首页|Northeastern University Reports Findings in Machine Learning [Machine Learning-Based Interfacial Tension Equations for (H2 + CO2)-Water/Brine Systems over a Wide Range of Temperature and Pressure]
Northeastern University Reports Findings in Machine Learning [Machine Learning-Based Interfacial Tension Equations for (H2 + CO2)-Water/Brine Systems over a Wide Range of Temperature and Pressure]
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Machine Learning is th e subject of a report. According to news reporting originating in Shenyang, Peop le's Republic of China, by NewsRx journalists, research stated, "Large-scale und erground hydrogen storage (UHS) plays a vital role in energy transition. H-brine interfacial tension (IFT) is a crucial parameter in structural trapping in unde rground geological locations and gaswater two-phase flow in subsurface porous m edia." The news reporters obtained a quote from the research from Northeastern Universi ty, "On the other hand, cushion gas, such as CO, is often co-injected with H to retain reservoir pressure. Therefore, it is imperative to accurately predict the (H + CO)-water/brine IFT under UHS conditions. While there have been a number o f experimental measurements on H-water/brine and (H + CO)-water/brine IFT, an ac curate and efficient (H + CO)-water/brine IFT model under UHS conditions is stil l lacking. In this work, we use molecular dynamics (MD) simulations to generate an extensive (H + CO)-water/brine IFT databank (840 data points) over a wide ran ge of temperature (from 298 to 373 K), pressure (from 50 to 400 bar), gas compos ition, and brine salinity (up to 3.15 mol/kg) for typical UHS conditions, which is used to develop an accurate and efficient machine learning (ML)-based IFT equ ation. Our MLbased IFT equation is validated by comparing to available experime ntal data and other IFT equations for various systems (H-brine/water, CO-brine/w ater, and (H + CO)-brine/water), rendering generally good performance (with = 0. 902 against 601 experimental data points)."
ShenyangPeople's Republic of ChinaAs iaCyborgsEmerging TechnologiesMachine Learning
NETL
NSTL
