Title:
Machine Learning Models for Predicting Rheological Properties of Self-Consolidating Concrete (SCC)
Author(s):
Abdelhamid Hafidi, Ilhame Harbouz, Benoit Hilloulin, Ahmed Loukili, and Ammar Yahia
Publication:
Symposium Paper
Volume:
362
Issue:
Appears on pages(s):
249-267
Keywords:
machine learning (ML); rheology; self-consolidating concrete (SCC); supplementary cementitious materials (SCM); viscosity; yield stress
DOI:
10.14359/51740887
Date:
6/6/2024
Abstract:
This study investigates the potential of machine learning (ML) models to predict the rheological properties of self-consolidating concrete (SCC), with a focus on yield stress and viscosity. The significance of this research arises from the environmental impact of cement production and the pressing need to explore low-carbon alternatives. Supplementary cementitious materials (SCM), such as slag and fly ash, offer promise for reducing carbon emissions in the cement industry. However, their incorporation can alter the rheological properties of concrete, impacting its mechanical and durability characteristics. Predicting these properties is complex due to the multifaceted interplay of various factors. To address this challenge, ML models were employed, including Random Forest (RF) and Gradient Boosting (GB). A comprehensive database comprising 12 input parameters, such as mixture proportions, aggregate characteristics, and rheological attributes, was meticulously compiled from existing literature. Training and testing these ML models revealed GB as a standout performer for predicting yield stress, while RF excelled in forecasting viscosity. Furthermore, a comprehensive SHapley Additive exPlanations (SHAP) analysis was conducted to unravel the most influential parameters impacting yield stress and viscosity. These findings can contribute in advancing our understanding of SCC behavior and the development of sustainable construction materials that align with environmental objectives.
Related References:
1. B. S. Thomas, J. Yang, K. H. Mo, J. A. Abdalla, R. A. Hawileh, et E. Ariyachandra, « Biomass ashes from agricultural wastes as supplementary cementitious materials or aggregate replacement in cement/geopolymer concrete: A comprehensive review », J. Build. Eng., vol. 40, p. 102332, 2021, doi: 10.1016/j.jobe.2021.102332
2. Md. R. Karim, M. F. M. Zain, M. Jamil, F. C. Lai, et Md. N. Islam, « Use of Wastes in Construction Industries as an Energy Saving Approach », Energy Procedia, vol. 12, p. 915‑919, janv. 2011, doi: 10.1016/j.egypro.2011.10.120
3. M. Kovačević, S. Lozančić, E. K. Nyarko, et M. Hadzima-Nyarko, « Application of Artificial Intelligence Methods for Predicting the Compressive Strength of Self-Compacting Concrete with Class F Fly Ash », Materials, vol. 15, no 12, p. 4191, juin 2022, doi: 10.3390/ma15124191
4. O. Boukendakdji, S. Kenai, E. H. Kadri, et F. Rouis, « Effect of slag on the rheology of fresh self-compacted concrete », Constr. Build. Mater., vol. 23, no 7, p. 2593‑2598, juill. 2009, doi: 10.1016/j.conbuildmat.2009.02.029
5. G. Slavcheva, O. Artamonova, D. Babenko, et A. Ibryaeva, « Effect of Limestone Filler Dosage and Granulometry on the 3D printable Mixture Rheology », IOP Conf. Ser. Mater. Sci. Eng., vol. 972, no 1, p. 012042, nov. 2020, doi: 10.1088/1757-899X/972/1/012042
6. D. Li, D. Wang, C. Ren, et Y. Rui, « Investigation of rheological properties of fresh cement paste containing ultrafine circulating fluidized bed fly ash », Constr. Build. Mater., vol. 188, p. 1007‑1013, nov. 2018, doi: 10.1016/j.conbuildmat.2018.07.186
7. A. Neville, « The confused world of sulfate attack on concrete », Cem. Concr. Res., vol. 34, no 8, p. 1275‑1296, août 2004, doi: 10.1016/j.cemconres.2004.04.004
8. K. Kovler et N. Roussel, « Properties of fresh and hardened concrete », Cem. Concr. Res., vol. 41, no 7, p. 775‑792, juill. 2011, doi: 10.1016/j.cemconres.2011.03.009
9. « Workability and compressive strength properties of normal weight concrete using high dosage of fly ash as cement replacement | SpringerLink ». Consulté le: 11 septembre 2023. En ligne.. Disponible sur: https://link.springer.com/article/10.1007/s41024-019-0065-5
10. R. Mandal, S. K. Panda, et S. Nayak, « Rheology of Concrete: Critical Review, recent Advancements, and future prospectives », Constr. Build. Mater., vol. 392, p. 132007, août 2023, doi: 10.1016/j.conbuildmat.2023.132007
11. « How Admixtures Affect Yield Stresses of Cement », ACI Mater. J., vol. 118, no 6, nov. 2021, doi: 10.14359/51734149
