A novel complex network-based deep learning method for characterizing gas–liquid two-phase flow

Abstract

Gas-liquid two-phase flow widely exits in production and transportation of petroleum industry. Characterizing gas-liquid flow and measuring flow parameters represent challenges of great importance, which contribute to the recognition of flow regime and the optimal design of industrial equipment. In this paper, we propose a novel complex network-based deep learning method for characterizing gas-liquid flow. Firstly, we map the multichannel measurements to multiple limited penetrable visibility graphs (LPVGs) and obtain their degree sequences as the graph representation. Based on the degree distribution, we analyze the complicated flow behavior under different flow structures. Then, we design a dual-input convolutional neural network to fuse the raw signals and the graph representation of LPVGs for the classification of flow structures and measurement of gas void fraction. We implement the model with two parallel branches with the same structure, each corresponding to one input. Each branch consists of a channel-projection convolutional part, a spatial-temporal convolutional part, a dense block and an attention module. The outputs of the two branches are concatenated and fed into several full connected layers for the classification and measurement. At last, our method achieves an accuracy of 95.3% for the classification of flow structures, and a mean squared error of 0.0038 and a mean absolute percent error of 6.3% for the measurement of gas void fraction. Our method provides a promising solution for characterizing gas-liquid flow and measuring flow parameters.

Machine learning for soft and liquid molecular materials

“…Using graph files as inputs, Gao et al classified samples by flow structure via convolutional neural networks. 88 Two convolutional neural networks were used to classify 6 flow structures and void fraction (Fig. 9a).…”

Gas–Liquid Two-Phase Flow Measurement Based on Optical Flow Method with Machine Learning Optimization Model

“…Zhongke Gao et al [12] designed a branch-aggregation network (BAN) for classifying flow patterns in gas-liquid two-phase flow images, achieving a fast convergence speed and a recognition accuracy of 99.60%, highlighting its advantage in noise resistance. Zhong-Ke Gao et al [13] proposed a deep learning method based on complex networks that combined the original signals of limited penetrable visibility graphs (LPVG) with images for flow pattern classification and gas void fraction measurement. Their results showed a classification accuracy of 95.3% and an average root mean square error (RMSE) of 0.0038, with an average absolute percentage error of 6.3% for gas void fraction measurement.…”

Research on Slug Flow Elimination Method Based on Kinetic Energy Conversion

“…The purpose of this study is to eliminate or weaken the slug flow and provide a stable flow pattern for gasliquid two-phase measurements while increasing the stability of the instrument operation. Based on the principle of kinetic energy conversion and turbulent diffusion [21], a new slug flow elimination method is put forward to change the distribution pattern of gas and liquid phases [22]. This method can effectively reduce the slug flow frequency and achieve the purpose of weakening or eliminating the slug flow.…”