Predicting Concrete Compressive Strength Using Aggregate Properties and Concrete Equivalent Mortar Tool Data A Machine Learning Approach
Loading...
Date
Journal Title
Journal ISSN
Volume Title
Publisher
Department of Civil and Environmental Engineering(MPE), Islamic University of Technology(IUT), Board Bazar, Gazipur-1704, Bangladesh
Abstract
With the goal to offer a productive, non-destructive alternative for typical, resource- intensive
compressive strength (CS) tests, this thesis examines the potential uses of ma- chine learning
(ML) techniques. This study aims to establish accurate predictive models for concrete
quality assessment by incorporating sustainable materials, particularly used concrete
aggregate, black stone, and brick chips. A dataset of 180 samples, divided us- ing an
80/20 ratio, was used to train and test several machine learning algorithms, such as Linear,
KNN, and XGBoost.Two distinct approaches of prediction were developed. The first
method used six features based on coarse aggregate physical properties (like absorption and
angularity number) and the Concrete Equivalent Mortar (CEM) tool.
With a R2 score of 0.6867 and an RMSE of 3.7280 MPa, the KNN Regression model proved
to be the most reliable predictor on the test set in the present scenario. The second approach
used 15 features, including component contents and engineered features ( such as load, age,
and water-to-cement ratio), to predict CS directly from the full mix design parameters. With
the Linear Regression model obtaining a superior R2 score of 0.9500 and an RMSE of
1.500 MPa, this method achieved significantly greater accuracy. The main reason for the
substantial disparity in model performance—between the R2 values of 0.6867 and 0.9500—
is the variation in input complexity; Compared to the physical properties approach, which used
six features, the mix design approach had fifteen features, an increased number of influential
variables which more accurately captured the multitude of relationships governing concrete
strength. This study encourages the sustainable and cost-effective evaluation of concrete
performance by successfully confirming the use of feature engineering with machine learning
and detailed mix design parameters to achieve exceptional forecasting reliability.
Description
Supervised by
Mohammad Zunaied-Bin-Harun ,
Assistant Professor,
Department of Civil and Environmental Engineering (CEE)
Islamic University of Technology (IUT)
Board Bazar, Gazipur, Bangladesh
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Civil and Environmental Engineering, 2025
Citation
ACI Committee 318. (2019). Building Code Requirements for Structural Concrete. American Concrete Institute. Ahmed, S. et al. (2022). “Machine Learning Applications in Concrete Strength Pre- diction.” Construction Materials Journal, 15(3), 210–225. Abbas, A., Fathifazl, G., Isgor, O. B., Razaqpur, A. G., Fournier, B., & Foo, S. (2009). Durability of recycled aggregate concrete designed with equivalent mortar volume method. Cement and Concrete Composites, 31(8), 555–563. Ahmed, M. (2025). Understanding MSE, RMSE, MAE, and R² score in machine learning model evaluation. LinkedIn. https://www.linkedin.com/pulse/understanding-mse-rmse-mae r-score-machine-learning-model-ahmed-rwloe Ala'a, R., et al. (2025). Application of machine learning techniques to predict the strength of steel fiber reinforced concrete. Scientific Reports, 15, 1–21. Amara, H., Assaad, J. J., Moussa, G., & Harb, J. (2022). Unconventional tools for the study of the flow properties of concrete equivalent mortar based on recycled concrete aggregates. Materials and Structures, 55(4), 1–18. https://doi.org/10.1617/s11527-021-01862-9 Anike, E. E., Saidani, M., Ganjian, E., Tyrer, M., & Olubanwo, A. O. (2020). Evaluation of conventional and Equivalent