Support Vector Regression and Computational Fluid Dynamics Modeling of Newtonian and Non-Newtonian Fluids in Annulus With Pipe Rotation

被引:25
作者
Sorgun, Mehmet [1 ]
Ozbayoglu, A. Murat [2 ]
Ozbayoglu, M. Evren [3 ]
机构
[1] Izmir Katip Celebi Univ, Dept Civil Engn, TR-35620 Izmir, Turkey
[2] TOBB Univ Econ & Technol, Dept Comp Engn, TR-06560 Ankara, Turkey
[3] Univ Tulsa, McDougall Sch Petr Engn, Tulsa, OK 74104 USA
来源
JOURNAL OF ENERGY RESOURCES TECHNOLOGY-TRANSACTIONS OF THE ASME | 2015年 / 137卷 / 03期
关键词
ANN; CFD; non-Newtonian fluids; laminar flow; pipe rotation; pressure loss; SVR; FLOW REGIME IDENTIFICATION; LAMINAR-FLOW; ECCENTRICITY;
D O I
10.1115/1.4028694
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
The estimation of the pressure losses inside annulus during pipe rotation is one of the main concerns in various engineering professions. Pipe rotation is a considerable parameter affecting pressure losses in annulus during drilling. In this study, pressure losses of Newtonian and non-Newtonian fluids flowing through concentric horizontal annulus are predicted using computational fluid dynamics (CFD) and support vector regression (SVR). SVR and CFD results are compared with experimental data obtained from literature. The comparisons show that CFD model could predict frictional pressure gradient with an average absolute percent error less than 3.48% for Newtonian fluids and 19.5% for non-Newtonian fluids. SVR could predict frictional pressure gradient with an average absolute percent error less than 5.09% for Newtonian fluids and 5.98% for non-Newtonian fluids.
引用
收藏
页数:5
相关论文
共 31 条
[1]  
Ahmed R., 2010, SPE ANN TECHN C EXH
[2]  
Ahmed R., 2008, IADC SPE DRILL C ORL
[3]   Prediction of crude oil viscosity curve using artificial intelligence techniques [J].
Al-Marhoun, M. A. ;
Nizamuddin, S. ;
Raheem, A. A. Abdul ;
Ali, S. Shujath ;
Muhammadain, A. A. .
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING, 2012, 86-87 :111-117
[4]  
[Anonymous], 2006, ANSYS CFX-Solver Theory Guide
[5]  
[Anonymous], AUTOMATION REMOTE CO
[6]  
[Anonymous], ANSYS VERS 12 1
[7]   SUPPORT-VECTOR NETWORKS [J].
CORTES, C ;
VAPNIK, V .
MACHINE LEARNING, 1995, 20 (03) :273-297
[8]  
Drucker H, 1997, ADV NEUR IN, V9, P155
[9]   Forecasting PVT properties of crude oil systems based on support vector machines modeling scheme [J].
El-Sebakhy, Emad A. .
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING, 2009, 64 (1-4) :25-34
[10]   Effect of Drillstring Deflection and Rotary Speed on Annular Frictional Pressure Losses [J].
Erge, Oney ;
Ozbayoglu, Mehmet E. ;
Miska, Stefan Z. ;
Yu, Mengjiao ;
Takach, Nicholas ;
Saasen, Arild ;
May, Roland .
JOURNAL OF ENERGY RESOURCES TECHNOLOGY-TRANSACTIONS OF THE ASME, 2014, 136 (04)