Evaluation and Prediction of Compressive Strength of Self-compacting Concrete Containing Ultrafine Ground Granulated Blast Furnace Slag Using Random Forest Algorithm

In this work, Self-compacting concrete (SCC) made with mixtures of blended Ultrafine Ground Granulated Blast Furnace Slag (UFGGBS) was examined, and to predict the strength performance, Random Forest Algorithm (RFA) was employed. Eleven SCC mixes (450/0 to 350/100) were formulated by varying the cement and UFGGBS content to examine their compressive strength properties and fresh properties. The total binder content was kept as 450 kg/m³, and it is varied for different series of proportions. It was inferred that all eleven mixes showed better fresh and hardened properties. The SCC (390/60) mix with 60 kg/m³ of UFGGBS achieved a maximal strength. This result shows that the RFA model is an efficient tool for predicting Compressive strength.