Complex networks have established themselves in recent years as being particularly suitable and flexible for representing and modelling many complex natural and artificial systems. Oil-water two-phase flow is one of t...Complex networks have established themselves in recent years as being particularly suitable and flexible for representing and modelling many complex natural and artificial systems. Oil-water two-phase flow is one of the most complex systems. In this paper, we use complex networks to study the inclined oil water two-phase flow. Two different complex network construction methods are proposed to build two types of networks, i.e. the flow pattern complex network (FPCN) and fluid dynamic complex network (FDCN). Through detecting the community structure of FPCN by the community-detection algorithm based on K-means clustering, useful and interesting results are found which can be used for identifying three inclined oil-water flow patterns. To investigate the dynamic characteristics of the inclined oil-water two-phase flow, we construct 48 FDCNs under different flow conditions, and find that the power-law exponent and the network information entropy, which are sensitive to the flow pattern transition, can both characterize the nonlinear dynamics of the inclined oil-water two-phase flow. In this paper, from a new perspective, we not only introduce a complex network theory into the study of the oil-water two-phase flow but also indicate that the complex network may be a powerful tool for exploring nonlinear time series in practice.展开更多
We generate a directed weighted complex network by a method based on Markov transition probability to represent an experimental two-phase flow. We first systematically carry out gas-liquid two-phase flow experiments f...We generate a directed weighted complex network by a method based on Markov transition probability to represent an experimental two-phase flow. We first systematically carry out gas-liquid two-phase flow experiments for measuring the time series of flow signals. Then we construct directed weighted complex networks from various time series in terms of a network generation method based on Markov transition probability. We find that the generated network inherits the main features of the time series in the network structure. In particular, the networks from time series with different dynamics exhibit distinct topological properties. Finally, we construct two-phase flow directed weighted networks from experimental signals and associate the dynamic behavior of gas-liquid two-phase flow with the topological statistics of the generated networks. The results suggest that the topological statistics of two-phase flow networks allow quantitative characterization of the dynamic flow behavior in the transitions among different gas-liquid flow patterns.展开更多
The flow pattern in a pipeline is a very important topic in petroleum exploitation. This paper is to classify the flow pattern of oil-gas-water flow in a pipeline by using BP neural network. The effects of different p...The flow pattern in a pipeline is a very important topic in petroleum exploitation. This paper is to classify the flow pattern of oil-gas-water flow in a pipeline by using BP neural network. The effects of different parameter combinations are investigated to find the most important ones. It is shown that BP neural network can be used in the analysis of the flow pattern of three-phase flow in pipelines. In most cases, the mean square error is large for the horizontal pipes. The optimized neuron number of the middle layer changes with conditions. So, we must changes the neuron number of the middle layer in simulation for any conditions to seek the best results. These conclusions can be taken as references for further study of the flow pattern of oil-gas-water in a pipeline.展开更多
界面面积浓度(Interfacial Area Concentration,IAC)是两相流动的封闭两流体模型中界面传递项的关键参数,用于表征气液界面传输能力的强弱。对界面面积浓度的建模预测通常有经验关联式和界面面积输运方程等方法,但这些方法都有较大的数...界面面积浓度(Interfacial Area Concentration,IAC)是两相流动的封闭两流体模型中界面传递项的关键参数,用于表征气液界面传输能力的强弱。对界面面积浓度的建模预测通常有经验关联式和界面面积输运方程等方法,但这些方法都有较大的数据依赖性。而对神经网络模型增添可解释性可以为模型修正提供方向,严谨提升预测精度。为更好地预测两相流动的IAC,基于神经网络建立了IAC的预测模型,结合不同气泡行为、物理关系及统计分布并利用事后可解释性方法,对比分析了不同输入特征组合的神经网络模型预测能力;并通过神经网络每层的结构参数大小,分析输出比重挑选合适的数据预处理方法。通过事后可解释性分析得到空泡份额是IAC预测的重要因素,而对训练数据进行对数变换预处理能够显著提高模型对真实数据的预测能力。展开更多
The knowledge of flow regimes is very important in the study of a two phase flow system. A new flow regime identification method based on a Probability Density Function (PDF) and a neural network is proposed in this...The knowledge of flow regimes is very important in the study of a two phase flow system. A new flow regime identification method based on a Probability Density Function (PDF) and a neural network is proposed in this paper. The instantaneous differential pressure signals of a horizontal flow were acquired with a differential pressure sensor. The characters of differential pressure signals for different flow regimes are analyzed with the PDF. Then, four characteristic parameters of the PDF curves are defined, the peak number (K 1 ), the maximum peak value (K 2 ), the peak position (K 3 ) and the PDF variance (K 4 ). The characteristic vectors which consist of the four characteristic parameters as the input vectors train the neural network to classify the flow regimes. Experimental results show that this novel method for identifying air water two phase flow regimes has the advantages with a high accuracy and a fast response. The results clearly demonstrate that this new method could provide an accurate identification of flow regimes.展开更多
基金Project supported by the National Natural Science Foundation of China (Grant Nos 50674070 and 60374041)the National High Technology Research and Development Program of China (Grant No 2007AA06Z231)
文摘Complex networks have established themselves in recent years as being particularly suitable and flexible for representing and modelling many complex natural and artificial systems. Oil-water two-phase flow is one of the most complex systems. In this paper, we use complex networks to study the inclined oil water two-phase flow. Two different complex network construction methods are proposed to build two types of networks, i.e. the flow pattern complex network (FPCN) and fluid dynamic complex network (FDCN). Through detecting the community structure of FPCN by the community-detection algorithm based on K-means clustering, useful and interesting results are found which can be used for identifying three inclined oil-water flow patterns. To investigate the dynamic characteristics of the inclined oil-water two-phase flow, we construct 48 FDCNs under different flow conditions, and find that the power-law exponent and the network information entropy, which are sensitive to the flow pattern transition, can both characterize the nonlinear dynamics of the inclined oil-water two-phase flow. In this paper, from a new perspective, we not only introduce a complex network theory into the study of the oil-water two-phase flow but also indicate that the complex network may be a powerful tool for exploring nonlinear time series in practice.
