The identification of flow pattern is a basic and important issue in multiphase systems. Because of the complexity of phase interaction in gas-liquid two-phase flow, it is difficult to discern its flow pattern objectively. In this paper, we make a systematic study on the vertical upward gas-liquid two-phase flow using complex network. Three unique network construction methods are proposed to build three types of networks, i.e., flow pattern complex network (FPCN), fluid dynamic complex network (FDCN), and fluid structure complex network (FSCN). Through detecting the community structure of FPCN by the community-detection algorithm based on -mean clustering, useful and interesting results are found which can be used for identifying five vertical upward gas-liquid two-phase flow patterns. To investigate the dynamic characteristics of gas-liquid two-phase flow, we construct 50 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 gas-liquid two-phase flow. Furthermore, we construct FSCN and demonstrate how network statistic can be used to reveal the fluid structure of gas-liquid two-phase flow. In this paper, from a different perspective, we not only introduce complex network theory to the study of gas-liquid two-phase flow but also indicate that complex network may be a powerful tool for exploring nonlinear time series in practice.
Characterizing complex patterns arising from horizontal oil-water two-phase flows is a contemporary and challenging problem of paramount importance. We design a new multisector conductance sensor and systematically carry out horizontal oil-water two-phase flow experiments for measuring multivariate signals of different flow patterns. We then infer multivariate recurrence networks from these experimental data and investigate local cross-network properties for each constructed network. Our results demonstrate that a cross-clustering coefficient from a multivariate recurrence network is very sensitive to transitions among different flow patterns and recovers quantitative insights into the flow behavior underlying horizontal oil-water flows. These properties render multivariate recurrence networks particularly powerful for investigating a horizontal oil-water two-phase flow system and its complex interacting components from a network perspective.
21 February 2024 in IEEE Transactions on Industrial Informatics
Complex network has been a powerful tool for time series analysis by encoding dynamical temporal information in network topology. In this article, we introduce a framework to build a bridge between complex network and artificial intelligence for chaotic time series analysis. First, the chaotic time series are transformed to graph signals by phase space embedding. Then, the node information has been aggregated along the links through a cutting-edge technology termed graph convolutional network. We tested this method in the typical chaos system, and the phase space graph convolutional network (PSGCN) achieves better performance in the system control parameter prediction. To validate it in practical application, PSGCN is utilized in the flow-parameter prediction of gas-liquid two phase flow. The result indicates that complex network combined with graph convolutional network provide a potential perspective for exploring chaotic time series in practice.
Deep learning (DL) has dramatically improved the peak-to-average power ratio (PAPR) performance. However, the high computational complexity and excessive training data constitute a significant hurdle. In this letter, a model-driven deep learning algorithm is proposed for PAPR reduction in orthogonal frequency division multiplexing (OFDM) system. Precisely, an iterative peak-canceling signal generation scheme is unfolded as a layer structure of the DL network. The scheme falls into the category of tone reservation technique. A set of trainable parameters, which optimizes the clipping threshold and weights time-domain kernel function, has been designed and introduced into the iterative scheme. Compared with the existing approaches, the simulation results demonstrate that the proposed algorithm achieves comparable PAPR performance with low complexity and training costs.
31 December 2013 in Experimental Thermal and Fluid Science
A novel coaxial three-electrode distributed conductance sensor (CTDCS) is proposed to achieve salinity and oil content independent measurement of liquid film thickness in multiphase slug flow. Conductance sensor obtains liquid film thickness by measuring the conductance between electrodes. However, the conductance depends on the liquid film thickness and the liquid conductivity. For gas-water and oil-gas-water flows in industrial process, the variations of salinity and oil content of liquid phase change the liquid conductivity. This will seriously affects the measurement of liquid film thickness using conventional two-electrode sensor. Owing to its novel three-electrode configuration, the proposed CTDCS can overcome the problem mentioned above. The optimal geometry of CTDCS are determined by exhaustive search using finite element method, and the electronic circuit suitable for the condition of conductivity variation is investigated. The ratio of two-channel outputs which is independent of conductivity is acquired and its relationship with the liquid film thickness is established. The advantages of the CTDCS are that it can on-line compensate conductivity variations, and acquire the circumferential distribution of liquid film thicknesses. Hence, salinity and oil content independent measurement of liquid film thickness is realized for the first time.