Steel and Composite Structures

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Machine learning-based probabilistic predictions of shear resistance of welded studs in deck slab ribs transverse to beams

  • Vitaliy V. Degtyarev (School of Engineering, University of Warwick) ;
  • Stephen J. Hicks (School of Engineering, University of Warwick)
  • Received : 2023.03.23
  • Accepted : 2023.07.23
  • Published : 2023.10.10
⟨ Previous Next ⟩

Abstract

Headed studs welded to steel beams and embedded within the concrete of deck slabs are vital components of modern composite floor systems, where safety and economy depend on the accurate predictions of the stud shear resistance. The multitude of existing deck profiles and the complex behavior of studs in deck slab ribs makes developing accurate and reliable mechanical or empirical design models challenging. The paper addresses this issue by presenting a machine learning (ML) model developed from the natural gradient boosting (NGBoost) algorithm capable of producing probabilistic predictions and a database of 464 push-out tests, which is considerably larger than the databases used for developing existing design models. The proposed model outperforms models based on other ML algorithms and existing descriptive equations, including those in EC4 and AISC 360, while offering probabilistic predictions unavailable from other models and producing higher shear resistances for many cases. The present study also showed that the stud shear resistance is insensitive to the concrete elastic modulus, stud welding type, location of slab reinforcement, and other parameters considered important by existing models. The NGBoost model was interpreted by evaluating the feature importance and dependence determined with the SHapley Additive exPlanations (SHAP) method. The model was calibrated via reliability analyses in accordance with the Eurocodes to ensure that its predictions meet the required reliability level and facilitate its use in design. An interactive open-source web application was created and deployed to the cloud to allow for convenient and rapid stud shear resistance predictions with the developed model.

