Machine learning prediction of recycled concrete powder with experimental validation and life cycle assessment study

The environmental effect of the construction sector has recently drawn attention, leading to research which promotes sustainability. Therefore, different researcher recommends different alternative materials such as fly ash, waste glass red mud and solid waste. Environmental sustainability and mechanical performance are two major concerns in the construction industry. Furthermore, the complex internal relationships between the components of such concrete determine the mix design, which is crucial for attaining the required compressive strength. This study addresses two key issues associated with the current concrete production. First, it uses recycled concrete powder (RCP) as a cement replacement (0 %, 5 %, 10 %, and 15 %) to promote sustainability and the undesirable impact of cement on the environment. Secondly, it proposes a predictive model based on machine learning for the compressive strength of RCP based concrete. A comprehensive dataset containing 270 experimental data points was compiled to train and test various machine learning (ML) models. The experimental results indicated that the optimum RCP mix with 10 % replacement, achieved a compressive strength that was 15.8 % higher than that of the reference concrete without RCP. Furthermore, scanning electronic microscopy indicates that internal structure improved with RCP due to filling and pozzolanic reaction. ML models indicate that Gradient Boosting was found to be the most precise, exhibiting the highest coefficient of determination with the lowest values for root mean squared error and mean absolute error. These findings provide valuable insights for engineers, contractors, and stakeholders, facilitating enhanced design optimization and promoting the efficient use of resources in concrete construction projects.