Identification of two-phase flow regimes based on support vector machine and electrical capacitance tomography

It is important to identify two-phase flow regimes for the accuracy measurement of other flow parameters. Electrical capacitance tomography (ECT) is often used to identify two-phase/multi-phase flow regimes. The support vector machine (SVM) is a machine-learning algorithm based on the statistical learning theory, which has desirable classification ability with fewer training samples, and can be used for flow regime identification. The capacitance measurement data obtained from an ECT system contain flow regime information. The principal component analysis method has been used to reduce the dimension of the capacitance measurements. Simulation was carried out using the SVM method. The results show its feasibility. Static and dynamic experiments were also done for typical flow regimes, and the results indicate that this method is fast in speed and can identify these flow regimes correctly