Structural Engineering and Mechanics

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Comparison of support vector machines enabled WAVELET algorithm, ANN and GP in construction of steel pallet rack beam to column connections: Experimental and numerical investigation

  • Hossein Hasanvand (Department of Civil Engineering, Faculty of Civil & Earth Resources Engineering, Central Tehran Branch, Islamic Azad University) ;
  • Tohid Pourrostam (Department of Civil Engineering, Faculty of Civil & Earth Resources Engineering, Central Tehran Branch, Islamic Azad University) ;
  • Javad Majrouhi Sardroud (Department of Civil Engineering, Faculty of Civil & Earth Resources Engineering, Central Tehran Branch, Islamic Azad University) ;
  • Mohammad Hasan Ramasht (Department of Civil Engineering, Faculty of Civil & Earth Resources Engineering, Central Tehran Branch, Islamic Azad University)
  • Received : 2023.04.01
  • Accepted : 2023.05.13
  • Published : 2023.07.10
⟨ Previous Next ⟩

Abstract

This paper describes the experimental investigation of steel pallet rack beam-to-column connec-tions. Total behavior of moment-rotation (M-φ) curve and the effect of particular characteristics on the behavior of connection were studied and the associated load strain relationship and corre-sponding failure modes are presented. In this respect, an estimation of SPRBCCs moment and rotation are highly recommended in early stages of design and construction. In this study, a new approach based on Support Vector Machines (SVMs) coupled with discrete wavelet transform (DWT) is designed and adapted to estimate SPRBCCs moment and rotation according to four input parameters (column thickness, depth of connector and load, beam depth,). Results of SVM-WAVELET model was compared with genetic programming (GP) and artificial neural networks (ANNs) models. Following the results, SVM-WAVELET algorithm is helpful in order to enhance the accuracy compared to GP and ANN. It was conclusively observed that application of SVM-WAVELET is especially promising as an alternative approach to estimate the SPRBCCs moment and rotation.

Keywords

References

  1. Adamowski, J. and Chan, H.F. (2011), "A wavelet neural network conjunction model for groundwater level forecasting", J. Hydrol., 407(1), 28-40. https://doi.org/10.1016/j.jhydrol.2011.06.013.
  2. Bashir, R. and Ashour, A. (2012), "Neural network modelling for shear strength of concrete members reinforced with FRP bars", Compos. Part B: Eng., 43(8), 3198-3207. https://doi.org/10.1016/j.compositesb.2012.04.011.
  3. Chapelle, O., Vapnik, V., Bousquet, O. and Mukherjee, S. (2002), "Choosing multiple parameters for support vector machines", Mach. Learn., 46(1), 131-159. https://doi.org/10.1023/A:1012450327387.
  4. Chen, J., Tong, H., Yuan, J., Fang, Y. and Gu, R. (2022), "Permeability prediction model modified on Kozeny-Carman for building foundation of clay soil", Build., 12(11), 1798. https://doi.org/10.3390/buildings12111798.
  5. Chen, L., Yang, H., Song, K., Huang, W., Ren, X. and Xu, H. (2021), "Failure mechanisms and characteristics of the Zhongbao landslide at Liujing Village, Wulong, China", Landslid., 18(4), 1445-1457. https://doi.org/10.1007/s10346-020-01594-1.
  6. Chung, K.M., Kao, W.C., Sun, C.L., Wang, L.L. and Lin, C.J. (2003), "Radius margin bounds for support vector machines with the RBF kernel", Neur. Comput., 15(11), 2643-2681. https://doi.org/10.1162/089976603322385108.
  7. Ding, C., Liang, X., Yang, R., Zhang, Z. X., Guo, X., Feng, C., ... & Xie, Q. (2023), "A study of crack propagation during blasting under high in-situ stress conditions based on an improved CDEM method", Mech. Adv. Mater. Struct., 1-18. https://doi.org/10.1080/15376494.2023.2208112.
