Systematic Multiscale Models to Predict the Compressive Strength of Cement Paste as a Function of Microsilica and Nanosilica Contents, Water/Cement Ratio, and Curing Ages

Sustainable construction requires high-strength cement materials that additives with silica content could provide the requirements as well. In this study, effect of micro and nano-size on compressive strength paste using different mathematical approaches is investigated. This study compares preferentially replaced pastes microsilica (MS) nanosilica (NS) incorporation by proposing several models. 205 data were extracted from literature analyzed. The modeling processes considered most significant variables input influence compression strength, such curing time, which ranged between 3 90 days, water-cement ratio, varied 0.4 0.85, NS 0 15%. MS 40% based weight cement. process, modified was modeled four models, including Linear Regression Model (LR), Nonlinear (NLR), Multi-Logistic (MLR), artificial neural network (ANN). efficiency suggested models evaluated statistical assessments, Root Mean Squared Error (RMES), Absolute (MAE), Scatter Index (SI), Objective value (OBJ), coefficient determination (R2). findings revealed ANN model conducted better performance for predicting than other assessment. addition, assessment sensitivity parameters, had more an paste, 6.3% MS.