PDF下载
[1].Gas-liquid slug flow liquid holdup measurement using semantic segmentation[J].油气储运,2021,40(11):1272-1277.
　LIANG Fachun,ZHAO Jingwen,MENG Jia,et al.Gas-liquid slug flow liquid holdup measurement using semantic segmentation[J].Oil & Gas Storage and Transportation,2021,40(11):1272-1277.
点击复制

Gas-liquid slug flow liquid holdup measurement using semantic segmentation

《油气储运》[ISSN:1000-8241/CN:13-1093/TE] 卷: 40 期数: 2021年11期 页码: 1272-1277 栏目: 出版日期: 2021-11-25
Title:

Gas-liquid slug flow liquid holdup measurement using semantic segmentation

文章编号:
1000-8241(2021)11-1272-06
Author(s):

LIANG Fachun1; 2;  ZHAO Jingwen1;  MENG Jia1;  LI Qigui1;  LI Naiming2

1. College of Pipeline and Civil Engineering, China University of Petroleum (East China); 2. Jiangsu Forged Pipe Fittings Co. Ltd.

Keywords:

oil-gas field development;  gas-liquid two-phase flow;  liquid holdup;  semantic segmentation;  deep learning;  high-speed camera;  measurement

Abstract:

Liquid holdup is one of the most important parameters of gas-liquid two-phase flow. Affected by the image noise, the traditional liquid holdup measurement method based on image processing is difficult to accurately extract the gas-liquid interface, resulting in the great error of the liquid holdup measurement. Hence, a network model based on Deeplab V3+ was established with the semantic segmentation algorithm of deep learning, which was also trained by the image data set obtained from the slug flow pattern acquisition experiment, and then the interface of the gas and liquid flow area in the slug flow was identified and extracted to realize the measurement of the liquid holdup of the gas-liquid two-phase slug flow. The results show that the semantic segmentation model can extract the images of the gas-liquid two-phase flow online, and accurately divide the gas zone, liquid zone and background zone. In addition, the liquid holdup obtained by the top interface extraction is relatively high, while that obtained by the bottom interface extraction is relatively low, but the liquid holdup obtained by the average liquid film thickness is the closest to the true value measured by WMS （Wire-mesh Sensors） grid imaging sensors, with the maximum error less than 10%. The research results provide a new way for real-time monitoring of liquid holdup. (12 Figures, 18 References)

参考文献/References:

[1] FENG S C, GUO K C. Oil & gas gathering transportation and processing in mines[M]. Dongying： China University of Petroleum Press, 2006:169-175.
[2] WOROSZ T, BERNARD M, KONG R, TOPTAN A, KIM S, HOXIE C. Sensitivity studies on the multi-sensor conductivity probe measurement technique for two-phase flows[j]. Nuclear Engineering and Design, 2016,310:552-563.
[3] FATEHI PEIKANI A, ROSHANI G H, FEGHHI S A H. Volume fraction measurement and flow regime recognition in dynamic gas-liquid two phase flow using gamma ray radiation technique[J]. Instruments and Experimental Techniques, 2017,60(5):752-758.
[4] ZHAO Y, BI Q C, YUAN Y E, LYU H C. Void fraction measurement in steam-water two-phase flow using the gamma ray attenuation under high pressure and high temperature evaporating conditions[J]. Flow Measurement and Instrumentation, 2016,49:18-30.
[5] SCHÄFER T, NEUMANN-KIPPING M, BIEBERLE A, BIEBERLE M, HAMPEL U. Ultrafast X-ray computed tomography imaging for hydrodynamic investigations of gas- liquid two-phase flow in centrifugal pumps[J]. Journal of Fluids Engineering, 2020, 142(4):041502.
[6] MA Y X, ZHENG Z C, XU L A, LIU X P, WU Y X. Application of electrical resistance tomography system to monitor gas/liquid two-phase flow in a horizontal pipc[J]. Flow Measurement and Instrumentation, 2001,12(4):259-265.
[7] SHELHAMER E, LONG J, DARRELL T. Fully convolutional networks for semantic segmentation[j]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017,39(4):640-651.
[8] TIAN X, WANG L, DING Q. Review of image semantic segmentation based on deep learning[J]. Journal of Software, 2019,30(2):440-468.
[9] ZHANG R, ZHAO K Q, GU K. Road image semantic segmentation based on convolutional neural network[J]. Computer and Digital Engineering, 2020,48(7):1772-1775,1803.
[10] JING Z W, GUAN H Y, PENG D F, YU Y T. Survey of research in image semantic segmentation based on deep neural network[J]. Computer Engineering, 2020,46(10):1-17.
[11] ZHENG K, LI J S. An overview of image semantic segmentation based on deep learning[J]. Geomatics & Spatial Information Technology, 2020,43(10):119-125.
[12] TIAN Q C, MENG Y. Image semantic segmentation based on convolutional neural network[J]. Journal of Chinese Computer Systems, 2020,41(6):1302-1313.
[13] CHEN Y D, ZHANG Q, LAN L, PENG L, YIN J. A review of deep convolutional neural networks in medical image segmentation[J]. Chinese Journal of Health Informatics and Management, 2021,18(2):278-284.
[14] LI Z N, LIU R R, LIANG G M. Semantic segmentation of medical cervical cell images based on convolutional neural network[J]. Computer Applications and Software, 2019, 36(11): 152-156.
[15] WENG R Y, SUN B, ZHAO Y X, ZHANG J Y, WEN Y J. Flow pattern recognition method of gas-liquid two-phase
flow based on adaptive optimal kernel and convolution neural network[J]. CIESC Journal, 2018, 69(12): 5065-5072.
[16] XI Y F, SUN L L, HE L M, LYU Y. Semantic segmentation based on improved Deeplab V3+ network[J]. Computer
Systems & Applications, 2020, 29(9): 178-183.
[17] ZHAI L S, YANG J, MENG Z H. Detection of transientgas-liquid flow structures in horizontal shale gas well using wire-mesh sensor[J]. Journal of Natural Gas Science and Engineering, 2019, 72: 103013.
[18] PRASSER H M, KREPPER E, LUCAS D, ZSCHAU J, PETERS D. Fast wire-mesh sensors for gas-liquid flows and decomposition of gas fraction profiles according to bubble size classes[C]. Tsukuba: Second Japanese-European Two-Phase Flow Group Meeting, 2000: 41-58.

备注/Memo

Received date: 30 Jun.2021. Revised date:27 Jul.2021. Edited by: ZHANG jingnan）
Foundation Item: supported by the National Natural Science Foundation of China,“Metering theory and realization method of critical split sampling of underwater oil and gas”(51574272); National Key Research and development Program,“Damage mechanism and evolution of offshore oil and gas pipelines and onshore terminal facilities”(2016YFC0802301).
About the author: LIANG fachun, male, born in 1977, professor, he was graduated from Xi'an Jiaotong University in 2006 with a doctor degree, majoring in power engineering and engineering thermophysics. Address:No.66, West Changjiang Road, Huangdao District, Qingdao, China, 266580. Tel:0532-86981224. Email:liangfch@upc.edu.cn

更新日期/Last Update: 2022-09-25