  8. Du, M., Liu, J., Ye, W., Yang, F. and Lin, G. (2022), "A new semi-analytical approach for bending, buckling and free vibration analyses of power law functionally graded beams", Struct. Eng. Mech., 81(2), 179-194. https://doi.org/10.12989/sem.2022.81.2.179.
  9. Feng, Y., Mohammadi, M., Wang, L., Rashidi, M. and Mehrabi, P. (2021), "Application of artificial intelligence to evaluate the fresh properties of self-consolidating concrete", Mater., 14(17), 4885. https://doi.org/10.3390/ma14174885.
  10. Firouzianhaji, A., Usefi, N., Samali, B. and Mehrabi, P. (2021), "Shake table testing of standard cold-formed steel storage rack", Appl. Sci., 11(4), 1821. https://doi.org/10.3390/app11041821.
  11. Friedrichs, F. and Igel, C. (2005), "Evolutionary tuning of multiple SVM parameters", Trends in Neurocomputing: 12th European Symposium on Artificial Neural Networks 2004, 64, 107-117. https://doi.org/10.1016/j.neucom.2004.11.022.
  12. Fu, Q., Gu, M., Yuan, J. and Lin, Y. (2022), "Experimental study on vibration velocity of piled raft supported embankment and foundation for ballastless high speed railway", Build., 12(11), 1982. https://doi.org/10.3390/buildings12111982.
  13. Gilbert, B.P. and Rasmussen, K.J.R. (2009), "Experimental test on steel storage rack components (No. R899)", Report R899.
  14. Gilbert, B.P., Rasmussen, K.J.R., Baldassino, N., Cudini, T. and Rovere, L. (2012), "Determining the transverse shear stiffness of steel storage rack upright frames", J. Constr. Steel Res., 78, 107-116. https://doi.org/10.1016/j.jcsr.2012.06.012.
  15. Gong, X., Wang, L., Mou, Y., Wang, H., Wei, X., Zheng, W. and Yin, L. (2022), "Improved four-channel PBTDPA control strategy using force feedback bilateral teleoperation system", Int. J. Control Autom. Syst., 20(3), 1002-1017. https://doi.org/10.1007/s12555-021-0096-y.
  16. Gu, M., Cai, X., Fu, Q., Li, H., Wang, X. and Mao, B. (2022), "Numerical analysis of passive piles under surcharge load in extensively deep soft soil", Build., 12(11), 1988. https://doi.org/10.3390/buildings12111988.
  17. Han, S., Zheng, D., Mehdizadeh, B., Nasr, E. A., Khandaker, M. U., Salman, M. and Mehrabi, P. (2023), "Sustainable design of self-consolidating green concrete with partial replacements for cement through neural-network and fuzzy technique", Sustainab., 15(6), 4752. https://doi.org/10.3390/su15064752.
  18. Han, S., Zhu, Z., Mortazavi, M., El-Sherbeeny, A.M. and Mehrabi, P. (2023), "Analytical assessment of the structural behavior of a specific composite floor system at elevated temperatures using a newly developed hybrid intelligence method", Build., 13(3), 799. https://doi.org/10.3390/buildings13030799.
  19. Hasannejad, A., Majrouhi Sardroud, J., Shirzadi Javid, A.A., Purrostam, T. and Ramesht, M.H. (2022), "An improvement in clash detection process by prioritizing relevance clashes using fuzzy-AHP methods", Build. Serv. Eng. Res. Technol., 43(4), 485-506. https://doi.org/10.1177/01436244221080023.
  20. Hsu, C.W., Chang, C.C. and Lin, C.J. (2003), "A practical guide to support vector classification", Department of Computer Science, National Taiwan University.
  21. Huang, H., Yao, Y., Liang, C. and Ye, Y. (2022), "Experimental study on cyclic performance of steel-hollow core partially encased composite spliced frame beam", Soil Dyn. Earthq. Eng., 163, 107499. https://doi.org/10.1016/j.soildyn.2022.107499.
