Abstract
Timber constructions face the challenge of degradation of wood and its connections when exposed to harsh environmental conditions, leading to a reduction in load-bearing capacity. It is essential to precisely estimate the load-carrying capacity of timber joints under such conditions to maintain the health and stability of the buildings. This study aimed to develop a dependable machine learning model to support two targets, namely the ultimate load and free end slip of the glued-in rod (GIR), using data obtained from a pull-out experiment conducted in the literature in which 63 specimens of glued-in GFRP rebar in timber cubes were tested after exposure to cycles of the harsh environment of drying–wetting of water with chloride ion and also to the ultra-violet (UV) light. To accomplish this, the XGBoost algorithm was employed, and after the data were preprocessed, it was integrated into the existing dataset. The resulting \({R}^{2}\) score and MSE values for the model with the ultimate load target were 0.97 and 1.88, respectively, whereas the corresponding values for the model with the free end slip target were 0.97 and 0.01. Additionally, to gain a deeper understanding of the machine learning model, the SHapley values technique was utilized to illustrate the impact of each feature on the predicted values.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data and associated codes
GitHub hosts both the experimental database and Jupyter Notebook Python code for the XGBoost model and Shapley values used in this study. (https://github.com/AlirezaMahmoudian/Explainable-XGBoost-machine-learning-model-for-prediction-of-ultimate-load-and-free-end-slip-of-GFRP).
References
Ahmed, S., & Arocho, I. (2019). Emission of particulate matters during construction: A comparative study on a cross laminated timber (CLT) and a steel building construction project. Journal of Building Engineering, 22, 281–294. https://doi.org/10.1016/j.jobe.2018.12.015
Al Mamari, A. H. S., Al Ghafri, R. S. H. H., Aravind, N., Dhandapani, R., Al Hatali, E. M. A. M., & Pandian, R. (2023). Experimental study and development of machine learning model using random forest classifier on shear strength prediction of RC beam with externally bonded GFRP composites. Asian Journal of Civil Engineering, 24(1), 267–286. https://doi.org/10.1007/s42107-022-00502-3
Al-Hasani, L. E., Perez, G., Herndon, H. N., Park, J., Poole, J. L., Tien, I., Washburn, N. R., Cho, Y. K., Gentry, T. R., & Kurtis, K. E. (2023). Prediction of heat of hydration of cementitious systems using Gaussian process regression enables mass concrete thermal modeling. Materials and Structures, 56(2), 45. https://doi.org/10.1617/s11527-023-02134-8
Aloisio, A., Alaggio, R., & Fragiacomo, M. (2021). Equivalent viscous dam** of cross-laminated timber structural archetypes. Journal of Structural Engineering. https://doi.org/10.1061/(ASCE)ST.1943-541X.0002947
Ayansola, G. S., Tannert, T., & Vallee, T. (2022). Glued-in multiple steel rod connections in cross-laminated timber. The Journal of Adhesion, 98(6), 810–826. https://doi.org/10.1080/00218464.2021.1962715
Azinović, B., Cabrero, J. M., Danielsson, H., & Pazlar, T. (2022). Brittle failure of laterally loaded self-tap** screw connections for cross-laminated timber structures. Engineering Structures, 266, 114556. https://doi.org/10.1016/j.engstruct.2022.114556
Bekdaş, G., Yücel, M., & Nigdeli, S. M. (2021). Estimation of optimum design of structural systems via machine learning. Frontiers of Structural and Civil Engineering, 15(6), 1441–1452. https://doi.org/10.1007/s11709-021-0774-0
Botella, R., Lo Presti, D., Vasconcelos, K., Bernatowicz, K., Martínez, A. H., Miró, R., Specht, L., Mercado, E. A., Pires, G. M., Pasquini, E., Ogbo, C., Preti, F., Pasetto, M., del Barco Carrión, A. J., Roberto, A., Orešković, M., Kuna, K. K., Guduru, G., Martin, A. E., et al. (2022). Machine learning techniques to estimate the degree of binder activity of reclaimed asphalt pavement. Materials and Structures, 55(4), 112. https://doi.org/10.1617/s11527-022-01933-9
Bouchard, R., Salenikovich, A., Frenette, C., & Bedard-Blanchet, G. (2021). Experimental investigation of joints with multiple glued-in rods in glued-laminated timber under axial tensile loading. Construction and Building Materials, 293, 122614. https://doi.org/10.1016/j.conbuildmat.2021.122614
