An improved random forest model to predict bond strength of FRP-to-concrete

    Li Tao Affiliation
    ; Xinhua Xue Affiliation


Fiber-reinforced polymer (FRP) is an excellent building material for strengthening concrete structures, but it is difficult to accurately evaluate the bond strength of FRP-to-concrete due to the influence of various parameters. In this study, a novel hybrid model which combines particle swarm optimization (PSO) with random forest (RF) was proposed to predict the bond strength of FRP-to-concrete. The PSO algorithm was used to optimize the hyperparameters of the RF model. A total of 749 specimens collected from the literature were used to develop the proposed PSO-RF model. Each sample contains 11 parameters required for the model. These 11 parameters are (1) the compressive strength of concrete, (2) the tensile strength of concrete, (3) the width of concrete specimen, (4) the maximum aggregate size of concrete, (5) the tensile strength of FRP, (6) the thickness of FRP, (7) the elastic modulus of FRP, (8) the tensile strength of adhesive, (9) the bond length of FRP, (10) the bond width of FRP, and (11) the bond strength of FRP-to-concrete. The proposed PSO-RF model was compared with other machine learning models as well as ten empirical equations. Six statistical indices, namely root mean squared error (RMSE), mean absolute error (MAE), coefficient of determination (R2), Nash-Sutcliffe efficiency coefficient (NSE), Willmott’s Index of Agreement (WIA), and Legates-McCabe’s Index (LM) were used to evaluate the prediction performance of the abovementioned models. The results show that the RMSE, MAE, R2, NSE, WIA and LM values of the PSO-RF model are 1.529 kN, 0.942 kN, 0.986, 0.984, 0.996 and 0.892, respectively, for the training datasets and 2.672 kN, 1.967 kN, 0.963, 0.961, 0.989 and 0.761, respectively, for the test datasets. It can be concluded that the proposed PSO-RF model has the best comprehensive performance in predicting the bond strength of FRP-to-concrete. In addition, the sensitivity analysis of the PSO-RF model was also conducted in this study.

Keyword : fiber-reinforced polymer, multivariate adaptive regression splines, wavelet neural network, particle swarm optimization, random forest

How to Cite
Tao, L., & Xue, X. (2024). An improved random forest model to predict bond strength of FRP-to-concrete. Journal of Civil Engineering and Management, 30(6), 520–535.
Published in Issue
Jul 5, 2024
Abstract Views
PDF Downloads
Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.


Accardi, M., Cucchiara, C., & La Mendola, L. (2007). Bond behavior between CFRP strips and calcarenite stone. In Proceedings of the 6th International Conference on Fracture Mechanics of Concrete and Concrete Structures, Catania, Italy.

Alam, M. A., Onik, S. A., & Bin Mustapha, K. N. (2020). Crack based bond strength model of externally bonded steel plate and CFRP laminate to predict debonding failure of shear strengthened RC beams. Journal of Building Engineering, 27, Article 100943.

Al-Saadi, N. T. K., Mohammed, A, & Al-Mahaidi, R. (2018). Bond performance of NSM CFRP strips embedded in concrete using direct pull-out testing with cementitious adhesive made with graphene oxide. Construction and Building Materials, 162, 523–533.

Ascione, F., Lamberti, M., Napoli, A., Razaqpur, A. G., & Realfonzo, R. (2019). Modeling SRP-concrete interfacial bond behavior and strength. Engineering Structures, 187, 220–230.

Barham, W. S., Obaidat, Y. T., & Al-Maabreh, A. I. (2019). Effect of aggregate size on the bond behavior between carbon fiber-reinforced polymer sheets and concrete. Journal of Materias in Civil Engineering, 31(12), Article 04019295.

Barris, C., Correia, L., & Sena-Cruz, J. (2018). Experimental study on the bond behaviour of a transversely compressed mechanical anchorage system for externally bonded reinforcement. Composite Structures, 200, 217–228.

Bakis, C. E., Uppuluri, V. S., Nanni, A., & Boothby, T. E. (1998). Analysis of bonding mechanisms of smooth and lugged FRP rods embedded in concrete. Composites Science and Technology, 58(8), 1307–1319.

Breiman, L. (2001). Random forests. Machine Learning, 45, 5–32.

Cascardi, A., Micelli, F., & Aiello, M. A. (2017). An artificial neural networks model for the prediction of the compressive strength of FRP-confined concrete circular columns. Engineering Structures, 140, 199–208.

Chróścielewski, J., Ferenc, T., Mikulski, T., Miśkiewicz, M., & Pyrzowski, Ł. (2019). Numerical modelling and experimental validation of full-scale segment to support design of novel GFRP footbridge. Composite Structures, 213, 299–307.

Chen, J. F., & Teng, J. (2001). Anchorage strength models for FRP and steel plates bonded to concrete. Journal of Structural Engineering, 127(7), 784–791.

