journal article·2023-05Open access

Predicting the crack width of the engineered cementitious materials via standard machine learning algorithms

Xiongzhou Yuan, Qingyu Cao, Muhammad Nasir Amin, Ayaz Ahmad, Waqas Ahmad, Fadi Althoey, Ahmed Farouk Deifalla

Abstract

This study aims to develop various machine learning (ML) models to investigate the self-healing capacity of engineered cementitious composites (ECC) and to evaluate the effect of input parameters (raw materials and crack width before the healing process) on output parameters (crack width after the healing process) via Shapley additive explanations (SHAP) analysis. The combination of the individual and ensemble ML models has been introduced to check and compare the accuracy level towards the prediction of crack width after the healing process to access the most suitable model for this application. The support vector machine (SVM) from the individual, while XGBoost (XGB) and random forest (RF) from ensemble ML models have been investigated for prediction purposes. As per the obtained results, the RF model outperforms both the SVM and XGB algorithms in forecasting the fracture width after the healing process for the selected ECC in concrete material. The performance indicator, such as the coefficient of determination (R2), was reported as 0.97 for RF, 0.96 for XGB, and 0.93 for the SVM model. Statistical results and k-fold cross-validation for the employed ML models also confirm their legitimacy. It was also noted from the result of the SHAP analysis that the significant contribution was for the crack width before healing towards the prediction of crack width after the healing process. Furthermore, the ML models can also be utilized to anticipate the healing ability of the other ECC, such as soda glass powder, marble powder, and bagasse ash.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Microbial Applications in Construction Materials · Concrete and Cement Materials Research · Innovative concrete reinforcement materials

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (92)