  22. Huang, H., Xue, C., Zhang, W. and Guo, M. (2022), "Torsion design of CFRP-CFST columns using a data-driven optimization approach", Eng. Struct., 251, 113479. https://doi.org/10.1016/j.engstruct.2021.113479.
  23. Jain, P., Garibaldi, J.M. and Hirst, J.D. (2009), "Supervised machine learning algorithms for protein structure classification", Comput. Biol. Chem., 33(3), 216-223. https://doi.org/10.1016/j.compbiolchem.2009.04.004.
  24. Jawerth, B. and Sweldens, W. (1994), "An overview of wavelet based multiresolution analyses", SIAM Rev., 36(3), 377-412. https://doi.org/10.1137/1036095.
  25. Ji, Y. and Sun, S. (2013), "Multitask multiclass support vector machines: Model and experiments", Pattern Recog., 46(3), 914-924. https://doi.org/10.1016/j.patcog.2012.08.010.
  26. Jiang, J., Ye, M., Chen, L., Zhu, Z. and Wu, M. (2023), "Study on static strength of Q690 built-up K-joints under axial loads", Struct., 51, 760-775. https://doi.org/10.1016/j.istruc.2023.03.034.
  27. Kalteh, A.M. (2013), "Monthly river flow forecasting using artificial neural network and support vector regression models coupled with wavelet transform", Comput. Geosci., 54, 1-8. https://doi.org/10.1016/j.cageo.2012.11.015.
  28. Kaur, I., Lata, P. and Singh, K. (2022), "Thermoelastic damping in generalized simply supported piezo-thermo-elastic nanobeam", Struct. Eng. Mech., 81(1), 29-37. https://doi.org/10.12989/sem.2022.81.1.029.
  29. Khajehzadeh, M., Kalhor, A., Tehrani, M.S. and Jebeli, M. (2022), "Optimum design of retaining structures under seismic loading using adaptive sperm swarm optimization", Struct. Eng. Mech., 81, 93-102. https://doi.org/10.12989/sem.2022.81.1.093.
  30. Li, S. (2022), "Efficient algorithms for scheduling equal-length jobs with processing set restrictions on uniform parallel batch machines", Math. Biosci. Eng., 19(11), 10731-10740. https://doi.org/10.3934/mbe.2022502.
  31. Li, X. and Sun, Y. (2020), "Stock intelligent investment strategy based on support vector machine parameter optimization algorithm", Neur. Comput. Appl., 32, 1765-1775. https://doi.org/10.1007/s00521-019-04566-2.
  32. Liu, B., Yang, H. and Karekal, S. (2020), "Effect of water content on argillization of mudstone during the tunnelling process", Rock Mech. Rock Eng., 53, 799-813. https://doi.org/10.1007/s00603-019-01947-w.
  33. Liu, H., Chen, Z., Liu, Y., Chen, Y., Du, Y. and Zhou, F. (2023), "Interfacial debonding detection for CFST structures using an ultrasonic phased array: Application to the Shenzhen SEG building", Mech. Syst. Signal Pr., 192, 110214. https://doi.org/10.1016/j.ymssp.2023.110214.
  34. Lorena, A.C. and de Carvalho, A.C.P.L.F. (2008), "Evolutionary tuning of SVM parameter values in multiclass problems", Advances in Neural Information Processing (ICONIP 2006)/Brazilian Symposium on Neural Networks (SBRN 2006), 71(16), 3326-3334. https://doi.org/10.1016/j.neucom.2008.01.031.
  35. Lu, Z.Q., Gu, D.H., Ding, H., Lacarbonara, W. and Chen, L.Q. (2020), "Nonlinear vibration isolation via a circular ring", Mech. Syst. Signal Pr., 136, 106490. https://doi.org/10.1016/j.ymssp.2019.106490.
  36. Luo, C., Wang, L., Xie, Y. and Chen, B. (2022), "A new conjugate gradient method for moving force identification of vehicle-bridge system", J. Vib. Eng. Technol., 1-18. https://doi.org/10.1007/s42417-022-00824-1.
