Study the Efficiency of the XGBoost Algorithm for Squat RC Wall Shear Strength Prediction and Parametric Analysis
Keywords:
Machine Learning (ML), Squat RC walls, Shear strength, XGBoost Model, Empirical ModelAbstract
Squat-reinforced concrete (RC) shear walls with an aspect ratio of less than two are considered effective structural members, where shear is the dominant failure mechanism. Squat shear walls are widely used in nuclear power plants and building construction and feature optimal cost and outstanding performance, due to their lateral strength and high rigidity to resist lateral loads. However, since the accurate evaluation of the shear strength of squat shear walls must meet the design specifications, its calculation may be very complex, challenging, and inaccurate using experimental and theoretical equations due to many influential and overlapping design factors, so it takes more time and higher cost to determine it. This study uses machine learning (ML) methods to build a shear strength prediction efficient model for squat RC walls to address these issues. First, a huge dataset of 1424 RC squat wall test specimens gathered from the literature is utilized for developing an ML model, by employing XGBoost, to predict the shear strength. Results verified that the XGBoost model had the best accuracy and least error while assessing the squat walls' strength at shear. Moreover, an XGBoost optimum algorithm fared better than the empirical models based on mechanics, with a 99.2% accuracy. Finally, to prove that the model can identify the most important variables that significantly affect the shear strength, parameter and sensitivity analyses were performed and the results showed that the wall length is the factor that contributes most to the ultimate shear strength of the squat shear wall as a percentage (7.62%), followed by the yield strength. For the web as a ratio. (6.88%), concrete strength (6.75%), reinforcement ratio information (6.56%), and geometric properties (6.01%), while the axial load represents the smallest contribution, reaching (4.16%).
Downloads
References
Gulec, C. K. (2009). Performance-based assessment and design of squat reinforced concrete shear walls. State University of New York at Buffalo.
D.-C. Feng, W.-J. Wang, S. Mangalathu, and E. Taciroglu, “Interpretable XGBoost-SHAP Machine-Learning Model for Shear Strength Prediction of Squat RC Walls,” J. Struct. Eng., vol. 147, no. 11, pp. 1–13, 2021, doi: 10.1061/(asce)st.1943-541x.0003115. DOI: https://doi.org/10.1061/(ASCE)ST.1943-541X.0003115
P. Chetchotisak, W. Chomchaipol, and J. Teerawong, “Strut-and-tie model for predicting the shear strength of squat shear walls under earthquake loads,” Eng. Struct., vol. 256, no. October 2021, p. 114042, 2022, doi: 10.1016/j.engstruct.2022.114042. DOI: https://doi.org/10.1016/j.engstruct.2022.114042
W. Kassem, “Shear strength of squat walls: A strut-and-tie model and closed-form design formula,” Eng. Struct., vol. 84, pp. 430–438, Feb. 2015, doi: 10.1016/J.ENGSTRUCT.2014.11.027. DOI: https://doi.org/10.1016/j.engstruct.2014.11.027
L. M. Massone, “Strength prediction of squat structural walls via calibration of a shear–flexure interaction model,” Eng. Struct., vol. 32, no. 4, pp. 922–932, Apr. 2010, doi: 10.1016/J.ENGSTRUCT.2009.12.018. DOI: https://doi.org/10.1016/j.engstruct.2009.12.018
H.-W. Yu and S.-J. Hwang, “Evaluation of Softened Truss Model for Strength Prediction of Reinforced Concrete Squat Walls,” J. Eng. Mech., vol. 131, no. 8, pp. 839–846, 2005, doi: 10.1061/(asce)0733-9399(2005)131:8(839). DOI: https://doi.org/10.1061/(ASCE)0733-9399(2005)131:8(839)
C. K. Gulec and A. S. Whittaker, “Empirical equations for peak shear strength of low aspect ratio reinforced concrete walls,” ACI Struct. J., vol. 108, no. 6, p. 777, 2011. DOI: https://doi.org/10.14359/51664205
