Identification of oil–gas two-phase flow pattern based on SVM and electrical capacitance tomography technique

Zhang, Lifeng; Wang, Huaxiang

doi:10.1016/j.flowmeasinst.2009.08.006

Cited by 36 publications

(17 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…According to the study of Lifeng Zhang, Huaxiang Wang [19] , The SVM method was introduced to the identification of the Flow pattern for oil gas two-phase flow in this paper. The DDAG for multi-class classification was presented.…”

Section: S--t-b Flow Pattern Identification Methodsmentioning

confidence: 99%

The research reviewed about the monitoring of gas-liquid phase flow pattern

Wang

Rao

et al. 2011

2011 International Conference on Electrical and Control Engineering

View full text Add to dashboard Cite

The phenomenon of two-phase flow is common in nature and production practice. Two phase flow exists different flow patterns under different environment, namely flow pattern, and it immensely influences the flow characteristics and heat and mass transfer properties of two phase flow, at the same time, it affects measuring accurately of flow parameters and the operation of equipment. The flow resistance of different flow patterns can change a few times even a few times under the same mass flow. The paper briefly explains the relevant knowledge about two phase flow pattern.This paper analyses the direct and indirect methods about two-phase flow pattern monitoring at home and abroad particularly. What's more, this paper has pointed out the advantages and disadvantages of the various observation methods, and mainly analyzes the advantage of several latest indirect method and the condition of test,and forecasts the development trend of current monitoring method. Finally, the paper points out, although we had made fruitful achievements, the development of monitoring technology still has a long way to go.

show abstract

Section: S--t-b Flow Pattern Identification Methodsmentioning

confidence: 99%

The research reviewed about the monitoring of gas-liquid phase flow pattern

Wang

Rao

et al. 2011

2011 International Conference on Electrical and Control Engineering

View full text Add to dashboard Cite

show abstract

“…For the classification process, two types of supervised classifiers were considered: (i) Support Vector Machines (SVM) and (ii) K-Nearest Neighbors (KNN). These techniques have also been used in multiphase flow data classification [70,71]. A SVM classifier maps a given set of binary labeled training data into a high dimensional feature space, and it separates the classes with a maximum margin hyperplane [72].…”

Section: Experimental Data Processingmentioning

confidence: 99%

“…KNN is a classification based on a majority vote of its K neighbors [73]. Further details about the mathematical description of these classifiers are found in Duda et al [74], Tarca et al [70], and Zhang and Wang [71]. The main features of these processes are described below.…”

Section: Experimental Data Processingmentioning

confidence: 99%

Probabilistic approach of a flow pattern map for horizontal, vertical, and inclined pipes

Amaya-Gómez

López

Pineda

et al. 2019

Oil Gas Sci. Technol. – Rev. IFP Energies nouvelles

View full text Add to dashboard Cite

A way to predict two-phase liquid-gas flow patterns is presented for horizontal, vertical and inclined pipes. A set of experimental data (7702 points, distributed among 22 authors) and a set of synthetic data generated using OLGA Multiphase Toolkit v.7.3.3 (59 674 points) were gathered. A filtering process based on the experimental void fraction was proposed. Moreover, a classification of the pattern flows based on a supervised classification and a probabilistic flow pattern map is proposed based on a Bayesian approach using four pattern flows: Segregated Flow, Annular Flow, Intermittent Flow, and Bubble Flow. A new visualization technique for flow pattern maps is proposed to understand the transition zones among flow patterns and provide further information than the flow pattern map boundaries reported in the literature. Following the methodology proposed in this approach, probabilistic flow pattern maps are obtained for oil–water pipes. These maps were determined using an experimental dataset of 11 071 records distributed among 53 authors and a numerical filter with the water cut reported by OLGA Multiphase Toolkit v7.3.3.

show abstract

“…The above researchers concluded that five methods presented good results, with the exemption of the algorithm based on Single Decision Tree (STD). Using artificial intelligence systems based on fuzzy logic techniques and data of void fraction obtained by a Wire-Mesh Sensor (WMS), [14] identified several flow patterns. [14] used Support Vector Machine (SVM) to identify the oil-air flow patterns.…”

Section: Introductionmentioning

confidence: 99%

Specialist system in flow pattern identification using artificial neural Networks

Camperos¹,

Diaz²,

Cely³

2023

J Appl Eng Science

View full text Add to dashboard Cite

In this work, an application of artificial intelligence in the oils & gas industry is developed to iden-tify flow patterns in horizontal and vertical pipes of two-phase flow of oil and water, normalizing the word information and converting it to numerical values through the development of an artifi-cial neural network, whose input layer is composed of the surface velocities of each fluid, the ve-locity of the mixture, the volumetric fraction of the substances, diameter and the inclination of pipelines and the oil viscosity. The Artificial Neural Networks (ANN) has two hidden layers composed of 45 neurons. The database with which the model was trained, validated, and tested has 6993 rows of information corresponding to the inputs of the intelligent system and particular-ized for annular flow in horizontal pipes and DO/W in vertical pipelines. Notice that the infor-mation was obtained after re-engineering the information presented by 12 and 18 authors for hor-izontal and vertical piping, respectively. Finally, the mean square error obtained by the model was around 1.38%, with a maximum coefficient of determination of 0.79.

show abstract

Identification of oil–gas two-phase flow pattern based on SVM and electrical capacitance tomography technique

Cited by 36 publications

References 17 publications

The research reviewed about the monitoring of gas-liquid phase flow pattern

The research reviewed about the monitoring of gas-liquid phase flow pattern

Probabilistic approach of a flow pattern map for horizontal, vertical, and inclined pipes

Specialist system in flow pattern identification using artificial neural Networks

Contact Info

Product

Resources

About