12. M. Cheyrezy, « RHEOLOGIE DES BETONS FLUIDES », 1995.
13. D. Feys, R. Cepuritis, S. Jacobsen, K. Lesage, E. Secrieru, et A. Yahia, « Measuring Rheological Properties of Cement Pastes: Most common Techniques, Procedures and Challenges », RILEM Tech. Lett., vol. 2, p. 129‑135, déc. 2017, doi: 10.21809/rilemtechlett.2017.43
14. B. Hilloulin et V. Q. Tran, « Using machine learning techniques for predicting autogenous shrinkage of concrete incorporating superabsorbent polymers and supplementary cementitious materials », J. Build. Eng., vol. 49, p. 104086, mai 2022, doi: 10.1016/j.jobe.2022.104086
15. M. Liang, Z. Chang, Z. Wan, Y. Gan, E. Schlangen, et B. Šavija, « Interpretable Ensemble-Machine-Learning models for predicting creep behavior of concrete », Cem. Concr. Compos., vol. 125, p. 104295, janv. 2022, doi: 10.1016/j.cemconcomp.2021.104295
16. B. Hilloulin, I. Bekrine, E. Schmitt, et A. Loukili, « Modular deep learning segmentation algorithm for concrete microscopic images », Constr. Build. Mater., vol. 349, p. 128736, sept. 2022, doi: 10.1016/j.conbuildmat.2022.128736
17. A. Hafidi, B. Hilloulin, S. Boudache, R. Umunnakwe, et A. Loukili, « Comparison of Machine Learning algorithms for the prediction of the external sulfate attack resistance of blended cements ».
18. B. Hilloulin, A. Hafidi, S. Boudache, et A. Loukili, « Interpretable Ensemble Machine Learning for the prediction of the 1 expansion of cementitious materials under external sulfate attack », JBE, 2023.
19. M. Hosseinzadeh, S. S. Mousavi, A. Hosseinzadeh, et M. Dehestani, « An efficient machine learning approach for predicting concrete chloride resistance using a comprehensive dataset », Sci. Rep., vol. 13, no 1, p. 15024, sept. 2023, doi: 10.1038/s41598-023-42270-3
20. I.-C. Yeh, « Modeling slump flow of concrete using second-order regressions and artificial neural networks », Cem. Concr. Compos., vol. 29, no 6, p. 474‑480, juill. 2007, doi: 10.1016/j.cemconcomp.2007.02.001
21. A. Hafidi, B. Hilloulin, I. Harbouz, L. Lemesre, et A. Loukili, « Modélisation de l’étalement des bétons autoplaçants par apprentissage automatique », vol. 41, 2023.
