Predicting the Shear Strength of Reinforced Concrete Dapped End Beams Using Machine Learning Techniques

Quadri, Ajibola Ibrahim; Ojile, Agnes Onyeje; Kupolati, William Kehinde; Ackerman, Chris; Jacque Snyman, Jacque Snyman; Ndambuki, Julius Musyoka

doi:10.22115/scce.2025.480929.1957

Predicting the Shear Strength of Reinforced Concrete Dapped End Beams Using Machine Learning Techniques

Document Type : Regular Article

Authors

Ajibola Ibrahim Quadri ¹

Agnes Onyeje Ojile ²

William Kehinde Kupolati ³

Chris Ackerman ⁴

Jacque Snyman Jacque Snyman ³

Julius Musyoka Ndambuki ³

¹ Ph.D., Department of Civil Engineering, Tshwane University of Technology, South Africa

² MSc., Department of Civil and Environmental Engineering, The Federal University of Technology, Akure

³ Professor, Department of Civil Engineering, Tshwane University of Technology, South Africa

⁴ Senior Lecturer, Department of Civil Engineering, Tshwane University of Technology, South Africa

10.22115/scce.2025.480929.1957

Abstract

Reinforced concrete dapped end beams (RCDEBs) are prone to shear failure due to sudden changes in the cross-section. Hence there is a need to study the shear behavior of the member under loading. This research collected 203 experimental results of RCDEB tests from 17 investigations to predict the shear strength. Geometrical features, concrete strength, amount, and reinforcement layout were considered. The collected datasets were used to train support vector machine (SVM), K-nearest neighbor (KNN), and multilayer perceptron (MLP) models for the shear strength prediction in WEKA software. Variable importance was also carried out to identify the most relevant parameters for predicting the shear strength of RCDEBs. The finding revealed a high prediction accuracy of the shear strength with R of 99, 98, and 97% for SVM, MLP, and KNN, respectively under the percentage split, revealing a strong correlation between the actual dataset and the predicted values. The SVM outperforms MLP and KNN models by 0.52% and 3.27%, respectively. Furthermore, the variable importance analysis revealed that compressive strength, the amount of reinforcement, and geometry are the main parameters influencing the shear capacity of RCDEBs.

Graphical Abstract

Predicting the Shear Strength of Reinforced Concrete Dapped End Beams Using Machine Learning Techniques

Highlights

· Shear strength prediction of reinforced dapped end beams (RCDEBs) has been investigated

· Machine learning using WEKA software

· Support vector machine (SVM), K- nearest neighbor (KNN), and Multilayer perception (MLP) algorithms were employed

· Parameters affecting the shear strength of RCDEBs were observed

Keywords

RCDEBs

Shear capacity

WEKA

Support vector machine

K nearest neighbor

Multilayer perceptron

Subjects

Machine Learning

[1] Aksoylu C, Özkılıç YO, Arslan MH. Damages on prefabricated concrete dapped-end purlins due to snow loads and a novel reinforcement detail. Eng Struct 2020;225:111225. https://doi.org/10.1016/j.engstruct.2020.111225.

[2] Yang K-H, Ashour AF, Lee J-K. Shear strength of reinforced concrete dapped-end beams using mechanism analysis. Mag Concr Res 2011;63:81–97. https://doi.org/10.1680/macr.9.00006.

[3] Lu W-Y, Chen T-C, Lin I-J. Shear strength of reinforced concrete dapped-end beams with shear span-to-depth ratios larger than unity. J Mar Sci Technol 2015;23:5.

[4] di Prisco M, Colombo M, Martinelli P, Coronelli D. The technical causes of the collapse of Annone overpass on SS. 36. Calcestruzzo Strutt. Oggi Teor. Impieghi Mater. Tec., ITA; 2018, p. 1–16.

[5] Cook WD, Mitchell D. Studies of Disturbed Regions Near Discontinuities in Reinforced Concrete Members. ACI Struct J 1988;85. https://doi.org/10.14359/2772.

