Neural network modeling on evolution of hydration reaction for Portland cement

Abstract

The hydration reaction of Portland cement paste has an important impact on the formation of microstructure and development of strength. However, simulating the evolution of hydration reaction is very difficult because there are multi-phased, multi-sized and interrelated complex chemical and physical reactions during cement hydration. In this paper, a feedforward neural network model is built for predicting the evolution of degree of hydration. In order to reduce the computing time, GPUs are used for acceleration in parallel. Studies have shown that according to the established model, simulation curve of hydration is in good accordance with the observed experimental data.