XGBoost and Artificial Neural Networks as Surrogate Models for Vapor–Liquid Equilibrium in PC-SAFT

Phase equilibrium calculations are crucial in chemical engineering design and optimization processes. The PC-SAFT equation of state (EoS) can precisely calculate phase equilibrium, but is relatively complex and computationally intensive. Surrogate models are mathematically simple models that map or regress the input–output relationships of more complex, computationally demanding models. This work employs XGBoost and a hybrid XGBoost-artificial neural networks (XGBoost-ANN) model as surrogate models to replace PC-SAFT EoS calculations for the vapor–liquid equilibrium (VLE) of binary associating systems. This work investigates the VLE of five binary associating systems using data generated by the PC-SAFT EoS. The surrogate models take temperature, pressure, liquid phase mole fractions, and the PC-SAFT parameters for binary associating systems as inputs, and predict the vapor phase mole fractions. Both surrogate models significantly reduce the computational time for calculating VLE data compared to the PC-SAFT EoS, while achieving good prediction results.