Show source-provided references
1. Jonkers · 2007 · 195
2. Efficiency of basalt fiber length and content on mechanical and microstructural properties of hybrid fiber concrete10.1111/ffe.13483 ↗
3. Schlangen · 2009
4. Restrained cracking failure behavior of concrete containing MgO compound expansive agent under adiabatic condition at early age10.1016/j.cemconcomp.2022.104825 ↗
5. Early-age autogenous shrinkage and tensile creep of hooked-end steel fiber reinforced concrete with different thermal treatment temperatures10.1016/j.cemconcomp.2022.104550 ↗
6. Early-age behavior and cracking resistance of high-strength concrete reinforced with Dramix 3D steel fiber10.1016/j.conbuildmat.2018.10.125 ↗
7. Early-age autogenous shrinkage, tensile creep, and restrained cracking behavior of ultra-high-performance concrete incorporating polypropylene fibers10.1016/j.cemconcomp.2023.104948 ↗
8. Influence of Barchip fiber length on early-age behavior and cracking resistance of concrete internally cured with super absorbent polymers10.1016/j.conbuildmat.2019.03.209 ↗
9. Influence of curing temperature on autogenous shrinkage and cracking resistance of high-performance concrete at an early age10.1016/j.conbuildmat.2015.11.039 ↗
10. Effect of different PVA and steel fiber length and content on mechanical properties of CaCO 3 whisker reinforced cementitious composites10.3989/mc.2019.12918 ↗
11. Review on different testing methods and factors affecting fracture properties of fiber reinforced cementitious composites10.1016/j.conbuildmat.2020.121766 ↗
12. Uniaxial tensile behavior, flexural properties, empirical calculation and microstructure of multi-scale fiber reinforced cement-based material at elevated temperature10.3390/ma14081827 ↗
13. Influence of cracking on the diffusion properties of cement-based materials: Part I: influence of continuous cracks on the steady-state regime10.1016/S0008-8846(99)00201-X ↗
14. Edvardsen · 1999 · 473
15. Experimental characterization of the self-healing of cracks in an ultra high performance cementitious material: mechanical tests and acoustic emission analysis10.1016/j.cemconres.2006.12.005 ↗
16. Self-sealing, autogenous healing and continued hydration: what is the difference?10.1007/BF02481539 ↗
17. Extent of healing of cracked normal strength concrete10.1061/(ASCE)0899-1561(2000)12:1(92) ↗
18. Effect of cracking and healing on chloride transport in OPC concrete10.1016/0008-8846(96)00072-5 ↗
19. Theoretical estimation of the elastic moduli of self-healing concrete relevant to the evolution of cracks closing due to crystallization- and precipitation-based mechanism
20. First UK field application and performance of microcapsule-based self-healing concrete10.1016/j.conbuildmat.2019.02.178 ↗
21. The effects of hydraulic pressure and crack width on water permeability of penetration crack-induced concrete10.1016/j.conbuildmat.2010.11.107 ↗
22. Hybrid fiber concrete with different basalt fiber length and content10.1002/suco.202000472 ↗
23. Efficiency of supplementary cementitious materials and natural fiber on mechanical performance of concrete10.1007/s13369-020-04769-z ↗
24. Influence of cracks and crack width on penetration depth of chlorides in concrete10.1080/19648189.2009.9693134 ↗
25. Corrosion in cracked and uncracked concrete–influence of crack width, concrete quality and crack reopening10.1680/macr.2010.62.6.393 ↗
26. Corrosion initiation in cracked fibre reinforced concrete: influence of crack width, fibre type and loading conditions10.1016/j.corsci.2015.05.021 ↗
27. W.R.L.d. Silva, D.S.d. Lucena, Concrete cracks detection based on deep learning image classification, MDPI AG, p. 489.10.3390/ICEM18-05387 ↗
28. Industrial application of biological self-healing concrete: challenges and economical feasibility10.5912/jcb662 ↗
29. A review of self-healing concrete research development
30. Effectiveness of calcium carbonate whisker in cementitious composites, periodica polytechnica
31. K. Van Breugel, Is there a market for self-healing cement-based materials, pp. 1-9.
32. Bacteria-based concrete: from concept to market10.1088/0964-1726/25/8/084006 ↗
33. Plasticity model for concrete using the bounding surface concept10.1016/0749-6419(94)90051-5 ↗
34. Bacteria based self healing concrete–A review10.1016/j.conbuildmat.2017.07.040 ↗
35. Bacteria based self healing concrete–A review10.1016/j.conbuildmat.2017.07.040 ↗
36. Application of ureolysis-based microbial CaCO3 precipitation in self-healing of concrete and inhibition of reinforcement corrosion10.1016/j.conbuildmat.2020.120364 ↗
37. Influence of prewetted lightweight aggregates on the behavior and cracking potential of internally cured concrete at an early age10.1016/j.conbuildmat.2015.08.093 ↗
38. Self-healing cementitious materials by the combination of microfibres and superabsorbent polymers10.1177/1045389X12438623 ↗
39. Autogenous healing performance of internal curing agent-based self-healing cementitious composite10.1016/j.cemconcomp.2020.103825 ↗
40. Evaluating self healing capability of bituminous mastics10.1007/s11340-011-9573-1 ↗
41. Determining hydration mechanisms for initial fall and main hydration peak in tricalcium silicate hydration using a two-scale hydration simulation model10.1016/j.cemconres.2022.106763 ↗
42. Influence of Barchip fiber on early-age autogenous shrinkage of high strength concrete10.1016/j.conbuildmat.2020.119223 ↗