Chen, T., & Guestrin, C. (2016). XGBoost. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining (pp. 785–794). https://doi.org/10.1145/2939672.2939785
Churkina, G., Organschi, A., Reyer, C. P. O., Ruff, A., Vinke, K., Liu, Z., Reck, B. K., Graedel, T. E., & Schellnhuber, H. J. (2020). Buildings as a global carbon sink. Nature Sustainability, 3(4), 269–276. https://doi.org/10.1038/s41893-019-0462-4
Fathi, H., Nasir, V., & Kazemirad, S. (2020). Prediction of the mechanical properties of wood using guided wave propagation and machine learning. Construction and Building Materials, 262, 120848. https://doi.org/10.1016/j.conbuildmat.2020.120848
Fragiacomo, M., & Batchelar, M. (2012). Timber frame moment joints with glued-in steel rods. I: Design. Journal of Structural Engineering, 138(6), 789–801. https://doi.org/10.1061/(ASCE)ST.1943-541X.0000419
Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. The Annals of Statistics. https://doi.org/10.1214/aos/1013203451
Gonthina, M., Chamata, R., Duppalapudi, J., & Lute, V. (2023). Deep CNN-based concrete cracks identification and quantification using image processing techniques. Asian Journal of Civil Engineering, 24(3), 727–740. https://doi.org/10.1007/s42107-022-00526-9
Gonzales, E., Tannert, T., & Vallee, T. (2016). The impact of defects on the capacity of timber joints with glued-in rods. International Journal of Adhesion and Adhesives, 65, 33–40. https://doi.org/10.1016/j.ijadhadh.2015.11.002
Gonzalez, E., Avez, C., & Tannert, T. (2016). Timber joints with multiple glued-in steel rods. The Journal of Adhesion, 92(7–9), 635–651. https://doi.org/10.1080/00218464.2015.1099098
Grunwald, C., Fecht, S., Vallée, T., & Tannert, T. (2014). Adhesively bonded timber joints—Do defects matter? International Journal of Adhesion and Adhesives, 55, 12–17. https://doi.org/10.1016/j.ijadhadh.2014.07.003
Hamidia, M., Mansourdehghan, S., Asjodi, A. H., & Dolatshahi, K. M. (2022). Machine learning-based seismic damage assessment of non-ductile RC beam-column joints using visual damage indices of surface crack patterns. Structures, 45, 2038–2050. https://doi.org/10.1016/j.istruc.2022.09.010
Harte, A. M. (2017). Mass timber—The emergence of a modern construction material. Journal of Structural Integrity and Maintenance, 2(3), 121–132. https://doi.org/10.1080/24705314.2017.1354156
Hassanieh, A., Valipour, H. R., Bradford, M. A., & Jockwer, R. (2018). Glued-in-rod timber joints: Analytical model and finite element simulation. Materials and Structures, 51(3), 61. https://doi.org/10.1617/s11527-018-1189-9
Huang, Z., Shi, S. Q., & Cai, L. (2014). Experimental analysis on strength and failure modes of wood beam-column connections. Frontiers of Structural and Civil Engineering, 8(3), 260–269. https://doi.org/10.1007/s11709-014-0261-y
Inaba, K., Tanigawa, H., & Naito, H. (2023). A study on evaluating supporting condition of railway track slab with impact acoustics and non-defective machine learning. Construction and Building Materials, 373, 130905. https://doi.org/10.1016/j.conbuildmat.2023.130905
Kasal, B., & Anthony, R. W. (2004). Advances inin situ evaluation of timber structures. Progress in Structural Engineering and Materials, 6(2), 94–103. https://doi.org/10.1002/pse.170
Kaveh, A., Dadras Eslamlou, A., Javadi, S. M., & Geran Malek, N. (2021). Machine learning regression approaches for predicting the ultimate buckling load of variable-stiffness composite cylinders. Acta Mechanica, 232(3), 921–931. https://doi.org/10.1007/s00707-020-02878-2
Kaveh, A., Gholipour, Y., & Rahami, H. (2008). Optimal design of transmission towers using genetic algorithm and neural networks. International Journal of Space Structures, 23(1), 1–19. https://doi.org/10.1260/026635108785342073
Kaveh, A., & Iranmanesh, A. (1998). Comparative study of backpropagation and improved counterpropagation neural nets in structural analysis and optimization. International Journal of Space Structures, 13(4), 177–185. https://doi.org/10.1177/026635119801300401
Kaveh, A., & Khalegi, A. (1998). Prediction of strength for concrete specimens using artificial neural networks. In: 1st International conference on engineering computational technology/4th international conference on computational structures technology (pp. 165–171).
