Skip to Main Content
In this paper, a novel approach is presented to the measurement of wet gas flows by using a throat-extended Venturi meter (TEVM) and soft-computing approximation techniques. Results obtained by using an industrial-scale test rig suggest that the flow rate of wet gas flowing in the TEVM is related not only to the static features but also to the dynamic features of the differential pressures (DPs) across the converging and the extended throat sections of the Venturi meter, as well as the static pressure and temperature signals within the Venturi meter. The relation between the signal features and the gas/liquid flow rates of wet gas is established through the use of backpropagation (BP) artificial neural network (ANN) and support vector machine (SVM) approximation techniques. The experimental test carried out within static pressure range of 0.3-0.8 MPa, gas flow rate range of 0.0139-0.0444 m3/s, and liquid flow rate range of 3.0556 × 10-4-0.0015 m3/s suggested that it is a cost-effective and viable method to solve the problem of wet gas metering by combining a revised Venturi meter and soft-computing approximation techniques.