[6] Rajapakse C, Degée H, Mihaylov B. Assessment of Failure along Re-Entrant Corner Cracks in Existing RC Dapped-End Connections. Struct Eng Int 2021;31:216–26. https://doi.org/10.1080/10168664.2021.1878975.

[7] Mata-Falcón J, Pallarés L, Miguel PF. Proposal and experimental validation of simplified strut-and-tie models on dapped-end beams. Eng Struct 2019;183:594–609. https://doi.org/10.1016/j.engstruct.2019.01.010.

[8] Masėnas V, Meškėnas A, Valivonis J. Analysis of the Bearing Capacity of Reinforced Concrete Dapped-End Beams. Appl Sci 2023;13:5228. https://doi.org/10.3390/app13095228.

[9] Hussain HA, Shadhan KK. The Effect of Construction Joint on Behavior of Reinforced Concrete Dapped End Beam. J Phys Conf Ser 2021;1973:012030. https://doi.org/10.1088/1742-6596/1973/1/012030.

[10] Aksoylu C, Özkılıç YO, Arslan MH. Experimental and numerical investigation of shear strength at dapped end beams having different shear span and recess corner length. Structures 2023;48:79–90. https://doi.org/10.1016/j.istruc.2022.12.076.

[11] Di Carlo F, Meda A, Molaioni F, Rinaldi Z. Experimental evaluation of the corrosion influence on the structural response of Gerber half-joints. Eng Struct 2023;285:116052. https://doi.org/10.1016/j.engstruct.2023.116052.

[12] Quadri AI, Fujiyama C. Cyclic Shear Response of Reinforced Concrete Dapped-End Beams (RCDEBs) Under Bond Deterioration. Int. PhD Symp. Civ. Eng., n.d., p. 227.

[13] Melesse G, Behailu T, Kaske Kassa H. Finite Element Analysis of a Reinforced Concrete Dapped-End Beam under the Effects of Impact Velocity and Dapped-End Beam Cross-Section Geometry. Adv Mater Sci Eng 2023;2023:1–13. https://doi.org/10.1155/2023/5869552.

[14] Hussain HN, M. Shakir Q. Experimental Study of the Behavior of Reinforced Concrete Beams with Composite Dapped End under Effect of Static and Repeated Loads. Int J Appl Sci 2019;2:p43. https://doi.org/10.30560/ijas.v2n1p43.

[15] Quadri AI, Fujiyama C. Response of Reinforced Concrete Dapped-End Beams Exhibiting Bond Deterioration Subjected to Static and Cyclic Loading. J Adv Concr Technol 2021;19:536–54. https://doi.org/10.3151/jact.19.536.

[16] SHAKIR QM, Alliwe R. Upgrading of deficient disturbed regions in precast RC beams with near surface mounted (NSM) steel bars. J Mater Eng Struct «JMES» 2020;7:167–84.

[17] Lu W-Y, Lin I-J, Yu H-W. Behaviour of reinforced concrete dapped-end beams. Mag Concr Res 2012;64:793–805. https://doi.org/10.1680/macr.11.00116.

[18] Atalla A, ALjebouri K. Parameters Affecting the Strength and Behavior of RC Dapped-End Beams: A Numerical Study. J Eng 2022;28:78–97. https://doi.org/10.31026/j.eng.2022.10.06.

[19] Quadri AI, Ali K. Numerical Appraisal of Reinforced Concrete Dapped-End Girder Under High-Fatigue Fixed Pulsating and Moving Loads. Transp Res Rec J Transp Res Board 2024;2678:257–78. https://doi.org/10.1177/03611981231184176.

[20] Mohammed BS, Aswin M, Liew MS, Zawawi NAWA. Structural Performance of RC and R-ECC Dapped-End Beams Based on the Role of Hanger or Diagonal Reinforcements Combined by ECC. Int J Concr Struct Mater 2019;13:44. https://doi.org/10.1186/s40069-019-0356-x.

[21] Quadri AI. Behavior of disturbed region of RC precast beams upgraded with near surface mounted CFRP fiber. Asian J Civ Eng 2023;24:1859–73. https://doi.org/10.1007/s42107-023-00605-5.

