Steel and Composite Structures

  • 제45권2호
  • /
  • Pages.159-173
  • /
  • 2022
  • /
  • 1229-9367(pISSN)
  • /
  • 1598-6233(eISSN)
테크노프레스 (Techno-Press)
권호 표지
DOI QR코드

DOI QR Code

Patch loading resistance prediction of steel plate girders using a deep artificial neural network and an interior-point algorithm

  • Mai, Sy Hung (Department of Hydraulic Engineering and Construction, Hanoi University of Civil Engineering (HUCE)) ;
  • Tran, Viet-Linh (Department of Civil Engineering, Vinh University) ;
  • Nguyen, Duy-Duan (Department of Civil Engineering, Vinh University) ;
  • Nguyen, Viet Tiep (Department of Hydraulic Engineering and Construction, Hanoi University of Civil Engineering (HUCE)) ;
  • Thai, Duc-Kien (Department of Civil and Environmental Engineering, Sejong University)
  • 투고 : 2021.04.05
  • 심사 : 2022.10.24
  • 발행 : 2022.10.25
⟨ 이전 논문 다음 논문 ⟩

초록

This paper proposes a hybrid machine-learning model, which is called DANN-IP, that combines a deep artificial neural network (DANN) and an interior-point (IP) algorithm in order to improve the prediction capacity on the patch loading resistance of steel plate girders. For this purpose, 394 steel plate girders that were subjected to patch loading were tested in order to construct the DANN-IP model. Firstly, several DANN models were developed in order to establish the relationship between the patch loading resistance and the web panel length, the web height, the web thickness, the flange width, the flange thickness, the applied load length, the web yield strength, and the flange yield strength of steel plate girders. Accordingly, the best DANN model was chosen based on three performance indices, which included the R^2, RMSE, and a20-index. The IP algorithm was then adopted to optimize the weights and biases of the DANN model in order to establish the hybrid DANN-IP model. The results obtained from the proposed DANN-IP model were compared with of the results from the DANN model and the existing empirical formulas. The comparison showed that the proposed DANN-IP model achieved the best accuracy with an R^2 of 0.996, an RMSE of 23.260 kN, and an a20-index of 0.891. Finally, a Graphical User Interface (GUI) tool was developed in order to effectively use the proposed DANN-IP model for practical applications.

키워드

과제정보

This research is funded by the Hanoi University of Civil Engineering (HUCE), Hanoi, Vietnam under grant number 55-2021/KHXD-TD.

