Flow Pattern Transition in Pipes Using Data-Driven and Physics-Informed Machine Learning

2020 ◽  
Author(s):  
André M. Quintino ◽  
Davi L. L. N. da Rocha ◽  
Roberto Fonseca Jr. ◽  
Oscar M. H. Rodriguez
Keyword(s):  
Machine Learning ◽  
Experimental Data ◽  
Flow Pattern ◽  
Liquid Flow ◽  
Two Phase Flow ◽  
Data Driven ◽  
Phase Flow ◽  
Two Phase ◽  
Flow Pattern Transition ◽  
Gas Liquid Flow

Abstract Flow pattern is an important engineering design factor in two-phase flow in the chemical, nuclear and energy industries, given its effects on pressure drop, holdup, and heat and mass transfer. The prediction of two-phase flow patterns through phenomenological models is widely used in both industry and academy. In contrast, as more experimental data become available for gas-liquid flow in pipes, the use of data-driven models to predict flow-pattern transition, such as machine learning, has become more reliable. This type of heuristic modeling has a high demand for experimental data, which may not be available in some industrial applications. As a consequence, it may fail to deliver a sufficiently generalized transition prediction. Incorporation of physics in machine learning is being proposed as an alternative to improve prediction and also to reduce the demand for experimental data. This paper evaluates the use of hybrid-physics-data machine learning to predict gas-liquid flow-pattern transition in pipes. Random forest and artificial neural network are the chosen tools. A database of experiments available in the open literature was collected and is shared in this work. The performance of the proposed hybrid model is compared with phenomenological and data-driven machine learning models through confusion matrices and graphics. The results show improvement in prediction performance even with a low amount of data for training. The study also suggests that graphical comparison of flow-pttern transition boundaries provides better understanding of the performance of the models than the traditional metric

Flow Configure in Vertical 180 Degree Turning Duct

2001 ◽  
Author(s):  
Lu Yuanwei ◽  
Zhou Fangde ◽  
Wang Yueshe ◽  
Qian Huanqun ◽  
Hu Zhihua
Keyword(s):  
Flow Pattern ◽  
Liquid Flow ◽  
Two Phase Flow ◽  
Vertical Tube ◽  
Experimental Result ◽  
Phase Flow ◽  
Two Phase ◽  
Vertical Part ◽  
Flow Situation ◽  
Gas Liquid Flow

Abstract Bend is applied in many industries, which exert an influence on fluid and make the flow complicate. The second flow caused by the bend is strong enough that the flow behind it very long can be affected, so it is hard to make the flow in it steady. The long-term unsteady flow can make the pipe fatigue, so make the tube crack and leak. It is important to improve this situation. In this paper a throttle is built in the exit of the bend to control the non-homogeneous flow inside the bend, which can overcome the disadvantage of bend in industrial application. Through computed the flow field behind the bend by water, we can see that the throttle can improve the flow situation and make the flow steady behind it. Applying this method to the gas-liquid flow, the experimental result showed that the void fraction behind the bend is alike the fully developed flow. It means that the throttle can improve the two-phase flow situation in the invert U bend. At last the gas-liquid flow pattern in-bend was studied by experiment and built the flow pattern map in the vertical parts of the invert U bend. It was found that the flow pattern in the vertical part of invert U bend is different from the fully developed gas-liquid flow in vertical tube. The throttle built in the bend make the unsteady region of two-phase flow being reduced.

Two-Phase Flow Modeling in Oil and Gas Applications

2015 ◽  
Author(s):  
M. M. Awad ◽  
S. D. Butt
Keyword(s):  
Experimental Data ◽  
Asymptotic Analysis ◽  
Liquid Flow ◽  
Oil And Gas ◽  
Two Phase Flow ◽  
Phase Flow ◽  
Flow Modeling ◽  
Two Phase ◽  
New Model ◽  
Gas Liquid Flow

In the current study, two-phase flow modeling in oil and gas applications using asymptotic analysis is presented. Examples of two-phase liquid-liquid flow in pipes, two-phase gas-liquid flow in fractures, and two-phase gas-liquid flow in porous media are presented. In the present study, a simple semi-theoretical method for calculating the two-phase frictional pressure gradient in oil and gas applications using asymptotic analysis is presented. The proposed model can be transformed into two-phase frictional multiplier as a function of the Lockhart-Martinelli parameter, X. The advantage of the new model is that it has only one fitting parameter (p). Therefore, calibration of the new model to experimental data is greatly simplified. The new model is able to model the existing multi parameters correlations by fitting the single parameter p. Comparison with experimental data for two-phase frictional multiplier versus the Lockhart-Martinelli parameter (X) is presented.

Detecting the Flow Pattern Transition in the Gas-Liquid Two-Phase Flow Using Multivariate Multi-Scale Entropy Analysis

2019 ◽  
Vol 74 (10) ◽  
pp. 837-848 ◽  
Author(s):  
Yudong Liu ◽  
Dayang Wang ◽  
Yingyu Ren ◽  
Ningde Jin
Keyword(s):  
Flow Pattern ◽  
Two Phase Flow ◽  
Flow Patterns ◽  
Mean Value ◽  
Entropy Rate ◽  
Permutation Entropy ◽  
Phase Flow ◽  
Two Phase ◽  
Multi Scale ◽  
Flow Pattern Transition

AbstractDue to the complex flow structure and non-uniform phase distribution in the vertical upward gas-liquid two-phase flow, an eight-electrode rotating electric field conductance sensor is used to obtain multi-channel conductance signals. The flow patterns of the vertical upward gas-liquid two-phase flow are classified according to the images obtained from a high-speed camera. Then, we employ the multivariate weighted multi-scale permutation entropy (MWMPE) to detect the instability of flow pattern transition in the gas-liquid two-phase flow. Afterwards, we compare the results of the MWMPE with those of the single-channel weighted multi-scale permutation entropy (SCWMPE) and multivariate multi-scale sample entropy (MMSE). The comparison results indicate that, compared with the SCWMPE and MMSE, the MWMPE has superior performance in terms of the high-resolution presentation of flow instability in the gas-liquid two-phase flow. Finally, we extract the mean value of the MWMPE in whole scales and the entropy rate of the MWMPE in the small scales. The results indicate that the normalized mean value and normalized entropy rate of MWMPE are very sensitive to the transitions of flow patterns, thus allowing the detection of the instability of flow pattern transition.