[22] Aswin M, Syed ZI, Wee T, Liew MS. Prediction of Failure Loads of RC Dapped-End Beams. Appl Mech Mater 2014;567:463–8. https://doi.org/10.4028/www.scientific.net/AMM.567.463.

[23] Herzinger R, Elbadry M. Alternative Reinforcing Details in Dapped Ends of Precast Concrete Bridge Girders. Transp Res Rec J Transp Res Board 2007;2028:111–21. https://doi.org/10.3141/2028-13.

[24] Menichini G, Gusella F, Orlando M. Methods for evaluating the ultimate capacity of existing RC half-joints. Eng Struct 2024;299:117087. https://doi.org/10.1016/j.engstruct.2023.117087.

[25] Desnerck P, Lees JM, Morley CT. The effect of local reinforcing bar reductions and anchorage zone cracking on the load capacity of RC half-joints. Eng Struct 2017;152:865–77. https://doi.org/10.1016/j.engstruct.2017.09.021.

[26] Tapeh ATG, Naser MZ. Artificial Intelligence, Machine Learning, and Deep Learning in Structural Engineering: A Scientometrics Review of Trends and Best Practices. Arch Comput Methods Eng 2023;30:115–59. https://doi.org/10.1007/s11831-022-09793-w.

[27] Fakharian P, Nouri Y, Ghanizadeh AR, Safi Jahanshahi F, Naderpour H, Kheyroddin A. Bond strength prediction of externally bonded reinforcement on groove method (EBROG) using MARS-POA. Compos Struct 2024;349–350:118532. https://doi.org/10.1016/j.compstruct.2024.118532.

[28] Ma C, Wang S, Zhao J, Xiao X, Xie C, Feng X. Prediction of shear strength of RC deep beams based on interpretable machine learning. Constr Build Mater 2023;387:131640. https://doi.org/10.1016/j.conbuildmat.2023.131640.

[29] Megahed K. Prediction and reliability analysis of shear strength of RC deep beams. Sci Rep 2024;14:14590. https://doi.org/10.1038/s41598-024-64386-w.

[30] Keshavarz Z, Torkian H. Application of ANN and ANFIS models in determining compressive strength of concrete. J Soft Comput Civ Eng 2018;2:62–70.

[31] Lee S-C. Prediction of concrete strength using artificial neural networks. Eng Struct 2003;25:849–57. https://doi.org/10.1016/S0141-0296(03)00004-X.

[32] Mohamed O, Kewalramani M, Ati M, Hawat W Al. Application of ANN for prediction of chloride penetration resistance and concrete compressive strength. Materialia 2021;17:101123. https://doi.org/10.1016/j.mtla.2021.101123.

[33] Mater Y, Kamel M, Karam A, Bakhoum E. ANN-Python prediction model for the compressive strength of green concrete. Constr Innov 2023;23:340–59. https://doi.org/10.1108/CI-08-2021-0145.

[34] Chen L, Nouri Y, Allahyarsharahi N, Naderpour H, Rezazadeh Eidgahee D, Fakharian P. Optimizing compressive strength prediction in eco-friendly recycled concrete via artificial intelligence models. Multiscale Multidiscip Model Exp Des 2025;8:24. https://doi.org/10.1007/s41939-024-00641-x.

[35] Nouri Y, Ghanbari MA, Fakharian P. An integrated optimization and ANOVA approach for reinforcing concrete beams with glass fiber polymer. Decis Anal J 2024;11:100479. https://doi.org/10.1016/j.dajour.2024.100479.

[36] Paudel S, Pudasaini A, Shrestha RK, Kharel E. Compressive strength of concrete material using machine learning techniques. Clean Eng Technol 2023;15:100661. https://doi.org/10.1016/j.clet.2023.100661.

[37] Eskandari-Naddaf H, Kazemi R. ANN prediction of cement mortar compressive strength, influence of cement strength class. Constr Build Mater 2017;138:1–11. https://doi.org/10.1016/j.conbuildmat.2017.01.132.

