Modeling the compressive strength of green mortar modified with waste glass granules and fly ash using soft computing techniques

Waste materials of all kinds are among the problems facing third world countries in protecting the environment. One of the major parts of waste materials is waste glass. With the development, of any civilization, concrete and mortar are the most used materials in the construction process, which make their compositions, reduce in the environment day after day. One of the interesting ways of using waste material is to be added to concrete and mortar instead as a partial replacement of one of the concrete or mortar compositions. In this paper, 123 data are collected from previous papers with different parameters and statically analyzed and represented in four models (Linear regression model (LRM) and nonlinear regression model (NLR), multi-linear regression model (MLR) and ANN model) to predict compressive strength. In the process of modeling, these variables are important and affect the value of compressive strength, such as curing time, w/c, cement content, fly ash, sand content, waste glass content and curing time. Various statistical assessments such as Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Scatter Index (SI), Objective (OBJ) value, and the coefficient of determination (R-2) were used to evaluate the efficiency and performance of the proposed models. The obtained results showed that the ANN model showed better efficiency for predicting the compressive strength of mortar mixtures containing fine glass and fly ash compared to other models. The R-2, MAE, and RMSE for this model were 0.97, 1.57, and 2.08, respectively.