Kaveh, A., & Khavaninzadeh, N. (2023). Efficient training of two ANNs using four meta-heuristic algorithms for predicting the FRP strength. Structures, 52, 256–272. https://doi.org/10.1016/j.istruc.2023.03.178
Kohl, D., Ratsch, N., Böhm, S., Voß, M., Kaufmann, M., & Vallée, T. (2020). Influence of manufacturing methods and imperfections on the load capacity of glued-in rods. The Journal of Adhesion, 96(8), 738–759. https://doi.org/10.1080/00218464.2018.1508351
Kumar, S. P., & Beenamol, M. (2023). Multiple layer radial basis neural network with remora regression tree optimum feature extraction for structural health monitoring. Asian Journal of Civil Engineering, 24(4), 989–999. https://doi.org/10.1007/s42107-022-00547-4
Li, K., Pan, L., & Wang, Y. (2022). Random forest-based modelling of parameters of fractional derivative concrete creep model with Bayesian optimization. Materials and Structures, 55(8), 215. https://doi.org/10.1617/s11527-022-02054-z
Liu, K., Zheng, J., Dong, S., **e, W., & Zhang, X. (2023). Mixture optimization of mechanical, economical, and environmental objectives for sustainable recycled aggregate concrete based on machine learning and meta-heuristic algorithms. Journal of Building Engineering, 63, 105570. https://doi.org/10.1016/j.jobe.2022.105570
Lundberg, S., & Lee, S. I. (2017). A unified approach to interpreting model predictions. Advances in neural information processing systems, 30.
Lundberg, S. M., Erion, G. G., & Lee, S. I. (2018). Consistent individualized feature attribution for tree ensembles. ar**v preprint. ar**v:1802.03888
Mangalathu, S., Hwang, S.-H., & Jeon, J.-S. (2020). Failure mode and effects analysis of RC members based on machine-learning-based SHapley Additive exPlanations (SHAP) approach. Engineering Structures, 219, 110927. https://doi.org/10.1016/j.engstruct.2020.110927
Mangalathu, S., Shin, H., Choi, E., & Jeon, J.-S. (2021). Explainable machine learning models for punching shear strength estimation of flat slabs without transverse reinforcement. Journal of Building Engineering, 39, 102300. https://doi.org/10.1016/j.jobe.2021.102300
Mansourdehghan, S., Dolatshahi, K. M., & Asjodi, A. H. (2022). Data-driven damage assessment of reinforced concrete shear walls using visual features of damage. Journal of Building Engineering, 53, 104509. https://doi.org/10.1016/j.jobe.2022.104509
Naderpour, H., Rafiean, A. H., & Fakharian, P. (2018). Compressive strength prediction of environmentally friendly concrete using artificial neural networks. Journal of Building Engineering, 16, 213–219. https://doi.org/10.1016/j.jobe.2018.01.007
Nasir, V., Fathi, H., & Kazemirad, S. (2021). Combined machine learning–wave propagation approach for monitoring timber mechanical properties under UV aging. Structural Health Monitoring, 20(4), 2035–2053. https://doi.org/10.1177/1475921721995987
Navaratnam, S., Thamboo, J., Ponnampalam, T., Venkatesan, S., & Chong, K. B. (2022). Mechanical performance of glued-in rod glulam beam to column moment connection: An experimental study. Journal of Building Engineering, 50, 104131. https://doi.org/10.1016/j.jobe.2022.104131
Nazar, S., Yang, J., Wang, X.-E., Khan, K., Amin, M. N., Javed, M. F., Althoey, F., & Ali, M. (2023). Estimation of strength, rheological parameters, and impact of raw constituents of alkali-activated mortar using machine learning and SHapely Additive exPlanations (SHAP). Construction and Building Materials, 377, 131014. https://doi.org/10.1016/j.conbuildmat.2023.131014
