Optimal Aqueous Biphasic Systems Design for the Recovery of Ionic Liquids

Ionic liquid-based aqueous biphasic systems (IL-ABS) have attracted much attention in both academia and industries due to their superior performance many applications. In order better utilize these novel liquid–liquid for recovering hydrophilic ILs from dilute solutions, a machine learning (ML)-based ABS design method is proposed such purpose this work. method, an ML-based model, i.e., artificial neural network (ANN)-group contribution (GC) employed predict the phase equilibrium behaviors of IL-ABS. Based on integration with computer-aided technique, optimal IL-ABS determined by formulating solving optimization-based mixed-integer non-linear programming problem, where structure denoted as input vector ANN-GC model. As proof concept, results recovery 1-butyl-3-methylimidazolium chloride ([C4mIm][Cl]) n-butylpyridinium trifluoromethanesulfonate ([C4Py][TfO]) solutions are presented. The [C4mIm][Cl]-H2O-(NH4)2SO3 (identified work) gives IL efficiency 95.0 wt % salting-out agent 2.36 kg/kg recovery, [C4mIm][Cl]-H2O-K2CO3 (reported literature), they 81.7 5.25, respectively. For second case, our [C4Py][TfO]-H2O-KH2PO4 95.6 1.81 reported [C4Py][TfO]-H2O-(NH4)2SO4, 80.6 3.16,