scholarly journals CNN-Based Volume Flow Rate Prediction of Oil–Gas–Water Three-Phase Intermittent Flow from Multiple Sensors

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1245
Author(s):  
Jinku Li ◽  
Delin Hu ◽  
Wei Chen ◽  
Yi Li ◽  
Maomao Zhang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Volume Flow ◽  
Superficial Velocity ◽  
Intermittent Flow ◽  
Horizontal Pipe ◽  
Flow Rates ◽  
Multiple Sensors ◽  
Three Phase ◽  
Test Loop ◽  
Oil Gas

In this paper, we propose a deep-learning-based method using a convolutional neural network (CNN) to predict the volume flow rates of individual phases in the oil–gas–water three-phase intermittent flow simultaneously by analyzing the measurement data from multiple sensors, including a temperature sensor, a pressure sensor, a Venturi tube and a microwave sensor. To build datasets, a series of experiments for the oil–gas–water three-phase intermittent flow in a horizontal pipe, in which gas volume fraction and water-in-liquid ratio ranges are 23.77–94.45% and 14.95–86.97%, respectively, and gas flow superficial velocity and liquid flow superficial velocity ranges are 0.66–5.23 and 0.27–2.14 m/s, respectively, have been carried out on a test loop pipeline. The preliminary results indicate that the model can provide relative prediction errors on the testing-1 dataset for the volume flow rates of oil-phase, gas-phase and water-phase within ±10% with 94.49%, 92.56% and 95.71% confidence levels, respectively. Additionally, the prediction results on the testing-2 dataset also demonstrate the generalization ability of the model. The consuming time of a prediction with one sample is 0.43 s on an Intel Xeon CPU E5-2678 v3, and 0.01 s on an NVIDIA GeForce GTX 1080 Ti GPU. Hence, the proposed CNN-based prediction model, which can fulfill the real-time application requirements in the petroleum industry, reveals the potential of using deep learning to obtain accurate results in the multiphase flow measurement field.

Influence of Gas-Liquid Two-Phase Intermittent Flow on Hydraulic Sand Dune Migration in Horizontal Pipelines

2010 ◽  
Vol 132 (7) ◽  
Author(s):  
Afshin Goharzadeh ◽  
Peter Rodgers ◽  
Chokri Touati
Keyword(s):  
High Speed ◽  
Sand Dune ◽  
Front Velocity ◽  
Intermittent Flow ◽  
Sand Particle ◽  
Two Phase ◽  
Horizontal Pipe ◽  
Particle Mobility ◽  
Three Phase ◽  
Gas Ratio

This paper presents an experimental study of three-phase flows (air-water-sand) inside a horizontal pipe. The results obtained aim to enhance the fundamental understanding of sand transportation due to saltation in the presence of a gas-liquid two-phase intermittent flow. Sand dune pitch, length, height, and front velocity were measured using high-speed video photography. Four flow compositions with differing gas ratios, including hydraulic conveying, were assessed for sand transportation, having the same mixture velocity. For the test conditions under analysis, it was found that the gas ratio did not affect the average dune front velocity. However, for intermittent flows, the sand bed was transported further downstream relative to hydraulic conveying. It was also observed that the slug body significantly influences sand particle mobility. The physical mechanism of sand transportation was found to be discontinuous with intermittent flows. The sand dune local velocity (within the slug body) was measured to be three times higher than the averaged dune velocities, due to turbulent enhancement within the slug body.

Oil-Gas-Water Three-Phase Slug Flow Liquid Holdup Model in Horizontal Pipeline

2006 ◽  
Author(s):  
Jing Mei Zhao ◽  
Jing Gong ◽  
Da Yu
Keyword(s):  
Slug Flow ◽  
Water Film ◽  
Mineral Oil ◽  
Superficial Velocity ◽  
Oil Viscosity ◽  
Liquid Holdup ◽  
Three Phase ◽  
Water Based ◽  
Water Cut ◽  
Oil Gas

According to experiments and relational documents, slug regime, appeared in this experiment, can be divided into the following flow regimes: oil-based separated slug, oil-based dispersed slug, water-based separated and water-based dispersed slug. Experiments for oil-gas-water three-phase flow in a stainless steel pipe loop (25.7mm inner diameter, 52m long) are conducted. Compressed air, mineral oil and water are used as experiment medium. Mineral oil Viscosity is 64.5mPa.s at 20°C. Gas superficial velocity, liquid superficial velocity and water cut ranges are 0.5∼15 m/s, 0.05∼0.5 m/s and 0∼100% respectively. There are some strange observed in this experiment. At the very low gas superficial velocity less than 1m/s, the average liquid holdup of low liquid superficial velocity was larger than that of higher liquid superficial velocity especially in higher inlet water cut experiments. This is because at very low gas superficial velocity, the regime is separated slug flow which has water film below their liquid film zone, velocity difference between oil film and water film will affect the average liquid holdup greatly. With the increase of gas and liquid superficial velocity, the regime becomes dispersed slug flow which oil and water are homogeneous. It will be more obvious with the increasing of water cut for the thicker water film. A new liquid holdup model of oil-based and water-based separated slug has been developed. Based on statistical analysis, it is observed that the new model gives excellent results against the experimental data.

