A novel complex network-based deep learning method for characterizing gas-liquid two-phase flow

Gas-liquid two-phase flow widely exits in production and transportation of petroleum industry.Characterizing gas-liquid flow and measuring flow parameters represent challenges of great importance,which contribute to the recognition of flow regime and the optimal design of industrial equipment.In this paper,we propose a novel complex network-based deep learning method for characterizing gas-liquid flow.Firstly,we map the multichannel measurements to multiple limited penetrable visibility graphs(LPVGs)and obtain their degree sequences as the graph representation.Based on the degree distribution,we analyze the complicated flow behavior under different flow structures.Then,we design a dual-input convolutional neural network to fuse the raw signals and the graph representation of LPVGs for the classification of flow structures and measurement of gas void fraction.We implement the model with two parallel branches with the same structure,each corresponding to one input.Each branch consists of a channel-projection convolutional part,a spatial-temporal convolutional part,a dense block and an attention module.The outputs of the two branches are concatenated and fed into several full connected layers for the classification and measurement.At last,our method achieves an accuracy of 95.3%for the classification of flow structures,and a mean squared error of 0.0038 and a mean absolute percent error of 6.3%for the measurement of gas void fraction.Our method provides a promising solution for characterizing gas-liquid flow and measuring flow parameters.

Experimental study of the critical sand starting velocity of gas-watersand flow in an inclined pipe

The purpose of this paper is to study the critical sand starting velocity and transformation law of flow pattern based on gas-water-sand three-phase flow in an inclined pipe.Firstly,the indoor simulation experiment system of gas-water-sand three-phase flow was used to test the conversion law of flow pattern based upon the different gas void fraction.Secondly,the influence of slug bubbles on sand migration was investigated according to distinctive hole deviation angles,gas void fraction and sand concentration.Finally,the critical sand starting velocity was tested based on dissimilar hole deviation angles,gas void fraction,sand concentration and sand particle size,and then the influence of the abovementioned key parameters on the sand starting velocity was debated based on the force analysis of the sand particles.The experimental results illustrated that when the gas void fraction was less than 5%,it was bubbly flow.When it increased from 5%to 30%,the bubbly flow and slug flow coexisted.When it was between 30%and 50%,the slug flow and agitated flow coexisted.When it reached 50%,it was agitated flow.Providing that the hole deviation angle was 90°,the phenomenon of overall migration and wavelike migration on the surface of sand bed was observed.On the contrary,the phenomenon of rolling and jumping migration was recognized.The critical sand starting velocity was positively correlated with the hole deviation angle and sand particle size,but negatively associated with the gas void fraction and sand concentration.This research can provide a certain reference for sand-starting production in the field of petroleum engineering.

A unified fractional flow framework for predicting the liquid holdup in two-phase pipe flows

Two-phase pipe flow occurs frequently in oil&gas industry,nuclear power plants,and CCUS.Reliable calculations of gas void fraction(or liquid holdup)play a central role in two-phase pipe flow models.In this paper we apply the fractional flow theory to multiphase flow in pipes and present a unified modeling framework for predicting the fluid phase volume fractions over a broad range of pipe flow conditions.Compared to existing methods and correlations,this new framework provides a simple,approximate,and efficient way to estimate the phase volume fraction in two-phase pipe flow without invoking flow patterns.Notably,existing correlations for estimating phase volume fraction can be transformed and expressed under this modeling framework.Different fractional flow models are applicable to different flow conditions,and they demonstrate good agreement against experimental data within 5%errors when compared with an experimental database comprising of 2754 data groups from 14literature sources,covering various pipe geometries,flow patterns,fluid properties and flow inclinations.The gas void fraction predicted by the framework developed in this work can be used as inputs to reliably model the hydraulic and thermal behaviors of two-phase pipe flows.

Investigation on the performance of a helico-axial multiphase pump under slug flow

The helico-axial multiphase pump is often used for gas-liquid mixture transportation in offshore oilfields,and slug flow is the main reason for the unstable operation of the pump.Aimed for slug flow condition,a self-designed three-stage multiphase pump is set to the object to perform unsteady simulations and fluid-structure interaction calculations,and the inlet gas void fraction(IGVF)is set from 20%to 80%.The results show that affected by the flow from the slug,the gas-liquid two-phase flow pattern in the multiphase pump changes sharply,resulting in severe fluctuations in the differential pressure,spindle torque and deformation of the multiphase pump.The gas-phase enters the first-impeller along the suction blade surface when affected by Taylor bubbles,while the second and third-stage impellers gas-phases are in the form of small air masses flow into the impeller along the pressure blade surface.The deformation trend of impeller torque,differential pressure and the main pump spindle is similar to that of trigonometric function,while the fluctuation of torque is more intense,and the shape variable of spindle increases with the inflow of liquid plug,and the maximum deformation amount increases by10.9%at high GVF relative to IGVF.

Pressure fluctuation characteristics in the pressurization unit of a multiphase pump

The tip clearance induces the tip leakage vortex(TLV),which has a great impact on the pressure fluctuation characteristics of the multiphase pump.To investigate the effect of the tip clearance on the pressure fluctuations,based on the Reynolds time-averaged Navier-Stokes equation and the shear stress transfer(SST)k-ωturbulence model,the three-dimensional turbulent flow in the pump is numerically simulated for different tip clearances in the water and gas-liquid two-phase cases by using the ANSYS CFX software and the results are verified with experimental data.It is shown the greater pressure fluctuation intensity corresponds with the TLV both in the water and gas-liquid two-phase cases.In the meantime,the location of the maximum pressure fluctuation intensity is related to the tip clearance size.In addition,for different tip clearances,the pressure fluctuation intensity with the rotor and stator interaction(RSI)is relatively larger.The difference is that when R_(tc)=1.5 mm,the pressure fluctuation intensity near the impeller middle point is also relatively larger.On the whole,the pressure fluctuation intensity in the gas-liquid two-phase case is larger than that in the water case.Furthermore,the gas causes the frequency of the high-amplitude pressure fluctuation in the impeller and the diffuser to be shifted from 7 f_(n)(f_(n) denotes impeller rotational frequency)and 3 f_(n) to the low-frequency region,respectively.The pressure fluctuations at the blade-passing frequency(BPF)and the multiple BPFs gradually disappear.Meanwhile,the amplitude at the dominant frequency in the gas-liquid two-phase case is at least one order of magnitude smaller than that in the water case,and the peak-to-peak value of the pressure fluctuation is also much smaller.