Estimation of Fiber Pullout Curve from Cement Base Matrix Using Machine Learning

Document Type : Research Article

Authors

1 Faculty of Civil Engineering, Shahrood University of Technology, Shahrood, Iran

2 Department of Civil Engineering, Toronto Metropolitan University, Ontario, Canada

Abstract

Pull-out tests and corresponding curves help analyze fiber pull-out behavior, which significantly influences the tensile and flexural properties of fiber-reinforced concrete. Artificial intelligence techniques provide an efficient means to predict fiber pull-out curves. In this study, four models based on convolutional neural networks (CNN), long short-term memory networks (LSTM), and extreme gradient boosting (XGBoost) are used to predict fiber pull-out curves: CNN1D, CNN2D, LSTM, and XGBoost. A dataset of 502 experimental samples was compiled, primarily from laboratory studies conducted by one of the authors of this paper. Fiber aspect ratio, loading rate, type and quantity of cement, amount of: binder, silica fume, sand, gravel, quartz, superplasticizer, water, water-to-cement ratio, water-to-binder ratio, curing age, fiber embedded length, end-type of the fibers, the pitch of spirals, number of twists, fiber inclination angle, fiber length and diameter, and concrete compressive strength are among the used input parameters. To represent the expected curve, the model output comprises 1000 pairs of data (pull-out force vs slip). Among the tested models, XGBoost demonstrated superior performance with the lowest mean absolute error (8.39) and highest R² value (0.71), making it the optimal choice for predicting fiber pull-out curves. The parameters “embedded length”, “number of twists”, “Silica fume”, and “pitch of spirals” were more important and influenced the model and prediction accuracy, as can be seen from the evaluation of the feature importance graph.

