Thermodynamics and Machine Learning Based Approaches for Vapor–Liquid–Liquid Phase Equilibria in n-Octane/Water, as a Naphtha–Water Surrogate in Water Blends

摘要: The prediction of phase equilibria for hydrocarbon/water blends in separators, is a subject considerable importance chemical processes. Despite its relevance, there are still pending questions. Among them, the correct number phases. While stability analysis using Gibbs Free Energy mixing and NRTL model, provide good understanding with calculation issues, when HYSYS V9 Aspen Plus software, this shows that significant equilibrium uncertainties exist. To clarify these matters, n-octane water blends, surrogates naphtha/water mixtures. Runs were developed CREC vapor–liquid (VL_Cell operated octane–water mixtures under dynamic conditions used to establish two-phase (liquid–vapor) three (liquid–liquid–vapor) domains. Results obtained demonstrate two region (full solubility liquid phase) at 100 °C 10−4 mol fraction range, it larger than 10−5 predicted by 10−7 reported technical literature. Furthermore, an effective accurate method predicting phases, machine learning (ML) technique was implemented successfully demonstrated, present study.