The liquid loading is one of the most frequently encountered phenomena in the transportation of gas pipeline,reducing the transmission efficiency and threatening the flow assurance.However,most of the traditional mech...The liquid loading is one of the most frequently encountered phenomena in the transportation of gas pipeline,reducing the transmission efficiency and threatening the flow assurance.However,most of the traditional mechanism models are semi-empirical models,and have to be resolved under different working conditions with complex calculation process.The development of big data technology and artificial intelligence provides the possibility to establish data-driven models.This paper aims to establish a liquid loading prediction model for natural gas pipeline with high generalization ability based on machine learning.First,according to the characteristics of actual gas pipeline,a variety of reasonable combinations of working conditions such as different gas velocity,pipe diameters,water contents and outlet pressures were set,and multiple undulating pipeline topography with different elevation differences was established.Then a large number of simulations were performed by simulator OLGA to obtain the data required for machine learning.After data preprocessing,six supervised learning algorithms,including support vector machine(SVM),decision tree(DT),random forest(RF),artificial neural network(ANN),plain Bayesian classification(NBC),and K nearest neighbor algorithm(KNN),were compared to evaluate the performance of liquid loading prediction.Finally,the RF and KNN with better performance were selected for parameter tuning and then used to the actual pipeline for liquid loading location prediction.Compared with OLGA simulation,the established data-driven model not only improves calculation efficiency and reduces workload,but also can provide technical support for gas pipeline flow assurance.展开更多
Lauramine is widely considered to be an asphaltene flocculant,but its effect on the modification of crude oil by PPDs has been little studied.In this paper,the effect of LA dosage on the rheology improvement of EVA PP...Lauramine is widely considered to be an asphaltene flocculant,but its effect on the modification of crude oil by PPDs has been little studied.In this paper,the effect of LA dosage on the rheology improvement of EVA PPDs(100 ppm)on Qinghai waxy crude oil was investigated through rheological measurement,wax precipitating analysis,granularity test and resins/asphaltenes FTIR analysis.Compared with pure EVA,the compounding of LA and EVA obviously enhances the agglomeration degree and reduces the number of fine wax crystals,thus further enhancing the rheology of the oil samples,and the best performance is at the LA dosage of 200 ppm.At relatively small LA dosages,the LA facilitates the adsorption of EVA molecules on the asphaltene surfaces,which favors the becoming of EVA/asphaltenes composite particles;but at relatively high LA dosages,the LA makes the asphaltenes more aggregated and disturbs the EVA adsorption on the asphaltenes,which is adverse for the formation of EVA/asphaltenes compound particles.The compound particles can serve as wax precipitating templates and significantly influence its morphology,thus further improving the crude oil rheology.In consequence,the rheology improvement of EVA PPDs on Qinghai waxy crude oil first increases and then decreases with increasing the LA dosage.展开更多
Transportation of heavy oil by the so-called water-ring technique is a very promising method by which pressure drop and pollution can be significantly reduced.Dedicated experiments have been carried out by changing th...Transportation of heavy oil by the so-called water-ring technique is a very promising method by which pressure drop and pollution can be significantly reduced.Dedicated experiments have been carried out by changing the phase’s density,viscosity,velocity and interfacial tension to systematically analyze the characteristics of the water ring.On the basis of such experimental data,a mathematical model for pressure drop prediction has been introduced.This research shows that as long as the density of oil and water remains the same,a concentric water ring can effectively be formed.In such conditions,the oil-water viscosity difference has little effect on the shape of water ring,and it only affects the pressure drop.The greater the viscosity of heavy oil,the smaller the pressure drop of the oil-water ring transportation system.The influence of phases’interfacial tension on the characteristics and pressure drop of the heavy oil-water ring can be considered negligible.The pressure drop prediction model introduced on the basis of the Buckingham’s principle provides values in good agreement(95%)with the experimental data.展开更多
Microscopic computed tomography(Micro-CT)is used to visualize microscopic flow in sandstone core samples during emulsion flooding.The images obtained during the experiment are processed quantitatively with a series of...Microscopic computed tomography(Micro-CT)is used to visualize microscopic flow in sandstone core samples during emulsion flooding.The images obtained during the experiment are processed quantitatively with a series of methods to evaluate the occurrence characteristics and oil recovery enhancement mechanisms of emulsion.(1)The emulsion is distributed in the cores in spherical shape,and its sphericity is significantly different from that of the remaining oil.Sphericity can be taken as a characteristic parameter to identify emulsion.(2)The emulsion with specific size prefers to stay in pores with matching sizes;when the emulsion volume is smaller than the product of the lower limit of pore occupancy and the corresponding pore vol-ume,it will not be able to effectively trap in the pore to achieve conformance control.In the process of emulsion displacement designing,we need to design emulsion with suitable particle size according to the pore distribution of the reservoir.(3)Mobi-lization ratio of the pores can be increased from 23.1%to 59.3%by emulsion flooding after subsequent water flooding,and the average oil displacement efficiency at the pore-scale can be increased from 22.9%to 75.8%under the test conditions;(4)After emulsion flooding,the clustered remaining oil and the oil phase in the trapped emulsion are the main targets for further EOR.展开更多
基金supported by the National Science and Technology Major Project of China(2016ZX05066005-001)Zhejiang Province Key Research and Development Plan(2021C03152)Zhoushan Science and Technology Project(2021C21011)
文摘The liquid loading is one of the most frequently encountered phenomena in the transportation of gas pipeline,reducing the transmission efficiency and threatening the flow assurance.However,most of the traditional mechanism models are semi-empirical models,and have to be resolved under different working conditions with complex calculation process.The development of big data technology and artificial intelligence provides the possibility to establish data-driven models.This paper aims to establish a liquid loading prediction model for natural gas pipeline with high generalization ability based on machine learning.First,according to the characteristics of actual gas pipeline,a variety of reasonable combinations of working conditions such as different gas velocity,pipe diameters,water contents and outlet pressures were set,and multiple undulating pipeline topography with different elevation differences was established.Then a large number of simulations were performed by simulator OLGA to obtain the data required for machine learning.After data preprocessing,six supervised learning algorithms,including support vector machine(SVM),decision tree(DT),random forest(RF),artificial neural network(ANN),plain Bayesian classification(NBC),and K nearest neighbor algorithm(KNN),were compared to evaluate the performance of liquid loading prediction.Finally,the RF and KNN with better performance were selected for parameter tuning and then used to the actual pipeline for liquid loading location prediction.Compared with OLGA simulation,the established data-driven model not only improves calculation efficiency and reduces workload,but also can provide technical support for gas pipeline flow assurance.