O’Neill, C., McPolin, D., Taylor, S. E., Harte, A. M., O’Ceallaigh, C., & Sikora, K. S. (2017). Timber moment connections using glued-in basalt FRP rods. Construction and Building Materials, 145, 226–235. https://doi.org/10.1016/j.conbuildmat.2017.03.241
Otero Chans, D., Estévez Cimadevila, J., & Martín Gutiérrez, E. (2011). Strength of joints with epoxy-glued threaded steel rods in tali timber. Journal of Materials in Civil Engineering, 23(4), 453–458. https://doi.org/10.1061/(ASCE)MT.1943-5533.0000191
Pratap, B., Shubham, K., Mondal, S., & Rao, B. H. (2023). Exploring the potential of neural network in assessing mechanical properties of geopolymer concrete incorporating fly ash and phosphogypsum in pavement applications. Asian Journal of Civil Engineering. https://doi.org/10.1007/s42107-023-00735-w
Ratsch, N., Burnett-Barking, M., Böhm, S., Myslicki, S., Voß, M., Adam, M., & Vallée, T. (2021). Resistive curing of glued-in rods. Construction and Building Materials, 268, 121127. https://doi.org/10.1016/j.conbuildmat.2020.121127
Salmi, Z. J., Khodakarami, M. I., & Behnamfar, F. (2023). Development of seismic fragility curves for RC/MR frames using machine learning methods. Asian Journal of Civil Engineering, 24(3), 823–836. https://doi.org/10.1007/s42107-022-00533-w
Serrano, E. (2001). Glued-in rods for timber structures—An experimental study of softening behaviour. Materials and Structures, 34(4), 228–234. https://doi.org/10.1007/BF02480593
Shapley, L. S. (1953). A value for n-person games (pp. 307–317).
Shekarchi, M., Farahani, E. M., & Oskouei, A. V. (2019). Effect of seawater on pull-out behavior of glued-in single rods set parallel to the grain of timber joints. Construction and Building Materials, 222, 342–357. https://doi.org/10.1016/j.conbuildmat.2019.06.140
Shekarchi, M., Shakiba, M., Yekrangnia, M., & Tannert, T. (2022). Performance of glued-in rod timber joints under seawater and UV exposure cycles. Construction and Building Materials, 322, 126418. https://doi.org/10.1016/j.conbuildmat.2022.126418
Steiger, R., Gehri, E., & Widmann, R. (2007). Pull-out strength of axially loaded steel rods bonded in glulam parallel to the grain. Materials and Structures, 40(1), 69–78. https://doi.org/10.1617/s11527-006-9111-2
Svatoš-Ražnjević, H., Orozco, L., & Menges, A. (2022). Advanced timber construction industry: a review of 350 multi-storey timber projects from 2000–2021. Buildings, 12(4), 404. https://doi.org/10.3390/buildings12040404
Tannert, T., Vallée, T., & Hehl, S. (2012). Experimental and numerical investigations on adhesively bonded timber joints. Wood Science and Technology, 46(1–3), 579–590. https://doi.org/10.1007/s00226-011-0423-1
Tannert, T., Zhu, H., Myslicki, S., Walther, F., & Vallée, T. (2017). Tensile and fatigue investigations of timber joints with glued-in FRP rods. The Journal of Adhesion, 93(11), 926–942. https://doi.org/10.1080/00218464.2016.1190653
Toumpanaki, E., & Ramage, M. H. (2021). Glued-in CFRP and GFRP rods in block laminated timber subjected to monotonic and cyclic loading. Composite Structures, 272, 114201. https://doi.org/10.1016/j.compstruct.2021.114201