Keywords

References

  1. Abambres, M. and He, J. (2019), "Shear capacity of headed studs in steel-concrete structures: analytical prediction via soft computing", https://hal.science/hal-02074833/.
  2. Akiba, T., Sano, S., Yanase, T., Ohta, T. and Koyama, M. (2019), "Optuna: A next-generation hyperparameter optimization framework", ArXiv. https://doi.org/10.48550/arXiv.1907.10902.
  3. Amari, S.-I. (1998), "Natural gradient works efficiently in learning", Neural Comput., 10(2), 251-276. https://doi.org/10.1162/089976698300017746.
  4. AISC 360 (2022). Specification for Structural Steel Buildings. American Institute of Steel Construction, Chicago, Illinois.
  5. Avci-Karatas, C. (2022), "Application of machine learning in prediction of shear capacity of headed steel studs in steel-concrete composite structures", Int. J. Steel Struct., 22, 539-556. https://doi.org/10.1007/s13296-022-00589-z.
  6. Bonilla, J., Bezerra, L.M., Mirambell, E. and Massicotte, B. (2018), "Review of stud shear resistance prediction in steel-concrete composite beams", Steel Compos. Struct., 27(3), 355-370. https://doi.org/10.12989/scs.2018.27.3.355.
  7. Chen, S.-Z., Feng, D.-C., Wang, W.-J. and Taciroglu, E. (2022), "Probabilistic machine-learning methods for performance prediction of structure and infrastructures through natural gradient boosting", J. Struct. Eng., 148(8), 04022096. https://doi.org/10.1061/(ASCE)ST.1943-541X.0003401.
  8. 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.
  9. Cortes, C. and Vapnik, V. (1995), "Support-vector networks", Machine learning, 20(3), 273-297. https://doi.org/10.1007/BF00994018.
  10. CTBUH (2021), "Tall Buildings in 2020: COVID-19 Contributes to Dip in Year-On-Year Completions", CTBUH Journal, 40-49
  11. Degtyarev, V.V. (2022), "Machine learning models for predicting bond strength of deformed bars in concrete", ACI Struct. J., 119(5), 46-56. https://doi.org/10.14359/51734833.
  12. Degtyarev, V.V. and Hicks, S.J. (2022), "Reliability-based design shear resistance of headed studs in solid slabs predicted by machine learning models", Architect., Struct. Construct., 1-27. https://doi.org/10.1007/s44150-022-00078-1.
  13. Degtyarev, V.V., Hicks, S.J., and Hajjar, J.F. (2022), "Design models for predicting shear resistance of studs in solid concrete slabs based on symbolic regression with genetic programming", Steel Compos. Struct., 43(3), 293-309. https://doi.org/10.12989/scs.2022.43.3.293.
  14. Degtyarev, V.V. and Tsavdaridis, K.D. (2022), "Buckling and ultimate load prediction models for perforated steel beams using machine learning algorithms", J. Build. Eng., 51, 104316. https://doi.org/10.1016/j.jobe.2022.104316.
  15. Degtyarev, V.V. and Naser, M.Z. (2021), "Boosting machines for predicting shear strength of CFS channels with staggered web perforations", Structures, 34, 3391-3403. https://doi.org/10.1016/j.istruc.2021.09.060.
  16. Dorogush, A.V., Ershov, V. and Gulin, A. (2018), "CatBoost: Gradient boosting with categorical features support", ArXiv. https://doi.org/10.48550/arXiv.1810.11363.
  17. Duan, T., Avati, A., Ding, D.Y., Thai, K.K., Basu, S., Ng, A.Y. and Schuler, A. (2020), "NGBoost: Natural gradient boosting for probabilistic prediction". 37th International Conference on Machine Learning, Vienna, Austria, PMLR 119.
  18. EN 10143 (2006), Continuously hot-dip coated steel sheet and strip - Tolerances on dimensions and shape, European Committee for Standardization, Brussels, Belgium.
  19. EN 1090-4 (2018), Execution of steel structures and aluminium structures - Part 4: Technical requirements for cold-formed structural steel elements and cold-formed structures for roof, ceiling, floor and wall applications, European Committee for Standardization, Brussels, Belgium.
  20. EN 1990:2002+A1 (2005). Eurocode: Basis of structural design, European Committee for Standardization, Brussels, Belgium.
  21. EN 1992-1-1 (2004). Eurocode 2: Design of concrete structures - Part 1-1: General rules and rules for buildings, European Committee for Standardization, Brussels, Belgium.
  22. EN 1994-1-1 (2004). Eurocode 4: Design of composite steel and concrete structures - Part 1-1: General rules and rules for buildings, European Committee for Standardization, Brussels, Belgium.
