Fast Estimation of Supercritical CO2 Thermal Conductivity by a Supervised Learning Machine - Implications for EOR

Author(s):  
A. Rostami ◽  
M. Arabloo ◽  
E. Joonaki ◽  
S. Ghanaatian ◽  
A. Hassanpouryouzband
Polymer ◽  
2020 ◽  
Vol 206 ◽  
pp. 122912
Author(s):  
Naoya Yanagishima ◽  
Shinji Kanehashi ◽  
Hiromu Saito ◽  
Kenji Ogino ◽  
Takeshi Shimomura

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 64533-64544 ◽  
Author(s):  
Tianheng Song ◽  
Dazi Li ◽  
Zhiyin Liu ◽  
Weimin Yang

2020 ◽  
Vol 42 (1) ◽  
Author(s):  
Asbat E. Ramazanova ◽  
Ilmutdin M. Abdulagatov

2019 ◽  
Vol 127 ◽  
pp. 110730 ◽  
Author(s):  
Sophie Gillain ◽  
Mohamed Boutaayamou ◽  
Cedric Schwartz ◽  
Olivier Brüls ◽  
Olivier Bruyère ◽  
...  

2012 ◽  
Vol 433-440 ◽  
pp. 3584-3590 ◽  
Author(s):  
Rui Zhang ◽  
Tong Bo Liu ◽  
Ming Wen Zheng

Support vector machine (SVM) is a general and powerful learning machine, which adopts supervised manner. However, for many practical machine learning and data mining applications, unlabeled training examples are readily available but labeled ones are very expensive to be obtained. Therefore, semi-supervised learning emerges as the times require. At present, the combination of SVM and semi-supervised learning (S3VM) has attracted more and more attentions. In general, S3VM deals with problems with small training sets and large working sets. When the training set is large relative to the working set, We propose a new SVM model to solve the above classification problem by introducing the fuzzy memberships to each unlabeled point. Simulation results demonstrate that the proposed method can exploit unlabeled data to yield good performance effectively.


Author(s):  
Qian Zhang ◽  
Huixiong Li ◽  
Xianliang Lei ◽  
Xiangfei Kong ◽  
Jialun Liu ◽  
...  

Heat transfer enhancement (HTE) of supercritical CO2 flowing in heated vertical tube with an inner diameter of 6.32 mm was investigated numerically in present paper. The studies were performed for HTE cases with the pressure being 8.12 MPa, the mass flux being 400 and 1000 kg/m2s, and the heat flux being 30 and 50 kW/m2. Four turbulence models, including the RNG k-ε, the SST k-ω and two low-Reynolds number models (LB and LS), were evaluated with the experimental data collected from literatures. The SST k-ω model was shown to be the best among the four models, and then was used for the simulation in this study. The effect of five factors, including buoyancy, thermal acceleration, thermal conductivity, specific heat and viscosity of the fluid, on HTE were respectively analyzed according to the numerical results. It was shown that the buoyancy had a little negative influence on HTE and was negligible for the heat transfer. The thermal acceleration effect was detrimental to the HTE by accelerating the fluid near the wall and at the same time reducing the turbulence kinetic energy in the core of the flow. The rapid decrease of thermal conductivity of the fluid at the pseudo-critical region was also bad for HTE. Variation of the specific heat of the fluid had strong positive effect on the HTE. When most of the buffer layer was occupied by fluid with the large specific heat, the heat absorbing capability of the fluid was increased and more heat was carried away efficiently. Moreover, decrease in viscosity of the fluid with increasing temperature also significantly promoted the HTE because of the increase in flow turbulence and the reduction in thermal-conduction resistance. After that, the weight of above five factors effect on HTE was compared quantitatively.


Author(s):  
Gricelda Medina-Veloz ◽  
Francisco Javier Luna-Rosas ◽  
Kelly Carolina Martínez-Valadez ◽  
Juan Felipe Tavarez-Avendaño

In particular, the R5 HIV-1 viruses use CCR5 as co-receptor for the virus entrance, the X4 virus HIV-1 use the CXCR4, while some strange viruses known as R5X4 or D-tropic, have the ability to use both co-receptors. The X4 and R5X4 viruses are associated with rapid progress in HIV-1. In this article a series of experiments will be carried out to implement a Supervised Learning Machine in Parallel that allows optimizing the response time in the prediction of co-receptors (CCR5, CXCR4) of the virus that cause AIDS (HIV-1) in CD4 cells. To implement the machine in parallel we will use Snow in R. Snow provides the support to easily execute functions in R in parallel. Most functions in parallel in Snow are variations of the standard lapply () function. To implement the functions in parallel, Snow uses a master / slave architecture where the teacher sends tasks to the workers, and the workers execute the tasks and return the results to the teacheR.


Sign in / Sign up

Export Citation Format

Share Document