[38] Lin C-J, Wu N-J. An ANN Model for Predicting the Compressive Strength of Concrete. Appl Sci 2021;11:3798. https://doi.org/10.3390/app11093798.

[39] Moradi MJ, Khaleghi M, Salimi J, Farhangi V, Ramezanianpour AM. Predicting the compressive strength of concrete containing metakaolin with different properties using ANN. Measurement 2021;183:109790. https://doi.org/10.1016/j.measurement.2021.109790.

[40] Noori F, Varaee H. Nonlinear seismic response approximation of steel moment frames using artificial neural networks. Jordan J Civ Eng 2022;16.

[41] ARIFUZZAMAN M. Application of Machine Learning for Predicting Concrete Strength: Ensembles vs. Instance-Based Algorithms in WEKA 2024. https://doi.org/10.21203/rs.3.rs-4745693/v1.

[42] Saad S, Ishtiyaque M, Malik H. Selection of most relevant input parameters using WEKA for artificial neural network based concrete compressive strength prediction model. 2016 IEEE 7th Power India Int. Conf., IEEE; 2016, p. 1–6. https://doi.org/10.1109/POWERI.2016.8077368.

[43] Sharma N, Thakur MS, Sihag P, Malik MA, Kumar R, Abbas M, et al. Machine Learning Techniques for Evaluating Concrete Strength with Waste Marble Powder. Materials (Basel) 2022;15:5811. https://doi.org/10.3390/ma15175811.

[44] Mattock AH. Strut-and-Tie Models for Dapped-End Beams. Concr Int 2012;34.

[45] Quadri AI, Fujiyama C. Assessment of repaired reinforced concrete dapped-end beams exhibiting bond deterioration under static and cyclic loading. Constr Build Mater 2023;403:133070. https://doi.org/10.1016/j.conbuildmat.2023.133070.

[46] Werner MP. Shear Design of Prestressed Concrete Stepped Beams. PCI J 1973;18:37–49. https://doi.org/10.15554/pcij.07011973.37.49.

[47] Mattock AH, Chan TC. Design and Behavior of Dapped-End Beams. PCI J 1979;24:28–45. https://doi.org/10.15554/pcij.11011979.28.45.

[48] Kashyap V, Alyaseen A, Poddar A. Supervised and unsupervised machine learning techniques for predicting mechanical properties of coconut fiber reinforced concrete. Asian J Civ Eng 2024;25:3879–99. https://doi.org/10.1007/s42107-024-01018-8.

[49] Bajwa OI, Baluch HA, Saeed HA. Machine learning approach for predicting key design parameters in UAV conceptual design. Ain Shams Eng J 2024;15:102932. https://doi.org/10.1016/j.asej.2024.102932.

[50] Ngamkhanong C, Alzabeebee S, Keawsawasvong S, Thongchom C. Performance of different machine learning techniques in predicting the flexural capacity of concrete beams reinforced with FRP rods. Asian J Civ Eng 2024;25:525–36. https://doi.org/10.1007/s42107-023-00792-1.

[51] Pham A-D, Ngo N-T, Nguyen T-K. Machine learning for predicting long-term deflections in reinforce concrete flexural structures. J Comput Des Eng 2020;7:95–106. https://doi.org/10.1093/jcde/qwaa010.

[52] Lu W, Lin I, Hwang S, Lin Y. Shear strength of high‐strength concrete dapped‐end beams. J Chinese Inst Eng 2003;26:671–80. https://doi.org/10.1080/02533839.2003.9670820.

[53] Smith TC, Frank E. Introducing Machine Learning Concepts with WEKA, 2016, p. 353–78. https://doi.org/10.1007/978-1-4939-3578-9_17.

[54] Vapnik VN. The Nature of Statistical Learning Theory. New York, NY: Springer New York; 2000. https://doi.org/10.1007/978-1-4757-3264-1.