  23. EN 206 (2013), Concrete. Specification, performance, production and conformity, European Committee for Standardization, Brussels, Belgium.
  24. EN ISO 13918 (2017). Welding - Studs and ceramic ferrules for arc stud welding, European Committee for Standardization, Brussels, Belgium.
  25. Friedman, J.H. (2001), "Greedy function approximation: a gradient boosting machine", Annals of Statistics, 29(5), 1189-1232. https://doi.org/10.1214/aos/1013203451.
  26. Grant, J.A., Fisher, J.W. and Slutter, R.G. (1977), "Composite beams with formed steel deck", AISC Eng. J., 14(1), 24-43. https://doi.org/10.62913/engj.v14i1.282
  27. Hanswille, G. (1993), Eurocode 4 Part 1-1: Clause 6.3.3.2 Shear resistance of headed studs with profiled steel sheeting. Technical Paper H7, Bergische Universitat Wuppertal. Wuppertal, Germany.
  28. Hastie, T., Tibshirani, R., and Friedman, J. (2009), The Elements of Statistical Learning: Data Mining, Inference, and Prediction, (2nd Edition), Springer Science & Business Media.
  29. Hicks, S.J. (2017), "Design shear resistance of headed studs embedded in solid slabs and encasements", J. Construct. Steel Res., 139, 339-352. https://doi.org/10.1016/j.jcsr.2017.09.018.
  30. Hicks, S.J. and Degtyarev, V.V. (2023), "Database of push tests on specimens with headed stud shear connectors welded within the ribs of profiled steel decking transverse to the supporting beams", Mendeley Data, V2. http://doi.org/10.17632/nfmhnzbfy9.2.
  31. Johnson, R. (2008), "Calibration of resistance of shear connectors in troughs of profiled sheeting", Proceedings of the Institution of Civil Engineers-Structures and Buildings, 161(3), 117-126. https://doi.org/10.1680/stbu.2008.161.3.117.
  32. Johnson, R. and Yuan, H. (1998), "Models and design rules for stud shear connectors in troughs of profiled sheeting", Proceedings of the Institution of Civil Engineers-Structures and Buildings, 128(3), 252-263. https://doi.org/10.1680/istbu.1998.30459.
  33. Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T.-Y. (2017), "LightGBM: A highly efficient gradient boosting decision tree", Adv. Neural Inform. Processing Syst., 30, 3146-3154.
  34. Konrad, M. (2011), "Tragverhalten von Kopfbolzen in Verbundtragern bei senkrecht spannenden Trapezprofilblechen", Ph.D. Thesis, Institute of Structural Design, University of Stuttgart, Stuttgart, Germany.
  35. Konrad, M., Eggert, F., Kuhlmann, U., and Schorr, J. (2020), "New approach for the design shear resistance of headed studs in profiled steel sheeting with ribs transverse to supporting beam", Steel Construct., 13(4), 252-263. https://doi.org/10.1002/stco.202000018.
  36. Lundberg, S. and Lee, S.-I. (2017), "A unified approach to interpreting model predictions", ArXiv. https://doi.org/10.48550/arXiv.1705.07874.
  37. Lungershausen, H. (1988), "Zur Schubtragfahigkeit von Kopfbolzendubeln", Ph.D. Thesis, Ruhr-Universitat Bochum, Bochum, Germany.
  38. Mei, Y., Sun, Y., Li, F., Xu, X., Zhang, A., and Shen, J. (2022), "Probabilistic prediction model of steel to concrete bond failure under high temperature by machine learning", Eng. Failure Anal., 142, 106786. https://doi.org/10.1016/j.engfailanal.2022.106786.
  39. Naser, M. (2021), "An engineer's guide to eXplainable Artificial Intelligence and Interpretable Machine Learning: Navigating causality, forced goodness, and the false perception of inference", Autom. Construct., 129, 103821. https://doi.org/10.1016/j.autcon.2021.103821.
  40. Nellinger, S. (2015), "On the behaviour of shear stud connections in composite beams with deep decking", Ph.D. Thesis, University of Luxembourg, Luxembourg, Luxembourg.
  41. Nellinger, S., Odenbreit, C., Obiala, R. and Lawson, M. (2017), "Influence of transverse loading onto push-out tests with deep steel decking", J. Construct. Steel Res., 128, 335-353. https://doi.org/10.1016/j.jcsr.2016.08.021.
  42. Ollgaard, J.G., Slutter, R.G. and Fisher, J.W. (1971), "Shear strength of stud connectors in lightweight and normal-weight concrete", AISC Engineering Journal, 8(2), 55-64 https://doi.org/10.62913/engj.v8i2.160