Keywords

Main Subjects

References

[1] E. Zeighami, F. Jandaghi Alaee, M. Jamee, M. Soltani Mohammadi, Experimental investigation of pull-out behavior of inclined fiber from cementitious matrix, Modares Civil Engineering journal, 16(2) (2016) 173-186. http://mcej.modares.ac.ir/article-16-6742-en.html
[2] F. Isla, G. Ruano, B. Luccioni, Analysis of steel fibers pull-out. Experimental study, Construction and Building Materials, 100 (2015) 183-193. https://doi.org/10.1016/j.conbuildmat.2015.09.034
[3] E.M. Zanjani, S. Barnett, D. Begg, Pullout behaviour of hooked end steel fibres embedded in concrete with various cement replacement materials, in:  Proc., 9th RILEM Int. Symp. of Fiber Reinforced Concrete. Vancouver, Canada, 2016.
[4] Z. Wu, K.H. Khayat, C. Shi, How do fiber shape and matrix composition affect fiber pullout behavior and flexural properties of UHPC?, Cement and Concrete Composites, 90 (2018) 193-201. https://doi.org/10.1016/j.cemconcomp.2018.03.021
[5] A.C. McSwain, K.A. Berube, G. Cusatis, E.N. Landis, Confinement effects on fiber pullout forces for ultra-high-performance concrete, Cement and Concrete Composites, 91 (2018) 53-58. https://doi.org/10.1016/j.cemconcomp.2018.04.011
[6] F. Deng, X. Ding, Y. Chi, L. Xu, L. Wang, The pull-out behavior of straight and hooked-end steel fiber from hybrid fiber reinforced cementitious composite: Experimental study and analytical modelling, Composite Structures, 206 (2018) 693-712. https://doi.org/10.1016/j.compstruct.2018.08.066
[7] Y. Cao, Q. Yu, H. Brouwers, W. Chen, Predicting the rate effects on hooked-end fiber pullout performance from Ultra-High Performance Concrete (UHPC), Cement and Concrete Research, 120 (2019) 164-175. https://doi.org/10.1016/j.cemconres.2019.03.022
[8] H. Feng, M.N. Sheikh, M.N. Hadi, L. Feng, D. Gao, J. Zhao, Pullout behaviour of different types of steel fibres embedded in magnesium phosphate cementitious matrix, International Journal of Concrete Structures and Materials, 13(1) (2019) 1-17. https://doi.org/10.1186/s40069-019-0344-1
[9] B. Chun, D.-Y. Yoo, N. Banthia, Achieving slip-hardening behavior of sanded straight steel fibers in ultra-high-performance concrete, Cement and Concrete Composites, 113 (2020) 103669. https://doi.org/10.1016/j.cemconcomp.2020.103669
[10] H. Zhang, R.C. Yu, Inclined fiber pullout from a cementitious matrix: A numerical study, Materials, 9(10) (2016) 800. https://doi.org/10.3390/ma9100800
[11] L. Hoppe, Numerical simulation of fiber-matrix debonding in single fiber pull-out tests, GAMM Archive for Students (GAMMAS), 2(1) (2020) 21-35. https://doi.org/10.14464/gammas.v2i1.437
[12] A. Hemmatian, M. Jalali, H. Naderpour, M.L. Nehdi, Machine learning prediction of fiber pull-out and bond-slip in fiber-reinforced cementitious composites, Journal of Building Engineering, 63 (2023) 105474. https://doi.org/10.1016/j.jobe.2022.105474
[13] J.-X. Huang, X.-Z. Shi, N. Zhang, Y.-Q. Hu, J.-Q. Wang, Prediction of Bond Strength between Fibers and the Matrix in UHPC Utilizing Machine Learning and Experimental Data, Materials Today Communications,  (2024) 111136. https://doi.org/10.1016/j.mtcomm.2024.111136
[14] L. Huang, M. Yuan, B. Wei, D. Yan, Y. Liu, Experimental investigation on sing fiber pullout behaviour on steel fiber-matrix of reactive powder concrete (RPC), Construction and Building Materials, 318 (2022) 125899. https://doi.org/10.1016/j.conbuildmat.2021.125899
[15] S. Sharda, M. Singh, S. Singh, A review on Properties of Fiber Reinforced Cement-based materials, Iosr. J. Mech. Civ. Eng.(IOSR-JMCE), 13 (2016) 104-112. https://doi.org/10.9790/1684-130501104112
[16] G. Pachideh, M. Gholhaki, A. Moshtagh, Performance of concrete containing recycled springs in post-fire conditions, Proceedings of the Institution of Civil Engineers - Structures and Buildings, 173(1) (2018) 3-16. https://doi.org/10.1680/jstbu.18.00042
[17] G. Pachideh, M. Gholhaki, Using steel and polypropylene fibres to improve the performance of concrete sleepers, Proceedings of the Institution of Civil Engineers-Structures and Buildings, 173(9) (2020) 690-702.https:/doi.org/10.1680/jstbu.18.00154
[18] G. Pachideh, V. Toufigh, Strength of SCLC recycled springs and fibers concrete subject to high temperatures, Structural Concrete, 23(1) (2022) 285-299. https://doi.org/10.1002/suco.202100183
[19] M. Khalily, V. Saberi, H. Saberi, V. Mansouri, A. Sadeghi, G. Pachideh, An Experimental Study on the Effect of High Temperatures on Performance of the Plastic Lightweight Concrete Containing Steel, Polypropylene and Glass Fibers, Journal of Structural and Construction Engineering, 8(12) (2022) 284-307. https://dx.doi.org/10.22065/jsce.2021.254752.2277
[20] Y.M. Abbas, M. Iqbal Khan, Fiber–Matrix Interactions in Fiber-Reinforced Concrete: A Review, Arabian Journal for Science and Engineering, 41(4) (2016) 1183-1198. https://doi.org/10.1007/s13369-016-2099-1
[21] L.F. Friedrich, C. Wang, Continuous modeling technique of fiber pullout from a cement matrix with different interface mechanical properties using finite element program, Latin American Journal of Solids and Structures, 13(10) (2016) 1937-1953. https://doi.org/10.1016/j.conbuildmat.2021.125899
[22] E. Wölfel, H. Brünig, I. Curosu, V. Mechtcherine, C. Scheffler, Dynamic Single-Fiber Pull-Out of Polypropylene Fibers Produced with Different Mechanical and Surface Properties for Concrete Reinforcement, Materials (Basel), 14(4) (2021). https://doi.org/10.3390/ma14040722
[23] M.S. Barkhordari, S. Ghavaminejad, M. Tehranizadeh, Predicting Autogenous Shrinkage of Concrete Including Superabsorbent Polymers and Other Cementitious Ingredients Using Convolution-based Algorithms, Periodica Polytechnica Civil Engineering,  (2024). https://doi.org/10.3311/PPci.23568