22. M. Sonebi et A. Cevik, « Genetic programming based formulation for fresh and hardened properties of selfcompacting concrete containing pulverised fuel ash », Constr. Build. Mater., vol. 23, no 7, p. 2614‑2622, juill. 2009, doi: 10.1016/j.conbuildmat.2009.02.012
23. M. Sonebi et A. Cevik, « Prediction of Fresh and Hardened Properties of Self-Consolidating Concrete Using Neurofuzzy Approach », J. Mater. Civ. Eng., vol. 21, no 11, p. 672‑679, nov. 2009, doi: 10.1061/(ASCE)0899-1561(2009)21:11(672)
24. Md. Safiuddin, J. S. West, et K. A. Soudki, « Flowing ability of self-consolidating concrete and its binder paste and mortar components incorporating rice husk ash », Can. J. Civ. Eng., vol. 37, no 3, p. 401‑412, mars 2010, doi: 10.1139/L09-155
25. A. A. A. Hassan, M. Lachemi, et K. M. A. Hossain, « Effect of metakaolin and silica fume on the durability of self-consolidating concrete », Cem. Concr. Compos., vol. 34, no 6, p. 801‑807, juill. 2012, doi: 10.1016/j.cemconcomp.2012.02.013
26. S. D. Bauchkar et H. S. Chore, « Rheological properties of self consolidating concrete with various mineral admixtures », Struct. Eng. Mech., vol. 51, no 1, p. 1‑13, 2014, doi: 10.12989/sem.2014.51.1.001
27. R. Saleh Ahari, T. Kemal Erdem, et K. Ramyar, « Effect of various supplementary cementitious materials on rheological properties of self-consolidating concrete », Constr. Build. Mater., vol. 75, p. 89‑98, janv. 2015, doi: 10.1016/j.conbuildmat.2014.11.014
28. R. Saleh Ahari, T. K. Erdem, et K. Ramyar, « Permeability properties of self-consolidating concrete containing various supplementary cementitious materials », Constr. Build. Mater., vol. 79, p. 326‑336, mars 2015, doi: 10.1016/j.conbuildmat.2015.01.053
29. M. Benaicha, Y. Burtschell, A. H. Alaoui, et K. Elharrouni, « Theoretical calculation of self-compacting concrete plastic viscosity », Struct. Concr., vol. 18, no 5, p. 710‑719, 2017, doi: 10.1002/suco.201600064
30. M. Benaicha, X. Roguiez, O. Jalbaud, Y. Burtschell, et A. H. Alaoui, « Influence of silica fume and viscosity modifying agent on the mechanical and rheological behavior of self compacting concrete », Constr. Build. Mater., vol. 84, p. 103‑110, juin 2015, doi: 10.1016/j.conbuildmat.2015.03.061
31. M. Benaicha, A. Belcaid, A. H. Alaoui, O. Jalbaud, et Y. Burtschell, « Effects of limestone filler and silica fume on rheology and strength of self-compacting concrete », Struct. Concr., vol. 20, no 5, p. 1702‑1709, 2019, doi: 10.1002/suco.201900150
32. M. Benaicha, A. Hafidi Alaoui, O. Jalbaud, et Y. Burtschell, « Dosage effect of superplasticizer on selfcompacting concrete: correlation between rheology and strength », J. Mater. Res. Technol., vol. 8, no 2, p. 2063‑2069, avr. 2019, doi: 10.1016/j.jmrt.2019.01.015
33. « sklearn.preprocessing.StandardScaler », scikit-learn. Consulté le: 28 septembre 2023. En ligne.. Disponible sur: https://scikit-learn/stable/modules/generated/sklearn.preprocessing.StandardScaler.html
34. « Determination of the Coefficient of Correlation | Science ». Consulté le: 29 septembre 2023. En ligne..Disponible sur: https://www.science.org/doi/10.1126/science.30.757.23
35. L. Breiman, « Random Forests », Mach. Learn., vol. 45, no 1, p. 5‑32, oct. 2001, doi: 10.1023/A:1010933404324
36. J. H. Friedman, « Greedy function approximation: A gradient boosting machine. », Ann. Stat., vol. 29, no 5, oct. 2001, doi: 10.1214/aos/1013203451
37. Z. Wei, Y. Meng, W. Zhang, J. Peng, et L. Meng, « Downscaling SMAP soil moisture estimation with gradient boosting decision tree regression over the Tibetan Plateau », Remote Sens. Environ., vol. 225, p. 30‑44, mai 2019, doi: 10.1016/j.rse.2019.02.022
38. « Remote Sensing | Free Full-Text | Combining Partial Least Squares and the Gradient-Boosting Method for Soil Property Retrieval Using Visible Near-Infrared Shortwave Infrared Spectra ». Consulté le: 14 septembre 2023. Enligne.. Disponible sur: https://www.mdpi.com/2072-4292/9/12/1299
39. L. Kopitar, P. Kocbek, L. Cilar, A. Sheikh, et G. Stiglic, « Early detection of type 2 diabetes mellitus using machine learning-based prediction models », Sci. Rep., vol. 10, no 1, Art. no 1, juill. 2020, doi: 10.1038/s41598-020-68771-z
