Abstract
We employed deep neural networks (NNs) as an efficient and intelligent surrogate of molecular simulations for complex sorption equilibria using probabilistic modeling. Canonical (N 1 N 2 VT) Gibbs ensemble Monte Carlo simulations were performed to model a single-stage equilibrium desorptive drying process for (1,4-butanediol or 1,5-pentanediol)/water and 1,5-pentanediol/ethanol from all-silica MFI zeolite and 1,5-pentanediol/water from all-silica LTA zeolite. A multi-task deep NN was trained on the simulation data to predict equilibrium loadings as a function of thermodynamic state variables. The NN accurately reproduces simulation results and is able to obtain a continuous isotherm function. Its predictions can be therefore utilized to facilitate optimization of desorption conditions, which requires a laborious iterative search if undertaken by simulation alone. Furthermore, it learns information about the binary sorption equilibria as hidden layer representations. This allows for application of transfer learning with limited data by fine-tuning a pretrained NN for a different alkanediol/solvent/zeolite system.
Highlights
Phase and sorption equilibria are ubiquitous, and are necessary for the design of various engineering and industrial operations.[1,2,3,4] the dimensionality of the xi,P,T-hypersurface of a mixture of interest increases with each additional component
A multi-task deep neural networks (NNs) was trained on the simulation data to predict equilibrium loadings as a function of thermodynamic state variables
A desired thermodynamic property is measured as the expectation value of its corresponding thermodynamic variable in a statistical ensemble obeying a set of thermodynamic constraints
Summary
Phase and sorption equilibria are ubiquitous, and are necessary for the design of various engineering and industrial operations.[1,2,3,4] the dimensionality of the xi,P,T-hypersurface of a mixture of interest increases with each additional component. Binary equilibria are more difficult to measure experimentally than single-component equilibria.[5] Gmehling et al estimated that less than 2% of the binary mixtures of technical interest have data available for equation of state and excess Gibbs energy models.[6] To address the lack of experimental data available, molecular simulation has been an effective tool for predicting phase and sorption equilibrium properties in complex thermodynamic systems.[7,8,9] to implement these simulation-based equilibria in modeling of an industrial process, a continuous function is necessary to describe the xi,P,T-hypersurface
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