참고문헌

  1. Ahmadi, M., Naderpour, H. and Kheyroddin, A. (2014), "Utilization of artificial neural networks to prediction of the capacity of CCFT short columns subject to short term axial load", Arch. Civ. Mech. Eng., 14, 510-517. https://doi.org/10.1016/j.acme.2014.01.006.
  2. Ahmadi, M., Naderpour, H. and Kheyroddin, A. (2017), "ANN model for predicting the compressive strength of circular steelconfined concrete", Int. J. Civ. Eng., 15, 213-221. https://doi.org/10.1007/s40999-016-0096-0.
  3. Albuquerque, J.S., Gopal, V., Staus, G.H., Biegler, L.T. and Ydstie, B.E. (1997), "Interior point SQP strategies for structured process optimization problems", Comput. Chem. Eng., 21, 853-859. https://doi.org/10.1016/s0098-1354(97)87609-0.
  4. Andrei, N. (2017), Continuous Nonlinear Optimization for Engineering Applications in GAMS Technology, Cham, Switzerland: Springer.
  5. Armaghani, D.J., Hatzigeorgiou, G.D., Karamani, C., Skentou, A., Zoumpoulaki, I. and Asteris, P.G. (2019), "Soft computingbased techniques for concrete beams shear strength", Procedia Struct. Integr., 17, 924-933. https://doi.org/10.1016/j.prostr.2019.08.123.
  6. Arora, R.K. (2016), Optimization: Algorithms and Applications, Choice Reviews Online. https://doi.org/10.5860/choice.195857
  7. Asteris, P.G. and Mokos, V.G. (2019), "Concrete compressive strength using artificial neural networks", Neural Comput. Appl., 2. https://doi.org/10.1007/s00521-019-04663-2.
  8. Bagchi, D.K. and Rockey, K.C. (1975), Postbuckling Behaviour of a Webplate Under Partial Edge Loading. 251-284.
  9. Bamm, D., Lindner, J. and Voss, R.P. (1983), "Traglastversuche an ausgesteiften tragerauflagern", Stahlbau, 52(10), 296-300.
  10. Bergfelt (1971), "Studies and tests on slender plate girders without stiffeners - Shear strength and local web crippling", Proceedings, IABSE Colloquium, London, 67-83.
  11. Bergfelt A, n.d. Girder web stiffening for patch loading. s831. Goteborg Chalmers Univ. Technol. Publ. 1983, p. 1-78.
  12. Bergfelt, A. (1979), Patch Loading on a Slender Web: Influence of Horizontal and Vertical Web Stiffeners on the Load Carrying Capacity, Chalmers University of Technology.
  13. Blodgett, O.W. (1966), Design of Welded Structures, Cleveland: James F. Lincoln Arc Welding Foundation.
  14. Boggs, P.T. and Tolle, J.W. (1995), Sequential Quadratic Programming. Acta Numer. 4, 1-51. https://doi.org/10.1017/S0962492900002518
  15. Devikanniga, D., Vetrivel, K. and Badrinath, N. (2019), "Review of meta-heuristic optimization based artificial neural networks and its applications", J. Phys. Conf. Ser., 1362. https://doi.org/10.1088/1742-6596/1362/1/012074.
  16. Drdacky M, N.R., n.d. Partial edge load-carrying capacity tests of thick plate girder webs. Acta Tech CSAV, V. 1977;87(5)614-20.
  17. Drdacky, M., n.d. Limit states of steel plate girder webs under patch loading. Proceedings, Reg. Colloq. Stab. Steel Struct. Ivanyi M. edt., Tihany, Hungary, 687-694.
  18. Dubas, P. and Tschamper, H. (1990), "Stabilite des ames soumises a une charge concentree et a une flexion globale", Constr. Met. 2, 25-39.
  19. EN 1993-1-5. Eurocode 3 (1993), Design of Steel Structures - Part 1-5: Plated Structural Elements. Brussels Eur. Comm. Stand. (CEN) 2006.
  20. Fonseca, E.T., Vellasco, P.C.G.D.S., De Andrade, S.A.L. and Vellasco, M.M.B.R. (2003), "Neural network evaluation of steel beam patch load capacity", Adv. Eng. Softw., 34, 763-772. https://doi.org/10.1016/S0965-9978(03)00104-2.
  21. Fonseca, E.T., Vellasco, P.C.G.D.S., Vellasco, M.M.B.R. and de Andrade, S.A.L. (2008), "A neuro-fuzzy evaluation of steel beams patch load behaviour", Adv. Eng. Softw., 39, 558-572. https://doi.org/10.1016/j.advengsoft.2007.07.005.
  22. Fonseca, Elaine T., Pedro, P.C.G., De Andrade, S.A.L. and Vellasco, M.M.B.R. (2003), "A patch load parametric analysis using neural networks", J. Constr. Steel Res., 59, 251-267. https://doi.org/10.1016/S0143-974X(02)00024-X.
