Prediction of Pressure Gradient in Two and Three-Phase Flows in Vertical Pipes Using an Artificial Neural Network Model

Joseph Xavier Francisco Ribeiro, Ruiquan Liao, Aliyu Musa Aliyu, Zilong Liu

Research output: Contribution to journalArticle

Abstract

The concurrent flow of gas with a mixture of oil and water is often observed in production tubing in the petroleum industry. Lack of physical understanding of the several phenomenological characteristics of three-phase flow can lead to unsatisfactory production rates or even oversizing of pipelines. Additional investigations to gain more insight and development of more accurate correlations for prediction of flow characteristics including pressure drop is necessary. In this study, an experimental study was conducted using air-water and air-water-oil mixtures in a 0.075m diameter pipe. Superficial gas and liquid velocities ranged from 0.03 to 0.13 m/s and 1.26 to 41.58 m/s respectively. Slug flow was the main flow pattern observed. In addition, the transition from churn to annular flow and annular were also observed. Due to the homogeneous nature of the oil-water-air mixture, the three-phase flow was evaluated as a pseudo-two-phase mixture. An Artificial Neural Network (ANN) model developed for the prediction of two-phase and three-phase pressure drop performed better than all models considered during the evaluation. Generally, it was found that the accuracies for pressure drop were considered adequate.

Original languageEnglish
Pages (from-to)155-170
Number of pages16
JournalInternational Journal of Engineering and Technology Innovation
Volume9
Issue number3
Publication statusPublished - 1 Jul 2019
Externally publishedYes

Fingerprint

Pressure gradient
Pipe
Pressure drop
Neural networks
Water
Air
Petroleum industry
Tubing
Flow patterns
Flow of gases
Pipelines
Liquids
Gases
Oils

Cite this

@article{29a5c67997724b4594b907a1b4181087,
title = "Prediction of Pressure Gradient in Two and Three-Phase Flows in Vertical Pipes Using an Artificial Neural Network Model",
abstract = "The concurrent flow of gas with a mixture of oil and water is often observed in production tubing in the petroleum industry. Lack of physical understanding of the several phenomenological characteristics of three-phase flow can lead to unsatisfactory production rates or even oversizing of pipelines. Additional investigations to gain more insight and development of more accurate correlations for prediction of flow characteristics including pressure drop is necessary. In this study, an experimental study was conducted using air-water and air-water-oil mixtures in a 0.075m diameter pipe. Superficial gas and liquid velocities ranged from 0.03 to 0.13 m/s and 1.26 to 41.58 m/s respectively. Slug flow was the main flow pattern observed. In addition, the transition from churn to annular flow and annular were also observed. Due to the homogeneous nature of the oil-water-air mixture, the three-phase flow was evaluated as a pseudo-two-phase mixture. An Artificial Neural Network (ANN) model developed for the prediction of two-phase and three-phase pressure drop performed better than all models considered during the evaluation. Generally, it was found that the accuracies for pressure drop were considered adequate.",
keywords = "Artificial neural networks, Pressure drop, Three-phase flow, Two-phase flow, Vertical pipes",
author = "Ribeiro, {Joseph Xavier Francisco} and Ruiquan Liao and Aliyu, {Aliyu Musa} and Zilong Liu",
year = "2019",
month = "7",
day = "1",
language = "English",
volume = "9",
pages = "155--170",
journal = "International Journal of Engineering and Technology Innovation",
issn = "2223-5329",
publisher = "Taiwan Association of Engineering and Technology Innovation",
number = "3",

}

Prediction of Pressure Gradient in Two and Three-Phase Flows in Vertical Pipes Using an Artificial Neural Network Model. / Ribeiro, Joseph Xavier Francisco; Liao, Ruiquan; Aliyu, Aliyu Musa; Liu, Zilong.

In: International Journal of Engineering and Technology Innovation, Vol. 9, No. 3, 01.07.2019, p. 155-170.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Prediction of Pressure Gradient in Two and Three-Phase Flows in Vertical Pipes Using an Artificial Neural Network Model

AU - Ribeiro, Joseph Xavier Francisco

AU - Liao, Ruiquan

AU - Aliyu, Aliyu Musa

AU - Liu, Zilong

PY - 2019/7/1

Y1 - 2019/7/1

N2 - The concurrent flow of gas with a mixture of oil and water is often observed in production tubing in the petroleum industry. Lack of physical understanding of the several phenomenological characteristics of three-phase flow can lead to unsatisfactory production rates or even oversizing of pipelines. Additional investigations to gain more insight and development of more accurate correlations for prediction of flow characteristics including pressure drop is necessary. In this study, an experimental study was conducted using air-water and air-water-oil mixtures in a 0.075m diameter pipe. Superficial gas and liquid velocities ranged from 0.03 to 0.13 m/s and 1.26 to 41.58 m/s respectively. Slug flow was the main flow pattern observed. In addition, the transition from churn to annular flow and annular were also observed. Due to the homogeneous nature of the oil-water-air mixture, the three-phase flow was evaluated as a pseudo-two-phase mixture. An Artificial Neural Network (ANN) model developed for the prediction of two-phase and three-phase pressure drop performed better than all models considered during the evaluation. Generally, it was found that the accuracies for pressure drop were considered adequate.

AB - The concurrent flow of gas with a mixture of oil and water is often observed in production tubing in the petroleum industry. Lack of physical understanding of the several phenomenological characteristics of three-phase flow can lead to unsatisfactory production rates or even oversizing of pipelines. Additional investigations to gain more insight and development of more accurate correlations for prediction of flow characteristics including pressure drop is necessary. In this study, an experimental study was conducted using air-water and air-water-oil mixtures in a 0.075m diameter pipe. Superficial gas and liquid velocities ranged from 0.03 to 0.13 m/s and 1.26 to 41.58 m/s respectively. Slug flow was the main flow pattern observed. In addition, the transition from churn to annular flow and annular were also observed. Due to the homogeneous nature of the oil-water-air mixture, the three-phase flow was evaluated as a pseudo-two-phase mixture. An Artificial Neural Network (ANN) model developed for the prediction of two-phase and three-phase pressure drop performed better than all models considered during the evaluation. Generally, it was found that the accuracies for pressure drop were considered adequate.

KW - Artificial neural networks

KW - Pressure drop

KW - Three-phase flow

KW - Two-phase flow

KW - Vertical pipes

UR - http://www.scopus.com/inward/record.url?scp=85067252870&partnerID=8YFLogxK

UR - http://ijeti.imeti.org/v9-n3.php

M3 - Article

AN - SCOPUS:85067252870

VL - 9

SP - 155

EP - 170

JO - International Journal of Engineering and Technology Innovation

JF - International Journal of Engineering and Technology Innovation

SN - 2223-5329

IS - 3

ER -