[55] Çevik A, Kurtoğlu AE, Bilgehan M, Gülşan ME, Albegmprli HM. Support Vector Machines in Structural Engineering: a Review. J Civ Eng Manag 2015;21:261–81. https://doi.org/10.3846/13923730.2015.1005021.

[56] Ahmad S, Elahi A, Hafeez J, Fawad M, Ahsan Z. Evaluation of the shear strength of dapped ended beam. Life Sci J 2013;10:1038–44.

[57] Abdallah MH, Thoeny ZA, Henedy SN, Al-Abdaly NM, Imran H, Bernardo LFA, et al. The Machine-Learning-Based Prediction of the Punching Shear Capacity of Reinforced Concrete Flat Slabs: An Advanced M5P Model Tree Approach. Appl Sci 2023;13:8325. https://doi.org/10.3390/app13148325.

[58] Nguyen H, Vu T, Vo TP, Thai H-T. Efficient machine learning models for prediction of concrete strengths. Constr Build Mater 2021;266:120950. https://doi.org/10.1016/j.conbuildmat.2020.120950.

[59] Üstün B, Melssen WJ, Buydens LMC. Facilitating the application of Support Vector Regression by using a universal Pearson VII function based kernel. Chemom Intell Lab Syst 2006;81:29–40. https://doi.org/10.1016/j.chemolab.2005.09.003.

[60] Aswin M, Mohammed BS, Liew MS, Syed ZI. Shear Failure of RC Dapped-End Beams. Adv Mater Sci Eng 2015;2015:1–11. https://doi.org/10.1155/2015/309135.

[61] Wang Q, Guo Z, Hoogenboom PCJ. Experimental investigation on the shear capacity of RC dapped end beams and design recommendations. Struct Eng Mech 2005;21:221–35. https://doi.org/10.12989/sem.2005.21.2.221.

[62] Aswin M, Al-Fakih A, Syed Z, Liew M. Influence of Different Dapped-End Reinforcement Configurations on Structural Behavior of RC Dapped-End Beam. Buildings 2023;13:116. https://doi.org/10.3390/buildings13010116.

[63] Huang P-C, Nanni A. Dapped-End Strengthening of Full-Scale Prestressed Double Tee Beams with FRP Composites. Adv Struct Eng 2006;9:293–308. https://doi.org/10.1260/136943306776987010.

[64] Liem SK. Maximum shear strength of dapped-end or corbel 1983.

[65] Fayed S, Madenci E, Özkılıç YO. Flexural Behavior of RC Beams with an Abrupt Change in Depth: Experimental Work. Buildings 2022;12:2176. https://doi.org/10.3390/buildings12122176.

[66] Ghanem SY, Elgazzar H. Predicting the behavior of reinforced concrete columns confined by fiber reinforced polymers using data mining techniques. SN Appl Sci 2021;3:170. https://doi.org/10.1007/s42452-020-04136-5.

[67] Gholamy A, Kreinovich V, Kosheleva O. Why 70/30 or 80/20 relation between training and testing sets: A pedagogical explanation 2018.

[68] Kantardzic M. Data mining: concepts, models, methods, and algorithms. John Wiley & Sons; 2011.

[69] Mansour MY, Dicleli M, Lee JY, Zhang J. Predicting the shear strength of reinforced concrete beams using artificial neural networks. Eng Struct 2004;26:781–99. https://doi.org/10.1016/j.engstruct.2004.01.011.

[70] DAŞ O. Prediction of the natural frequencies of various beams using regression machine learning models. Sigma J Eng Nat Sci – Sigma Mühendislik ve Fen Bilim Derg 2023. https://doi.org/10.14744/sigma.2023.00040.

[71] Upadhya A, Thakur MS, Sihag P. Predicting Marshall Stability of Carbon Fiber-Reinforced Asphalt Concrete Using Machine Learning Techniques. Int J Pavement Res Technol 2024;17:102–22. https://doi.org/10.1007/s42947-022-00223-5.

[72] Quadri AI. Shear response of reinforced concrete deep beams with and without web opening. Innov Infrastruct Solut 2023;8:316. https://doi.org/10.1007/s41062-023-01286-4.