期刊
JOURNAL OF NATURAL GAS SCIENCE AND ENGINEERING
卷 77, 期 -, 页码 -出版社
ELSEVIER SCI LTD
DOI: 10.1016/j.jngse.2020.103271
关键词
CO2; Viscosity; Data-driven; Correlations; MLP; GEP
资金
- Research Council of Norway
- ConocoPhillips Skandinavia AS
- Aker BP ASA
- Var Energi AS
- Equinor ASA
- Neptune Energy Norge AS
- Lundin Norway AS
- Halliburton AS
- Schlumberger Norge AS
- Wintershall DEA
- National IOR Centre of Norway
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 (R-2) 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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据