Surrogate modelling of VLE: Integrating machine learning with thermodynamic constraints

Andres Carranza-Abaid,Hallvard F Svendsen,Jana P Jakobsen

doi:10.1016/j.cesx.2020.100080

Andres Carranza-Abaid, Hallvard F Svendsen + Show 1 more

Open Access

https://doi.org/10.1016/j.cesx.2020.100080

Copy DOI

Abstract

An easy-to-implement methodology to develop accurate, fast and thermodynamically consistent surrogate machine learning (ML) models for multicomponent phase equilibria is proposed. The methodology is successfully applied to predict the vapour-liquid equilibrium (VLE) behavior of a mixture containing CO2, monoethanolamine (MEA), and water (H2O). The accuracy of the surrogate model predictions of VLE for this system is found to be satisfactory as the results provide an average absolute relative difference of 0.50% compared to the estimates obtained with a rigorous thermodynamic model (eNRTL + Peng-Robinson).It is further demonstrated that the integration of Gibbs phase rule and physical constraints into the development of the ML models is necessary, as it ensures that the models comply with fundamental thermodynamic relationships.Finally, it is shown that the speed of ML based surrogate models can be ~10 times faster than interpolation methods and ~1000 times faster than rigorous VLE calculations.

Highlights

One of the most promising approaches to operate cleaner industrial processes is the implementation of CO2 capture and storage
The high energy demand associated with the CO2 capture process is its main challenge (Svendsen et al, 2011)
The electro-neutrality constraint is a restriction that only exists in electrolytic systems. This equation arises from the principle that the overall sum of local charges must be 0 in a system at thermodynamic equilibrium (Prausnitz et al, 1999)

Summary

Introduction

The emission of anthropogenic greenhouse gases has been one of the main subjects of environmental concerns over the past decades. Development of new, clean and enhanced industrial processes has become a must in order to reach international and national sustainability goals. One of the most promising approaches to operate cleaner industrial processes is the implementation of CO2 capture and storage. It has been labeled as one of the key technologies that will assist in achieving a global temperature increment of no more than 1.5 °C by the end of 2030 (IPCC, 2018). The high energy demand associated with the CO2 capture process is its main challenge (Svendsen et al, 2011)

Objectives

Methods

Results

Conclusion