Enhancing Sustainable Concrete Production by Utilizing Fly Ash and Recycled Concrete Aggregate with Experimental Investigation and Machine Learning Modeling

Over the last decade, there has been a substantial increase in the amount of construction waste, leading to growing societal and environmental concerns around the recycling of this refuse. Concrete waste is one of the most significant forms of construction waste. As a result, in order to examine the influence of recycled coarse aggregate (RCA) on concrete, this study substitutes natural coarse aggregate (NCA) with RCA at varying replacement percentages: 0%, 10%, 20%, and 30%. Additionally, fly ash is used to replace cement at a consistent replacement rate of 36% in all combinations. The controlled concrete was evaluated, and its fresh and hardened characteristics were compared using various mixed amounts. Subsequently, two machine learning (ML) techniques, Linear Regression (LR) and Random Forest (RF) were used to forecast and examine the fresh and hardened characteristics. In this experiment, the results showed that when RCA increased, the concrete's performance dropped. The addition of 10% to 30% RCA content was shown to almost decrease the workability value of new concrete from 11.45% to 34.14%. Recycled aggregate (RCA) with a replacement rate of 20% produced the best compressive strength values for lightweight concrete, and it has been shown that up to 30% RCA replacement may offer optimal tensile strength. The RF model showed superior forecasting performance than the RF model, with a high correlation coefficient (R2) value of 0.98. Both ML models prove feasible for accurately predicting the fresh characteristics of RCA concrete, demonstrating strong correlation values. However, the RF model provides more satisfactory results for predicting mechanical properties compared to the LR model. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.