Intelligent Microfluidics Research on Relative Permeability Measurement and Prediction of Two-Phase Flow in Micropores

Abstract

Relative permeability is a key index in resource exploitation, energy development, environmental monitoring, and other fields. However, the current determination methods of relative permeability are inefficient and invisible without considering wetting order and pore structure characteristics either. In this study, microfluidic experiments were designed for figuring out key factors impacting on the two-phase relative permeability. The optimized intelligent image recognition was established for saturation extraction. The deep learning was conducted for the prediction of two-phase permeability based on the inputs from microfluidic experiments and image recognition and optimized. Results revealed that phase saturation, wetting order, and pore topology were the key factors influencing the two-phase relative permeability, with the importance of 38.22%, 34.84%, and 26.94%, respectively. The deep learning-based relative permeability model performed well, with MSE < 0.05 and operational efficiency of 3 ms/epoch. Aiming at relative permeability model optimization, on the one hand, the dividing ratio of training set and testing set for flooding phase relative permeability prediction achieved the highest prediction accuracy at 7 : 3, while that for displaced phase was 6 : 4. On the other hand, tanh() activation function performed 40% more accurate than the sigmoid() activation function.

Wettability Alteration Mechanisms in Enhanced Oil Recovery with Surfactants and Nanofluids: A Review with Microfluidic Applications

“…Secondly, the experiment somewhat changes the core's wetting condition and micropore structures. Hence, multiple experiments in a single core would raise the stochastic error [55]. Lastly, the invisibility of the internal flow in conventional core experiments leaves the effect of pore structure unattained [55].…”

“…Hence, multiple experiments in a single core would raise the stochastic error [55]. Lastly, the invisibility of the internal flow in conventional core experiments leaves the effect of pore structure unattained [55]. Because of its importance in oil recovery, many experiments have been performed to determine the relative permeability of a steady-state multiphase core displacement [55][56][57][58].…”

“…Lastly, the invisibility of the internal flow in conventional core experiments leaves the effect of pore structure unattained [55]. Because of its importance in oil recovery, many experiments have been performed to determine the relative permeability of a steady-state multiphase core displacement [55][56][57][58]. Despite the quantitative outcomes of core experiments, there are some drawbacks to the accuracy and practicality of these approaches.…”

“…For example, phase saturation in the pore network was considered as the significant parameter controlling relative permeability in the reservoirs, but with the microfluidic experimental studies; it is found that pore structure and flow patterns of the fluid can have a high impact on relative permeability and, to an extent, oil recovery. In one experiment, the investigation of the oil flooding by water with the microfluidic approach with the use of deep learning and an image recognition intelligent model was conducted (Figure 8) [55]. Based on the artificial intelligent models, it was found that the relative permeability or oil recovery is affected by phase saturation, wetting order, and pore structure with 36.23%, 33.20%, and 30.57%, respectively.…”

Numerical Investigation on EOR in Porous Media by Cyclic Water Injection with Vibration Frequency

“…Though higher EOR has been achieved via the enhanced oil recovery techniques than the water flooding, these techniques required the oil companies to append the gas compressor investment, update the surface pipe network system and pump stations and re-consider the compatibility of surfactants, polymers and microorganisms with the original equipment [7][8][9]. In addition, the residual surfactants, polymers and microorganisms in reservoirs after the enhanced oil recovery probably contaminated the groundwater [10][11][12]. Meanwhile, the injected micro/nanoparticles plug the reservoir pores, which is not conducive to the recycling and sustainability of the reservoir for CO 2 capture, utilization and underground storage and hydrogen underground storage [13,14].…”