C. M. Adorno-bonilla, “Shear Strength and Displacement Capacity,” 2016.
J. Ma, C.-L. Ning, and B. Li, “Peak Shear Strength of Flanged Reinforced Concrete Squat Walls,” J. Struct. Eng., vol. 146, no. 4, pp. 1–11, 2020, doi: 10.1061/(asce)st.1943-541x.0002575. DOI: https://doi.org/10.1061/(ASCE)ST.1943-541X.0002575
C. K. Gulec, A. S. Whittaker, B. Stojadinovic, W. W. El-Dakhakhni, B. R. Banting, and S. C. Miller, “Shear Strength of Squat Rectangular Reinforced Concrete Walls,” ACI Struct. J., vol. 106, no. 3, pp. 488–497, 2008, doi: 10.1061/(asce)st.1943-541x.0000713.
W. W. El-Dakhakhni, B. R. Banting, and S. C. Miller, “Seismic Performance Parameter Quantification of Shear-Critical Reinforced Concrete Masonry Squat Walls,” J. Struct. Eng., vol. 139, no. 6, pp. 957–973, 2013, doi: 10.1061/(asce)st.1943-541x.0000713. DOI: https://doi.org/10.1061/(ASCE)ST.1943-541X.0000713
H. Sun, H. V. Burton, and H. Huang, “Machine learning applications for building structural design and performance assessment: State-of-the-art review,” J. Build. Eng., vol. 33, p. 101816, Jan. 2021, doi: 10.1016/J.JOBE.2020.101816. DOI: https://doi.org/10.1016/j.jobe.2020.101816
X. L. C. J. P. Fu and J. L. Y. J. F. Gan, “Prediction of shear strength for squat RC walls using a hybrid ANN–PSO model,” Eng. Comput., vol. 0, no. 0, p. 0, 2017, doi: 10.1007/s00366-017-0547-5. DOI: https://doi.org/10.1007/s00366-017-0547-5
M. A. H.-A. Mohammad Javad Moradi, Developing a Library of Shear Walls Database and the Neural Network Based Predictive Meta-Model. 2019. doi: 10.3390/app9122562. DOI: https://doi.org/10.3390/app9122562
S. Mangalathu and J.-S. Jeon, “Machine Learning–Based Failure Mode Recognition of Circular Reinforced Concrete Bridge Columns: Comparative Study,” J. Struct. Eng., vol. 145, no. 10, pp. 1–12, 2019, doi: 10.1061/(asce)st.1943-541x.0002402. DOI: https://doi.org/10.1061/(ASCE)ST.1943-541X.0002402
S. Mangalathu, H. Jang, S. Hwang, and J. Jeon, “Data-driven machine-learning-based seismic failure mode identification of reinforced concrete shear walls,” Eng. Struct., vol. 208, no. January, p. 110331, 2020, doi: 10.1016/j.engstruct.2020.110331. DOI: https://doi.org/10.1016/j.engstruct.2020.110331
D. Feng et al., “Data-Driven Approach to Predict the Plastic Hinge Length of Reinforced Concrete Columns and Its Application,” vol. 147, no. 2012, pp. 1–17, 2021, doi: 10.1061/(ASCE)ST.1943-541X.0002852. DOI: https://doi.org/10.1061/(ASCE)ST.1943-541X.0002852
H. Zhang, X. Cheng, Y. Li, and X. Du, “Prediction of failure modes, strength, and deformation capacity of RC shear walls through machine learning,” J. Build. Eng., vol. 50, no. January, 2022, doi: 10.1016/j.jobe.2022.104145. DOI: https://doi.org/10.1016/j.jobe.2022.104145
H. U. Ahmed et al., “Innovative modeling techniques including MEP, ANN, and FQ to forecast the compressive strength of geopolymer concrete modified with nanoparticles,” Neural Comput. Appl., vol. 3, 2023, doi: 10.1007/s00521-023-08378-3. DOI: https://doi.org/10.1007/s00521-023-08378-3
J. Chou, C. Liu, H. Prayogo, R. R. Khasani, D. Gho, and G. G. Lalitan, “Predicting the nominal shear capacity of a reinforced concrete wall in a building by metaheuristics-optimized machine learning,” J. Build. Eng., vol. 61, no. August, p. 105046, 2022, doi: 10.1016/j.jobe.2022.105046. DOI: https://doi.org/10.1016/j.jobe.2022.105046
George E. Brown Jr., “NEES Database: The Shear Wall Database ,” DEEDS, 2007. https://datacenterhub.org/dataviewer/view/neesdatabases:db/shearwalldb/
M. U. Santiago Pujol, ACI Subcommittee 445B, Cheng Song, Ying Wang, Aishwarya Puranam, “ACI 445B Shear Wall Database,” DEEDS, 2019.
