Searching for Sustainable Refrigerants by Bridging Molecular Modeling with Machine Learning

Abstract

We present here a novel integrated approach employing machine learning algorithms for predicting thermophysical properties of fluids. The approach allows obtaining molecular parameters to be used in the polar soft-statistical associating fluid theory (SAFT) equation of state using molecular descriptors obtained from the conductor-like screening model for real solvents (COSMO-RS). The procedure is used for modeling 18 refrigerants including hydrofluorocarbons, hydrofluoroolefins, and hydrochlorofluoroolefins. The training dataset included six inputs obtained from COSMO-RS and five outputs from polar soft-SAFT parameters, with the accurate algorithm training ensured by its high statistical accuracy. The predicted molecular parameters were used in polar soft-SAFT for evaluating the thermophysical properties of the refrigerants such as density, vapor pressure, heat capacity, enthalpy of vaporization, and speed of sound. Predictions provided a good level of accuracy (AADs = 1.3–10.5%) compared to experimental data, and within a similar level of accuracy using parameters obtained from standard fitting procedures. Moreover, the predicted parameters provided a comparable level of predictive accuracy to parameters obtained from standard procedure when extended to modeling selected binary mixtures. The proposed approach enables bridging the gap in the data of thermodynamic properties of low global warming potential refrigerants, which hinders their technical evaluation and hence their final application.

What Data Are Most Valuable to Screen Ionic Liquid Entrainers for Hydrofluorocarbon Refrigerant Reuse and Recycling?

“…Furthermore, we found several opportunities for utilizing model-based design of experiments (MBDoE) to inform the minimum required data set for screening at each step of the framework. Finally, a SAFT-based , or machine learning method may be implemented to predict ILs for HFC separations.…”

Multitask Neural Network for Mapping the Glass Transition and Melting Temperature Space of Homo- and Co-Polyhydroxyalkanoates Using σProfiles Molecular Inputs

“…The 3D structures were then geometrically optimized at the density functional theory (DFT) level by combining def-TZVP ″triple-ζ valence polarized″ functions with the generalized BP86 ″Becke-Perdew 86″ gradient approximation and after that exported as COSMO files. 81 The generated files were then imported into the COSMO-ThermX software (2022 version) to calculate the σ Profiles of all 24 monomers. The resulting σ Profiles contained 51 points in the range of ±25 [e/Å 2 × 10 3 ].…”

“…This methodology was developed based on our previous works. − For each monomer, the SMILES ″Simplified Molecular Input Line Entry Specification″ was initially uploaded to Turbomole software (TmoleX version 4.5.1) to form the 3D molecular structures. The 3D structures were then geometrically optimized at the density functional theory (DFT) level by combining def-TZVP ″triple-ζ valence polarized″ functions with the generalized BP86 ″Becke-Perdew 86″ gradient approximation and after that exported as COSMO files . The generated files were then imported into the COSMOThermX software (2022 version) to calculate the σ Profiles of all 24 monomers.…”

Machine Learning-Enabled Development of Accurate Force Fields for Refrigerants

“…As such, technologies to recycle these HFCs are developing quickly. For example, recent work demonstrates how ionic liquids (ILs) can facilitate HFC separation. − Other works have used machine learning to search for new refrigerants and estimate HFC solubility in ILs. , However, all HFC separation endeavors require the often limited knowledge of the thermophysical properties of these HFC mixtures. , Computer-aided molecular design of HFC separations ,, has shown promise to accelerate the development of novel processes to meet the required goals. Accurate vapor–liquid equilibrium (VLE) data of HFC mixtures are desired, as is a microscopic understanding of the underlying physics that governs their physical properties.…”