Steel and Composite Structures

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Hybrid machine learning with HHO method for estimating ultimate shear strength of both rectangular and circular RC columns

  • Quang-Viet Vu (Laboratory for Computational Civil Engineering, Institute for Computational Science and Artificial Intelligence, Van Lang University) ;
  • Van-Thanh Pham (Faculty of Civil Engineering, Thuyloi University) ;
  • Dai-Nhan Le (Faculty of Building and Industrial Construction, Hanoi University of Civil Engineering) ;
  • Zhengyi Kong (Institute for Sustainable Built Environment, Heriot-Watt University) ;
  • George Papazafeiropoulos (Department of Structural Engineering, School of Civil Engineering, National Technical University of Athens) ;
  • Viet-Ngoc Pham (Faculty of Civil Engineering, Thuyloi University)
  • Received : 2023.08.16
  • Accepted : 2024.06.24
  • Published : 2024.07.25
⟨ Previous Next ⟩

Abstract

This paper presents six novel hybrid machine learning (ML) models that combine support vector machines (SVM), Decision Tree (DT), Random Forest (RF), Gradient Boosting (GB), extreme gradient boosting (XGB), and categorical gradient boosting (CGB) with the Harris Hawks Optimization (HHO) algorithm. These models, namely HHO-SVM, HHO-DT, HHO-RF, HHO-GB, HHO-XGB, and HHO-CGB, are designed to predict the ultimate strength of both rectangular and circular reinforced concrete (RC) columns. The prediction models are established using a comprehensive database consisting of 325 experimental data for rectangular columns and 172 experimental data for circular columns. The ML model hyperparameters are optimized through a combination of cross-validation technique and the HHO. The performance of the hybrid ML models is evaluated and compared using various metrics, ultimately identifying the HHO-CGB model as the top-performing model for predicting the ultimate shear strength of both rectangular and circular RC columns. The mean R-value and mean a20-index are relatively high, reaching 0.991 and 0.959, respectively, while the mean absolute error and root mean square error are low (10.302 kN and 27.954 kN, respectively). Another comparison is conducted with four existing formulas to further validate the efficiency of the proposed HHO-CGB model. The Shapely Additive Explanations method is applied to analyze the contribution of each variable to the output within the HHO-CGB model, providing insights into the local and global influence of variables. The analysis reveals that the depth of the column, length of the column, and axial loading exert the most significant influence on the ultimate shear strength of RC columns. A user-friendly graphical interface tool is then developed based on the HHO-CGB to facilitate practical and cost-effective usage.

Keywords

Acknowledgement

The authors sincerely thank the Editor and Reviewers for their constructive comments on the earlier version of the manuscript.

References

  1. Ahmed, A., Mohammed, A.M.Y. and Maekawa, K. (2021), "Correlation of high cycle fatigue behavior of circular and square reinforced concrete columns subjected to shear controlled cyclic loading", KSCE J. Civ. Eng., 25(5), 1755-1764. https://doi.org/10.1007/s12205-021-0850-y.
  2. Al-Bayati, A.F. (2023), "Shear strength of circular and rectangular reinforced concrete columns", KSCE J. Civ. Eng., 2(2013). https://doi.org/10.1007/s12205-023-0027-y.
  3. American Concrete Institute (2014), Building Code Requirements for Structural Concrete (ACI 318-14), In American Concrete Institute. Farmington Hills, MI, USA.
  4. Asteris, P.G., Lemonis, M.E., Nguyen, T.A., Van Le, H. and Pham, B.T. (2021), "Soft computing-based estimation of ultimate axial load of rectangular concrete-filled steel tubes", Steel Compos. Struct., 39(4), 471-491. https://doi.org/10.12989/scs.2021.39.4.471.
  5. Aval, S.B.B., Ketabdari, H. and Gharebaghi, S.A. (2017), "Estimating shear strength of short rectangular reinforced concrete columns using nonlinear regression and gene expression programming", Structures, 12, 13-23.
