Skip to Main Content
Slotted orifice is a new type of flow sensor, and its flow coefficient is insensitive to the upstream velocity profile of single phase flow. It is found that for the gas-liquid two phase flow measurement, especially for the two-phase flow with low liquid fractions, various characteristics of its measured signal are stable and closely correlated with the mass flow rate of gas and liquid. In this paper, the complex relationships between the features and the two-phase flow rate are established through the use of a back propagation neural network. Results obtained from a laboratory test rig so far suggest that the slotted orifice couple with a trained neural network may provide a simple and efficient solution for the development of two-phase flow meter, and the output of neural network is stable and repeatable with the technique of neural network ensemble.