Exploring economic and environmental impacts of recycled aggregate concrete using particle swarm optimization algorithm

Recycled aggregate concrete (RAC) is a sustainable alternative that encounters challenges due to varying sources and processing methods. This study introduces a novel approach to optimize the mix proportions of RAC through machine learning and multi-objective optimization techniques. It identifies the key factors influencing the compressive strength of concrete, aiming to minimize costs and environmental impacts while meeting compressive strength requirements. Six machine learning models were developed based on a database of 522 samples to predict the cubic compressive strength of RAC. Among these, the XGBoost model demonstrated the highest accuracy, establishing a functional relationship between cubic compressive strength and mix proportions, achieving an R 2 of 0.965 and a composite performance index of 0.081. Additionally, life cycle cost analysis and life cycle assessment were employed to evaluate both cost and environmental impacts. Using the particle swarm optimization algorithm, the optimization of strength, cost, and environmental impact was conducted, comparing RAC with conventional concrete. The significant factors affecting cubic compressive strength were identified as curing age, water-to-cement ratio, and sand content, contributing 28.6%, 20.6%, and 15.8% to the variation in strength, respectively. Cement content and the fly ash-to-cement ratio were found to significantly influence cost and environmental factors, respectively. Optimal reductions in cost and environmental impact were achieved with a recycled aggregate replacement ratio of 45%-60%, resulting in decreases of up to 18.94% and 41.72%, respectively.