Flow pattern identification of gas-liquid two-phase flow using dual-modality sensor

Gas-liquid two-phase flow is widely encountered in industrial processes, and accurate flow pattern recognition is of great significance to process monitoring and control. The traditional methods of flow pattern recognition are usually based on extracting a single sensor signal feature, and the calculation steps too complicated for online recognition. In this paper, a method to fuse conductance and pulsed wave ultrasonic echoes for flow pattern recognition is presented. Water holdup and its variance extracted from conductance sensor indicate different flow patterns’ characteristics and gas-liquid interface information is obtained based on the energy of pulsed-wave ultrasonic echoes. The extracted features are simple to compute and can meet the requirements of online flow pattern recognition. The results show that the fusion of these two sensors can identify flow pattern with an accuracy of 93.0%.