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 t...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.展开更多
In order to investigate the influence of the entrance effect on the spatial distribution of phases, the experiments on gas-liquid two-phase slug flow in a vertical pipe of 0.03m ID were carried out by using optical pr...In order to investigate the influence of the entrance effect on the spatial distribution of phases, the experiments on gas-liquid two-phase slug flow in a vertical pipe of 0.03m ID were carried out by using optical probes and an EKTAPRO 1000 high speed motion analyzer. It demonstrates that the radial profile of slug flow void fraction is parabolic. Influenced by the falling liquid film, the radial profile curve of liquid slug void fraction in the wake region is also parabolic. Since fully turbulent velocity distribution is built up in the developed region,the void fraction profile in this region is the saddle type. At given superficial liquid velocity, the liquid slug void fraction increases with gas velocity. The radial profiles of liquid slug void fraction at different axial locations are all saddle curves, but void fraction is obviously high around the centerline in the entrance region. The nearer the measuring station is from the entrance, the farther the peak location is away from the wall.展开更多
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 w...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.展开更多
基金supported by the National Natural Science Foundation of China under Grants 61922062 and 61873181。
文摘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.
文摘In order to investigate the influence of the entrance effect on the spatial distribution of phases, the experiments on gas-liquid two-phase slug flow in a vertical pipe of 0.03m ID were carried out by using optical probes and an EKTAPRO 1000 high speed motion analyzer. It demonstrates that the radial profile of slug flow void fraction is parabolic. Influenced by the falling liquid film, the radial profile curve of liquid slug void fraction in the wake region is also parabolic. Since fully turbulent velocity distribution is built up in the developed region,the void fraction profile in this region is the saddle type. At given superficial liquid velocity, the liquid slug void fraction increases with gas velocity. The radial profiles of liquid slug void fraction at different axial locations are all saddle curves, but void fraction is obviously high around the centerline in the entrance region. The nearer the measuring station is from the entrance, the farther the peak location is away from the wall.
基金financial support from the Energize Program between the University of Texas at Austin and Southwest Research InstituteHydraulic Fracturing and Sand Control Industrial Affiliates Program at the University of Texas at Austin for financially supporting this research。
文摘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.
