Flow regime identification of mini-pipe gas-liquid two-phase flow based on textural feature series

A method for the identification of gas-liquid two-phase flow regime in mini-pipes is proposed based on textural feature series. A high-speed image acquisition system is used to capture images of gas-liquid two-phase flow in the mini-pipe with inner diameter of 2.8mm, and five typical flow regimes (stratified flow, wavy flow, bubbly flow, slug flow and annular flow) are observed in the experiment. Two textural features (dissimilarity and entropy) of images are extracted by gray level co-occurrence matrix (GLCM). And then the mean value and the standard deviation of the textural feature series are used as the inputs of support vector machine (SVM) to identify the current flow regime. The identification accuracies of the five typical flow regimes are all above 91%. The results show that the method is feasible and effective, and can be used for gas-liquid two phase flow regime identification in mini-pipes.