Identification Method of Gas-Liquid Two-Phase Flow Regime Based on Image Moment Invariants and SVM

摘要

Gas-liquid two-phase flow widely exists in modern industry production. The accurate measurement of other parameters and the performance character of two-phase flow are influenced by the flow regimes. So the identification of different flow regimes has long been a signification topic in the parameter measurement of two-phase system. A Gas-liquid two-phase flow regime identification method based on image moment invariants features and support vector machine was proposed. Gas-liquid two-phase flow images including bubbly flow, plug flow, slug flow, stratified flow, wavy flow, annular flow and mist flow were captured by digital high speed video systems in the horizontal tube. The image moment invariants eigenvectors were extracted using image processing techniques. The support vector machine was trained using these eigenvectors as flow regime samples, and the flow regime intelligent identification was realized. The test results show that image moment invariants features can excellently reflect the difference between seven typical flow regimes, and successful training the support vector machine can quickly and accurately identify seven typical flow regimes of gas-liquid two-phase flow in the horizontal tube. The whole identification accuracy is 100%, and an estimation of the processing time for each image is 0.8s for online flow regime identification of a new and effective method.