  43. Pallares, L. and Hajjar, J.F. (2010), "Headed steel stud anchors in composite structures, Part I: Shear", J. Construct. Steel Res., 66(2), 198-212. https://doi.org/10.1016/j.jcsr.2009.08.009.
  44. Panev, Y., Kotsovinos, P., Deeny, S. and Flint, G. (2021), "The use of machine learning for the prediction of fire resistance of composite shallow floor systems", Fire Technol., 57(6), 3079-3100. https://doi.org/10.1007/s10694-021-01108-y.
  45. Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., et al. (2011), "Scikit-learn: Machine learning in Python", Journal of Machine Learning Research, 12, 2825-2830.
  46. Peleg, B. and Sudholter, P. (2007), Introduction to the Theory of Cooperative Games, (vol. 34), Springer Science & Business Media.
  47. Ravindra, M. K., and Galambos, T.V. (1978), "Load and resistance factor design for steel", J. Struct. Div., 104(9), 1337-1353. https://doi.org/10.1061/JSDEAG.0004981.
  48. Roddenberry, M., Easterling, W. and Murray, T. (2002), Behavior and strength of welded stud shear connectors, Report No. CE/VPI-02/04, Virginia Polytechnic Institute and State University, Blacksburg, VA. Blacksburg, VA.
  49. Roik, K., Hanswille, G. and Cunze-O Lanna, A. (1989), Harmonisation of the European construction codes - Eurocode 2, 4 and 8/Part 3 - Report on Eurocode 4 Clause 6.3.2 Stud connectors, Report EC4/8/88, Institut fur Konstruktiven Ingenieurbau, Ruhr-Universitat-Bochum. Bochum, Germany.
  50. Saeys, Y., Inza, I. and Larranaga, P. (2007), "A review of feature selection techniques in bioinformatics", Bioinformatics, 23(19), 2507-2517. https://doi.org/10.1093/bioinformatics/btm344.
  51. 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.
  52. SCI (2010), NCCI: Resistance of headed stud shear connectors in transverse sheeting, Steel Construction Institute, Ascot, UK.
  53. Setvati, M. R. and Hicks, S. J. (2022), "Machine learning models for predicting resistance of headed studs embedded in concrete", Eng. Struct., 254, 113803. https://doi.org/10.1016/j.engstruct.2021.113803.
  54. Stark, J. and Hove, B. van (1991), Statistical analysis of push-out tests on stud connectors in composite steel and concrete structures - Part 3: Composite steel and concrete slabs, Research report No. BI-91-163, Delft. Delft, Netherlands.
  55. Sun, H., Burton, H.V., and Huang, H. (2020), "Machine learning applications for building structural design and performance assessment: state-of-the-art review", J. Build. Eng., 101816. https://doi.org/10.1016/j.jobe.2020.101816.
  56. Thai, H.-T. (2022), "Machine learning for structural engineering: A state-of-the-art review", Structures, 38, 448-491. https://doi.org/10.1016/j.istruc.2022.02.003.
  57. Vapnik, V. (1995), The Nature of Statistical Learning Theory, Springer, New York, NY.
  58. Vapnik, V., Golowich, S.E., and Smola, A. (1996), "Support vector method for function approximation, regression estimation, and signal processing", Adv. Neural Inform. Processing Syst., 9, 281-287.
  59. Vigneri, V. (2021), "Load bearing mechanisms of headed stud shear connections in profiled steel sheeting transverse to the beam", Ph.D. Thesis, University of Luxembourg, Luxembourg, Luxembourg.
  60. Vigneri, V., Hicks, S.J., Taras, A. and Odenbreit, C. (2022), "Design models for predicting the resistance of headed studs in profiled sheeting", Steel Compos. Struct., 42(5), 633-647. https://doi.org/10.12989/scs.2022.42.5.633.
  61. Wang, X., Liu, Y., Chen, A. and Ruan, X. (2022), "Auto-tuning ensemble models for estimating shear resistance of headed studs in concrete", J. Build. Eng., 52, 104470. https://doi.org/10.1016/j.jobe.2022.104470.
  62. Zhang, F., Wang, C., Zou, X., Wei, Y., Chen, D., Wang, Q. and Wang, L. (2023), "Prediction of the shear resistance of headed studs embedded in precast steel-concrete structures based on an interpretable machine learning method", Buildings, 13(2), 496. https://doi.org/10.3390/buildings13020496.
  63. Zhu, J. and Farouk, A.I.B. (2023), "Development of hybrid models for shear resistance prediction of grouped stud connectors in concrete using improved metaheuristic optimization techniques", Structures, 50, 286-302. https://doi.org/10.1016/j.istruc.2023.02.040.