  6. Azadi Kakavand, M.R., Sezen, H. and Taciroglu, E. (2021), "Datadriven models for predicting the shear strength of rectangular and circular reinforced concrete columns", J. Struct. Eng., 147(1), 1-12. https://doi.org/10.1061/(asce)st.1943-541x.0002875.
  7. Bardhan, A., Biswas, R., Kardani, N., Iqbal, M., Samui, P., Singh, M.P. and Asteris, P.G. (2022), "A novel integrated approach of augmented grey wolf optimizer and ANN for estimating axial load carrying-capacity of concrete-filled steel tube columns", Constr. Build. Mater., 337(February), 127454. https://doi.org/10.1016/j.conbuildmat.2022.127454.
  8. Bentejac, C., Csorgo, A. and Martinez-Munoz, G. (2021), "A comparative analysis of gradient boosting algorithms", Artificial Intell. Rev., 54. https://doi.org/10.1007/s10462-020-09896-5.
  9. Biskinis, D.E., Roupakias, G.K. and Fardis, M.N. (2004), "Degradation of shear strength of reinforced concrete members with inelastic cyclic displacements", Struct. J., 101(6), 773-783.
  10. Breiman, L. (2001), "Random forests", Mach. Learn., 45(1), 5-32. https://doi.org/10.1023/A:1010933404324.
  11. Caglar, N. (2009), "Neural network based approach for determining the shear strength of circular reinforced concrete columns", Constr. Build. Mater., 23(10), 3225-3232.
  12. Canadian Standards Association (1995), A23. 3-94, Design of Concrete Structures, In Canadian Standard Association. Rexdale, Ontario.
  13. Cassese, P., De Risi, M.T. and Verderame, G.M. (2019), "A modelling approach for existing shear-critical RC bridge piers with hollow rectangular cross section under lateral loads", Bull. Earthq. Eng., 17, 237-270.
  14. Chen, T. and Guestrin, C. (2016), "XGBoost: A scalable tree boosting system", Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785-794. https://doi.org/10.1145/2939672.2939785.
  15. Cortes, C. and Vapnik, V., (1995), Support-vector networks, Mach. Learn., 20(3), 273-297. https://doi.org/10.1007/BF00994018. 
  16. Cristianini, N. and Ricci, E. (2008), Support Vector Machines, Encyclopedia of Algorithms, 928-932. https://doi.org/10.1007/978-0-387-30162-4_415.
  17. Dorogush, A.V., Ershov, V. and Gulin, A. (2018), CatBoost: Gradient Boosting with Categorical Features Support, 1-7. Retrieved from http://arxiv.org/abs/1810.11363.
  18. EC8 (2004), Eurocode 8: Design of structures for earthquake resistance - Part 1: General rules, seismic actions and rules for buildings, In European Committee for Standardization. Brussels, Belgium.
  19. Feng, D.-C., Liu, Z.-T., Wang, X.-D., Jiang, Z.-M. and Liang, S.- X., (2020), "Failure mode classification and bearing capacity prediction for reinforced concrete columns based on ensemble machine learning algorithm", Adv. Eng. Inform., 45, 101126.
  20. Fiore, A., Marano, G. C., Laucelli, D., and Monaco, P., (2014), Evolutionary modeling to evaluate the shear behavior of circular reinforced concrete columns, Adv. Civ. Eng., 2014.
  21. Freund, Y. and Mason, L., (1999), The alternating decision tree learning algorithm, Icml, 99, 124-133.
  22. Friedman, J.H. (2001), Greedy function approximation: A gradient boosting machine, Ann. Stat., 29(5), 1189-1232. https://doi.org/10.1214/aos/1013203451.
