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
The cracking behaviour of X-70 pipeline steel in near-neutral pH solutions was studied under different modes of cyclic loading. The crack propagation process of X-70 pipeline steel under low frequency cyclic loading c...The cracking behaviour of X-70 pipeline steel in near-neutral pH solutions was studied under different modes of cyclic loading. The crack propagation process of X-70 pipeline steel under low frequency cyclic loading condition was controlled mainly by stress corrosion cracking （SCC） mechanism. Under mixed-mode cyclic loading, both higher tensile stress and shear stress made cracks easier to propagate. Applied cathodic potentials and high content of carbon dioxide in solutions also promoted the propagation of cracks. The propagation directions of cracks were different under different cyclic loading conditions. Under mode I （pure tensile stress） cyclic loading condition, cracks were straight and perpendicular to the tensile stress axis, while under mixed-mode 1/111 （tensile/shear stress） cyclic loading,cracks were sinuous and did not propagate in the direction perpendicular to the main tensile stress axis. Under the mixed-mode cyclic loading, cracks were much easier to propagate, suggesting that shear stress intensified the role of tensile stress. In addition, shear stress promoted the interaction between cracks, resulting in easier coalescence of cracks.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This work was supported by the Special Funds for the Major State Basic Research Projects in China(No.G19990650)also supported by the Science and Technology Comm is—sion of Shanghai Municipality(Projects Nos.025258036 and 02ZE14031
文摘The cracking behaviour of X-70 pipeline steel in near-neutral pH solutions was studied under different modes of cyclic loading. The crack propagation process of X-70 pipeline steel under low frequency cyclic loading condition was controlled mainly by stress corrosion cracking （SCC） mechanism. Under mixed-mode cyclic loading, both higher tensile stress and shear stress made cracks easier to propagate. Applied cathodic potentials and high content of carbon dioxide in solutions also promoted the propagation of cracks. The propagation directions of cracks were different under different cyclic loading conditions. Under mode I （pure tensile stress） cyclic loading condition, cracks were straight and perpendicular to the tensile stress axis, while under mixed-mode 1/111 （tensile/shear stress） cyclic loading,cracks were sinuous and did not propagate in the direction perpendicular to the main tensile stress axis. Under the mixed-mode cyclic loading, cracks were much easier to propagate, suggesting that shear stress intensified the role of tensile stress. In addition, shear stress promoted the interaction between cracks, resulting in easier coalescence of cracks.