基金financially supported by the National Natural Science Foundation of China(grant number 51774311,51904327)China Postdoctoral Science Foundation(grant number 2019TQ0354,2019M662468)。
文摘Lauramine is widely considered to be an asphaltene flocculant,but its effect on the modification of crude oil by PPDs has been little studied.In this paper,the effect of LA dosage on the rheology improvement of EVA PPDs(100 ppm)on Qinghai waxy crude oil was investigated through rheological measurement,wax precipitating analysis,granularity test and resins/asphaltenes FTIR analysis.Compared with pure EVA,the compounding of LA and EVA obviously enhances the agglomeration degree and reduces the number of fine wax crystals,thus further enhancing the rheology of the oil samples,and the best performance is at the LA dosage of 200 ppm.At relatively small LA dosages,the LA facilitates the adsorption of EVA molecules on the asphaltene surfaces,which favors the becoming of EVA/asphaltenes composite particles;but at relatively high LA dosages,the LA makes the asphaltenes more aggregated and disturbs the EVA adsorption on the asphaltenes,which is adverse for the formation of EVA/asphaltenes compound particles.The compound particles can serve as wax precipitating templates and significantly influence its morphology,thus further improving the crude oil rheology.In consequence,the rheology improvement of EVA PPDs on Qinghai waxy crude oil first increases and then decreases with increasing the LA dosage.
基金Foundation Projects:Major National R&D Project(2016ZX05025-004-005).
文摘Transportation of heavy oil by the so-called water-ring technique is a very promising method by which pressure drop and pollution can be significantly reduced.Dedicated experiments have been carried out by changing the phase’s density,viscosity,velocity and interfacial tension to systematically analyze the characteristics of the water ring.On the basis of such experimental data,a mathematical model for pressure drop prediction has been introduced.This research shows that as long as the density of oil and water remains the same,a concentric water ring can effectively be formed.In such conditions,the oil-water viscosity difference has little effect on the shape of water ring,and it only affects the pressure drop.The greater the viscosity of heavy oil,the smaller the pressure drop of the oil-water ring transportation system.The influence of phases’interfacial tension on the characteristics and pressure drop of the heavy oil-water ring can be considered negligible.The pressure drop prediction model introduced on the basis of the Buckingham’s principle provides values in good agreement(95%)with the experimental data.
基金Supported by the National Science and Technology Major Project(2017ZX05009-005-003)National Natural Science Foundation of China Funded General Project(52174045)+1 种基金Chinese Academy of Engineering Strategic Consulting Project(2018-XZ-09)China Nation al Petroleum Cor-poration-China University of Petroleum(Beijing)Strategic Cooperation Science and Technology Project(ZLZX2020-01)。
文摘Microscopic computed tomography(Micro-CT)is used to visualize microscopic flow in sandstone core samples during emulsion flooding.The images obtained during the experiment are processed quantitatively with a series of methods to evaluate the occurrence characteristics and oil recovery enhancement mechanisms of emulsion.(1)The emulsion is distributed in the cores in spherical shape,and its sphericity is significantly different from that of the remaining oil.Sphericity can be taken as a characteristic parameter to identify emulsion.(2)The emulsion with specific size prefers to stay in pores with matching sizes;when the emulsion volume is smaller than the product of the lower limit of pore occupancy and the corresponding pore vol-ume,it will not be able to effectively trap in the pore to achieve conformance control.In the process of emulsion displacement designing,we need to design emulsion with suitable particle size according to the pore distribution of the reservoir.(3)Mobi-lization ratio of the pores can be increased from 23.1%to 59.3%by emulsion flooding after subsequent water flooding,and the average oil displacement efficiency at the pore-scale can be increased from 22.9%to 75.8%under the test conditions;(4)After emulsion flooding,the clustered remaining oil and the oil phase in the trapped emulsion are the main targets for further EOR.