[24] D. Griffiths, J. Boehm, Rapid object detection systems, utilising deep learning and unmanned aerial systems (uas) for civil engineering applications, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 42 (2018) 391-398. https://doi.org/10.5194/isprs-archives-XLII-2-391-2018
[25] F. Şermet, I. Pacal, Deep learning approaches for autonomous crack detection in concrete wall, brick deck and pavement, Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi, 15(2) (2024) 503-513. https://doi.org/10.24012/dumf.1450640
[26] D. Yang, Deep Learning Based Image Recognition Technology for Civil Engineering Applications, Applied Mathematics and Nonlinear Sciences, 9(1) (2024). https://doi.org/10.2478/amns-2024-0183
[27] M. Padsumbiya, V. Brahmbhatt, S.P. Thakkar, Automatic crack detection using convolutional neural network, Journal of Soft Computing in Civil Engineering, 6(3) (2022) 1-17. https://doi.org/10.22115/scce.2022.325596.1397
[28] G. Van Houdt, C. Mosquera, G. Nápoles, A review on the long short-term memory model, Artificial Intelligence Review, 53(8) (2020) 5929-5955. https://doi.org/10.1007/s10462-020-09838-1
[29] J. Madiniyeti, Y. Chao, T. Li, H. Qi, F. Wang, Concrete dam deformation prediction model research based on SSA–LSTM, Applied Sciences, 13(13) (2023) 7375. https://doi.org/10.3390/app13137375
[30] A. Gogineni, M.K.D. Rout, K. Shubham, Evaluating machine learning algorithms for predicting compressive strength of concrete with mineral admixture using long short-term memory (LSTM) Technique, Asian Journal of Civil Engineering,  (2023) 1-13. https://doi.org/10.1007/s42107-023-00885-x
[31] M. Impraimakis, Deep recurrent-convolutional neural network learning and physics Kalman filtering comparison in dynamic load identification, Structural Health Monitoring,  (2024). https://doi.org/10.1177/14759217241262972
[32] D.-K. Thai, D.-N. Le, Q.H. Doan, T.-H. Pham, D.-N. Nguyen, A hybrid model for classifying the impact damage modes of fiber reinforced concrete panels based on XGBoost and Horse Herd Optimization algorithm, Structures, 60 (2024) 105872. https://doi.org/10.1016/j.istruc.2024.105872
[33] J. Wang, S. Zhou, Particle swarm optimization‐XGBoost‐based modeling of radio‐frequency power amplifier under different temperatures, International Journal of Numerical Modelling: Electronic Networks, Devices and Fields, 37(2) (2024) e3168. https://doi.org/10.1002/jnm.3168
[34] A. Pal, K.S. Ahmed, S. Mangalathu, Data-driven machine learning approaches for predicting slump of fiber-reinforced concrete containing waste rubber and recycled aggregate, Construction and Building Materials, 417 (2024) 135369. https://doi.org/10.1016/j.conbuildmat.2024.135369
[35] Z. Shen, A.F. Deifalla, P. Kamiński, A. Dyczko, Compressive strength evaluation of ultra-high-strength concrete by machine learning, Materials, 15(10) (2022) 3523. https://doi.org/10.3390/ma15103523
[36] G. Airlangga, Comparison of Predictive Modeling Concrete Compressive Strength with Machine Learning Approaches, UKaRsT, 8(1) (2024) 28-41. https://doi.org/10.30737/ukarst.v8i1.5532
[37] D. Sathyan, D. Govind, C. Rajesh, K. Gopikrishnan, G.A. Kannan, J. Mahadevan, Modelling the shear flow behaviour of cement paste using machine learning–XGBoost, in:  Journal of Physics: Conference Series, IOP Publishing, 2020, pp. 012026. https://doi.org/10.1088/1742-6596/1451/1/012026
[38] Y. Wei, R. Ji, Q. Li, Z. Song, Mechanical Performance Prediction Model of Steel Bridge Deck Pavement System Based on XGBoost, Applied Sciences, 13(21) (2023) 12048. https://doi.org/10.3390/app132112048
[39] N.M. Shahani, Q. Xiaowei, X. Wei, L. Jun, T. Aizitiliwumaier, M. Xiaohu, Q. Shigui, C. Weikang, L. Longhe, Hybrid PSO with tree-based models for predicting uniaxial compressive strength and elastic modulus of rock samples, Frontiers in Earth Science, 12 (2024) 1337823. https://doi.org/10.3389/feart.2024.1337823
[40] S. Ataee, M. Jalali, M.L. Nehdi, Pull-out behavior of twin-twisted steel fibers from various strength cement-based matrices, Construction and Building Materials, 445 (2024) 137855. https://doi.org/10.1016/j.conbuildmat.2024.137855
[41] A.H. Peyvandi, M. Jalali, M. Hajsadeghi, S. Das, Experimental investigation on the performance of engineered spiral fiber: Fiber pull-out and direct tension tests, Construction and Building Materials, 347 (2022) 128569. https://doi.org/10.1016/j.conbuildmat.2022.128569
[42] C. Yang, Y. Kim, S. Ryu, G.X. Gu, Prediction of composite microstructure stress-strain curves using convolutional neural networks, Materials & Design, 189 (2020) 108509. https://doi.org/10.1016/j.matdes.2020.108509
[43] M. Letif, R. Bahar, N. Mezouar, The Use of machine learning models and SHAP interaction values to predict the soil swelling index, Periodica Polytechnica Civil Engineering, 69(1) (2025) 239-250. https://doi.org/10.3311/PPci.36880
[44] Z. Chang, Z. Wan, Y. Xu, E. Schlangen, B. Šavija, Convolutional neural network for predicting crack pattern and stress-crack width curve of air-void structure in 3D printed concrete, Engineering Fracture Mechanics, 271 (2022) 108624. https://doi.org/10.1016/j.engfracmech.2022.108624
[45] S.A. Muzafar, K.N. Ali, M.A. Kassem, M.A. Khoiry, Civil engineering standard measurement method adoption using a structural equation modelling approach, Buildings, 13(4) (2023) 963. https://doi.org/10.3390/buildings13040963
[46] P. Ziolkowski, Computational Complexity and Its Influence on Predictive Capabilities of Machine Learning Models for Concrete Mix Design, Materials, 16(17) (2023) 5956. https://doi.org/10.3390/ma16175956
AUT Journal of Civil Engineering
Volume 9, Issue 2
2025
Pages 143-158

Files

Share

How to cite

Statistics