Assessment of Cubic Equations of State: Machine Learning for Rich Carbon-Dioxide Systems

Carbon capture and storage (CCS) has attracted renewed interest in the re-evaluation of equations state (EoS) for prediction thermodynamic properties. This study also evaluates EoS Peng–Robinson (PR) Soave–Redlich–Kwong (SRK) their capability to predict properties CO2-rich mixtures. The investigation was carried out using machine learning such as an artificial neural network (ANN) a classified learner. A lower average absolute relative deviation (AARD) 7.46% obtained PR comparison with SRK (AARD = 15.0%) three components system CO2 N2 CH4. Moreover, it found be 13.5% 19.50% five components’ (CO2 N2, CH4, Ar, O2) case. In addition, applying provided promise valuable insight deal engineering problems. implementation conjunction led getting predictive AARD contrast EoS. An 2.81% achieved 12.2% respective mixture.