基金Project supported by the National Natural Science Foundation of China ( Grant Nos. 61104148, 41174109, and 50974095)the National Science and Technology Major Project of the Ministry of Science and Technology of China (Grant No. 2011ZX05020-006)the Specialized Research Fund for the Doctoral Program of Higher Education of China (Grant No. 20110032120088)
文摘We generate a directed weighted complex network by a method based on Markov transition probability to represent an experimental two-phase flow. We first systematically carry out gas-liquid two-phase flow experiments for measuring the time series of flow signals. Then we construct directed weighted complex networks from various time series in terms of a network generation method based on Markov transition probability. We find that the generated network inherits the main features of the time series in the network structure. In particular, the networks from time series with different dynamics exhibit distinct topological properties. Finally, we construct two-phase flow directed weighted networks from experimental signals and associate the dynamic behavior of gas-liquid two-phase flow with the topological statistics of the generated networks. The results suggest that the topological statistics of two-phase flow networks allow quantitative characterization of the dynamic flow behavior in the transitions among different gas-liquid flow patterns.
文摘The flow pattern in a pipeline is a very important topic in petroleum exploitation. This paper is to classify the flow pattern of oil-gas-water flow in a pipeline by using BP neural network. The effects of different parameter combinations are investigated to find the most important ones. It is shown that BP neural network can be used in the analysis of the flow pattern of three-phase flow in pipelines. In most cases, the mean square error is large for the horizontal pipes. The optimized neuron number of the middle layer changes with conditions. So, we must changes the neuron number of the middle layer in simulation for any conditions to seek the best results. These conclusions can be taken as references for further study of the flow pattern of oil-gas-water in a pipeline.
文摘界面面积浓度(Interfacial Area Concentration,IAC)是两相流动的封闭两流体模型中界面传递项的关键参数,用于表征气液界面传输能力的强弱。对界面面积浓度的建模预测通常有经验关联式和界面面积输运方程等方法,但这些方法都有较大的数据依赖性。而对神经网络模型增添可解释性可以为模型修正提供方向,严谨提升预测精度。为更好地预测两相流动的IAC,基于神经网络建立了IAC的预测模型,结合不同气泡行为、物理关系及统计分布并利用事后可解释性方法,对比分析了不同输入特征组合的神经网络模型预测能力;并通过神经网络每层的结构参数大小,分析输出比重挑选合适的数据预处理方法。通过事后可解释性分析得到空泡份额是IAC预测的重要因素,而对训练数据进行对数变换预处理能够显著提高模型对真实数据的预测能力。
基金Project supported by the National High Technology and Research Development Program Special Fund of China (GrantNo: 2002AA616050).
文摘The knowledge of flow regimes is very important in the study of a two phase flow system. A new flow regime identification method based on a Probability Density Function (PDF) and a neural network is proposed in this paper. The instantaneous differential pressure signals of a horizontal flow were acquired with a differential pressure sensor. The characters of differential pressure signals for different flow regimes are analyzed with the PDF. Then, four characteristic parameters of the PDF curves are defined, the peak number (K 1 ), the maximum peak value (K 2 ), the peak position (K 3 ) and the PDF variance (K 4 ). The characteristic vectors which consist of the four characteristic parameters as the input vectors train the neural network to classify the flow regimes. Experimental results show that this novel method for identifying air water two phase flow regimes has the advantages with a high accuracy and a fast response. The results clearly demonstrate that this new method could provide an accurate identification of flow regimes.