Prediction of the compressive strength of concrete made with soap factory wastewater using machine learning

In recent years, the reuse of wastewater for making concrete has become a major issue for actors in the field of civil engineering. This paper used artificial neural networks (ANN) to estimate the compressive strength of concrete made with soap factory effluent water. Input parameters included amount of water, amount of cement, water/cement ratio, superplasticizers, fine aggregate, coarse aggregate, and age of maturation. A prediction equation for the compressive strength of concrete has been proposed. Mean squared error (MSE), coefficient of determination (R-2), and mean absolute error (MAE) were used to assess model performance. The performance of the model was then compared with that of other studies. A parametric study was carried out to evaluate the influence of the variation of the input parameters on the strength of the concrete. The results we obtained showed that the use of the ANN technique has very good performance for predicting the compressive strength of concrete made with soap factory effluent water.