Characteristics of Pressure Gradient Fluctuation for Oil-Gas-Water Three-Phase Flow Based on Flow Pattern

2011 ◽  
Vol 66-68 ◽  
pp. 1187-1192 ◽  
Author(s):  
Hai Qin Wang ◽  
Yong Wang ◽  
Lei Zhang
Keyword(s):  
Pressure Gradient ◽  
Flow Pattern ◽  
Flow Patterns ◽  
Phase Flow ◽  
Water Mixture ◽  
Three Phase ◽  
Test Loop ◽  
Three Phase Flow ◽  
Oil Water ◽  
Oil Gas

Experiments were conducted in a horizontal multiphase flow test loop (50mm inner diameter, 40m long) to study the flow patterns for oil-gas-water three-phase flow and the pressure gradient fluctuation based on flow patterns. Using new methods of definition, 12 types of flow patterns were obtained and phase distribution characteristics of each pattern were analyzed. A new flow pattern (SW║IN) was firstly found in this work. Characteristics of the pressure gradient based on 7 flow patterns were carefully discussed. It was found that the pressure gradient increased with the increase of gas superficial velocity and oil-water mixture velocity. However, characteristics of the pressure gradient became complex with the increase of input water cut. The influence of flow structure of oil-water two-phase should be fully considered.

Pressure Drop for Oil-Gas Two-Phase Flow Through Straight Horizontal Pipe

2007 ◽  
Author(s):  
Wenhong Liu ◽  
Liejin Guo ◽  
Ximin Zhang ◽  
Kai Lin ◽  
Long Yang ◽  
...  
Keyword(s):  
Pressure Drop ◽  
Two Phase Flow ◽  
Phase Flow ◽  
Two Phase ◽  
Horizontal Pipe ◽  
Flow Through ◽  
Oil Gas

Image Fusion of ECT/ERT for Oil-Gas-Water Three-Phase Flow

2011 ◽  
Vol 3 (2) ◽  
pp. 29-34 ◽  
Author(s):  
Lifeng Zhang
Keyword(s):  
Image Fusion ◽  
Electrical Capacitance Tomography ◽  
Phase Flow ◽  
Electrical Capacitance ◽  
Cross Sectional ◽  
Three Phase ◽  
Three Phase Flow ◽  
Capacitance Tomography ◽  
Oil Gas ◽  
Image Fusion Method

The tomographic imaging of process parameters for oil-gas-water three-phase flow can be obtained through different sensing modalities, such as electrical resistance tomography (ERT) and electrical capacitance tomography (ECT), both of which are sensitive to specific properties of the objects to be imaged. However, it is hard to discriminate oil, gas and water phases merely from reconstructed images of ERT or ECT. In this paper, the feasibility of image fusion based on ERT and ECT reconstructed images was investigated for oil-gas-water three-phase flow. Two cases were discussed and pixel-based image fusion method was presented. Simulation results showed that the cross-sectional reconstruction images of oil-gas-water three-phase flow can be obtained using the presented methods.

RENAL RESEARCH INSTITUTE SYMPOSIUM: Effective Diffusion Volume Flow Rates (Qe) for Urea, Creatinine, and Inorganic Phosphorous (Qeu, Qecr, QeiP) During Hemodialysis

2003 ◽  
Vol 16 (6) ◽  
pp. 474-476 ◽  
Author(s):  
Frank A. Gotch ◽  
Froilan Panlilio ◽  
Olga Sergeyeva ◽  
Laura Rosales ◽  
Tom Folden ◽  
...  
Keyword(s):  
Effective Diffusion ◽  
Volume Flow ◽  
Flow Rates ◽  
Inorganic Phosphorous ◽  
Research Institute

Particle Transport Coefficient (PTC) and Phase-Efficiency Diagram: A New Perspective to Evaluate Three-Phase Particle-Laden Flow

2020 ◽  
Author(s):  
Zhifeng Zhang ◽  
Antoine Jean-Claude Jacques Pruvot ◽  
Pablo Cisternas ◽  
James McAndrew
Keyword(s):  
Particle Transport ◽  
Transport Coefficient ◽  
Vertical Direction ◽  
Environmental Cost ◽  
Mathematical Form ◽  
Horizontal Pipe ◽  
Carrier Fluid ◽  
Transport Efficiency ◽  
Three Phase ◽  
New Perspective

Abstract Many technologies have been developed to improve the ability of fluids to transport particles. However, the evaluation of particle transport efficiency remains challenging, especially in complex flow such as three-phase flow. In the present research, theoretical and experimental work is conducted to develop a new perspective of evaluating particle transport technologies, particle transport coefficient (PTC) as the particle transport distance per unit volume of water consumption considering the transport efficiency and environmental cost. The mathematical form of the PTC for the steady-state transport case is derived, followed by three special transport cases: (a) PTC = 0 when particle settled or stuck, (b) PTC = infinity in the vertical direction, considering gravity or buoyant with carrier fluid stationary, while PTC = 0 in a horizontal pipe due to particle settlement; and (c) PTC = 2 for an infinitely small particle at the center of a fully-developed laminar flow in a pipe. Furthermore, the fluid property and surface property influence on PTC are experimentally demonstrated. We believe the proposed approach can promote the development of particle transport technologies.

Sign in / Sign up

Export Citation Format

Share Document