Chen, S. Z., Zhang, S. Y., Han, W. S., & Wu, G. (2021). Ensemble learning based approach for FRP-concrete bond strength prediction. Construction and Building Materials, 302, Article 124230.

Correial, L., Barris, C., Franca, P., & Sena-Curz, J. (2019). Effect of temperature on bond behavior of externally bonded FRP laminates with mechanical end anchorage. Journal of Composites for Construction, 23(5), Article 04019036.

Czaderski, C., Soudki, K., & Motavalli, M. (2010). Front and side view image correlation measurements on FRP to concrete pull-off bond tests. Journal of Composites for Construction, 14(4), 451–463.

Dai, J., Ueda, T., & Sato, Y. (2005). Development of the nonlinear bond stress–slip model of fiber reinforced plastics sheet–concrete interfaces with a simple method. Journal of Composites for Construction, 9(1), 52–62.

Dai, Y., Khandelwal, M., Qiu, Y., Zhou, J., Monjezi, M., & Yang, P. X. (2022). A hybrid metaheuristic approach using random forest and particle swarm optimization to study and evaluate backbreak in open-pit blasting. Neural Computing and Applications, 34, 6273–6288.

Daneshvar, D., & Behnood, A. (2020). Estimation of the dynamic modulus of asphalt concretes using random forests algorithm. International Journal of Pavement Engineering, 23(2), 250–260.

Daud, R. A., Cunningham, L. S., & Wang, Y. C. (2015). Static and fatigue behaviour of the bond interface between concrete and externally bonded CFRP in single shear. Engineering Structures, 97, 54–67.

Daud, R. A., Cunningham, L. S., Wang, & Y. C. (2017). New model for post-fatigue behaviour of CFRP to concrete bond interface in single shear. Composite Structures, 163, 63–76.

Friedman, J. H. (1991). Multivariate adaptive regression splines. Annals of Statistics, 19(1), 1–67.

Ferreira, C. (2001). Gene expression programming: a new adaptive algorithm for solving problems. Complex and Intelligent Systems, 13, 87–129.

Garzon-Roca, J., Sena-Cruz, J. M., Fernandes, P., & Xavier, J. (2015). Effect of wet-dry cycles on the bond behaviour of concrete elements strengthened with NSM CFRP laminate strips. Composite Structures, 132, 331–340.

Ghorbani, M., Mostofinejad, D., & Hosseini, A. (2017). Experimental investigation into bond behavior of FRP-to-concrete under mixed-mode I/II loading. Construction and Building Materials, 132, 303–312.

Haddad, R. H., Al-Rousan, R., Ghanma, L., & Nimri, Z. (2015). Modifying CFRP-concrete bond characteristics from pull-out testing. Magazine of Concrete Ressearch, 67(13), 707–717.

Hadigheh, S., Gravina, R., & Setunge, S. (2015). Identification of the interfacial fracture mechanism in the FRP laminated substrates using a modified single lap shear test set-up. Engineering Fracture Mechanics, 134, 317–329.

Hiroyuki, Y., & Wu, Z. S. (1997). Analysis of debonding fracture properties of CFS strengthened RC member subject to tension. In Proceedings of 3rd International Symposium on the Non-Metallic (FRP) Reinforcement for Concrete Structures, The Japan Concrete Institute, Japan.

Irshidat, M. R., & Al-Saleh, M. H. (2016). Effect of using carbon nanotube modified epoxy on bond-slip behavior between concrete and FRP sheets. Construction and Building Materials, 105, 511–518.

Ivakhnenko, A. G. (1971). Polynomial theory of complex systems. IEEE Transactions on Systems, Man, and Cybernetics, 4, 364–378.

Jahangir, H., & Eidgahee, D. R. (2021). A new and robust hybrid artificial bee colony algorithm – ANN model for FRP-concrete bond strength evaluation. Composite Structures, 257, Article 113160.

Japan Concrete Institute. (2003). Technical report of Technical Committee on retrofit technology.

Jekabsons, G. (2011). ARESLab: Adaptive regression splines toolbox for Matlab/Octave.

Khalifa, A., Gold, W. J., Nanni, A., & Abdel Aziz, M. I. (1998). Contribution of externally bonded FRP to shear capacity of RC flexural members. Journal of Composites for Construction, 2(4), 195–202.

Legates, D. R., & McCabe, G. J. (1999). Evaluating the use of “goodness-of-fit” measures in hydrologic and hydroclimatic model validation. Water Resources Research, 35(1), 233–241.

Luat, N. V., Shin, J., & Lee, K. (2021). Ultimate axial capacity prediction of CCFST columns using hybrid intelligence models-a new approach. Steel and Composite Structures, 40(3), 461–479.

