scholarly journals Machine learning applications to predict two-phase flow patterns

2021 ◽  
Vol 7 ◽  
pp. e798
Author(s):  
Harold Brayan Arteaga-Arteaga ◽  
Alejandro Mora-Rubio ◽  
Frank Florez ◽  
Nicolas Murcia-Orjuela ◽  
Cristhian Eduardo Diaz-Ortega ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Two Phase Flow ◽  
Classification Problem ◽  
Flow Patterns ◽  
Machine Learning Algorithms ◽  
Test Machine ◽  
Phase Flow ◽  
Classification Problems ◽  
Two Phase

Recent advances in artificial intelligence with traditional machine learning algorithms and deep learning architectures solve complex classification problems. This work presents the performance of different artificial intelligence models to classify two-phase flow patterns, showing the best alternatives for this specific classification problem using two-phase flow regimes (liquid and gas) in pipes. Flow patterns are affected by physical variables such as superficial velocity, viscosity, density, and superficial tension. They also depend on the construction characteristics of the pipe, such as the angle of inclination and the diameter. We selected 12 databases (9,029 samples) to train and test machine learning models, considering these variables that influence the flow patterns. The primary dataset is Shoham (1982), containing 5,675 samples with six different flow patterns. An extensive set of metrics validated the results obtained. The most relevant characteristics for training the models using Shoham (1982) dataset are gas and liquid superficial velocities, angle of inclination, and diameter. Regarding the algorithms, the Extra Trees model classifies the flow patterns with the highest degree of fidelity, achieving an accuracy of 98.8%.

Machine Learning Approach to Predict the Flow Rate for an Immiscible Two-Phase Flow at Pore Scale for Enhanced Oil Recovery Application

2018 ◽  
Author(s):  
Arturo Rodriguez ◽  
V. M. Krushnarao Kotteda ◽  
Luis F. Rodriguez ◽  
Vinod Kumar ◽  
Arturo Schiaffino ◽  
...  
Keyword(s):  
Machine Learning ◽  
Surface Tension ◽  
Pressure Drop ◽  
Flow Rate ◽  
Oil Recovery ◽  
Two Phase Flow ◽  
Machine Learning Algorithms ◽  
Phase Flow ◽  
Pore Scale ◽  
Two Phase

Due to global demand for energy, there is a need to maximize oil extraction from wet reservoir sedimentary formations, which implies the efficient extraction of oil at the pore scale. The approach involves pressurizing water into the wetting oil pore of the rock for displacing and extracting the oil. The two-phase flow is complicated because of the behavior of the fluid flow at the pore scale, and capillary quantities such as surface tension, viscosities, pressure drop, radius of the medium, and contact angle become important. In the present work, we use machine learning algorithms in TensorFlow to predict the volumetric flow rate for a given pressure drop, surface tension, viscosity and geometry of the pores. The TensorFlow software library was developed by the Google Brain team and is one of the most powerful tools for developing machine learning workflows. Machine learning models can be trained on data and then these models are used to make predictions. In this paper, the predicted values for a two-phase flow of various pore sizes and liquids are validated against the numerical and experimental results in the literature.

Two-Phase Flow Regime Identification Using Fluctuating Force Signals Under Machine Learning Techniques

2018 ◽  
Author(s):  
Yuta Saito ◽  
Shuhei Torisaki ◽  
Shuichiro Miwa
Keyword(s):  
Machine Learning ◽  
Flow Regime ◽  
Two Phase Flow ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Phase Flow ◽  
Two Phase ◽  
Learning Techniques ◽  
Flow Regime Identification

For rational design of industrial machineries such as nuclear power plants and heat exchanging devices, understanding of the two-phase flow regime is crucial. In this study, a new method of flow regime identification using the two-phase fluctuating force signals is proposed. Unlike the existing methodologies to measure two-phase flow parameters, the advantageous feature of utilizing the fluctuating force signal is that the measurement can be conducted under completely intrusive environment. Experiments were conducted using the tri-axial force transducers installed at the 90 degrees pipe bend of the vertical upward flow. For signal classification, machine learning techniques were utilized to identify flow regime, and four types flow regimes, namely, bubbly, slug, churn-turbulent, and annular flows were considered. From the obtained fluctuating force database, the features that characterize the signal were selected in the time and the frequency domain. In the current study, three types of machine learning algorithms such as the artificial neural network (ANN), support vector machine (SVM), and decision tree were examined and results obtained by each learning technique was compared.

scholarly journals Machine Learning Model of Dimensionless Numbers to Predict Flow Patterns and Droplet Characteristics for Two-Phase Digital Flows

2021 ◽  
Vol 11 (9) ◽  
pp. 4251
Author(s):  
Jinsong Zhang ◽  
Shuai Zhang ◽  
Jianhua Zhang ◽  
Zhiliang Wang
Keyword(s):  
Machine Learning ◽  
Learning Algorithms ◽  
Digital Microfluidics ◽  
Flow Patterns ◽  
Machine Learning Algorithms ◽  
Dimensionless Numbers ◽  
Two Phase ◽  
The Difference ◽  
Input Variables ◽  
Digital Microfluidic