  23. Garcia, F.J.M. (2012), Design of Concrete Structures.
  24. Ghannoum, W., B, Sivaramakrishnan, S., Pujol, A.C.C., S., Yoosuf, N. and Wang, Y. (2012b), "ACI 369 rectangular column database", In Network for Earthquake Engineering Simulation. Berkeley, CA.
  25. Ghannoum, W., B. Sivaramakrishnan, S., Pujol, A.C.C., Fernando, S., Yoosuf, N. and Wang, Y. (2012a), "ACI 369 circular column database", In Network for Earthquake Engineering Simulation. Berkeley, CA.
  26. Ghannoum, W.M. and Moehle, J.P. (2012), "Rotation-based shear failure model for lightly confined RC columns", J. Struct. Eng., 138(10), 1267-1278. https://doi.org/10.1061/(asce)st.1943-541x.0000555.
  27. Ghee, A.B., Priestley, M.J.N. and Paulay, T. (1989), "Seismic shear strength of circular reinforced concrete columns", ACI Struct. J., 86(1). https://doi.org/10.14359/2634.
  28. Haido, J.H. (2022), "Prediction of the shear strength of RC beamcolumn joints using new ANN formulations", Structures, 38(February), 1191-1209. https://doi.org/10.1016/j.istruc.2022.02.046.
  29. Heidari, A.A., Mirjalili, S., Faris, H., Aljarah, I., Mafarja, M. and Chen, H. (2019), "Harris hawks optimization: Algorithm and applications", Futur. Gener. Comput. Syst., 97, 849-872. https://doi.org/10.1016/j.future.2019.02.028.
  30. Hoang, V.N., Nguyen, N.L., Tran, Q.D., Vu, Q.V. and Nguyen, X.H. (2022), "Data-driven geometry-based topology optimization", Struct. Multidiscipl. Optim., 65(2). https://doi.org/10.1007/s00158-022-03170-8
  31. Hung, C.C., Hsiao, H.J., Shao, Y. and Yen, C.H. (2023), "A comparative study on the seismic performance of RC beamcolumn joints retrofitted by ECC, FRP, and concrete jacketing methods", J. Build. Eng., 64(November 2022), 105691. https://doi.org/10.1016/j.jobe.2022.105691.
  32. Kaveh, A., Talatahari, S. and Khodadadi, N., (2020), "Stochastic paint optimizer: theory and application in civil engineering", Eng. Comput., https://doi.org/10.1007/s00366-020-01179-5.
  33. Ketabdari, H., Karimi, F. and Rasouli, M., (2020), Shear strength prediction of short circular reinforced-concrete columns using soft computing methods", Adv. Struct. Eng., 23(14), 3048-3061.
  34. Kim, S.-E., Vu, Q.-V., Papazafeiropoulos, G., Kong, Z. and Truong, V.-H. (2020), "Comparison of machine learning algorithms for regression and classification of ultimate load-carrying capacity of steel frames. Steel Compos. Struct., 37(2), 193-209. https://doi.org/10.12989/SCS.2020.37.2.193.
  35. Kong, Z., Le, D.N., Pham, T.H., Keerthan, P., George, P. and Vu, Q.V. (2024), "Hybrid machine learning with optimization algorithm and resampling methods for patch load resistance prediction of unstiffened and stiffened plate girders", Expert Syst. Appl., 249(C), 123806. https://doi.org/10.1016/j.eswa.2024.123806.
  36. Le, D.N., Pham, T.H., George, P., Kong, Z., Tran, V.L. and Vu, Q.V. (2024), "Hybrid machine learning with Bayesian optimization methods for prediction of patch load resistance of unstiffened plate girders", Prob. Eng. Mech., 76, 103624. https://doi.org/10.1016/j.probengmech.2024.103624.
  37. Le, T.-T., Asteris, P.G. and Lemonis, M.E. (2022), "Prediction of axial load capacity of rectangular concrete-filled steel tube columns using machine learning techniques", Eng. Comput., 38(4), 3283-3316. https://doi.org/10.1007/s00366-021-01461-0.
