Paper Titles
Influence of the Configuration of Polypropylene-Based Dust Filters on the Pressure Drop in Filter Respirators
p.27
The Optical and Radiation Shielding Characteristics of Lead-Free Glasses Activated with Barium Oxide
p.41
Innovative Approaches to Radiation Shielding in Healthcare: The Role of Bismuth Doped Phosphate Glass
p.47
Enhancing Transparent Resistive Switching Performance of MgO via Oxygen Flow Modulation
p.53
Production of Titanium-Hydroxyapatite Composite Particles by Mechanical Alloying
p.59
Optimizing Compressive Strength Prediction in Fly Ash-Slag Concrete Using SHAP Machine Learning Models
p.67
Geo-Polymerization as an Eco-Friendly Solution for Cleaner Environment - A Critical Review
p.75
Improving Concrete Durability Using Rice Husk Ash through Advanced Water-Binder Ratio Prediction with XAI-Enhanced Models
p.85
Assessment of Flexural Capacity Prediction Models for Glulam Beams of Nigerian Wood Species
p.95

Optimizing Compressive Strength Prediction in Fly Ash-Slag Concrete Using SHAP Machine Learning Models

Article Preview

Abstract:

The use of supplementary cementitious materials (SCMs) has revolutionized the construction industry by significantly reducing the carbon footprint, minimizing waste, lowering labor costs, and enhancing both durability and precision in concrete structures. Accurately predicting compressive strength (CS), a critical mechanical property, is crucial for ensuring these structures' optimal performance and reliability. Given the nonlinear behavior of concrete mixtures incorporating fly ash and slag, machine learning (ML) techniques have become increasingly valuable for predictive modeling. This study assesses the performance of four ML models: Multilinear Regression (MLR), K-Nearest Neighbors (KNN), Random Forest (RF), and Random Forest integrated with Particle Swarm Optimization (RF-PSO). By addressing gaps related to compressive strength variability and comparing model performance, the study found that all four models achieved high accuracy in CS prediction, with RF-PSO consistently outperforming others based on multiple evaluation metrics. Visual analysis corroborates the models' effectiveness, highlighting potential advantages such as improved quality control, cost efficiency, enhanced safety, and environmental sustainability. Furthermore, an analysis of the importance of features was conducted to evaluate the contribution of individual variables in developing the RF-PSO model.

You might also be interested in these eBooks
Polymers and Composites, Functional and Sustainable Materials View Preview

Info:

Periodical:

Materials Science Forum (Volume 1162)

Pages:

67-74

DOI:

https://doi.org/10.4028/p-CaN1cp

Citation:

Cite this paper

Online since:

October 2025

Authors:

Paul O. Awoyera*, Abba Bashir, Andi Asiz, Sani I. Abba, Krishna P. Arunachalam, Daha Shehu Aliyu

Keywords:

Fly Ash, Machine Learning Models, Optimization Algorithm, Slag, Supplementary Materials

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

© 2025 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

* - Corresponding Author

References

[1] M. Atiyeh and E. Aydin, "Carbon-Fiber Enriched Cement-Based Composites for Better Sustainability," Materials (Basel)., vol. 13, no. 8, p.1899, Apr. 2020, doi:10.3390/ ma13081899.

DOI: 10.3390/ma13081899

Google Scholar

[2] J. Thomas, N. N. Thaickavil, and T. N. Syamala, "Supplementary Cement Replacement Materials for Sustainable Concrete," 2019, p.387–403.

DOI: 10.1007/978-981-13-1202-1_33

Google Scholar

[3] R. K. Ibrahim, R. Hamid, and M. R. Taha, "Fire resistance of high-volume fly ash mortars with nanosilica addition," Constr. Build. Mater., vol. 36, p.779–786, Nov. 2012.

DOI: 10.1016/j.conbuildmat.2012.05.028

Google Scholar

[4] C. Meyer, "The greening of the concrete industry," Cem. Concr. Compos., vol. 31, no. 8, p.601–605, 2009.