  23. Garson G.D. (1991), Interpreting Neural-Network Connection Strengths. AI Expert 6, 47-51.
  24. Gholizadeh, S., Pirmoz, A. and Attarnejad, R. (2011), "Assessment of load carrying capacity of castellated steel beams by neural networks", J. Constr. Steel Res., 67, 770-779. https://doi.org/10.1016/j.jcsr.2011.01.001.
  25. Giorgi, G. and Kjeldsen, T.H. (2014), "Traces and emergence of nonlinear programming", Traces Emerg. Nonlinear Program, 1- 434. https://doi.org/10.1007/978-3-0348-0439-4.
  26. Granholm, C.A. (1960), Tests on Girders with Extremely Thin Web Plates, Inst. for Byggnadsteknik, Goteborg.
  27. Guo, K. and Yang, G. (2020), "Load-slip curves of shear connection in composite structures: prediction based on ANNs", Steel Compos. Struct., 36, 493-506. https://doi.org/10.12989/scs.2020.36.5.493.
  28. Hornik, K., Stinchcombe, M. and White, H. (1989), "Multilayer feedforward networks are universal approximators", Neural Networks, 2, 359-366. https://doi.org/10.1016/0893- 6080(89)90020-8.
  29. Karina, C.N., Chun, P.J. and Okubo, K. (2017), "Tensile strength prediction of corroded steel plates by using machine learning approach", Steel Compos. Struct., 24(5), 635-641. https://doi.org/10.12989/scs.2017.24.5.635.
  30. Kennedy SJ, Kennedy DJL, Prabha KR, P.D., n.d. The bearing resistance of webs: a plate post-buckling strength problem. SSRC; 1997.
  31. 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, 193-209. https://doi.org/10.12989/scs.2020.37.2.193.
  32. Kojima, M., Megiddo, N. and Mizuno, S. (1993), "A primal-dual infeasible-interior-point algorithm for linear programming", Math. Program., 61, 263-280. https://doi.org/10.1007/BF01582151.
  33. Kovacevic, S. and Markovic, N. (2020), "Experimental study on the influence of patch load length on steel plate girders", ThinWall. Struct., 151, 106733. https://doi.org/10.1016/j.tws.2020.106733.
  34. Lagerqvist, O. and Johansson, B. (1996), "Resistance of I-girders to Concentrated Loads", J. Constr. Steel Res., 39, 87-119. https://doi.org/10.1016/S0143-974X(96)00023-5.
  35. Limbachiya, V. and Shamass, R. (2021), "Application of artificial neural networks for web-post shear resistance of cellular steel beams", Thin-Wall. Struct., 161, 107414. https://doi.org/10.1016/j.tws.2020.107414.
  36. Markovic, N. and Kovacevic, S. (2019), "Influence of patch load length on plate girders. Part I: Experimental research", J. Constr. Steel Res., 157, 207-228. https://doi.org/10.1016/j.jcsr.2019.02.035
  37. MATLAB (2018), MATLAB R2018b.
  38. Mohamed, A.R., Dahl, G. and Hinton, G. (2009), "Deep belief networks for phone recognition", Scholarpedia, 4, 1-9. https://doi.org/10.4249/scholarpedia.5947.
  39. Naderpour, H., Mirrashid, M. and Nagai, K. (2019), "An innovative approach for bond strength modeling in FRP strip-toconcrete joints using adaptive neuro-fuzzy inference system", Eng. Comput,. https://doi.org/10.1007/s00366-019-00751-y.
  40. Nguyen, M.S.T., Thai, D.K. and Kim, S.E. (2020), "Predicting the axial compressive capacity of circular concrete filled steel tube columns using an artificial neural network", Steel Compos. Struct., 35, 415-437.
  41. Ranganathan, A. (2004), The Levenberg-Marquardt algorithm 3 LM as a blend of gradient descent and Gauss-Newton itera. Internet Httpexcelsior Cs Ucsb Educoursescs290ipdfL MA Pdf, 142(June), 1-5.
  42. Roberts, F.S. and T.M. (2000), "Combined Shear-and-Patch loading of plate girders", J. Struct. Eng., 126, 316-321. https://doi.org/10.1061/(ASCE)0733-9445(2000)126:3(316)
  43. ROBERTS, T. and MARKOVIC, N. (1983), "Stocky plate girders subjected to edge loading", Proc. Inst. Civ. Eng., 75, 539-550. https://doi.org/10.1680/iicep.1983.1444.
  44. Roberts, T.M. (1981), "Slender plate girders subjected to edge loading", Proc. Instn Civ. Engrs., 71, 805-819.
