A new prediction model of CO2 diffusion coefficient in crude oil under reservoir conditions based on BP neural network

Hao Chen, Yu Wang, Mingsheng Zuo, Chao Zhang, Ninghong Jia, Xiliang Liu and Shenglai Yang

Energy, 2022, vol. 239, issue PC

Abstract: Diffusion is the key mechanism of enhanced oil recovery (EOR) by CO2 injection in unconventional oil reservoirs. The accurate measurement of the diffusion coefficient in porous media is essential for forecasting and optimizing CO2 injection. The pressure decay technique is the most commonly used method for measuring the diffusion coefficient, which is well acknowledged. However, it has a long experimental period with higher requirements on the equipment and operation. This paper firstly proposed a quick and simple prediction methods of diffusion coefficient for both CO2-oil systems within/without porous media based on back propagation (BP) neural network. The average errors are 18.73% and 18.80%, respectively. With the continuous supplement of the data, models can be continuously updated to provide more accurate estimates of the supercritical CO2-oil system without/with porous media conditions. Temperature, pressure, permeability, porosity and surface area positively correlate with the diffusion coefficient. Oil viscosity, oil density, and volume of porous media have a negative correlation with the diffusion coefficient. It is worth noting that for rocks with certain volume, the increase of surface area can significantly increase the diffusion coefficient, which implies that direct upscale of the measured CO2 diffusion coefficient in the lab is totally unreasonable.

Keywords: Diffusion coefficient; Machine learning; BP neural Network; CO2-Oil system; Porous media (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (10)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544221025342
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:239:y:2022:i:pc:s0360544221025342

DOI: 10.1016/j.energy.2021.122286

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().