Modeling early-age hydration kinetics of Portland cement using flexible neural tree

The early-age hydration of Portland cement paste has an important impact on the formation of microstructure and development of strength. However, manual derivation of analytic kinetic equation for hydration process is very difficult because there are multi-phased, multi-sized and interrelated complex chemical and physical reactions during cement hydration. In this paper, a flexible neural tree structure is built as the right-hand side of kinetics instead of traditional analytic expression. Two evolutionary algorithms gene expression programming and particle swarm optimization are used to evolve tree structure and rules' parameters, respectively. 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 early-age hydration is in good accordance with the observed experimental data. Furthermore, this model still has a good generalization ability even changing chemical composition, particle size and curing conditions.