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
Based on the assumption of gas-liquid stratified flow pattern in inclined gas wells,considering the influence of wettability and surface tension on the circumferential distribution of liquid film along the wellbore wa...Based on the assumption of gas-liquid stratified flow pattern in inclined gas wells,considering the influence of wettability and surface tension on the circumferential distribution of liquid film along the wellbore wall,the influence of the change of the gas-liquid interface configuration on the potential energy,kinetic energy and surface free energy of the two-phase system per unit length of the tube is investigated,and a new model for calculating the gas-liquid distribution at critical conditions is developed by using the principle of minimum energy.Considering the influence of the inclination angle,the calculation model of interfacial friction factor is established,and finally closed the governing equations.The interface shape is more vulnerable to wettability and surface tension at a low liquid holdup,resulting in a curved interface configuration.The interface is more curved when the smaller is the pipe diameter,or the smaller the liquid holdup,or the smaller the deviation angle,or the greater gas velocity,or the greater the gas density.The critical liquid-carrying velocity increases nonlinearly and then decreases with the increase of inclination angle.The inclination corresponding to the maximum critical liquid-carrying velocity increases with the increase of the diameter of the wellbore,and it is also affected by the fluid properties of the gas phase and liquid phase.The mean relative errors for critical liquid-carrying velocity and critical pressure gradient are 1.19%and 3.02%,respectively,and the misclassification rate is 2.38%in the field trial,implying the new model can provide a valid judgement on the liquid loading in inclined gas wells.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Supported by National Natural Science Foundation of China(21978171)。
文摘Based on the assumption of gas-liquid stratified flow pattern in inclined gas wells,considering the influence of wettability and surface tension on the circumferential distribution of liquid film along the wellbore wall,the influence of the change of the gas-liquid interface configuration on the potential energy,kinetic energy and surface free energy of the two-phase system per unit length of the tube is investigated,and a new model for calculating the gas-liquid distribution at critical conditions is developed by using the principle of minimum energy.Considering the influence of the inclination angle,the calculation model of interfacial friction factor is established,and finally closed the governing equations.The interface shape is more vulnerable to wettability and surface tension at a low liquid holdup,resulting in a curved interface configuration.The interface is more curved when the smaller is the pipe diameter,or the smaller the liquid holdup,or the smaller the deviation angle,or the greater gas velocity,or the greater the gas density.The critical liquid-carrying velocity increases nonlinearly and then decreases with the increase of inclination angle.The inclination corresponding to the maximum critical liquid-carrying velocity increases with the increase of the diameter of the wellbore,and it is also affected by the fluid properties of the gas phase and liquid phase.The mean relative errors for critical liquid-carrying velocity and critical pressure gradient are 1.19%and 3.02%,respectively,and the misclassification rate is 2.38%in the field trial,implying the new model can provide a valid judgement on the liquid loading in inclined gas wells.