  37. Ma, Z., Zheng, W., Chen, X. and Yin, L. (2021), "Joint embedding VQA model based on dynamic word vector", PeerJ. Comput. Sci., 7, e353. https://doi.org/10.7717/peerj-cs.353.
  38. Shariati, M., Trung, N.T., Wakil, K., Mehrabi, P., Safa, M. and Khorami, M. (2019), "Estimation of moment and rotation of steel rack connections using extreme learning machine", Steel Compos. Struct., 31(5), 427-435. https://doi.org/10.12989/scs.2019.31.5.427.
  39. Markazi, F.D., Beale, R.G. and Godley, M.H.R. (1997), "Experimental analysis of semi-rigid boltless connectors", Thin Wall. Struct., 28(1), 57-87. https://doi.org/10.1016/S0263-8231(97)00003-7.
  40. Mehrabi, P., Honarbari, S., Rafiei, S., Jahandari, S. and Alizadeh Bidgoli, M. (2021), "Seismic response prediction of FRC rectangular columns using intelligent fuzzy-based hybrid metaheuristic techniques", J. Amb. Intel. Human. Comput., 12(11), 10105-10123. https://doi.org/10.1007/s12652-020-02776-4.
  41. Ornella, L. and Tapia, E. (2010), "Supervised machine learning and heterotic classification of maize (Zea mays L.) using molecular marker data", Comput. Electron. Agric., 74(2), 250-257. https://doi.org/10.1016/j.compag.2010.08.013.
  42. Peng, J., Yan, G., Zandi, Y., Agdas, A.S., Pourrostam, T., El-Arab, I.E., Denic, N., Nesic, Z., Cirkovic, B. and Khadimallah, M.A. (2022), "Prediction and optimization of the flexural behavior of corroded concrete beams using adaptive neuro fuzzy inference system", Struct., 43, 200-208. https://doi.org/10.1016/j.istruc.2022.06.043.
  43. Peng, Z.K. and Chu, F.L. (2004), "Application of the wavelet transform in machine condition monitoring and fault diagnostics: A review with bibliography", Mech. Syst. Signal Pr., 18(2), 199-221. https://doi.org/10.1016/S0888-3270(03)00075-X.
  44. Shahgoli, A.F., Zandi, Y., Heirati, A., Khorami, M., Mehrabi, P. and Petkovic, D. (2020), "Optimisation of propylene conversion response by neuro-fuzzy approach", Int. J. Hydromechatron., 3(3), 228-237. https://doi.org/10.1504/IJHM.2020.109918.
  45. Shariati, M., Mafipour, M.S., Mehrabi, P., Bahadori, A., Zandi, Y., Salih, M.N., Nguyen, H., Dou, J., Song, X. and Poi-Ngian, S. (2019a), "Application of a hybrid Artificial Neural Network-Particle Swarm Optimization (ANN-PSO) model in behavior prediction of channel shear connectors embedded in normal and high-strength concrete", Appl. Sci., 9(24), 5534. https://doi.org/10.3390/app9245534.
  46. Shariati, M., Mafipour, M.S., Mehrabi, P., Zandi, Y., Dehghani, D., Bahadori, A., Shariati, A., Trung, N.T., Salih, M. and Poi-Ngian, S. (2019b), "Application of Extreme Learning Machine (ELM) and Genetic Programming (GP) to design steel-concrete composite floor systems at elevated temperatures", Steel Compos. Struct., 33(3), 319-332. https://doi.org/10.12989/scs.2019.33.3.319.
  47. Shariati, M., Mafipour, M.S., Mehrabi, P., Shariati, A., Toghroli, A., Trung, N.T. and Salih, M.N.A. (2021), "A novel approach to predict shear strength of tilted angle connectors using artificial intelligence techniques", Eng. Comput., 37(3), 2089-2109. https://doi.org/10.1007/s00366-019-00930-x.