Mortar Volume mix design methods for recycled aggregate concrete. Materials and Structures, 53(2), 22. Barrow Mix Concrete. (2024). What is the British Standard for concrete compressive strength? https://barrowmixconcrete.com/what-is-the-british-standard-for-concrete compressive-strength/ Chen, Q., Zhang, J., Wang, Z., Zhang, L., Wang, Z., Zhang, Y., & Zhao, T. (2024). Compressive strength prediction of high-performance concrete: Integrating multi-ingredient influences and mix proportion insights. Construction and Building Materials, 452, 138899. https://doi.org/10.1016/j.conbuildmat.2024.138899 Cihan, M. T. (2019). Prediction of concrete compressive strength and slump by machine learning methods. Advances in Civil Engineering, 2019, 3069046. DeRousseau, M. A., Kasprzyk, J. R., & Srubar III, W. V. (2024). Computational design optimization of concrete mixtures: A review. Cement and Concrete Research, 121, 106013. https://doi.org/10.1016/j.cemconres.2019.105998 Dong, Y., Tang, J., Xu, X., Li, W., Feng, X., Lu, C., Hu, Z., & Liu, J. (2025). A new method to evaluate features importance in machine-learning based prediction of concrete compressive strength. Journal of Building Engineering, 104, 110932. https://doi.org/10.1016/j.jobe.2025.110932 27 Esteghamati, M. Z., Lindt, J. W., & Kripka, M. (2025). Challenges in deploying machine learning models for structural engineering: Generalizability and explainability. Journal of Structural Engineering, 151(1), 04024192. https://doi.org/10.1061/JSENDH.STENG-13301 Ford, E., & DeRousseau, M. A. (2022). Transfer (machine) learning approaches coupled with data augmentation for predicting the mechanical properties of concrete. Advances in Civil Engineering Materials, 11(1), 20220066. https://doi.org/10.1016/j.sewm.2022.100066 Góra, J., Ting, W. H., & Ingham, J. M. (2020). Impact of mechanical resistance of aggregate on properties of ordinary and high-performance concretes. Construction and Building Materials, 261, 120–138. Heidary, K., Omidvar, R., & Woodard, D. (2024). Performance evaluation of machine learning algorithms in reduced dimensional spaces. Journal of Cyber Security, 6(1), 69–87. https://doi.org/10.32604/jcs.2024.051196 IRICEN. (n.d.). Compressive strength of concrete. Indian Railways Institute of Civil Engineering. JK Cement. (2025). What is cement hydration? Phases & its importance. https://www.jkcement.com/blog/basics-of-cement/what-is-cement-hydration/ Kalyanasundaram, P., & Kurien, V. J. (1975). Accelerated testing for prediction of 28-day strength of concrete. Transportation Research Record, 558, 77–83. Kępniak, M., & Woyciechowski, P. (2016). The statistical analysis of relation between compressive and tensile/flexural strength of high performance concrete. Archives of Civil Engineering, 62(4), 95–107. https://doi.org/10.1515/ace-2015-0110 Li, Z., Wang, X. F., Wang, H., & Ding, B. (2022). Machine learning in concrete science: Applications, challenges, and best practices. npj Computational Materials, 8(1), 127. https://doi.org/10.1038/s41524-022-00810-x Lyngdoh, G. A., Zaki, M., & Krishnan, N. M. A. (2022). Prediction of concrete strengths enabled by missing data imputation and interpretable machine learning. Cement and Concrete Composites, 128, 104414. https://doi.org/10.1016/j.cemconcomp.2022.104414 Maza, M., Tebbal, N., Rahmouni, Z. E. A., & Zitouni, S. (2023). Predicting mechanical properties of concrete using equivalent mortar: A comparative study. Annales de Chimie - Science des Matériaux, 47(5), 237–245. https://doi.org/10.18280/acsm.470501 Noroozi, Z., Orooji, A., & Erfannia, L. (2023). Analyzing the impact of feature selection methods on machine learning algorithms for heart disease prediction. Scientific Reports, 13, 22588. https://doi.org/10.1038/s41598-023-49962-w