Classifier surrogates to ensure phase stability in optimisation-based design of solvent mixtures

The ability to guarantee a single homogeneous liquid phase is a key consideration in computer-aided mixture/blend design (CAM b D). In this article, we investigate the use of a classifier surrogate of the phase stability condition within a CAM b D optimisation model for designing solvent mixtures with guaranteed phase stability properties. We show how to develop such classifiers for describing multiple candidate mixtures over a range of compositions and temperatures based on the generation of phase stability data using thermodynamic models such as UNIFAC. We test the approach on two solvent design case studies and illustrate its effectiveness in enabling the in silico design of stable mixtures, simultaneously providing a probability of phase stability as an interpretable metric. • A surrogate phase stability model is developed and embedded within solvent design. • The ANN-based classifier is trained on UNIFAC-generated phase stability data. • It achieves high reliability over many solvent mixtures and temperatures. • Improved solutions are found for molecular and process design problems.