  48. Soltanieh, G., Yam, M.C., Zhang, J.Z. and Ke, K. (2022), "Closed-form solution for the buckling behavior of the delaminated FRP plates with a rectangular hole using super-elastic SMA stitches", Struct. Eng. Mech., 81(1), 39-50. https://doi.org/10.12989/sem.2022.81.1.039.
  49. Taheri, E., Firouzianhaji, A., Mehrabi, P., Vosough Hosseini, B. and Samali, B. (2020), "Experimental and numerical investigation of a method for strengthening cold-formed steel profiles in bending", Appl. Sci., 10(11), 3855. https://doi.org/10.3390/app10113855.
  50. Taheri, E., Mehrabi, P., Rafiei, S. and Samali, B. (2021), "Numerical evaluation of the upright columns with partial reinforcement along with the utilisation of neural networks with combining feature-selection method to predict the load and displacement", Appl. Sci., 11(22), 11056. https://doi.org/10.3390/app112211056.
  51. Tang, Y., Liu, S., Deng, Y., Zhang, Y., Yin, L. and Zheng, W. (2021), "An improved method for soft tissue modeling", Biomed. Signal Pr. Control, 65, 102367. https://doi.org/10.1016/j.bspc.2020.102367.
  52. Teng, J.G., Yao, J. and Zhao, Y. (2003), "Distortional buckling of channel beam-columns", Thin Wall. Struct., 41(7), 595-617. https://doi.org/10.1016/S0263-8231(03)00007-7.
  53. Tian, L.M., Li, M.H., Li, L., Li, D.Y. and Bai, C. (2023), "Novel joint for improving the collapse resistance of steel frame structures in column-loss scenarios", Thin Wall. Struct., 182, 110219. https://doi.org/10.1016/j.tws.2022.110219.
  54. Vapnik, V.N. (1999), "An overview of statistical learning theory", IEEE Trans. Neur. Network., 10(5), 988-999. https://doi.org/10.1109/72.788640.
  55. Von Hagen, J. and Zhang, H. (2014), "Financial development, international capital flows, and aggregate output", J. Develop. Econom., 106, 66-77. https://doi.org/10.1016/j.jdeveco.2013.08.010.
  56. Wang, J., Liang, F., Zhou, H., Yang, M. and Wang, Q. (2022), "Analysis of position, pose and force decoupling characteristics of a 4-UPS/1-RPS parallel grinding robot", Symmetry, 14(4), 825. https://doi.org/10.3390/sym14040825.
  57. Wang, J., Tian, J., Zhang, X., Yang, B., Liu, S., Yin, L. and Zheng, W. (2022), "Control of time delay force feedback teleoperation system with finite time convergence.", Front. Neurorobot., 16, 877069. https://doi.org/10.3389/fnbot.2022.877069.
  58. Wang, J., Yang, M., Liang, F., Feng, K., Zhang, K. and Wang, Q. (2022), "An algorithm for painting large objects based on a nine-axis UR5 robotic manipulator", Appl. Sci., 12(14), 7219. https://doi.org/10.3390/app12147219.
  59. Wu, J., Yang, Y., Mehrabi, P. and Nasr, E.A. (2023), "Efficient machine-learning algorithm applied to predict the transient shock reaction of the elastic structure partially rested on the viscoelastic substrate", Mech. Adv. Mater. Struct., 1-25. https://doi.org/10.1080/15376494.2023.2183289.
  60. Xia, Y., Shi, M., Zhang, C., Wang, C., Sang, X., Liu, R., Zhao, P., An, G. and Fang, H. (2022), "Analysis of flexural failure mechanism of ultraviolet cured-in-place-pipe materials for buried pipelines rehabilitation based on curing temperature monitoring", Eng. Fail. Anal., 142, 106763. https://doi.org/10.1016/j.engfailanal.2022.106763.
  61. Xiao, X., Zhang, Q., Zheng, J. and Li, Z. (2023), "Analytical model for the nonlinear buckling responses of the confined polyhedral FGP-GPLs lining subjected to crown point loading", Eng. Struct., 282, 115780. https://doi.org/10.1016/j.engstruct.2023.115780.
