Evaluation of Internal Multiphase Flow Field using Artificial Intelligence

Multiphase flow of oil, gas, and water occurs in a reservoir’s underground formation and also within the associated downstream pipeline and structures. Computer simulations of such phenomena are essential in order to achieve the behavior of parameters including but not limited to evolution of phase fractions, temperature, velocity, pressure, and flow regimes. However, within the oil and gas industry, due to the highly complex nature of such phenomena seen in unconventional assets, an accurate and fast calculation of the aforementioned parameters has not been successful using numerical simulation techniques, i.e., computational fluid dynamic (CFD). In this study, a fast-track data-driven method based on artificial intelligence (AI) is designed, applied, and investigated in one of the most well-known multiphase flow problems. This problem is a two-dimensional dam-break that consists of a rectangular tank with the fluid column at the left side of the tank behind the gate. Initially, the gate is opened, which leads to the collapse of the column of fluid and generates a complex flow structure, including water and captured bubbles. The necessary data were obtained from the experience and partially used in our fast-track data-driven model. We built our models using Levenberg Marquardt algorithm in a feed-forward back propagation technique. We combined our model with stochastic optimization in a way that it decreased the absolute error accumulated in following time-steps compared to numerical computation. First, we observed that our models predicted the dynamic behavior of multiphase flow at each time-step with higher speed, and hence lowered the run time when compared to the CFD numerical simulation. To be exact, the computations of our models were more than one hundred times faster than the CFD model, an order of 8 h to minutes using our models. Second, the accuracy of our predictions was within the limit of 10% in cascading condition compared to the numerical simulation. This was acceptable considering its application in underground formations with highly complex fluid flow phenomena. Our models help all engineering aspects of the oil and gas industry from drilling and well design to the future prediction of an efficient production.

Download Full-text

Multiphase Flow Analysis for Air-Water Bubbly Flow in a Multiphase Pump

Volume 1A, Symposia: Keynotes; Advances in Numerical Modeling for Turbomachinery Flow Optimization; Fluid Machinery; Industrial and Environmental Applications of Fluid Mechanics; Pumping Machinery ◽

10.1115/fedsm2017-69239 ◽

2017 ◽

Cited By ~ 1

Author(s):

Jun-Won Suh ◽

Young-Seok Choi ◽

Jin-Hyuk Kim ◽

Kyoung-Yong Lee ◽

Won-Gu Joo

Keyword(s):

Flow Field ◽

Multiphase Flow ◽

Gas Phase ◽

Volume Fraction ◽

High Reliability ◽

Bubbly Flow ◽

Flow Analysis ◽

Internal Flow ◽

Hydraulic Performance ◽

Multiphase Pump

Owing to the exhaustion of onshore resources, the development of resources has been expanded to the deep subsea. As the necessity of offshore plants is steadily increasing, there is an increasing interest in studying multiphase transportation technology. Multiphase pumps differ from single phase pumps in many ways, including performance evaluation, internal flow characteristics, and complex design methods. The primary issue of multiphase flow transport technology is that the characteristics of the internal flow change according to the gas volume fraction (GVF). Many theoretical and experimental analyses have been conducted to understand the mechanism of the internal flow field in multiphase pumps. As advanced computational fluid dynamics (CFD) based on the three-dimensional Reynolds-averaged Navier-Stokes (RANS) equations have become reliable tools, numerical analyses accompanied by experimental research have been applied to investigate the hydraulic performance and internal flow field of multiphase pumps. A number of studies have been conducted to investigate these phenomena. However, the understanding of the detailed mechanisms of phase separation and the forces that occur in the internal flow is not completely clear. This study aimed to establish a multiphase flow analysis method with high reliability when the internal flow of the multiphase pump is bubbly flow. To ensure the reliability of the numerical analysis, the numerical results were compared with the experimental data. Additionally, to analyze the detailed dynamic flow phenomena in the multiphase pump, the effects of various interphase forces acting between the liquid and gas phase and the particle diameter of the gas phase on the hydraulic performance were investigated.

