Machine learning application to predict the Mechanical properties of Glass Fiber mortar

In this study, the mechanical properties of concrete mortars have been predicted using machine learning tools, Response Surface Methodology (RSM), and Artificial Neural Network (ANN) approach. This study focused on mortar, in which cement has been partially replaced by 20% fly ash (FA) and 20% hydrated lime. In the experiment, the compressive strength (CS) of mortar has determined after curing the mix for 7 and 28 days, respectively. Glass fiber was added in the proportions of 0%, 0.2%, 0.4%, 0.6%, 0.8%, and 1% by weight of concrete to the mortar accordingly. The compressive strength of mortar incorporated with glassfiber increases according to an increase in the proportion of the glass fiber. Results indicates that the optimal fiber proportion of the glass fiber in the mortar had been observed to be 0.6%. The predicted compressive strength at day 28 has been modeled using RSM and ANN. The RSM model has been used to predict mechanical properties (R2 >= 0.7534) accurately. Furthermore, the appropriate R threshold (R > 0.999) for training, testing, and validation demonstrates that the ANN model has successfully captured the variability in the data. The results show that with the high correlation between the experimental and prediction results in data, more accuracy has been observed in the ANN model than in the RSM model.