Maeda, T., Asano, Y., Sato, Y., Ueda, T., & Kakuta, Y. (1999). A study on bond mechanism of carbon fiber sheet. In Proceedings of the 3rd International Symposium on Non-Metallic (FRP) Reinforcement for Concrete Structures (pp. 279–286), Sapporo, Japan.

Mirzania, E., Vishwakarma, D. K., Bui, Q. A. T., Band, S. S., & Dehghani, R. (2023). A novel hybrid AIG-SVR model for estimating daily reference evapotranspiration. Arabian Journal of Geosciences, 16, Article 301.

Murad, Y., Ashteyat, A., & Hunaifat, R. (2019). Predictive model to the bond strength of FRP-to-concrete under direct pullout using gene expression programming. Journal of Civil Engineering and Management, 25(8), 773–784.

Nash, J. E., & Sutcliffe, J. V. (1970). River flow forecasting through conceptual models part I ̶ A discussion of principles. Journal of Hydrology, 10, 282–290.

Naser, M. Z., Kodur, V., Thai, H. T., Hawileh, R., Abdalla, J., & Degtyarev, V. V. (2021). StructuresNet and FireNet: Benchmarking datasets and machine learning algorithms in structural and fire engineering domains. Journal of Building Engineering, 44, Article 102977.

Nerilli, F., & Vairo, G. (2018). Experimental investigation on the debonding failure mode of basalt-based FRP sheets from concrete. Composites Part B: Engineering, 153, 205–216.

Neubauer, U., & Rostásy, F. S. (1997). Design aspects of concrete structures strengthened with externally bonded CFRP plates. In Proceedings of the 7th International Conference on Structural Faults and Repairs (Vol. 2, pp. 109–118). ECS Publications.

Niedermeier, R. (1996). Stellungnahme zur richtlinie für das verkleben von betonbauteilen durch ankleben von stahllaschen-entwurf. Technische University, Munich, Germany.

Nilsen, V., Le Pham, T., Hibbard, M., Klager, A., Cramer, S. M., & Morgan, D. (2019). Prediction of concrete coefficient of thermal expansion and other properties using machine learning. Construction and Building Materials, 220, 587–595.

Ozakkaloglu, T., Fang, C., & Gholampour, A. (2017). Influence of FRP anchor configuration on the behavior of FRP plates externally bonded on concrete members. Engineering Structures, 13, 133–150.

Pan, J., & Leung, C. K. (2007). Effect of concrete composition on FRP/concrete bond capacity. Journal of Composites for Construction, 11(6), 611–618.

Pei, Z., & Wei, Y. F. (2022). Prediction of the bond strength of FRP-to-concrete under direct tension by ACO-based ANFIS approach. Composite Structures, 282, Article 115070.

Peng, H., Hao, H., Zhang, J., Liu, Y., & Cai, C. S. (2015). Experimental investigation of the bond behavior of the interface between near-surface-mounted CFRP strips and concrete. Construction and Building Materials, 96, 11–19.

Siwowski, T., Rajchel, M., & Kulpa, M. (2019). Design and field evaluation of a hybrid FRP composite – Lightweight concrete road bridge. Composite Structures, 230, Article 111504.

Vishwakarma, D. K., Kuriqi, A., Abed, S. A., Kishore, G., Al-Ansari, N., Pandey, K., Kumar, P., Kushwaha, N. L., & Jewel, A. (2023). Forecasting of stage-discharge in a non-perennial river using machine learning with gamma test. Heliyon, 9, Article e16290.

Wan, B., Jiang, C., & Wu, Y. F. (2018). Effect of defects in externally bonded FRP reinforced concrete. Construction and Building Materials, 172, 63–76.

Willmott, C. J. (1981). On the validation of models. Physical Geography, 2(2), 184–194.

Yang, Y. X.,Yue, Q. R., & Hu, Y. C. (2001). Experimental study on bond performance between carbon fiber sheets and concrete. Journal of Building Structures, 22, 36–42 (in Chinese).

Yuan, C., Chen, W. S., Pham, T. M., Cui, J., Shi, Y. C., & Hao, H. (2019). Effect of aggregate size on the dynamic interfacial bond behaviour between basalt fiber reinforced polymer sheets and concrete. Construction and Building Materials, 227, Article 116584.

Zhang, Q., & Benveniste, A. (1992). Wavelet networks. IEEE Transactions on Neural Networks and Learning Systems, 3(6), 889–898.

Zhang, J. F., & Wang, Y. H. (2021). Evaluating the bond strength of FRP-to-concrete composite joints using metaheuristic-optimized least-squares support vector regression. Neural Computing and Applications, 33, 3621–3635.

Zhang, F., Wang, C. X., Liu, J., Zou, X. X., Sneed, L. H., Bao, Y., & Wang, L. B. (2023). Prediction of FRP-concrete interfacial bond strength based on machine learning. Engineering Structures, 274, Article 115156.