Download Full-text

Development of Multiphase Flow Field Feature Extraction Technique using Deep Convolutional Learning

The Proceedings of the Thermal Engineering Conference ◽

10.1299/jsmeted.2020.0172 ◽

2020 ◽

Vol 2020 (0) ◽

pp. 0172

Author(s):

Shuichiro Miwa ◽

Takuro Sasaki

Keyword(s):

Feature Extraction ◽

Flow Field ◽

Multiphase Flow ◽

Extraction Technique ◽

Feature Extraction Technique ◽

Field Feature

Download Full-text

Numerical Analyses of the Effects of Bend Orientation on Sand Erosion in Elbows for Annular Flow

Volume 11: Petroleum Technology ◽

10.1115/omae2020-19311 ◽

2020 ◽

Author(s):

Rong Kang ◽

Haixiao Liu

Keyword(s):

Numerical Model ◽

Flow Field ◽

Multiphase Flow ◽

Annular Flow ◽

Oil And Gas ◽

Particle Model ◽

Severe Problem ◽

Hydrocarbon Reservoir ◽

Sand Erosion ◽

Sand Particles

Abstract Sand erosion is a severe problem during the transportation of oil and gas in pipelines. The technology of multiphase transportation is widely applied in production, due to its high efficiency and low cost. Among various multiphase flow patterns, annular flow is a common flow pattern in the transportation process. During the transportation of oil and gas from the hydrocarbon reservoir to the final destination, the flow direction of the mixture in pipelines is mainly changed by the bend orientation. The bend orientation obviously changes the distributions of the liquid film and sand particles in annular flow, and this would further affect the sand erosion in elbows. Computational Fluid Dynamics (CFD) is an efficient tool to investigate the issues of sand erosion in multiphase flow. In the present work, a CFD-based numerical model is adopted to analyze the effects of bend orientation on sand erosion in elbows for annular flow. Volume of Fluid (VOF) method is adopted to simulate the flow field of annular flow, and sand particles in the flow field are tracked by employing Discrete Particle Model (DPM) simultaneously. Then, the particle impingement information is combined with the erosion model to obtain the maximum erosion ratio. The present numerical model is validated by experiments conducted in vertical-horizontal upward elbows. Finally, the effects of various bend orientations on the erosion magnitude are investigated according to the numerical simulations.

Download Full-text

Analysis of Flow Simulation Based on Particle Movement

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.204-210.453 ◽

2011 ◽

Vol 204-210 ◽

pp. 453-457

Author(s):

Zhen Yu Zhong

Keyword(s):

Flow Field ◽

Multiphase Flow ◽

Fluid Structure Interaction ◽

Flow Simulation ◽

Calculation Error ◽

Particle Movement ◽

Fluid Structure ◽

Structure Interaction ◽

Simulation Based

It is proposed the method based on particle movement to simulate flow in this paper. The force on particles can be obtained from N-S equations, and the calculation error caused by particles’ simulation is discussed. Results show that the method is more effective through the example of flow field affected by the cube. The advantage of this method is to solve problems of multiphase flow and fluid-structure interaction.

Download Full-text

Simulation of liquid flow with a combination artificial intelligence flow field and Adams–Bashforth method

Scientific Reports ◽

10.1038/s41598-020-72602-6 ◽

2020 ◽

Vol 10 (1) ◽

Author(s):

Meisam Babanezhad ◽

Iman Behroyan ◽

Ali Taghvaie Nakhjiri ◽

Azam Marjani ◽

Saeed Shirazian

Keyword(s):

Artificial Intelligence ◽

Machine Learning ◽

Fluid Flow ◽

Flow Field ◽

Computational Time ◽

Machine Learning Method ◽

Learning Method ◽

Particle Movement ◽

Lagrangian Framework ◽

Cfd Method

Abstract Direct numerical simulation (DNS) of particle hydrodynamics in the multiphase industrial process enables us to fully learn the process and optimize it on the industrial scale. However, using high-resolution computational calculations for particle movement and the interaction between the solid phase and other phases in fine timestep is limited to excellent computational resources. Solving the Eulerian flow field as a source of solid particle movement can be very time-consuming. However, by the revolution of the fast and accurate learning process, the Eulerian domain can be computed by smart modeling in a very short computational time. In this work, using the machine learning method, the flow field in the square shape cavity is trained, and then the Eulerian framework is replaced with a machine learning method to generate the artificial intelligence (AI) flow field. Then the Lagrangian framework is coupled with this AI flow field, and we simulate particle motion through the fully AI framework. The Adams–Bashforth finite element method is used as a conventional CFD method (Eulerian framework) to simulate the flow field in the cavity. After simulating fluid flow, the ANFIS method is used as an AI model to train the Eulerian data-set and represents AI fluid flow (framework). The Lagrangian framework is coupled with the AI method, and the particle freely migrates through this artificial framework. The results reveal that there is a great agreement between Euler-Lagrangian and AI- Lagrangian in the cavity. We also found that there is an excellent agreement between AI overview with the Adams–Bashforth approach, and the new combination of machine learning and CFD method can accelerate the calculation of the flow field in the square-shaped cavity. AI model can mimic the vortex structure in the cavity, where there is a zero-velocity structure in the center of the domain and maximum velocity near the moving walls.

Download Full-text