Modeling viscosity of CO2 at high temperature and pressure conditions

• Published in: Journal of natural gas science and engineering Vol. 77; p. 103271
• Main Authors: Amar, Menad Nait, Ghriga, Mohammed Abdelfetah, Ouaer, Hocine, El Amine Ben Seghier, Mohamed, Pham, Binh Thai, Andersen, Pål Østebø
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01-05-2020; Elsevier
• Subjects: Analytical chemistry; Chemical Sciences; CO2; Correlations; Data-driven; GEP; Material chemistry; MLP; or physical chemistry; Polymers; Theoretical and; Viscosity; Viscosity; MLP; GEP; Data-driven; Correlations; CO2
• ISSN: 1875-5100; 2212-3865
• DOI: 10.1016/j.jngse.2020.103271

The present work aims at applying Machine Learning approaches to predict CO2 viscosity at different thermodynamical conditions. Various data-driven techniques including multilayer perceptron (MLP), gene expression programming (GEP) and group method of data handling (GMDH) were implemented using 1124 experimental points covering temperature from 220 to 673 K and pressure from 0.1 to 7960 MPa. Viscosity was modelled as function of temperature and density measured at the stated conditions. Four backpropagation-based techniques were considered in the MLP training phase; Levenberg-Marquardt (LM), bayesian regularization (BR), scaled conjugate gradient (SCG) and resilient backpropagation (RB). MLP-LM was the most fit of the proposed models with an overall root mean square error (RMSE) of 0.0012 mPa s and coefficient of determination (R2) of 0.9999. A comparison showed that our MLP-LM model outperformed the best preexisting Machine Learning CO2 viscosity models, and that our GEP correlation was superior to preexisting explicit correlations.
•Machine learning was applied to model CO2 viscosity with temperature and density.•A large database with 1124 experimental points from the literature was employed.•Explicit functions by Group Method Data Handling and Gene Expression Programming.•Better performance observed than existing machine learning models and correlations.