0
Research Papers: Petroleum Engineering

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

[+] Author and Article Information
Mehmet Sorgun

Department of Civil Engineering,
Izmir Katip Celebi University,
Izmir 35620, Turkey
e-mail: mehmetsorgun@gmail.com

A. Murat Ozbayoglu

Department of Computer Engineering,
TOBB University of Economics and Technology,
Ankara 06560, Turkey

M. Evren Ozbayoglu

McDougall School of Petroleum Engineering,
The University of Tulsa,
Tulsa, OK 74104

1Corresponding author.

Contributed by the Petroleum Division of ASME for publication in the JOURNAL OF ENERGY RESOURCES TECHNOLOGY. Manuscript received April 5, 2014; final manuscript received August 25, 2014; published online October 21, 2014. Assoc. Editor: Christopher J. Wajnikonis.

J. Energy Resour. Technol 137(3), 032901 (Oct 21, 2014) (5 pages) Paper No: JERT-14-1096; doi: 10.1115/1.4028694 History: Received April 05, 2014; Revised August 25, 2014

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.

FIGURES IN THIS ARTICLE
<>
Copyright © 2015 by ASME
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Fig. 2

Illustration of how SVM decision boundary (separating line) is chosen

Grahic Jump Location
Fig. 1

The cost function associated with ε-SVR

Grahic Jump Location
Fig. 3

Determination of optimum tetrahedral mesh for CFD model

Grahic Jump Location
Fig. 4

Measured and predicted pressure gradient versus pipe rotation for test fluid A velocity = 1.96 ft/s

Grahic Jump Location
Fig. 5

Measured and predicted pressure gradient versus pipe rotation for test fluid B velocity = 0.13 ft/s

Grahic Jump Location
Fig. 6

Measured and predicted pressure gradient versus pipe rotation for test fluid C velocity = 0.035 ft/s

Grahic Jump Location
Fig. 7

Measured and predicted pressure gradient versus pipe rotation for test fluid D velocity = 0.44 ft/s

Grahic Jump Location
Fig. 8

Measured and predicted pressure gradient versus pipe rotation for test fluid E velocity = 0.09 ft/s

Tables

Errata

Discussions

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In