S. L. Wood, “Shear Strength of Low-Rise Reinforced Concrete Walls,” Struct. J., vol. 87, no. 1, pp. 99–107, Jan. 1990, doi: 10.14359/2951. DOI: https://doi.org/10.14359/2951
Nuclear Standards Committee, Seismic Design Criteria for Structures, Systems, and Components in Nuclear Facilities. United States of America.: American Society of Civil Engineers, 2005.
A. Farzinpour, E. Mohammadi Dehcheshmeh, V. Broujerdian, S. Nasr Esfahani, and A. H. Gandomi, “Efficient boosting-based algorithms for shear strength prediction of squat RC walls,” Case Stud. Constr. Mater., vol. 18, no. February, p. e01928, 20 doi: 10.1016/j.cscm.2023.e01928. DOI: https://doi.org/10.1016/j.cscm.2023.e01928
R. H. Faraj, A. A. Mohammed, A. Mohammed, K. M. Omer, and H. Unis, “Systematic multiscale models to predict the compressive strength of self-compacting concrete modified with nano-silica at different curing ages,” Eng. Comput., 2021, doi: 10.1007/s00366-021-01385-9. DOI: https://doi.org/10.1007/s00366-021-01385-9
M. S. Barkhordari and L. M. Massone, “Failure Mode Detection of Reinforced Concrete Shear Walls Using Ensemble Deep Neural Networks,” 2022. DOI: https://doi.org/10.1186/s40069-022-00522-y
H. U. Ahmed, A. S. Mohammed, A. A. Mohammed, and R. H. Faraj, “Systematic multiscale models to predict the compressive strength of fly ash-based geopolymer concrete at various mixture proportions and curing regimes,” PLoS One, vol. 16, no. 6 June, pp. 1–26, 2021, doi: 10.1371/journal.pone.0253006. DOI: https://doi.org/10.1371/journal.pone.0253006
Jonathan Paulus and Ika Bali, “SHEAR STRENGTH OF REINFORCED CONCRETE WALLS WITH BOUNDARY MEMBER,” Semin. Nas. Teknol. dan Sains II 2016, no. August 2016, pp. 1–6, 2016.
J. Chandra, K. Chanthabouala, and S. Teng, “Truss model for shear strength of structural concrete walls,” ACI Struct. J., vol. 115, no. 2, pp. 323–335, 2018, doi: 10.14359/51701129. DOI: https://doi.org/10.14359/51701129
M. L. Moretti, S. Kono, and T. Obara, “On the shear strength of reinforced concrete walls,” ACI Struct. J., vol. 117, no. 4, pp. 293–304, 2020, doi: 10.14359/51724668. DOI: https://doi.org/10.14359/51724668
D. Nguyen, V. Tran, D. Ha, V. Nguyen, and T. Lee, “A machine learning-based formulation for predicting the shear capacity of squat flanged RC walls,” Structures, vol. 29, no. December 2020, pp. 1734–1747, 2021, doi: 10.1016/j.istruc.2020.12.054. DOI: https://doi.org/10.1016/j.istruc.2020.12.054
A. F. Al-Bayati, “Shear Strength of Reinforced Concrete Squat Walls,” Civ. Eng. J., vol. 9, no. 2, pp. 273–304, 2023, doi: 10.28991/CEJ-2023-09-02-03. DOI: https://doi.org/10.28991/CEJ-2023-09-02-03
Published
How to Cite
Issue
Section
Copyright (c) 2024 Badie H. Sulaiman, Amer M. Ibrahim, Hadeel J. Imran
This work is licensed under a Creative Commons Attribution 4.0 International License.
