H., Aljarah, I., Mafarja, M. and Chen, H. (2019), "Harris Hawks optimization: Algorithm and applications", Future Gener. Comput. Syst., 97, 849-872. https://doi.org/10.1016/j.future.2019.02.028. 
  38. Hoang, N.D., Chen, C.T. and Liao, K.W. (2017), "Prediction of chloride diffusion in cement mortar using multi-gene genetic programming and multivariate adaptive regression splines", Measure., 112, 141-149. https://doi.org/10.1016/j.measurement.2017.08.031. 
  39. Hong, H., Pourghasemi, H.R. and Pourtaghi, Z.S. (2016), "Landslide susceptibility assessment in Lianhua County (China), A comparison between a random forest data mining technique and bivariate and multivariate statistical models", Geomorphol., 259, 105-18. https://doi.org/10.1016/j.geomorph.2016.02.012. 
  40. Kennedy, J. and Eberhart, R. (1995), "Particle swarm optimization", Proceedings of ICNN'95-International Conference on Neural Networks, IEEE, 4, 1942-1948. 
  41. Khoshaim, A.B., Elsheikh, A.H., Moustafa, E.B., Basha, M. and Mosleh, A.O. (2021), "Prediction of residual stresses in turning of pure iron using artificial intelligence-based methods", J. Mater. Res. Technol., 11, 2181-2194. https://doi.org/10.1016/j.jmrt.2021.02.042. 
  42. Komurka, V.E., Wagner, A.B. and Edil, T.B. (2003). Estimating Soil/Pile Set-Up, Wisconsin Highway Research Program, No. Report No. 03-05, Madison, WI, USA. 
  43. Lee, J., Prezzi, M. and Salgado, R. (2011), "Experimental investigation of the combined load response of model piles driven in sand", Geotech. Test. J., 34(6), 653-667. https://doi.org/10.1520/GTJ103269. 
  44. Lee, W., Kim, D., Salgado, R. and Zaheer, M. (2010), "Setup of driven piles in layered soil", Soil. Found., 50(5), 585-598. https://doi.org/10.3208/sandf.50.585. 
  45. Liaw, A. and Matthew, W. (2002), "Classification and Regression by RandomForest", R News, 2(3), 18-22. 
  46. 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), 439-453. https://doi.org/10.12989/gae.2021.25.6.439. 
  47. Looney, C.G. (1996), "Advances in feedforward neural networks: Demystifying knowledge acquiring black boxes", IEEE Trans. Knowl. Data Eng., 8(2), 211-226. https://doi.org/10.1109/69.494162. 
  48. 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), 385-397. https://doi.org/10.12989/gae.2020.20.5.385. 
  49. McVay, M.C., Schmertmann, J., Townsend, F. and Bullock, P. (1999), "Pile friction freeze: A field investigation study", Research Report No. WPI 0510632. 
  50. Moayedi, H. and Mosavi, A. (2021), "Synthesizing multi-layer perceptron network with ant lion biogeography-based dragonfly algorithm evolutionary strategy invasive weed and league champion optimization hybrid algorithms in predicting heating load in residential buildings", Sustain., 13(6), 3198. https://doi.org/10.3390/su13063198. 
  51. Mohammad, L.N., Raghavendra, P.A., Medeiros Jr, P.M. and Hassan, M. (2018), Louisiana Transportation Research Center, Contract, 3, 3B. 
  52. Mojumder, M.A.H. (2020), "Evaluation of undrained shear strength of soil, ultimate pile capacity and pile set-up parameter from Cone Penetration Test (CPT) Using Artificial Neural Network (ANN)", Louisiana State University and Agricultural & Mechanical College. 
  53. Ng, K.W., Roling, M., AbdelSalam, S.S., Suleiman, M.T. and Sritharan, S. (2013), "Pile setup in cohesive soil. II: Analytical quantifications and design recommendations", J. Geotech. Geoenviron. Eng., 139(2), 210-222. https://doi.org/10.1061/(ASCE)GT.1943-5606.0000753. 
