Simulation of concrete slump using neural networks

In this study, an artificial neural network-based modelling system was established to explore the feasibility of predicting the slump of concrete. Computational simulation of concrete slump was performed using the trained neural network. The variation in concrete slump was achieved by varying combinations of factors like the water-to-binder ratio (w/b), superplasticiser-to-binder ratio (SP/B), and water content. From the graphs of water content plotted against the slump generated using the trained neural networks developed in this study, two sets of graphs were produced to explore the effects of w/b and SP/B. It was found that: (a) the use of neural networks for the modelling of concrete slump appeared very promising; (b) although the water content and SP/B ratio were kept constant, a change in w/b ratio had a distinct effect on the consistency properties; (c) a certain saturation level for the SP existed, above which only a small effect of further dispersion was obtained; and (d) a certain saturation level for the water content existed, above which only a small effect, even a negative effect, on slump was obtained.