  38. Liu, X., Luo, Y., Lu, Y., Jin, Y., Vu, Q.V. and Kong, Z. (2023), "A dual attention network for automatic metallic corrosion detection in natural environment", J. Build. Eng., 75, 107014. https://doi.org/10.1016/j.jobe.2023.107014.
  39. Lundberg, S.M. and Lee, S.-I. (2017), "A unified approach to interpreting model predictions", Adv. Neural Inf. Process. Syst., 30, 4766-4775.
  40. Ma, C., Wang, S., Zhao, J., Xiao, X., Xie, C. and Feng, X. (2023), "Prediction of shear strength of RC deep beams based on interpretable machine learning", Constr. Build. Mater., 387(April), 131640. https://doi.org/10.1016/j.conbuildmat.2023.131640.
  41. Moehle, J., Elwood, K. and Sezen, H., (2001), "Gravity load collapse of Building Frames during Earthquakes, ACI Spec. Publ., 197, 215-238.
  42. Molnar, C. (2021), Interpretable Machine Learning. https://doi.org/10.1201/9780367816377-16.
  43. Nakamura, T. and Yoshimura, M. (2002), "Gravity load collapse of reinforced concrete columns with brittle failure modes, J. Asian Archit. Build. Eng., 1(1), 21-27. https://doi.org/10.3130/jaabe.1.21.
  44. Naser, M.Z. and Alavi, A. (2020), "Insights into performance fitness and error metrics for machine learning", ArXiv,abs/2006.0.
  45. Naser, M.Z., Kodur, V., Thai, H.T., Hawileh, R., Abdalla, J. and Degtyarev, V.V. (2021), "StructuresNet and FireNet: Benchmarking databases and machine learning algorithms in structural and fire engineering domains, J. Build. Eng., 44(July), 102977. https://doi.org/10.1016/j.jobe.2021.102977.
  46. Nick, H., Ashrafpoor, A. and Aziminejad, A. (2023), "Damage identification in steel frames using dual-criteria vibration-based damage detection method and artificial neural network", Structures, 51, 1833-1851. https://doi.org/https://doi.org/10.1016/j.istruc.2023.03.152.
  47. O'brien, R.M. (2007), "A caution regarding rules of thumb for variance inflation factors", Qual. & Quant., 41, 673-690.
  48. Pan, Y. and Zhang, L. (2021), Roles of artificial intelligence in construction engineering and management: A critical review and future trends", Autom. Constr., 122(October 2020), 103517. https://doi.org/10.1016/j.autcon.2020.103517.
  49. Pan, Z. and Li, B. (2013), "Truss-arch model for shear strength of shear-critical Reinforced Concrete Columns, J. Struct. Eng., 139(4), 548-560. https://doi.org/10.1061/(asce)st.1943-541x.0000677.
  50. Pham, V.-T., Thai, D.-K. and Kim, S.-E. (2024), "A novel procedure for cable damage identification of cable-stayed bridge using particle swarm optimization and machine learning", Struct. Heal. Monit., https://doi.org/10.1177/14759217241246501.
  51. Pham, V.T. and Kim, S.E. (2023), "A robust approach in prediction of RCFST columns using machine learning algorithm", Steel Compos. Struct., 46(2), 153-173. https://doi.org/10.12989/scs.2023.46.2.153.
  52. Pham, V.T., Jang, Y., Park, J.W., Kim, D.J. and Kim, S.E. (2022), "Cable damage identification of cable - stayed bridge using multi - layer perceptron and graph neural network", Steel Compos. Struct., 44(2), 241-254. https://doi.org/10.12989/scs.2022.44.2.241.
  53. Pham, V.T., Son, H.S., Kim, C.H., Jang, Y. and Kim, S.E. (2023), "A novel method for vehicle load detection in cable - stayed bridge using graph neural network", Steel Compos. Struct., 46(6), 731-744. https://doi.org/10.12989/scs.2023.46.6.731.