43. Simulations of diffusion-controlled and dissolution mechanisms with respect to the deceleration period of tricalcium silicate hydration10.1016/j.conbuildmat.2020.120458 ↗
44. Advances in understanding cement hydration mechanisms10.1016/j.cemconres.2019.105823 ↗
45. A review: self-healing in cementitious materials and engineered cementitious composite as a self-healing material10.1016/j.conbuildmat.2011.08.086 ↗
46. De Rooij · 2013 · Vol. 11
47. Factors affecting the self-healing efficiency of cracked concrete structures10.11648/j.ajasr.20170306.12 ↗
48. Cyclic and monotonic behavior of strengthened and unstrengthened square reinforced concrete columns
49. Repeatability and pervasiveness of self-healing in engineered cementitious composites
50. Influence of transverse crack width on reinforcement corrosion initiation and propagation in mortar beams10.1139/L07-117 ↗
51. Self-healing capability of cementitious composites incorporating different supplementary cementitious materials10.1016/j.cemconcomp.2012.08.013 ↗
52. Permeability and self-healing of cracked concrete as a function of temperature and crack width10.1016/S0008-8846(02)01099-2 ↗
53. Clear · 1985
54. Effect of internal curing with super absorbent polymers on residual stress development and stress relaxation in restrained concrete ring specimens10.1016/j.conbuildmat.2016.05.048 ↗
55. Characterization and quantification of self-healing behaviors of microcracks due to further hydration in cement paste10.1016/j.cemconres.2013.05.003 ↗
56. Estimating stress relaxation and cracking potential of high-strength concrete reinforced with polyvinyl alcohol fiber at early age10.1061/(ASCE)MT.1943-5533.0004374 ↗
57. Early-age cracking resistance of ground granulated blast furnace slag concrete10.1016/j.conbuildmat.2019.06.028 ↗
58. Modeling of self-healing concrete: a review
59. Continuum damage-healing and super healing mechanics in brittle materials: a state-of-the-art review10.3390/app8122350 ↗
60. Development of a bacteria-based self healing concrete
61. Quantification of crack-healing in novel bacteria-based self-healing concrete10.1016/j.cemconcomp.2011.03.012 ↗
62. Self-healing concrete by use of microencapsulated bacterial spores10.1016/j.cemconres.2013.11.009 ↗
63. Computational modeling of fracture in concrete: a review10.1007/s11709-020-0573-z ↗
64. Numerical modeling of high velocity impact applied to reinforced concrete panel10.1016/j.undsp.2018.04.007 ↗
65. Assessment of artificial intelligence strategies to estimate the strength of geopolymer composites and influence of input parameters10.3390/polym14122509 ↗
66. Split tensile strength prediction of recycled aggregate-based sustainable concrete using artificial intelligence methods10.3390/ma15124296 ↗
67. Compressive strength estimation of steel-fiber-reinforced concrete and raw material interactions using advanced algorithms10.3390/polym14153065 ↗
68. An energy approach to the solution of partial differential equations in computational mechanics via machine learning: concepts, implementation and applications10.1016/j.cma.2019.112790 ↗
69. Ahmad · 2021
70. A physics-based crystal plasticity model for the prediction of the dislocation densities in micropillar compression10.1016/j.jmps.2022.105006 ↗
71. Numerical modeling of microcrack behavior in encapsulation-based self-healing concrete under uniaxial tension10.1007/s12206-020-0405-z ↗
72. Optimizing the neural network hyperparameters utilizing genetic algorithm10.1631/jzus.A2000384 ↗
73. Transfer learning enhanced physics informed neural network for phase-field modeling of fracture10.1016/j.tafmec.2019.102447 ↗
74. Parametric deep energy approach for elasticity accounting for strain gradient effects10.1016/j.cma.2021.114096 ↗
75. Predicting the compressive strength of concrete with fly ash admixture using machine learning algorithms10.1016/j.conbuildmat.2021.125021 ↗
76. Self-healing performance assessment of bacterial-based concrete using machine learning approaches10.3390/ma15134436 ↗
77. Machine learning based computational approach for crack width detection of self-healing concrete
78. Artificial neural network methods for the solution of second order boundary value problems10.32604/cmc.2019.06641 ↗
79. Chen · 2022
80. Sufian · An Experimental and Empirical Study on the Use of Waste Marble Powder in Construction Material, Materials · 2021 · 14 · 3829
81. Prediction of self-healing of engineered cementitious composite using machine learning approaches10.3390/app12073605 ↗
82. Effective use of Pearson's product–moment correlation coefficient10.1016/j.anbehav.2014.05.003 ↗
83. New design equations for elastic modulus of concrete using multi expression programming10.3846/13923730.2014.893910 ↗
84. Smith · 1986 · 244
85. An overview of statistical learning theory10.1109/72.788640 ↗
86. Vapnik · 1999
87. T. Chen, C. Guestrin, Xgboost: a scalable tree boosting system, pp. 785-794.10.1145/2939672.2939785 ↗
88. Classification and regression by randomForest
89. Random forest for ordinal responses: prediction and variable selection10.1016/j.csda.2015.10.005 ↗
90. Compressive strength prediction via gene expression programming (GEP) and artificial neural network (ANN) for concrete containing RCA10.3390/buildings11080324 ↗
91. Application of soft computing techniques to predict the strength of geopolymer composites10.3390/polym14061074 ↗
92. Predictive modeling for sustainable high-performance concrete from industrial wastes: a comparison and optimization of models using ensemble learners10.1016/j.jclepro.2021.126032 ↗