Fusion of three-dimensional electrical capacitance tomography and fuzzy logic inference for phases fraction and flow structures identification in horizontal and vertical gas-liquid flow pipelines
R. Banasiaka, R. Wajmana, H. Fidosb, T. Jaworskia, P. Fidereka, P. Kapustaa,
M. Majchrowicza, D. Sankowskia
aInstitute of Applied Computer Science, Lodz University of Technology, Poland
bDepartment of Chemical Engineering, Lodz University of Technology, Poland
From variety of industry-oriented imaging solutions the electrical capacitance tomography applied to the two-phase gas- liquid mixtures visualization and the phase distribution calculation is getting popular. Especially, when flow key parameters are required by industrial applications. These flow key parameters particularly include an efficient and non-invasive automatic phase fraction calculation and flow structure identification for vertical and horizontal pipelines. Nowadays this problem can be solved by using non-deterministic fuzzy-logic based techniques for analysis of volumetric images. This study presents the automated two-phase gas-liquid flow pattern identification process based on the fuzzy evaluation of series of reconstructed ECT volumetric images. The set of volume data is obtained by using the 3D ECT hardware and non-linear image reconstruction algorithms. Finally the set of fuzzy-based features is calculated for flow classification. As the result of this analysis obtained features are used to classify given volumetric image into one of known flow regime structures.
Keywords: two-phase flow, 3D capacitance tomography, flow regime identification, fuzzy-based flow classification
Copyright © International Society for Industrial Process Tomography, 2013. All rights reserved.