  54. Phan, V.T., Tran, V.L., Nguyen, V.Q. and Nguyen, D.D. (2022), "Machine learning models for predicting Shear Strength and Identifying Failure Modes of Rectangular RC Columns", Buildings, 12(10). https://doi.org/10.3390/buildings12101493.
  55. Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A.V. and Gulin, A. (2018), "Catboost: Unbiased boosting with categorical features", Adv. Neural Inf. Process. Syst., 2018-Decem(Section 4), 6638-6648.
  56. Raja, M.N., Abbas Jaffar, S.T., Bardhan, A. and Shukla, S.K. (2023), "Predicting and validating the load-settlement behavior of large-scale geosynthetic-reinforced soil abutments using hybrid intelligent modeling", J. Rock Mech. Geotech. Eng., 15(3), 773-788. https://doi.org/10.1016/j.jrmge.2022.04.012.
  57. Raja, M.N.A. and Shukla, S.K. (2021), "Predicting the settlement of geosynthetic-reinforced soil foundations using evolutionary artificial intelligence technique", Geotext. Geomembranes, 49(5), 1280-1293. https://doi.org/10.1016/j.geotexmem.2021.04.007.
  58. Raja, M.N.A., Abdoun, T. and El-Sekelly, W. (2023), "Smart prediction of liquefaction-induced lateral spreading", J. Rock Mech. Geotech. Eng. https://doi.org/10.1016/j.jrmge.2023.05.017.
  59. Rajasekaran, S., Suresh, D. and Vijayalakshmi Pai, G.A. (2002), "Application of sequential learning neural networks to civil engineering modeling problems, Eng. Comput., 18(2), 138-147. https://doi.org/10.1007/s003660200012.
  60. Refaeilzadeh, P., Tang, L. and Liu, H. (2009), "Cross-validation", Encyclopedia Database Syst., 532-538. https://doi.org/10.1007/978-0-387-39940-9_565.
  61. Reich, Y., (1997), Machine learning techniques for civil engineering problems, Comput. Civ Infrastruct Eng, 12(4), 295-310.
  62. Saatcioglu, M. and Baingo, D., (1999), "Circular high-strength concrete columns under simulated seismic loading", J. Struct. Eng., 125(3), 272-280. https://doi.org/10.1061/(asce)0733-9445(1999)125:3(272).
  63. Said, A. and Gordon, N. (2019), "Predicting shear strength of RC columns using artificial neural networks", J. Build. Mater. Struct., 6(2), 64-76.
  64. Sandeep, M.S., Tiprak, K., Kaewunruen, S., Pheinsusom, P. and Pansuk, W. (2023), "Shear strength prediction of reinforced concrete beams using machine learning", Structures, 47, 1196-1211. https://doi.org/https://doi.org/10.1016/j.istruc.2022.11.140.
  65. Sezen, H. and Moehle, J.P. (2004), "Shear strength model for lightly reinforced concrete columns", J. Struct. Eng., (November 2004), 1692-1703. https://doi.org/10.1061/(ASCE)0733-9445(2004)130.
  66. Smola, A. and Scholkopf, B. (2004), "A tutorial on support vector regression", Stat. Comput., 14, 199-222.
  67. Son, H., Pham, V.-T., Jang, Y. and Kim, S.-E. (2021), "Damage localization and severity assessment of a cable-stayed bridge using a message passing neural network", Sensors, 21(9). https://doi.org/10.3390/s21093118.
  68. Sun, H., Burton, H.V. and Huang, H. (2021), "Machine learning applications for building structural design and performance assessment: State-of-the-art review", J. Build. Eng., 33(March 2020), 101816. https://doi.org/10.1016/j.jobe.2020.101816.
  69. Tran, C.T.N. and Li, B. (2014), "Shear strength model for reinforced concrete columns with low transverse reinforcement ratios", Adv. Struct. Eng., 17(10), 1373-1385.