  54. Nhu, V.H., Hoang, N.D., Duong, V.B., Vu, H.D. and Tien Bui, D. (2020), "A hybrid computational intelligence approach for predicting soil shear strength for urban housing construction: A case study at Vinhomes Imperia Project, Hai Phong City (Vietnam)", Eng. Comput., 36(2), 603-616. https://doi.org/10.1007/s00366-019-00718-z. 
  55. Paikowsky, S.G., Regan, J.E. and McDonnell, J.J. (1994), "A simplified field method for capacity evaluation of driven piles", Federal Highway Administration. 
  56. Pham, B.T., Qi, C., Ho, L.S., Nguyen-Thoi, T., Al-Ansari, N., Nguyen, M.D., ... & Prakash, I. (2020), "A novel hybrid soft computing model using random forest and particle swarm optimization for estimation of undrained shear strength of soil", Sustain., 12(6), 2218. https://doi.org/10.3390/su12062218. 
  57. Qi, C., Chen, Q., Fourie, A. and Zhang, Q. (2018), "An intelligent modelling framework for mechanical properties of cemented paste backfill", Miner. Eng., 123, 16-27. https://doi.org/10.1016/j.mineng.2018.04.010. 
  58. Qin, W., Wang, L., Liu, Y. and Xu, C. (2021), "Energy consumption estimation of the electric bus based on grey wolf optimization algorithm and support vector machine regression", Sustain., 13(9), 4689. https://doi.org/10.3390/su13094689. 
  59. Richardson, B.D. (2011), A Case Study on Pile Relaxation in Dilative Silts, University of Rhode Island. 
  60. Samson, L. and Authier, J. (1986), "Change in pile capacity with time: Case histories", Can. Geotech. J., 23(2), 174-180. https://doi.org/10.1139/t86-027. 
  61. Sarkhani Benemaran, R., Esmaeili-Falak, M. and Katebi, H. (2020), "Physical and numerical modelling of pile-stabilised saturated layered slopes", Proc. Inst. Civil Eng.-Geotech. Eng., 175(5), 523-538. https://doi.org/10.1680/jgeen.20.00152. 
  62. Sarkhani Benemaran, R., Esmaeili-Falak, M. and Javadi, A. (2022), "Predicting resilient modulus of flexible pavement foundation using extreme gradient boosting based optimised models", Int. J. Pave. Eng., 1-20. https://doi.org/10.1080/10298436.2022.2095385. 
  63. Benemaran, R.S. (2023), "Application of extreme gradient boosting method for evaluating the properties of episodic failure of borehole breakout", Geoenergy Sci. Eng., 226, 211837. https://doi.org/10.1016/j.geoen.2023.211837. 
  64. Schmertmann, J.H. (1991), "The mechanical aging of soils", J. Geotech. Eng., 117(9), 1288-1330. https://doi.org/10.1061/(ASCE)0733-9410(1991)117:9(1288). 
  65. Shahin, M.A., Maier, H.R. and Jaksa, M.B. (2004), "Data division for developing neural networks applied to geotechnical engineering", J. Comput. Civil Eng., 18(2), 105-114. https://doi.org/10.1061/(ASCE)0887-3801(2004)18:2(105). 
  66. Shehabeldeen, T.A., Abd Elaziz, M., Elsheikh, A.H. and Zhou, J. (2019), "Modeling of friction stir welding process using adaptive Neuro-Fuzzy inference system integrated with Harris Hawks optimizer", J. Mater. Res. Technol., 8(6), 5882-5892. https://doi.org/10.1016/j.jmrt.2019.09.060. 
  67. Shi, Y. and Eberhart, R.C. (1998), "Parameter Selection in particle swarm optimization", Evolutionary Programming VII: 7th International Conference, EP98 San Diego, California, USA, March. 
  68. Shi, X., Yu, X. and Esmaeili-Falak, M. (2023), "Improvedarithmetic optimization algorithm and its application to carbon fiber reinforced polymer-steel bond strength estimation", Compos. Struct., 306, 116599. https://doi.org/10.1016/j.compstruct.2022.116599. 