Pathan, M. S., Zantalis, F., Vougioukas, G., Malik, S. U., & Panaousis, E. (2022). Analyzing the impact of feature selection on the accuracy of heart disease prediction. Healthcare Analytics, 2, 100068. https://doi.org/10.1016/j.health.2022.100068 Penn State University. (n.d.). The effect of aggregate properties on concrete. https://www.engr.psu.edu/ce/courses/ce584/concrete/library/materials/aggregate/aggregates main.htm Peng, Y., Unluer, C., Doubrovski, E. L., & Soetanto, R. (2023). Modeling the mechanical 28 properties of recycled aggregate concrete using hybrid machine learning algorithms. Resources, Conservation and Recycling, 190, 106812. https://doi.org/10.1016/j.resconrec.2022.106812 Phoeuk, M., & Kwon, M. (2023). Accuracy prediction of compressive strength of concrete incorporating recycled aggregate using ensemble learning algorithms: Multinational dataset. Advances in Civil Engineering, 2023, 5076429. https://doi.org/10.1155/2023/5076429 QMira, etc. (2025). [Additional references from images uploaded are to be included as needed.] Ramu University. (n.d.). Compressive strength of concrete and factors affecting it. Department of Civil Engineering Lecture Notes. Sah, A. K., & Hong, Y. M. (2024). Performance comparison of machine learning models for concrete compressive strength prediction. Materials, 17(9), 2077. https://doi.org/10.3390/ma17092077 Santhosh, R., & Shivananda, P. (2025). Influence of aggregate properties on compressive strength of concrete: A statistical approach. SSRG International Journal of Civil Engineering, 12(6), 136–150. https://doi.org/10.14445/23488352/IJCE-V12I6P112 Schwartzentruber, A., & Catherine, C. (2000). Method of the concrete equivalent mortar (CEM): A new tool to design concrete containing admixture. Materials and Structures, 33(8), 475–482. Singh, D. (2024). Application of machine learning in civil engineering: Review. Advancements in Civil Engineering & Technology, 6(3), 1–4. https://doi.org/10.31031/ACET.2024.06.000639 Structure Magazine. (2025). Transforming structural engineering: Embracing the AI revolution. https://www.structuremag.org/article/transforming-structural-engineering embracing-the-ai-revolution/ Testbook. (2024). Compressive strength of concrete: Definition, formula, and test methods. https://testbook.com/civil-engineering/compressive-strength-of-concrete Talaat, A., et al. (2021). Factors affecting the results of concrete compression testing: A review. Ain Shams Engineering Journal, 12(1), 205–221. https://doi.org/10.1016/j.asej.2020.07.015 University of Mosul. (n.d.). Factors affecting strength of concrete. College of Engineering Lecture Notes. V Geotech Experts. (2023). Factors affecting the compressive strength of concrete. https://vgeotechexperts.com/factors-affecting-the-compressive-strength-of-concrete/ Wan, Z., Xu, Y., & Šavija, B. (2021). On the use of machine learning models for prediction of compressive strength of concrete: Influence of dimensionality reduction on the model performance. Materials, 14(4), 713. https://doi.org/10.3390/ma14040713 Wakjira, T. G., Xu, J. G., & Degtyarev, V. V. (Eds.). (2022). Machine learning applications in civil engineering. Frontiers in Built Environment. https://doi.org/10.3389/978-2-83251 637-4 29 Yang, S., et al. (2024). Prediction on compressive strength of recycled aggregate concrete. Construction and Building Materials. Zhang, W., Guo, J., & Ning, C. (2024). Prediction of concrete compressive strength using a Deepforest-based model. Scientific Reports, 14(18918). https://doi.org/10.1038/s41598-024 69616-9 Zhao, Z., Liu, Y., Lu, Y., Ji, C., Lin, C., Yao, L., Pu, Z., & de Brito, J. (2024). Prediction of properties of recycled aggregate concrete using machine learning models: A critical review. Journal of Building Engineering, 87, 108973. https://doi.org/10.1016/j.jobe.2024.10897