Modeling the mechanical properties of rubberized concrete using machine learning methods

The use of waste materials as a binder or aggregate in the concrete mixture is a great step towards sustainability in the construction industry. Waste rubber (WR) can be used as coarse and fine aggregates in concrete and improves the crack resistance, impact resistance, and fatigue life of the produced concrete. However, the mechanical properties of rubberized concrete degrade significantly by replacing the natural aggregate with WR. To have accurate estimations of the mechanical properties of rubberized concrete, two machine learning methods consisting of artificial neural network (ANN) and neuro-fuzzy system (NFS) were served in this study. To do this, a comprehensive dataset was collected from reliable literature, and two scenarios were addressed for the selection of input variables. In the first scenario, the critical ratios of the rubberized concrete and the concrete age were considered as the input variables. In contrast, the mechanical properties of concrete without WR and the percentage of aggregate volume replaced by WR were assumed as the input variables in the second scenario. The results show that the first scenario models outperform the models proposed by the second scenario. Moreover, the developed ANN models are more reliable than the proposed NFS models in most cases.