Fuzzy Neural Network Utilization in Prediction of Compressive Strength of Slag-Cement Based Mortars

Compressive strength of mortars is the major property that defines its quality during manufacturing and it is the most common performance measurement used by engineers in designing buildings and other structures. In this study, we used hybrid intelligent system called Neuro-Fuzzy systems that is a combination of Neural Network and Fuzzy Logic to predict the compressive strength of mortars containing GGBFS at 28 days. 52 specimens of high workability and high performance slag-cement based mortars were utilized to train and evaluate this system. The model was constructed and implemented in MATLAB software. Consequently, to verify the usefulness of the model, the predicted outputs from Neuro-Fuzzy model were compared with laboratory results. The results showed that the trained system has strong potential capability to predict compressive strength of mortars containing GGBFS. It shows its potential among other methods used in prediction of Compressive strength of mortars.