Characterizing gas-liquid two-phase flow behavior using complex network and deep learning

Gas-liquid two-phase flow is polymorphic and unstable, and characterizing its flow behavior is a major challenge in the study of multiphase flow. We first conduct dynamic experiments on gas-liquid two-phase flow in a vertical tube and obtain multi-channel signals using a self-designed four-sector distributed conductivity sensor. In order to characterize the evolution of gas-liquid two-phase flow, we transform the obtained signals using the adaptive optimal kernel time-frequency representation and build a complex network based on the time-frequency energy distribution. As quantitative indicators, global clustering coefficients of the complex network at various sparsity levels are computed to analyze the dynamic behavior of various flow structures. The results demonstrate that the proposed approach enables effective analysis of multi-channel measurement information for revealing the evolutionary mechanisms of gas-liquid two-phase flow. Furthermore, for the purpose of flow structure recognition, we propose a temporal-spatio convolutional neural network and achieve a classification accuracy of 95.83%.

Automated summary

Gas-liquid two-phase flow is a challenging topic in the study of multiphase flow. In this research, dynamic experiments are conducted using a self-designed four-sector distributed conductivity sensor to obtain multi-channel signals. The adaptive optimal kernel time-frequency representation is used to characterize the evolution of the flow, and a complex network is built based on the time-frequency energy distribution. The results show that this approach allows effective analysis of multi-channel measurement information and reveals the evolutionary mechanisms of gas-liquid two-phase flow. Furthermore, a temporal-spatial convolutional neural network is proposed for flow structure recognition, achieving a classification accuracy of 95.83%.