Identification of two-phase flow regime based on electrical capacitance tomography and soft-sensing technique

Abstract

Two-phase flow is a kind of mixed ambulatory regime which exits widely, such as the oil-gas and oil-water two-phase flow in the petroleum industry, and the gas-solid two-phase flow of the reaction unit of the fluidized bed in the chemical industry. Electrical capacitance tomography (ECT) technique is a new technique for two-phase flow measurement. This paper investigates the identification of flow regimes for gas-liquid two-phase flow using soft-sensing technique which is based on ECT and artificial neural network. Using ECT and artificial neural network technique, an online soft-sensing model used to identify flow regimes of gas-liquid two-phase is built. Using a two-layer self-organizing competitive neural network, a mathematic relationship between the second variable (the character parameters extracted from ECT sensor outputs) and primary variable (the flow regime of gas-liquid two-phase flow) of the soft-sensing model is built. After that, the identification of flow regimes for gas-liquid two-phase flow can be realized. Simulation results show that the proposed method has good identification precision and fast identification speed, which means it is an effective tool in two-phase flow regime online identification.