DOI: 10.1016/j.cemconcomp.2008.12.010

Google Scholar

[5] M. Arezoumandi, J. S. Volz, C. A. Ortega, and J. J. Myers, "Shear Behavior of High-Volume Fly Ash Concrete versus Conventional Concrete: Experimental Study," J. Struct. Eng., vol. 141, no. 3, Mar. 2015.

DOI: 10.1061/(ASCE)ST.1943-541X.0001003

Google Scholar

[6] M. Reiner and K. Rens, "High-Volume Fly Ash Concrete: Analysis and Application," Pract. Period. Struct. Des. Constr., vol. 11, no. 1, p.58–64, Feb. 2006.

DOI: 10.1061/(asce)1084-0680(2006)11:1(58)

Google Scholar

[7] A. Kaur, S. Bishnoi, and B. Bhattacharjee, "Characteristics of fly ashes in India for use in cement and concrete," Adv. Cem. Res., vol. 29, no. 6, p.258–268, Jun. 2017.

DOI: 10.1680/jadcr.16.00126

Google Scholar

[8] B. A. Young, A. Hall, L. Pilon, P. Gupta, and G. Sant, "Can the compressive strength of concrete be estimated from knowledge of the mixture proportions?: New insights from statistical analysis and machine learning methods," Cem. Concr. Res., vol. 115, p.379–388, Jan. 2019.

DOI: 10.1016/j.cemconres.2018.09.006

Google Scholar

[9] R. Shahrin and C. P. Bobko, "Characterizing Strength and Failure of Calcium Silicate Hydrate Aggregates in Cement Paste under Micropillar Compression," J. Nanomechanics Micromechanics, vol. 7, no. 4, Dec. 2017.

DOI: 10.1061/(ASCE)NM.2153-5477.0000137

Google Scholar

[10] I. M. A. K. Salain, "Effect of Water/Cement and Aggregate/Cement Ratios on Consistency and Compressive Strength of Concrete Using Volcanic Stone Waste as Aggregates," Civ. Eng. Archit., vol. 9, no. 6, p.1900–1908, Oct. 2021.

DOI: 10.13189/cea.2021.090621

Google Scholar

[11] K. Senthil, Z. Kubba, R. Sharma, and A. Thakur, "Experimental and Numerical Investigation on Reinforced Concrete Slab under Low Velocity Impact Loading," IOP Conf. Ser. Mater. Sci. Eng., vol. 1090, no. 1, p.012090, Mar. 2021.

DOI: 10.1088/1757-899X/1090/1/012090

Google Scholar

[12] S. Das Adhikary, B. Li, and K. Fujikake, "State-of-the-art review on low-velocity impact response of reinforced concrete beams," Mag. Concr. Res., vol. 68, no. 14, p.701–723, Jul. 2016.

DOI: 10.1680/jmacr.15.00084

Google Scholar

[13] A. Patchen, S. Young, L. Goodbred, S. Puplampu, V. Chawla, and D. Penumadu, "Lower Carbon Footprint Concrete Using Recycled Carbon Fiber for Targeted Strength and Insulation," Materials (Basel)., vol. 16, no. 15, p.5451, Aug. 2023.

DOI: 10.3390/ma16155451

Google Scholar

[14] Z. Qin, D. Zheng, X. Li, and H. Wang, "Influence of Inertia on the Dynamic Compressive Strength of Concrete," Materials (Basel)., vol. 15, no. 20, p.7278, Oct. 2022.

DOI: 10.3390/ma15207278

Google Scholar

[15] M. S. Morsy, Y. A. Al-Salloum, H. Abbas, and S. H. Alsayed, "Behavior of blended cement mortars containing nano-metakaolin at elevated temperatures," Constr. Build. Mater., vol. 35, p.900–905, Oct. 2012.

DOI: 10.1016/j.conbuildmat.2012.04.099

Google Scholar

[16] S. Ghani, N. Kumar, M. Gupta, and S. Saharan, "Machine learning approaches for real-time prediction of compressive strength in self-compacting concrete," Asian J. Civ. Eng., vol. 25, no. 3, p.2743–2760, 2024.

DOI: 10.1007/s42107-023-00942-5

Google Scholar