40. G. Ke et al., « LightGBM: A Highly Efficient Gradient Boosting Decision Tree ».
41. M. T. Ribeiro, S. Singh, et C. Guestrin, « “Why Should I Trust You?”: Explaining the Predictions of Any Classifier ». arXiv, 9 août 2016. doi: 10.48550/arXiv.1602.04938
42. S. Haufe et al., « On the interpretation of weight vectors of linear models in multivariate neuroimaging », NeuroImage, vol. 87, p. 96‑110, févr. 2014, doi: 10.1016/j.neuroimage.2013.10.067
43. Ó. H. Wallevik et I. Níelsson, PRO 33: 3rd International RILEM Symposium on Self-Compacting Concrete. RILEM Publications, 2003.
44. O. Wallevik, « Rheology - A scientific approach to develop self-compacting concrete », Proc. 3rd Int. RILEM Symp. Self-Compact. Concr., p. 23‑31, janv. 2003.
45. T. Li et J. Liu, « Effect of aggregate size on the yield stress of mortar », Constr. Build. Mater., vol. 305, p. 124739, oct. 2021, doi: 10.1016/j.conbuildmat.2021.124739
46. D. Jiao, C. Shi, Q. Yuan, X. An, Y. Liu, et H. Li, « Effect of constituents on rheological properties of fresh concrete-A review », Cem. Concr. Compos., vol. 83, p. 146‑159, oct. 2017, doi: 10.1016/j.cemconcomp.2017.07.016
47. « On the Effect of Coarse Aggregate Fraction and Shape on the Rheological Properties of Self-Compacting Concrete ». Consulté le: 28 septembre 2023. En ligne.. Disponible sur: https://www.astm.org/cca10484j.html
48. M. Barra Bizinotto, F. Faleschini, C. G. Jiménez Fernández, et D. F. Aponte Hernández, « Effects of chemical admixtures on the rheology of fresh recycled aggregate concretes », Constr. Build. Mater., vol. 151, p. 353‑362, oct. 2017, doi: 10.1016/j.conbuildmat.2017.06.111
49. K. Chalah, M. Mahdad, A. Benmounah, R. Kheribet, et A. Akouche, « Effect of silica fume on cement rheology properties in presence of superplasticisers », Mater. Today Proc., vol. 58, p. 1246‑1250, janv. 2022, doi: 10.1016/j.matpr.2022.02.006
50. J. J. Chen et A. K. H. Kwan, « Superfine cement for improving packing density, rheology and strength of cement paste », Cem. Concr. Compos., vol. 34, no 1, p. 1‑10, janv. 2012, doi: 10.1016/j.cemconcomp.2011.09.006
51. « Materials | Free Full-Text | Study on the Influence of Silica Fume (SF) on the Rheology, Fluidity, Stability, Time-Varying Characteristics, and Mechanism of Cement Paste ». Consulté le: 27 septembre 2023. En ligne.. Disponible sur: https://www.mdpi.com/1996-1944/15/1/90
52. M. Sonebi, M. Lachemi, et K. M. A. Hossain, « Optimisation of rheological parameters and mechanical properties of superplasticised cement grouts containing metakaolin and viscosity modifying admixture », Constr. Build. Mater., vol. 38, p. 126‑138, janv. 2013, doi: 10.1016/j.conbuildmat.2012.07.102
53. X. Zhang et J. Han, « The effect of ultra-fine admixture on the rheological property of cement paste », Cem. Concr. Res., vol. 30, no 5, p. 827‑830, mai 2000, doi: 10.1016/S0008-8846(00)00236-2
54. R. S. Ahari, T. K. Erdem, et K. Ramyar, « Thixotropy and structural breakdown properties of self consolidating concrete containing various supplementary cementitious materials », Cem. Concr. Compos., vol. 59, p. 26‑37, mai 2015, doi: 10.1016/j.cemconcomp.2015.03.009
55. N. Roussel, C. Stefani, et R. Leroy, « From mini-cone test to Abrams cone test: measurement of cement-based materials yield stress using slump tests », Cem. Concr. Res., vol. 35, no 5, p. 817‑822, mai 2005, doi: 10.1016/j.cemconres.2004.07.032