Behavior of the Two-Phase Gas-Liquid Flow at the Inlet of a Catalytic Reactor

2019 ◽  
Vol 19 (2) ◽  
pp. 123-131
Author(s):  
O. P. Klenov ◽  
A. S. Noskov
Keyword(s):  
Liquid Phase ◽  
Uniform Distribution ◽  
Liquid Flow ◽  
Two Phase Flow ◽  
Phase Flow ◽  
Catalytic Reactor ◽  
Two Phase ◽  
Gas Consumption ◽  
Flow Diagrams ◽  
Gas Liquid Flow

The work was aimed at studying the behavior of the two-phase gas-liquid flow at the inlet pipe of a catalytic reactor. Apart from the classical approach using literature flow diagrams, methods of computational hydrodynamics were used for 3D simulation of the space propagation of phases in the pipeline. The results obtained demonstrated non-uniform distribution of the liquid phase through the outlet section of the pipeline and the time-unsteady mass consumption of the liquid phase. The maximal peak consumptions were ca. 3 times as high as the average values. With the data on the flow diagrams, the CFD simulation demonstrated that variations in the gas consumption within the range under study do not cause changes in the behavior of the two-phase flow but an increase in the gas consumption results in smoothening of the non-uniform distribution of the liquid phase at the outlet pipe. The data on the flow behavior are necessary for designing catalytic reactors to provide uniform propagation of the two-phase flow over the catalyst bed, for example, hydrotreatment reactors used in refineries.

An Experimental Study on Air-Water Two-Phase Flow Patterns in Pebble Beds

2010 ◽  
Vol 132 (4) ◽  
Author(s):  
Bai Bofeng ◽  
Liu Maolong ◽  
Su Wang ◽  
Zhang Xiaojie
Keyword(s):  
Experimental Study ◽  
Flow Pattern ◽  
Test Section ◽  
Slug Flow ◽  
Annular Flow ◽  
Two Phase Flow ◽  
Flow Patterns ◽  
Phase Flow ◽  
Two Phase ◽  
Flow Pattern Transition

An experimental study was conducted on the air-water two-phase flow patterns in the bed of rectangular cross sections containing spheres of regular distribution. Three kinds of glass spheres with different diameters (3 mm, 6 mm, and 8 mm) were used for the establishment of the test section. By means of visual observations of the two-phase flow through the test section, it was discovered that five different flow patterns occurred within the experimental parameter ranges, namely, bubbly flow, bubbly-slug flow, slug flow, slug-annular flow, and annular flow. A correlation for the bubble and slug diameter in the packed beds was proposed, which was an extended expression of the Tung/Dhir model, Jamialahmadi’s model, and Schmidt’s model. Three correlations were proposed to calculate the void friction of the flow pattern transition in bubble flow, slug flow, and annular flow based on the bubble model in the pore region. The experimental result showed that the modified Tung and Dhir model of the flow pattern transition was in better agreement with the experimental data compared with Tung and Dhir’s model.

Numerical Simulation of the Gas-Liquid Flow in a Rotary Gas Separator

1998 ◽  
Vol 120 (1) ◽  
pp. 41-48 ◽  
Author(s):  
G. Lackner ◽  
F. J. S. Alhanati ◽  
S. A. Shirazi ◽  
D. R. Doty ◽  
Z. Schmidt
Keyword(s):  
Void Fraction ◽  
Liquid Flow ◽  
Two Phase Flow ◽  
Numerical Procedure ◽  
Phase Flow ◽  
Two Phase ◽  
Free Gas ◽  
Gas Separator ◽  
Gas Liquid Flow ◽  
Gas Void Fraction

The presence of free gas at the pump intake adversely affects the performance of an electrical submersible pump (ESP) system, often resulting in low efficiency and causing operational problems. One method of reducing the amount of free gas that the pump has to process is to install a rotary gas separator. The gas-liquid flow associated with the down hole installation of a rotary separator has been investigated to address its overall phase segregation performance. A mathematical model was developed to investigate factors contributing to gas-liquid separation and to determine the efficiency of the separator. The drift-flux approach was used to formulate this complex two-phase flow problem. The turbulent diffusivity was modeled by a two-layer mixing-length model and the relative velocity between phases was formulated based on published correlations for flows with similar characteristics. The well-known numerical procedure of Patankar-Spalding for single-phase flow computations was extended to this two-phase flow situation. Special discretization techniques were developed to obtain consistent results. Special under relaxation procedures were also developed to keep the gas void fraction in the interval [0, 1]. Predicted mixture velocity vectors and gas void fraction distribution for the two-phase flow inside the centrifuge are presented. The model’s predictions are compared to data gathered on a field scale experimental facility to support its invaluable capabilities as a design tool for ESP installations.

Sign in / Sign up

Export Citation Format

Share Document