  62. Xu, L., Cai, M., Dong, S., Yin, S., Xiao, T., Dai, Z. and Reza Soltanian, M. (2022), "An upscaling approach to predict mine water inflow from roof sandstone aquifers", J. Hydrol., 612, 128314. https://doi.org/10.1016/j.jhydrol.2022.128314.
  63. Yang, H., Zeng, Y., Lan, Y. and Zhou, X. (2014), "Analysis of the excavation damaged zone around a tunnel accounting for geostress and unloading", Int. J. Rock Mech. Min. Sci., 69, 59-66. https://doi.org/10.1016/j.ijrmms.2014.03.003.
  64. Yang, H., Li, Z., Jie, T. and Zhang, Z. (2018), "Effects of joints on the cutting behavior of disc cutter running on the jointed rock mass", Tunnel. Undergr. Space Technol., 81, 112-120. https://doi.org/10.1016/j.tust.2018.07.023.
  65. Yang, H., Xing, S., Wang, Q. and Li, Z. (2018), "Model test on the entrainment phenomenon and energy conversion mechanism of flow-like landslides", Eng. Geol., 239, 119-125. https://doi.org/10.1016/j.enggeo.2018.03.023.
  66. Yang, H., Wang, Z. and Song, K. (2020), "A new hybrid grey wolf optimizer-feature weighted-multiple kernel-support vector regression technique to predict TBM performance", Eng. Comput., 1-17. https://doi.org/10.1007/s00366-020-01217-2.
  67. Yang, H., Song, K. and Zhou, J. (2022), "Automated recognition model of geomechanical information based on operational data of tunneling boring machines", Rock Mech. Rock Eng., 1-18. https://doi.org/10.1007/s00603-021-02723-5.
  68. Yang, Y., Lin, B. and Zhang, W. (2023), "Experimental and numerical investigation of an arch-beam joint for an arch bridge", Arch. Civil Mech. Eng., 23(2), 101. https://doi.org/10.1007/s43452-023-00645-3.
  69. Yao, Y., Huang, H., Zhang, W., Ye, Y., Xin, L. and Liu, Y. (2022), "Seismic performance of steel-PEC spliced frame beam", J. Constr. Steel Res., 197, 107456. https://doi.org/10.1016/j.jcsr.2022.107456.
  70. Zaribafian, O., Pourrostam, T., Fazilati, M., S Moghadam, A.S.M. and Golsoorat Pahlaviani, A. (2023), "Improving the performance of a fuzzy logic model in seismic damage prediction using a guided adaptive search based particle swarm optimization algorithm", Sharif Journal of Civil Engineering.
  71. Zeinalnezhad, M. and Pourrostam, T. (2022), "Bag filter design using Neural Network algorithm and structural equation modeling (Case study: Cement factories)", Journal of New Researches in Mathematics.
  72. Zhai, S., Lyu, Y., Cao, K., Li, G., Wang, W. and Chen, C. (2023), "Seismic behavior of an innovative bolted connection with dual-slot hole for modular steel buildings", Eng. Struct., 279, 115619. https://doi.org/10.1016/j.engstruct.2023.115619.
  73. Zhang, C. (2023), "The active rotary inertia driver system for flutter vibration control of bridges and various promising applications", Sci. Chin. Technol. Sci., 66(2), 390-405. https://doi.org/10.1007/s11431-022-2228-0.
  74. Zhang, H., Ouyang, Z., Li, L., Ma, W., Liu, Y., Chen, F. and Xiao, X. (2022), "Numerical study on welding residual stress distribution of corrugated steel webs", Metal., 12(11), 1831. https://doi.org/10.3390/met12111831.
  75. Zhang, W., Kang, S., Liu, X., Lin, B. and Huang, Y. (2023), "Experimental study of a composite beam externally bonded with a carbon fiber-reinforced plastic plate", J. Build. Eng., 71, 106522. https://doi.org/10.1016/j.jobe.2023.106522.