Prediction of Compressive Strength of Self-Compacting Concrete using Machine Learning Techniques

Abstract

The paper deals with the use of Deep Neural Networks (DNN), Artificial Neural Network (ANN), and Random Forest (RF) for estimating the 28- day compressive strength of self-compacting concrete (SCC) containing silica and filler (fly ash, marble powder, and lime powder) with a comparative performance analysis of all techniques. A total of 179 data were taken from literature already published with eight input variables for modelling. The evaluation and comparison of the performance of predicted models were made using the same datasets in training and testing based on correlation coefficient (CC), Coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MAE). The results showed that proposed model's performance could be improved when training takes place in a Deep Neural Network model with multiple hidden layers. Sensitivity analysis was used to quantify the effect of different variables on concrete strength with coarse aggregate greatly affecting the compressive strength of SCC, followed by fine aggregate content and quantity of silica. A dependable prediction tool is provided through this investigation which suggests that the present model can help scientists and engineers in the optimization of the mixture design of SCC.