Varma, B. V., Prasad, E. V., & Singha, S. (2023). Study on predicting compressive strength of concrete using supervised machine learning techniques. Asian Journal of Civil Engineering. https://doi.org/10.1007/s42107-023-00662-w
Veerapandian, V., Pandulu, G., Jayaseelan, R., & Mohammed Asif, M. Y. (2023). Simplified deep-learning approach for estimating the ultimate axial load of circular composite columns. Asian Journal of Civil Engineering. https://doi.org/10.1007/s42107-023-00647-9
XGBoost Developers. (2022). XGBoost documentation.
**a, Z., Van De Kuilen, J.-W.G., Polastri, A., Ceccotti, A., & He, M. (2021). Influence of core stiffness on the behavior of tall timber buildings subjected to wind loads. Frontiers of Structural and Civil Engineering, 15(1), 213–226. https://doi.org/10.1007/s11709-021-0692-1
**n, Z., Ke, D., Zhang, H., Yu, Y., & Liu, F. (2022). Non-destructive evaluating the density and mechanical properties of ancient timber members based on machine learning approach. Construction and Building Materials, 341, 127855. https://doi.org/10.1016/j.conbuildmat.2022.127855
Xu, B. H., Bouchaïr, A., & Racher, P. (2012). Analytical study and finite element modelling of timber connections with glued-in rods in bending. Construction and Building Materials, 34, 337–345. https://doi.org/10.1016/j.conbuildmat.2012.02.087
Yeboah, D., Taylor, S., McPolin, D., & Gilfillan, R. (2013). Pull-out behaviour of axially loaded basalt fibre reinforced polymer (BFRP) rods bonded perpendicular to the grain of glulam elements. Construction and Building Materials, 38, 962–969. https://doi.org/10.1016/j.conbuildmat.2012.09.014
Zhang, H., Li, H., Dauletbek, A., Lorenzo, R., Corbi, I., & Corbi, O. (2023). Research status of glued-in rods connections in wood structures. Journal of Building Engineering, 65, 105782. https://doi.org/10.1016/j.jobe.2022.105782
Funding
The authors did not receive support from any organization for the submitted work.
Author information
Authors and Affiliations
Contributions
Nima Tajik: Conceptualization, Methodology, Visualization, Writing - Original Draft, Investigation, Formal analysis, preparation, Software Alireza Mahmoudian: Conceptualization, Methodology, Visualization, Writing - Original Draft, Software, Data curation, Formal analysis Mostafa Mohammadzadeh Taleshi: Conceptualization, Methodology, Visualization, Writing - Original Draft, preparation Mohammad Yekrangnia: Conceptualization, Resources, Supervision, Writing - Review & Editing, Project administration
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no competing interests. All authors certify that they have no affiliations with or involvement in any organization or entity with any financial interest or non-financial interest in the subject matter or materials discussed in this manuscript.
Ethics approval
There are no ethical issues that relate to patient consent or animal experimentation and the lack of ethical approval.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Tajik, N., Mahmoudian, A., Mohammadzadeh Taleshi, M. et al. Explainable XGBoost machine learning model for prediction of ultimate load and free end slip of GFRP rod glued-in timber joints through a pull-out test under various harsh environmental conditions. Asian J Civ Eng 25, 141–157 (2024). https://doi.org/10.1007/s42107-023-00764-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s42107-023-00764-5