  70. Tran, V.L. and Kim, S.E. (2020), "Efficiency of three advanced data-driven models for predicting axial compression capacity of CFDST columns", Thin-Wall. Struct., 152(November 2019), 106744. https://doi.org/10.1016/j.tws.2020.106744.
  71. Tran, V.L., Lee, T.H., Nguyen, D.D., Nguyen, T.H., Vu, Q.V. and Phan, H.T. (2023), "Failure mode identification and shear strength prediction of rectangular hollow RC columns using novel hybrid machine learning models", Bldg., 13(12), 2914. https://doi.org/10.3390/buildings13122914.
  72. Truong, V.H., George, P., Vu, Q.V., Pham, V.T. and Kong, Z. (2021), "Predicting the patch load resistance of stiffened plate girders using machine learning algorithms", Ocean Eng., 240, 109886. https://doi.org/10.1016/j.oceaneng.2021.109886.
  73. Truong, V.H., Vu, Q.V., Thai, H.T. and Ha, M.H. (2020), "A robust method for safety evaluation of steel trusses using Gradient Tree Boosting algorithm", Adv. Eng. Softw., 147, 102825. https://doi.org/10.1016/j.advengsoft.2020.102825.
  74. Vu, Q.V., Le, D.N., Pham, T.H., Wei, G. and Tangaramvong, S. (2024), "Hybrid machine learning with moth-flame optimization methods for strength prediction of CFDST columns under compression", Steel Compos. Struct., 51(6), 679-695. https://doi.org/10.12989/scs.2024.51.6.679.
  75. Vu, Q.V., Tangaramvong, S., Van, T.H. and Papazafeiropoulos, G. (2023), "Hybrid GA-ANN and PSO-ANN methods for accurate prediction of uniaxial compression capacity of CFDST columns", Steel Compos. Struct., 47(6), 759-779. https://doi.org/10.12989/scs.2023.47.6.759.
  76. Vu, Q.V., Truong, V.H. and Thai, H.T. (2021), "Machine learningbased prediction of CFST columns using gradient tree boosting algorithm", Compos. Struct., 259(July 2020), 113505. https://doi.org/10.1016/j.compstruct.2020.113505.
  77. Wakjira, T.G., Al-Hamrani, A., Ebead, U. and Alnahhal, W. (2022), "Shear capacity prediction of FRP-RC beams using single and ensenble ExPlainable Machine learning models", Compos. Struct., 287, 115381. https://doi.org/10.1016/j.compstruct.2022.115381.
  78. Wang, J., Zhou, W., Ren, X., Su, M. and Liu, J. (2023), "A waveform-based clustering and machine learning method for damage mode identification in CFRP laminates", Compos. Struct., 312(March), 116875. https://doi.org/10.1016/j.compstruct.2023.116875.
  79. Wang, X., Zhang, X. and Shahzad, M.M. (2021), "A novel structural damage identification scheme based on deep learning framework", Structures, 29, 1537-1549. https://doi.org/https://doi.org/10.1016/j.istruc.2020.12.036.
  80. Yi, W.J., Zhou, Y., Hwang, H.J., Cheng, Z.J. and Hu, X. (2018), "Cyclic loading test for circular reinforced concrete columns subjected to near-fault ground motion", Soil Dyn. Earthq. Eng., 112(April), 8-17. https://doi.org/10.1016/j.soildyn.2018.04.026.
  81. Yu, B., Liu, S. and Li, B. (2019), "Probabilistic calibration for shear strength models of reinforced concrete columns", J. Struct. Eng., 145(5), 4019026.
  82. Zhang, Z., Zhang, Z., Di Caprio, F. and Gu, G.X. (2022), "Machine learning for accelerating the design process of double-double composite structures", Compos. Struct., 285(June 2021), 115233. https://doi.org/10.1016/j.compstruct.2022.115233.