0
Multiphase Flows

Intelligent Image-Based Gas-Liquid Two-Phase Flow Regime Recognition

[+] Author and Article Information
Soheil Ghanbarzadeh, Pedram Hanafizadeh

Department of Petroleum and Geosystems Engineering,  University of Texas at Austin, Austin, TX 78712-1585Multiphase Flow Research Group, Center of Excellence in Energy Conversion,  School of Mechanical Engineering,  Sharif University of Technology, P. O. Box: 11155-9567, Azadi Street, Tehran, Iran

Mohammad Hassan Saidi1

Department of Petroleum and Geosystems Engineering,  University of Texas at Austin, Austin, TX 78712-1585saman@sharif.eduMultiphase Flow Research Group, Center of Excellence in Energy Conversion,  School of Mechanical Engineering,  Sharif University of Technology, P. O. Box: 11155-9567, Azadi Street, Tehran, Iransaman@sharif.edu

1

Corresponding author.

J. Fluids Eng 134(6), 061302 (May 29, 2012) (10 pages) doi:10.1115/1.4006613 History: Received October 19, 2011; Revised April 11, 2012; Published May 29, 2012; Online May 29, 2012

Identification of different flow regimes in industrial systems operating under two-phase flow conditions is necessary in order to safely design and optimize their performance. In the present work, experiments on two-phase flow have been performed in a large scale test facility with the length of 6 m and diameter of 5 cm. Four main flow regimes have been observed in vertical air-water two-phase flow at moderate superficial velocities of gas and water namely: Bubbly, Slug, Churn, and Annular. An image processing technique was used to extract information from each picture. This information includes the number of bubbles or objects, area, perimeter, as well as the height and width of objects (second phase). In addition, a texture feature extraction procedure was applied to images of different regimes. Some features which were adequate for regime identification were extracted such as contrast, energy, entropy, etc. To identify flow regimes, a fuzzy interface was introduced using characteristic of second phase in picture. Furthermore, an Adaptive Neuro Fuzzy (ANFIS) was used to identify flow patterns using textural features of images. The experimental results show that these methods can accurately identify the flow patterns in a vertical pipe.

Copyright © 2012 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Figure 1

Schematic view for the experimental system

Grahic Jump Location
Figure 2

(a) RGB picture, (b) gray picture, (c) background subtracted, and (d) median process of bubbly flow image

Grahic Jump Location
Figure 3

Binary image of bubbly two-phase flow

Grahic Jump Location
Figure 4

Final result of image processing of bubbly two-phase flow: (a) opening, (b) closing

Grahic Jump Location
Figure 5

Final processed picture of (a) slug, (b) churn, and (c) annular flow patterns

Grahic Jump Location
Figure 6

Contrast of images for four main regimes

Grahic Jump Location
Figure 7

Entropy of images for four main regimes

Grahic Jump Location
Figure 8

Energy of images for four main regimes

Grahic Jump Location
Figure 9

Homogeneity of images for four main regimes

Grahic Jump Location
Figure 10

Correlation of images for four main regimes

Grahic Jump Location
Figure 11

Cluster prominence of images for four main regimes

Grahic Jump Location
Figure 12

Membership for our fuzzy system outputs

Grahic Jump Location
Figure 13

Membership function for fuzzy inputs (a) number of objects, (b) area of biggest object, (c) mean perimeter of objects, and (d) PCBIE.

Grahic Jump Location
Figure 14

Schematic of fuzzy system

Grahic Jump Location
Figure 15

Structure of adaptive neuro fuzzy system

Grahic Jump Location
Figure 16

Training error of ANFIS versus different number of epochs

Grahic Jump Location
Figure 17

ANFIS (a) training, (b) testing, and (c) checking data versus index of input

Grahic Jump Location
Figure 18

Comparison of predicted flow regime with flow regime map of Hewitt and Roberts

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