GNNePCSAFT
Smart Thermodynamic Modeling with Graph Neural Networks
The project focuses on using Graph Neural Networks (GNN) to estimate the pure-component parameters of the Equation of State PC-SAFT.
Currently, the model takes into account the hard-chain, dispersive, and associative terms of PC-SAFT. Future work on polar and ionic terms is being studied.
FeOS is used for the PC-SAFT calculations. The estimated parameters can be used in DWSIM and Aspen HYSYS process simulators.