In the digital microfluidic experiments, the droplet characteristics and flow patterns are generally identified and predicted by the empirical methods, which are difficult to process a large amount of data mining. In addition, due to the existence of inevitable human invention, the inconsistent judgment standards make the comparison between different experiments cumbersome and almost impossible. In this paper, we tried to use machine learning to build algorithms that could automatically identify, judge, and predict flow patterns and droplet characteristics, so that the empirical judgment was transferred to be an intelligent process. The difference on the usual machine learning algorithms, a generalized variable system was introduced to describe the different geometry configurations of the digital microfluidics. Specifically, Buckingham’s theorem had been adopted to obtain multiple groups of dimensionless numbers as the input variables of machine learning algorithms. Through the verification of the algorithms, the SVM and BPNN algorithms had classified and predicted the different flow patterns and droplet characteristics (the length and frequency) successfully. By comparing with the primitive parameters system, the dimensionless numbers system was superior in the predictive capability. The traditional dimensionless numbers selected for the machine learning algorithms should have physical meanings strongly rather than mathematical meanings. The machine learning algorithms applying the dimensionless numbers had declined the dimensionality of the system and the amount of computation and not lose the information of primitive parameters.

scholarly journals Two-Phase Flow Mass Transfer Analysis of Airlift Pump for Aquaculture Applications

Fluids ◽  
2021 ◽  
Vol 6 (6) ◽  
pp. 226
Author(s):  
Rashal Abed ◽  
Mohamed M. Hussein ◽  
Wael H. Ahmed ◽  
Sherif Abdou
Keyword(s):  
Mass Transfer ◽  
Oxygen Transfer ◽  
Transfer Rate ◽  
Two Phase Flow ◽  
Oxygen Transfer Rate ◽  
Flow Patterns ◽  
Oxygen Mass Transfer ◽  
Phase Flow ◽  
Two Phase ◽  
Airlift Pump

Airlift pumps can be used in the aquaculture industry to provide aeration while concurrently moving water utilizing the dynamics of two-phase flow in the pump riser. The oxygen mass transfer that occurs from the injected compressed air to the water in the aquaculture systems can be experimentally investigated to determine the pump aeration capabilities. The objective of this study is to evaluate the effects of various airflow rates as well as the injection methods on the oxygen transfer rate within a dual injector airlift pump system. Experiments were conducted using an airlift pump connected to a vertical pump riser within a recirculating system. Both two-phase flow patterns and the void fraction measurements were used to evaluate the dissolved oxygen mass transfer mechanism through the airlift pump. A dissolved oxygen (DO) sensor was used to determine the DO levels within the airlift pumping system at different operating conditions required by the pump. Flow visualization imaging and particle image velocimetry (PIV) measurements were performed in order to better understand the effects of the two-phase flow patterns on the aeration performance. It was found that the radial injection method reached the saturation point faster at lower airflow rates, whereas the axial method performed better as the airflow rates were increased. The standard oxygen transfer rate (SOTR) and standard aeration efficiency (SAE) were calculated and were found to strongly depend on the injection method as well as the two-phase flow patterns in the pump riser.

Two-Phase Flow and Heat Transfer in Rectangular Micro-Channels

2003 ◽  
Author(s):  
Weilin Qu ◽  
Seok-Mann Yoon ◽  
Issam Mudawar
Keyword(s):  
Heat Transfer ◽  
Pressure Drop ◽  
Flow Pattern ◽  
Two Phase Flow ◽  
Flow Patterns ◽  
Heat Sinks ◽  
Phase Flow ◽  
Micro Channel ◽  
Two Phase ◽  
Micro Channels

Knowledge of flow pattern and flow pattern transitions is essential to the development of reliable predictive tools for pressure drop and heat transfer in two-phase micro-channel heat sinks. In the present study, experiments were conducted with adiabatic nitrogen-water two-phase flow in a rectangular micro-channel having a 0.406 × 2.032 mm cross-section. Superficial velocities of nitrogen and water ranged from 0.08 to 81.92 m/s and 0.04 to 10.24 m/s, respectively. Flow patterns were first identified using high-speed video imaging, and still photos were then taken for representative patterns. Results reveal that the dominant flow patterns are slug and annular, with bubbly flow occurring only occasionally; stratified and churn flow were never observed. A flow pattern map was constructed and compared with previous maps and predictions of flow pattern transition models. Annual flow is identified as the dominant flow pattern for conditions relevant to two-phase micro-channel heat sinks, and forms the basis for development of a theoretical model for both pressure drop and heat transfer in micro-channels. Features unique to two-phase micro-channel flow, such as laminar liquid and gas flows, smooth liquid-gas interface, and strong entrainment and deposition effects are incorporated into the model. The model shows good agreement with experimental data for water-cooled heat sinks.

Liquid–Liquid Two-Phase Flow Patterns in a Serpentine Microchannel

2012 ◽  
Vol 51 (13) ◽  
pp. 5056-5066 ◽  
Author(s):  
P. S. Sarkar ◽  
K. K. Singh ◽  
K. T. Shenoy ◽  
A. Sinha ◽  
H. Rao ◽  
...  
Keyword(s):  
Two Phase Flow ◽  
Flow Patterns ◽  
Phase Flow ◽  
Two Phase
Sign in / Sign up

Export Citation Format

Share Document