  69. Shozib, I.A., Ahmad, A., Rahaman, M.S.A., majdi Abdul-Rani, A., Alam, M.A., Beheshti, M. and Taufiqurrahman, I. (2021), "Modelling and optimization of microhardness of electroless Ni-P-TiO2 composite coating based on machine learning approaches and RSM", J. Mater. Res. Technol., 12, 1010-1025. https://doi.org/10.1016/j.jmrt.2021.03.063. 
  70. Skov, R. and Denver, H. (1988), "Time-dependence of bearing capacity of piles", Proceedings of the Third International Conference on the Application of Stress-Wave Theory to Piles, Ottawa, May. 
  71. Steward, E.J. and Wang, X. (2011), "Predicting pile setup (Freeze), A new approach considering soil aging and pore pressure dissipation", Geo-Frontiers 2011: Advances in Geotechnical Engineering, 11-19. https://doi.org/10.1061/41165(397)2. 
  72. Stone, M. (1974), "Cross-validatory choice and assessment of statistical predictions", J. Roy. Stat. Soc.: Ser. B (Methodolog.), 36(2), 111-133. https://doi.org/10.1111/j.2517-6161.1974.tb00994.x. 
  73. Stumpf, A. and Kerle, N. (2011), "Object-oriented mapping of landslides using random forests", Remote Sens. Environ., 115(10), 2564-2577. https://doi.org/10.1016/j.rse.2011.05.013. 
  74. Sun, D., Wen, H., Wang, D. and Xu, J. (2020), "A random forest model of landslide susceptibility mapping based on hyperparameter optimization using Bayes algorithm", Geomorph., 362, 107201. https://doi.org/10.1016/j.geomorph.2020.107201. 
  75. Svinkin, M.R., Morgano, C.M. and Morvant, M. (1994), "Pile capacity as a function of time in clayey and sandy soils", Deep Foundations Institute Fifth International Conference and Exhibition on Piling and Deep Foundations, June. 
  76. Trelea, I.C. (2003), "The particle swarm optimization algorithm: Convergence analysis and parameter selection", Inform. Proc. Lett., 85(6), 317-325. https://doi.org/10.1016/S0020-0190(02)00447-7. 
  77. Trigila, A., Iadanza, C., Esposito, C. and Scarascia-Mugnozza, G. (2015), "Comparison of logistic regression and random forests techniques for shallow landslide susceptibility assessment in Giampilieri (NE Sicily, Italy)", Geomorph., 249, 119-136. https://doi.org/10.1016/j.geomorph.2015.06.001. 
  78. Wang, J., Fa, Y., Tian, Y. and Yu, X. (2021), "A machine-learning approach to predict creep properties of Cr-Mo steel with time-temperature parameters", J. Mater. Res. Technol., 13, 635-650. https://doi.org/10.1016/j.jmrt.2021.04.079. 
  79. Wang, S.T. and Reese, L.C. (1989), "Predictions of response of piles to axial loading", Predicted and Observed Axial Behavior of Piles: Results of a Pile Prediction Symposium, ASCE, 173-187. 
  80. 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. 
  81. Yu, Z., Shi, X., Zhou, J., Chen, X. and Qiu, X. (2020), "Effective assessment of blast-induced ground vibration using an optimized random forest model based on a Harris Hawks optimization algorithm", App. Sci., 10(4), 1403. https://doi.org/10.3390/app10041403. 
  82. Zhang, P., Yin, Z.Y., Jin, Y.F. and Chan, T.H. (2020), "A novel hybrid surrogate intelligent model for creep index prediction based on particle swarm optimization and random forest", Eng. Geology, 265, 105328. https://doi.org/10.1016/j.enggeo.2019.105328. 
  83. Zhao, Z., Chen, S., Zhang, D., Peng, B., Li, X. and Zheng, Q. (2022), "Utilizing the GOA-RF hybrid model, predicting the CPT-based pile set-up parameters", Geomech. Eng., 31(1), 113. https://doi.org/10.12989/gae.2022.31.1.113.