Intelligent Image-Based Gas-Liquid Two-Phase Flow Regime Recognition

Abstract

Identification of different flow regimes in industrial systems operating under two-phase flow conditions is necessary in order to safely design and optimize their performance. In the present work, experiments on two-phase flow have been performed in a large scale test facility with the length of 6 m and diameter of 5 cm. Four main flow regimes have been observed in vertical air-water two-phase flow at moderate superficial velocities of gas and water namely: Bubbly, Slug, Churn, and Annular. An image processing technique was used to extract information from each picture. This information includes the number of bubbles or objects, area, perimeter, as well as the height and width of objects (second phase). In addition, a texture feature extraction procedure was applied to images of different regimes. Some features which were adequate for regime identification were extracted such as contrast, energy, entropy, etc. To identify flow regimes, a fuzzy interface was introduced using characteristic of second phase in picture. Furthermore, an Adaptive Neuro Fuzzy (ANFIS) was used to identify flow patterns using textural features of images. The experimental results show that these methods can accurately identify the flow patterns in a vertical pipe.