Fuzzy Recognition for Gas-liquid Two-phase Flow Pattern Based on Image Processing

Abstract

In order to identify the flow pattern automatically and accurately, a new identification method was developed. Flow images were captured by a high speed CCD in a horizontal pipe. The characteristics of bubbles such as area, width and height were obtained using image processing techniques. First, a fuzzy reasoning method was used to identify stratified flow and annular flow. Then a fuzzy neural network was used to identify the flow pattern of bubbly, slug and plug. Levenberg-Marquart optimized algorithm was used to learn the network, and its constringency is rapid. The experimental results show that the fuzzy method can accurately identify the flow patterns in a horizontal pipe.

Metrological evaluation of a 3D electrical capacitance tomography measurement system for two-phase flow fraction determination

“…Hence every ECT image (2D or 3D) can be freely treated as an already spatial fuzzy set, where each pixel/voxel can be described in terms such as 'this point seems to be more gas than liquid'. There were a few earlier research works in this field, with use of fuzzy logic (Shi 2008) and without use of fuzzy logic Zhang 2009, Zhou et al 2008); however only one research work (Li et al 1992) considers the spatial nature of the sensor. According to the current state-of-the-art, this is a pioneer research in flow pattern recognition concerning combination of fuzzy logic and volumetric 3D ECT images.…”

Convolutional neural network-based pattern recognition in natural circulation instability images

“…Several studies have focused on investigating two-phase flow in natural circulation using artificial intelligence techniques, such as Fuzzy Logic (de Mesquita et al, 2012;Ghanbarzadeh et al, 2012;Shi, 2007), as well as traditional machine learning methods based on feature extraction. These include Principal Component Analysis (PCA), Support Vector Machine (SVM) (Huang et al, 2011;Shanthi and Pappa, 2017;Xiao et al, 2018).…”