Supplementary cementitious materials in blended cement concrete: Advancements in predicting compressive strength through machine learning

Abstract

The increasing utilization of Portland cement raises environmental concerns. Thus, leading to the exploration of supplementary cementitious materials (SCMs) as alternatives to use in the construction industry. Incorporating SCMs into blended cement concrete (BCC) has shown improved mechanical and durability properties. However, predicting the compressive strength (CS) of BCC is challenging due to its complex composite nature and nonlinear behavior. This study comprehensively evaluated eleven commonly used machine-learning techniques (MLTs) for compressive strength prediction of BCC. Gene expression programming (GEP), artificial neural network (ANN), random forest (RF), support vector (SV), adaptive neuro-fuzzy inference system (ANFIS), optimized gaussian process regression (OGPR), gradient boost (GB), extreme gradient boost (XGB), ada boost (AB), k-nearest neighbor (KNN), and bagging regressor (BR) are used for prediction of compressive strength. The performance of ML models is assessed based on regression analysis and statistical metrics. The XGB model achieved the highest accuracy with an R2 value of 0.89. The R2 values of GB, SV, and OGPR models are 0.89, 0.83, and 0.8 respectively. Moreover, all ML models achieve MAE and RMSE error values below 10 MPa, except for the random forest model. In addition, this study also employs relative importance and Shapley analysis for model explainability. Thus, providing insights into the impact of SCMs on compressive strength of BCC. Overall, this research offers an improved approach to predicting the compressive strength of blended cement concrete.