Neural network predictions of the simulated rheological response of cement paste in the FlowCyl

For the past decades, computational fluid dynamics (CFD) simulations have been shown as a promising approach for understanding complex flow behavior of concrete. However, their application is often limited due to computationally heavy analysis. In this study, two artificial neural networks, multi-layer perceptron and radial basis function, are trained by results CFD model that simulates cement in FlowCyl equipment. Both models were investigated predicting single values volume loss over predetermined duration well full versus time curves. The show after training networks can accurately substitute predictions both perceptron, accurate predicts even obtained substantial reducing data, which illustrates coupling between network significantly decrease overall calculation time.