  45. Roberts, T.M. and Chong, C.K. (1981), "Collapse of plate girders under edge loading", ASCE, J. Struct. Div., 107, 1503-1509. https://doi.org/10.1061/JSDEAG.0005762
  46. Roberts, T.M. and Newark, A.C.B. (1997), "Strength of webs subjected to compressive edge loading", J. Struct. Eng., 123, 176-183. https://doi.org/10.1061/(asce)0733-9445(1997)123:2(176).
  47. Roberts, T.M. and Rockey, K.C. (1979), "A mechanism solution for predicting the collapse loads of slender plate girders when subjected to in-plane patch loading", Proceedings of the Institution of Civil Engineers, 67(1), 155-175. https://doi.org/10.1680/iicep.1979.2322
  48. Roberts, T.O. and Chong, C.K. (1981), "Collapse of plate girders under edge loading", J. Struct. Div., 107(8), 1503-1509. https://doi.org/10.1061/JSDEAG.0005762
  49. Rogac, M., Aleksic, S. and Lucic, D. (2020), "Influence of patch load length on resistance of I-girders. Part-I: Experimental research", J. Constr. Steel Res., 175, 1-21. https://doi.org/10.1016/j.jcsr.2020.106369.
  50. Salehi, H. and Burgueno, R. (2018), "Emerging artificial intelligence methods in structural engineering", Eng. Struct., 171, 170-189. https://doi.org/10.1016/j.engstruct.2018.05.084.
  51. Scheer, J., Liu, X.L., Falke, J. and Peil, U. (1988), "Traglastversuche zur lasteinleitung an I-formigen geschweissten biegetragern ohne steifen", Stahlbau, 57(4), 115-121.
  52. Sharifi, Y., Moghbeli, A., Hosseinpour, M. and Sharifi, H. (2020), "Study of Neural Network Models for the Ultimate Capacities of Cellular Steel Beams. Iran. J. Sci. Technol. - Trans. Civ. Eng. 44, 579-589. https://doi.org/10.1007/s40996-019-00281-z
  53. Shimizu, S., Yoshida, S. and Okuhara, H. (1987), "An experimental study on patch-loaded web plates", Proceedings, ECCS Colloquim, Stab. Plate Shell Struct. April. Ghent, Belgium, 85-94.
  54. Skaloud, M. and Drdacky, M. (1975), "Ultimate load design of webs of steel plated structures - Part 3 Webs under concentrated loads", Staveb. Casopis, 23, 140-160.
  55. Skaloud, M. and Novak, P., data taken from Roberts, T.M. and Rockey, K.C. (1979), "A mechanism solution for predicting the collapse loads of slender plate girders when subjected to inplane patch loading", Proc. Instn Civ. Engrs, Part 2, 67, 155-175.
  56. Tetougueni, C.D., Maiorana, E., Zampieri, P. and Pellegrino, C. (2019), "Plate girders behaviour under in-plane loading: A review", Eng. Fail. Anal., 95, 332-358. https://doi.org/10.1016/j.engfailanal.2018.09.021.
  57. Tran, V.L. and Kim, S.E. (2020a), "Efficiency of three advanced data-driven models for predicting axial compression capacity of CFDST columns", Thin-Walled Struct., 152. https://doi.org/10.1016/j.tws.2020.106744.
  58. Tran, V.L. and Kim, S.E. (2021), "A practical ANN model for predicting the PSS of two-way reinforced concrete slabs", Eng. Comput., 37(3), 2303-2327. https://doi.org/10.1007/s00366-020-00944-w.
  59. Tran, V.L., Thai, D.K. and Kim, S.E. (2019), "A new empirical formula for prediction of the axial compression capacity of CCFT columns" Steel Compos. Struct,. 33(2), 181-194. https://doi.org/10.12989/scs.2019.33.2.181.
  60. Tran, V.L., Thai, D.K. and Kim, S.E. (2019), "Application of ANN in predicting ACC of SCFST column", Compos. Struct., 228. https://doi.org/10.1016/j.compstruct.2019.111332.
  61. Tran, V.L., Thai, D.K. and Nguyen, D.D. (2020), "Practical artificial neural network tool for predicting the axial compression capacity of circular concrete-filled steel tube columns with ultra-high-strength concrete", Thin-Walled Struct., 151. https://doi.org/10.1016/j.tws.2020.106720.
  62. Unosson, E. (2003), Patch Loading of Stainless Steeel girders - Experiments and finite element analyses. Lulea Univ. Technol. ISRN LTU-LIC--03/12--SE.
  63. Zorlu, K., Gokceoglu, C., Ocakoglu, F. Nefeslioglu, H.A. and Acikalin, S. (2008), "Prediction of uniaxial compressive strength of sandstones using petrography-based models. Eng. Geol. 96, 141-158. https://doi.org/10.1016/j.enggeo.2007.10.009.