Al Tekreeti, Marwah, Bahadori-Jahromi, Ali ORCID: https://orcid.org/0000-0003-0405-7146, Room, Shah and Tariq, Zeeshan (2026) Optimized Machine Learning Models for Predicting Compressive, Tensile, and Flexural Strengths of Multi-Fiber Recycled Aggregate Concrete. Journal of Composites Science, 10 (3).

Preview

PDF Optimized Machine Learning Models for Predicting Compressive, Tensile and Flexural Strengths.pdf - Published Version Available under License Creative Commons Attribution. Download (4MB) | Preview

Abstract

The demand for concrete has led to increased use of raw materials and significant waste generation. Recycled aggregate concrete (RAC) offers a viable approach to sustainable concrete; however, the presence of weakly bonded mortar on recycled aggregates reduces strength and increases crack formation. Fiber reinforcement—particularly hybrid systems combining steel, glass, basalt, and polypropylene fibers—can enhance tensile and flexural properties. This study developed machine-learning models to predict the compressive, splitting tensile, and flexural strengths of hybrid fiber-reinforced RAC. Two models, deep neural networks (DNN) and XGBoost, were optimized using bald eagle search (BES), particle swarm optimization (PSO), and Bayesian optimization (BO). Results showed that PSO-XGBoost achieved the highest accuracy for predicting compressive and splitting tensile strengths, while BES-XGBoost performed best for flexural strength. SHAP-based analysis identified curing age and silica fume as the most influential parameters for compressive strength, whereas fiber volume and fiber characteristics strongly influenced tensile and flexural strengths. The developed models and a user-friendly interface provide a data-driven approach for optimizing RAC mix design and supporting sustainable concrete production.

Item Type:	Article
Identifier:	10.3390/jcs10030144
Keywords:	recycled aggregate concrete; fiber; machine learning; mechanical properties; hybrid fiber
Subjects:	Construction and engineering > Civil and structural engineering
Date Deposited:	10 Mar 2026
URI:	https://repository.uwl.ac.uk/id/eprint/14716
Sustainable Development Goals:	Goal 9: Industry, Innovation, and Infrastructure	Sustainable Development Goals:	Goal 11: Sustainable Cities and Communities	Sustainable Development Goals:	Goal 12: Responsible Consumption and Production

Downloads

Actions (admin access)